diff options
Diffstat (limited to 'site/docs/0.6.1/api/core/spark/rdd')
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/CoGroupedRDD.html | 1122 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/CoalescedRDD.html | 968 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/HadoopRDD.html | 990 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/NewHadoopRDD.html | 990 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/PipedRDD$.html | 383 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/PipedRDD.html | 978 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/RepartitionShuffledRDD.html | 982 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/SampledRDD.html | 964 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/ShuffledAggregatedRDD.html | 979 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/ShuffledRDD.html | 983 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/ShuffledSortedRDD.html | 982 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/UnionRDD.html | 964 | ||||
| -rw-r--r-- | site/docs/0.6.1/api/core/spark/rdd/package.html | 222 |
13 files changed, 11507 insertions, 0 deletions
diff --git a/site/docs/0.6.1/api/core/spark/rdd/CoGroupedRDD.html b/site/docs/0.6.1/api/core/spark/rdd/CoGroupedRDD.html new file mode 100644 index 000000000..5ea4de6dc --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/CoGroupedRDD.html @@ -0,0 +1,1122 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.CoGroupedRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>CoGroupedRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">CoGroupedRDD</span><span class="tparams">[<span name="K">K</span>]</span><span class="result"> extends <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])] with <a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a>, <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.CoGroupedRDD" class="in"><span>CoGroupedRDD</span></li><li name="spark.Logging" class="in"><span>Logging</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.CoGroupedRDD#this" data-isabs="false"> + <a id="this:CoGroupedRDD[K]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">CoGroupedRDD</span><span class="params">(<span name="rdds">rdds: Seq[<a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[Tuple2[_, _]]]</span>, <span name="part">part: <a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a></span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[(K, Seq[Seq[_]])]):RDD[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoGroupedRDD#aggr" data-isabs="false"> + <a id="aggr:CoGroupAggregator"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">aggr</span><span class="result">: <span name="spark.rdd.CoGroupAggregator" class="extype">CoGroupAggregator</span></span> + </span> + </h4> + + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, (K, Seq[Seq[_]])) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, (K, Seq[Seq[_]])) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[((K, Seq[Seq[_]]), U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[((K, Seq[Seq[_]]), U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoGroupedRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="s">s: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.CoGroupedRDD" class="extype" href="">CoGroupedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[(K, Seq[Seq[_]]), Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[(K, Seq[Seq[_]]), <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[(K, Seq[Seq[_]]), BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[(K, Seq[Seq[_]]), <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoGroupedRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[spark.Dependency[_]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[spark.Dependency[_]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.CoGroupedRDD" class="extype" href="">CoGroupedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter(((K, Seq[Seq[_]])) ⇒ Boolean):RDD[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: ((K, Seq[Seq[_]])) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():(K, Seq[Seq[_]])"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: (K, Seq[Seq[_]])</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U](((K, Seq[Seq[_]])) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, Seq[Seq[_]])) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold((K, Seq[Seq[_]]))(((K, Seq[Seq[_]]), (K, Seq[Seq[_]])) ⇒ (K, Seq[Seq[_]])):(K, Seq[Seq[_]])"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: (K, Seq[Seq[_]])</span>)</span><span class="params">(<span name="op">op: ((K, Seq[Seq[_]]), (K, Seq[Seq[_]])) ⇒ (K, Seq[Seq[_]])</span>)</span><span class="result">: (K, Seq[Seq[_]])</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach(((K, Seq[Seq[_]])) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: ((K, Seq[Seq[_]])) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[(K, Seq[Seq[_]])]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[(K, Seq[Seq[_]])]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, Seq[Seq[_]])) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[(K, Seq[Seq[_]])])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, Seq[Seq[_]])) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, Seq[Seq[_]])])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, Seq[Seq[_]])) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[(K, Seq[Seq[_]])])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, Seq[Seq[_]])) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, Seq[Seq[_]])])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#initLogging" data-isabs="false"> + <a id="initLogging():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">initLogging</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#log" data-isabs="false"> + <a id="log:Logger"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">log</span><span class="result">: <span name="org.slf4j.Logger" class="extype">Logger</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logDebug" data-isabs="false"> + <a id="logDebug(⇒ String,Throwable):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logDebug</span><span class="params">(<span name="msg">msg: ⇒ String</span>, <span name="throwable">throwable: Throwable</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logDebug" data-isabs="false"> + <a id="logDebug(⇒ String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logDebug</span><span class="params">(<span name="msg">msg: ⇒ String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logError" data-isabs="false"> + <a id="logError(⇒ String,Throwable):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logError</span><span class="params">(<span name="msg">msg: ⇒ String</span>, <span name="throwable">throwable: Throwable</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logError" data-isabs="false"> + <a id="logError(⇒ String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logError</span><span class="params">(<span name="msg">msg: ⇒ String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logInfo" data-isabs="false"> + <a id="logInfo(⇒ String,Throwable):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logInfo</span><span class="params">(<span name="msg">msg: ⇒ String</span>, <span name="throwable">throwable: Throwable</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logInfo" data-isabs="false"> + <a id="logInfo(⇒ String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logInfo</span><span class="params">(<span name="msg">msg: ⇒ String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logTrace" data-isabs="false"> + <a id="logTrace(⇒ String,Throwable):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logTrace</span><span class="params">(<span name="msg">msg: ⇒ String</span>, <span name="throwable">throwable: Throwable</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logTrace" data-isabs="false"> + <a id="logTrace(⇒ String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logTrace</span><span class="params">(<span name="msg">msg: ⇒ String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logWarning" data-isabs="false"> + <a id="logWarning(⇒ String,Throwable):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logWarning</span><span class="params">(<span name="msg">msg: ⇒ String</span>, <span name="throwable">throwable: Throwable</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="prt" name="spark.Logging#logWarning" data-isabs="false"> + <a id="logWarning(⇒ String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">logWarning</span><span class="params">(<span name="msg">msg: ⇒ String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd><dt>Definition Classes</dt><dd><a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U](((K, Seq[Seq[_]])) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, Seq[Seq[_]])) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[(K, Seq[Seq[_]])]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[(K, Seq[Seq[_]])]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[(K, Seq[Seq[_]])]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[(K, Seq[Seq[_]])]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoGroupedRDD#partitioner" data-isabs="false"> + <a id="partitioner:Some[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Some" class="extype">Some</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.CoGroupedRDD" class="extype" href="">CoGroupedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoGroupedRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):scala.collection.immutable.Nil.type"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="s">s: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: scala.collection.immutable.Nil.type</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.CoGroupedRDD" class="extype" href="">CoGroupedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce(((K, Seq[Seq[_]]), (K, Seq[Seq[_]])) ⇒ (K, Seq[Seq[_]])):(K, Seq[Seq[_]])"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: ((K, Seq[Seq[_]]), (K, Seq[Seq[_]])) ⇒ (K, Seq[Seq[_]])</span>)</span><span class="result">: (K, Seq[Seq[_]])</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoGroupedRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.CoGroupedRDD" class="extype" href="">CoGroupedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoGroupedRDD#splits_" data-isabs="false"> + <a id="splits_:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[(K, Seq[Seq[_]])]):RDD[(K, Seq[Seq[_]])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.Logging" class="parent"> + <h3>Inherited from <a name="spark.Logging" class="extype" href="../Logging.html">Logging</a></h3> + </div><div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[Seq[_]])]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/CoalescedRDD.html b/site/docs/0.6.1/api/core/spark/rdd/CoalescedRDD.html new file mode 100644 index 000000000..2f2e027df --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/CoalescedRDD.html @@ -0,0 +1,968 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.CoalescedRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>CoalescedRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">CoalescedRDD</span><span class="tparams">[<span name="T">T</span>]</span><span class="result"> extends <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="comment cmt"><p>Coalesce the partitions of a parent RDD (<code>prev</code>) into fewer partitions, so that each partition of +this RDD computes one or more of the parent ones. Will produce exactly <code>maxPartitions</code> if the +parent had more than this many partitions, or fewer if the parent had fewer.</p><p>This transformation is useful when an RDD with many partitions gets filtered into a smaller one, +or to avoid having a large number of small tasks when processing a directory with many files. +</p></div><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.CoalescedRDD" class="in"><span>CoalescedRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.CoalescedRDD#this" data-isabs="false"> + <a id="this:CoalescedRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">CoalescedRDD</span><span class="params">(<span name="prev">prev: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>, <span name="maxPartitions">maxPartitions: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[T]</span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[T]):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, T) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, T) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[(T, U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(T, U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoalescedRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.CoalescedRDD" class="extype" href="">CoalescedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[T, Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[T, <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[T, BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[T, <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoalescedRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[NarrowDependency[T]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[<a name="spark.NarrowDependency" class="extype" href="../NarrowDependency.html">NarrowDependency</a>[T]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.CoalescedRDD" class="extype" href="">CoalescedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter((T) ⇒ Boolean):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: (T) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U]((T) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (T) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold(T)((T, T) ⇒ T):T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: T</span>)</span><span class="params">(<span name="op">op: (T, T) ⇒ T</span>)</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach((T) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: (T) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[T]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[T]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K]((T) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[T])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: (T) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[T])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K]((T) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[T])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: (T) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[T])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U]((T) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (T) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[T]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[T]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[T]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[T]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#partitioner" data-isabs="false"> + <a id="partitioner:Option[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Option" class="extype">Option</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):Seq[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Seq[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce((T, T) ⇒ T):T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: (T, T) ⇒ T</span>)</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoalescedRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.CoalescedRDD" class="extype" href="">CoalescedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.CoalescedRDD#splits_" data-isabs="false"> + <a id="splits_:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[T]):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/HadoopRDD.html b/site/docs/0.6.1/api/core/spark/rdd/HadoopRDD.html new file mode 100644 index 000000000..843e3ac1d --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/HadoopRDD.html @@ -0,0 +1,990 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.HadoopRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>HadoopRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">HadoopRDD</span><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>]</span><span class="result"> extends <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="comment cmt"><p>An RDD that reads a Hadoop dataset as specified by a JobConf (e.g. files in HDFS, the local file +system, or S3, tables in HBase, etc). +</p></div><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.HadoopRDD" class="in"><span>HadoopRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.HadoopRDD#this" data-isabs="false"> + <a id="this:HadoopRDD[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">HadoopRDD</span><span class="params">(<span name="sc">sc: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span>, <span name="conf">conf: <span name="org.apache.hadoop.mapred.JobConf" class="extype">JobConf</span></span>, <span name="inputFormatClass">inputFormatClass: Class[_ <: org.apache.hadoop.mapred.InputFormat[K,V]]</span>, <span name="keyClass">keyClass: Class[K]</span>, <span name="valueClass">valueClass: Class[V]</span>, <span name="minSplits">minSplits: <span name="scala.Int" class="extype">Int</span></span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[(K, V)]):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, (K, V)) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, (K, V)) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[((K, V), U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[((K, V), U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.HadoopRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="theSplit">theSplit: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.HadoopRDD" class="extype" href="">HadoopRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.HadoopRDD#confBroadcast" data-isabs="false"> + <a id="confBroadcast:Broadcast[SerializableWritable[JobConf]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">confBroadcast</span><span class="result">: <a name="spark.broadcast.Broadcast" class="extype" href="../broadcast/Broadcast.html">Broadcast</a>[<a name="spark.SerializableWritable" class="extype" href="../SerializableWritable.html">SerializableWritable</a>[<span name="org.apache.hadoop.mapred.JobConf" class="extype">JobConf</span>]]</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[(K, V), Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[(K, V), <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[(K, V), BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[(K, V), <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.HadoopRDD#createInputFormat" data-isabs="false"> + <a id="createInputFormat(JobConf):InputFormat[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">createInputFormat</span><span class="params">(<span name="conf">conf: <span name="org.apache.hadoop.mapred.JobConf" class="extype">JobConf</span></span>)</span><span class="result">: <span name="org.apache.hadoop.mapred.InputFormat" class="extype">InputFormat</span>[K, V]</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.rdd.HadoopRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[spark.Dependency[_]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: List[spark.Dependency[_]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.HadoopRDD" class="extype" href="">HadoopRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter(((K, V)) ⇒ Boolean):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: ((K, V)) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U](((K, V)) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold((K, V))(((K, V), (K, V)) ⇒ (K, V)):(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: (K, V)</span>)</span><span class="params">(<span name="op">op: ((K, V), (K, V)) ⇒ (K, V)</span>)</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach(((K, V)) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: ((K, V)) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[(K, V)]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[(K, V)]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, V)) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[(K, V)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, V)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, V)) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[(K, V)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, V)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U](((K, V)) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[(K, V)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[(K, V)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[(K, V)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[(K, V)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#partitioner" data-isabs="false"> + <a id="partitioner:Option[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Option" class="extype">Option</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.HadoopRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):WrappedArray[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: <span name="scala.collection.mutable.WrappedArray" class="extype">WrappedArray</span>[<span name="java.lang.String" class="extype">String</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.HadoopRDD" class="extype" href="">HadoopRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce(((K, V), (K, V)) ⇒ (K, V)):(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: ((K, V), (K, V)) ⇒ (K, V)</span>)</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.HadoopRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.HadoopRDD" class="extype" href="">HadoopRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.HadoopRDD#splits_" data-isabs="false"> + <a id="splits_:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[(K, V)]):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/NewHadoopRDD.html b/site/docs/0.6.1/api/core/spark/rdd/NewHadoopRDD.html new file mode 100644 index 000000000..be2df6721 --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/NewHadoopRDD.html @@ -0,0 +1,990 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.NewHadoopRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>NewHadoopRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">NewHadoopRDD</span><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>]</span><span class="result"> extends <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)] with <a name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil" class="extype" href="../../org/apache/hadoop/mapreduce/HadoopMapReduceUtil.html">HadoopMapReduceUtil</a></span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil" class="extype" href="../../org/apache/hadoop/mapreduce/HadoopMapReduceUtil.html">HadoopMapReduceUtil</a>, <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.NewHadoopRDD" class="in"><span>NewHadoopRDD</span></li><li name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil" class="in"><span>HadoopMapReduceUtil</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.NewHadoopRDD#this" data-isabs="false"> + <a id="this:NewHadoopRDD[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">NewHadoopRDD</span><span class="params">(<span name="sc">sc: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span>, <span name="inputFormatClass">inputFormatClass: Class[_ <: org.apache.hadoop.mapreduce.InputFormat[K,V]]</span>, <span name="keyClass">keyClass: Class[K]</span>, <span name="valueClass">valueClass: Class[V]</span>, <span name="conf">conf: <span name="org.apache.hadoop.conf.Configuration" class="extype">Configuration</span></span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[(K, V)]):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, (K, V)) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, (K, V)) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[((K, V), U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[((K, V), U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.NewHadoopRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="theSplit">theSplit: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.NewHadoopRDD" class="extype" href="">NewHadoopRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.NewHadoopRDD#confBroadcast" data-isabs="false"> + <a id="confBroadcast:Broadcast[SerializableWritable[Configuration]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">confBroadcast</span><span class="result">: <a name="spark.broadcast.Broadcast" class="extype" href="../broadcast/Broadcast.html">Broadcast</a>[<a name="spark.SerializableWritable" class="extype" href="../SerializableWritable.html">SerializableWritable</a>[<span name="org.apache.hadoop.conf.Configuration" class="extype">Configuration</span>]]</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[(K, V), Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[(K, V), <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[(K, V), BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[(K, V), <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.NewHadoopRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[spark.Dependency[_]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: List[spark.Dependency[_]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.NewHadoopRDD" class="extype" href="">NewHadoopRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter(((K, V)) ⇒ Boolean):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: ((K, V)) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U](((K, V)) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold((K, V))(((K, V), (K, V)) ⇒ (K, V)):(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: (K, V)</span>)</span><span class="params">(<span name="op">op: ((K, V), (K, V)) ⇒ (K, V)</span>)</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach(((K, V)) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: ((K, V)) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[(K, V)]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[(K, V)]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, V)) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[(K, V)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, V)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, V)) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[(K, V)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, V)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U](((K, V)) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[(K, V)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[(K, V)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[(K, V)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[(K, V)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil#newJobContext" data-isabs="false"> + <a id="newJobContext(Configuration,JobID):JobContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">newJobContext</span><span class="params">(<span name="conf">conf: <span name="org.apache.hadoop.conf.Configuration" class="extype">Configuration</span></span>, <span name="jobId">jobId: <span name="org.apache.hadoop.mapreduce.JobID" class="extype">JobID</span></span>)</span><span class="result">: <span name="org.apache.hadoop.mapreduce.JobContext" class="extype">JobContext</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil" class="extype" href="../../org/apache/hadoop/mapreduce/HadoopMapReduceUtil.html">HadoopMapReduceUtil</a></dd></dl></div> + </li><li visbl="pub" name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil#newTaskAttemptContext" data-isabs="false"> + <a id="newTaskAttemptContext(Configuration,TaskAttemptID):TaskAttemptContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">newTaskAttemptContext</span><span class="params">(<span name="conf">conf: <span name="org.apache.hadoop.conf.Configuration" class="extype">Configuration</span></span>, <span name="attemptId">attemptId: <span name="org.apache.hadoop.mapreduce.TaskAttemptID" class="extype">TaskAttemptID</span></span>)</span><span class="result">: <span name="org.apache.hadoop.mapreduce.TaskAttemptContext" class="extype">TaskAttemptContext</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil" class="extype" href="../../org/apache/hadoop/mapreduce/HadoopMapReduceUtil.html">HadoopMapReduceUtil</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#partitioner" data-isabs="false"> + <a id="partitioner:Option[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Option" class="extype">Option</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.NewHadoopRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):WrappedArray[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: <span name="scala.collection.mutable.WrappedArray" class="extype">WrappedArray</span>[<span name="java.lang.String" class="extype">String</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.NewHadoopRDD" class="extype" href="">NewHadoopRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce(((K, V), (K, V)) ⇒ (K, V)):(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: ((K, V), (K, V)) ⇒ (K, V)</span>)</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.NewHadoopRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.NewHadoopRDD" class="extype" href="">NewHadoopRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[(K, V)]):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil" class="parent"> + <h3>Inherited from <a name="org.apache.hadoop.mapreduce.HadoopMapReduceUtil" class="extype" href="../../org/apache/hadoop/mapreduce/HadoopMapReduceUtil.html">HadoopMapReduceUtil</a></h3> + </div><div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/PipedRDD$.html b/site/docs/0.6.1/api/core/spark/rdd/PipedRDD$.html new file mode 100644 index 000000000..aa2b75da6 --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/PipedRDD$.html @@ -0,0 +1,383 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.PipedRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="value"> + <div id="definition"> + <a title="Go to companion" href="PipedRDD.html"><img src="../../lib/object_to_class_big.png" /></a> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1><a title="Go to companion" href="PipedRDD.html">PipedRDD</a></h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">object</span> + </span> + <span class="symbol"> + <span class="name">PipedRDD</span><span class="result"> extends <span name="scala.Serializable" class="extype">Serializable</span></span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.PipedRDD" class="in"><span>PipedRDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="prt" name="spark.rdd.PipedRDD#readResolve" data-isabs="false"> + <a id="readResolve():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">readResolve</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.rdd.PipedRDD#tokenize" data-isabs="false"> + <a id="tokenize(String):Seq[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">tokenize</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: Seq[String]</span> + </span> + </h4> + + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/PipedRDD.html b/site/docs/0.6.1/api/core/spark/rdd/PipedRDD.html new file mode 100644 index 000000000..45a5f5e9d --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/PipedRDD.html @@ -0,0 +1,978 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.PipedRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <a title="Go to companion" href="PipedRDD$.html"><img src="../../lib/class_to_object_big.png" /></a> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1><a title="Go to companion" href="PipedRDD$.html">PipedRDD</a></h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">PipedRDD</span><span class="tparams">[<span name="T">T</span>]</span><span class="result"> extends <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="comment cmt"><p>An RDD that pipes the contents of each parent partition through an external command +(printing them one per line) and returns the output as a collection of strings. +</p></div><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.PipedRDD" class="in"><span>PipedRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.PipedRDD#this" data-isabs="false"> + <a id="this:PipedRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">PipedRDD</span><span class="params">(<span name="parent">parent: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>, <span name="command">command: String</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[T]</span>)</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.rdd.PipedRDD#this" data-isabs="false"> + <a id="this:PipedRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">PipedRDD</span><span class="params">(<span name="parent">parent: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>, <span name="command">command: Seq[String]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[T]</span>)</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.rdd.PipedRDD#this" data-isabs="false"> + <a id="this:PipedRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">PipedRDD</span><span class="params">(<span name="parent">parent: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>, <span name="command">command: Seq[String]</span>, <span name="envVars">envVars: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[T]</span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, String) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, String) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[(String, U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(String, U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.PipedRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.PipedRDD" class="extype" href="">PipedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[String, Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[String, <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[String, BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[String, <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.PipedRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[OneToOneDependency[T]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[<a name="spark.OneToOneDependency" class="extype" href="../OneToOneDependency.html">OneToOneDependency</a>[T]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.PipedRDD" class="extype" href="">PipedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter((String) ⇒ Boolean):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: (String) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: String</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U]((String) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (String) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold(String)((String, String) ⇒ String):String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: String</span>)</span><span class="params">(<span name="op">op: (String, String) ⇒ String</span>)</span><span class="result">: String</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach((String) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: (String) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[String]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[String]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K]((String) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[String])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: (String) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[String])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K]((String) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[String])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: (String) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[String])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U]((String) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (String) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[String]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[String]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[String]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[String]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#partitioner" data-isabs="false"> + <a id="partitioner:Option[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Option" class="extype">Option</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):Seq[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Seq[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce((String, String) ⇒ String):String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: (String, String) ⇒ String</span>)</span><span class="result">: String</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.PipedRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.PipedRDD" class="extype" href="">PipedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[String]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/RepartitionShuffledRDD.html b/site/docs/0.6.1/api/core/spark/rdd/RepartitionShuffledRDD.html new file mode 100644 index 000000000..c3c70b6ec --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/RepartitionShuffledRDD.html @@ -0,0 +1,982 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.RepartitionShuffledRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>RepartitionShuffledRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">RepartitionShuffledRDD</span><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>]</span><span class="result"> extends <a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a>[K, V, V]</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="comment cmt"><p>Repartition a key-value pair RDD. +</p></div><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a>[K, V, V], <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div><div class="toggleContainer block"> + <span class="toggle">Known Subclasses</span> + <div class="subClasses hiddenContent"><a name="spark.rdd.ShuffledSortedRDD" class="extype" href="ShuffledSortedRDD.html">ShuffledSortedRDD</a></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.RepartitionShuffledRDD" class="in"><span>RepartitionShuffledRDD</span></li><li name="spark.rdd.ShuffledRDD" class="in"><span>ShuffledRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.RepartitionShuffledRDD#this" data-isabs="false"> + <a id="this:RepartitionShuffledRDD[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">RepartitionShuffledRDD</span><span class="params">(<span name="parent">parent: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>, <span name="part">part: <a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a></span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[(K, V)]):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, (K, V)) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, (K, V)) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[((K, V), U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[((K, V), U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.RepartitionShuffledRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.RepartitionShuffledRDD" class="extype" href="">RepartitionShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[(K, V), Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[(K, V), <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[(K, V), BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[(K, V), <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#dep" data-isabs="false"> + <a id="dep:ShuffleDependency[K, V, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dep</span><span class="result">: <a name="spark.ShuffleDependency" class="extype" href="../ShuffleDependency.html">ShuffleDependency</a>[K, V, V]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[ShuffleDependency[K, V, V]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[<a name="spark.ShuffleDependency" class="extype" href="../ShuffleDependency.html">ShuffleDependency</a>[K, V, V]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter(((K, V)) ⇒ Boolean):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: ((K, V)) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U](((K, V)) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold((K, V))(((K, V), (K, V)) ⇒ (K, V)):(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: (K, V)</span>)</span><span class="params">(<span name="op">op: ((K, V), (K, V)) ⇒ (K, V)</span>)</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach(((K, V)) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: ((K, V)) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[(K, V)]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[(K, V)]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, V)) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[(K, V)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, V)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, V)) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[(K, V)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, V)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U](((K, V)) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[(K, V)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[(K, V)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[(K, V)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[(K, V)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#partitioner" data-isabs="false"> + <a id="partitioner:Some[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Some" class="extype">Some</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):scala.collection.immutable.Nil.type"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: scala.collection.immutable.Nil.type</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce(((K, V), (K, V)) ⇒ (K, V)):(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: ((K, V), (K, V)) ⇒ (K, V)</span>)</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#splits_" data-isabs="false"> + <a id="splits_:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[(K, V)]):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.rdd.ShuffledRDD" class="parent"> + <h3>Inherited from <a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a>[K, V, V]</h3> + </div><div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/SampledRDD.html b/site/docs/0.6.1/api/core/spark/rdd/SampledRDD.html new file mode 100644 index 000000000..05b702807 --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/SampledRDD.html @@ -0,0 +1,964 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.SampledRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>SampledRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">SampledRDD</span><span class="tparams">[<span name="T">T</span>]</span><span class="result"> extends <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.SampledRDD" class="in"><span>SampledRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.SampledRDD#this" data-isabs="false"> + <a id="this:SampledRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">SampledRDD</span><span class="params">(<span name="prev">prev: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>, <span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="frac">frac: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[T]</span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[T]):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, T) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, T) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[(T, U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(T, U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.SampledRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="splitIn">splitIn: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.SampledRDD" class="extype" href="">SampledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[T, Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[T, <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[T, BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[T, <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.SampledRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[OneToOneDependency[T]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[<a name="spark.OneToOneDependency" class="extype" href="../OneToOneDependency.html">OneToOneDependency</a>[T]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.SampledRDD" class="extype" href="">SampledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter((T) ⇒ Boolean):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: (T) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U]((T) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (T) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold(T)((T, T) ⇒ T):T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: T</span>)</span><span class="params">(<span name="op">op: (T, T) ⇒ T</span>)</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach((T) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: (T) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[T]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[T]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K]((T) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[T])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: (T) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[T])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K]((T) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[T])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: (T) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[T])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U]((T) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (T) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[T]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[T]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[T]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[T]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#partitioner" data-isabs="false"> + <a id="partitioner:Option[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Option" class="extype">Option</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.SampledRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):Seq[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Seq[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.SampledRDD" class="extype" href="">SampledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce((T, T) ⇒ T):T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: (T, T) ⇒ T</span>)</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.SampledRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.SampledRDD" class="extype" href="">SampledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.SampledRDD#splits_" data-isabs="false"> + <a id="splits_:Array[SampledRDDSplit]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<span name="spark.rdd.SampledRDDSplit" class="extype">SampledRDDSplit</span>]</span> + </span> + </h4> + + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[T]):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/ShuffledAggregatedRDD.html b/site/docs/0.6.1/api/core/spark/rdd/ShuffledAggregatedRDD.html new file mode 100644 index 000000000..fe96fe03a --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/ShuffledAggregatedRDD.html @@ -0,0 +1,979 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.ShuffledAggregatedRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>ShuffledAggregatedRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">ShuffledAggregatedRDD</span><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>, <span name="C">C</span>]</span><span class="result"> extends <a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a>[K, V, C]</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="comment cmt"><p>The resulting RDD from shuffle and running (hash-based) aggregation. +</p></div><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a>[K, V, C], <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.ShuffledAggregatedRDD" class="in"><span>ShuffledAggregatedRDD</span></li><li name="spark.rdd.ShuffledRDD" class="in"><span>ShuffledRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.ShuffledAggregatedRDD#this" data-isabs="false"> + <a id="this:ShuffledAggregatedRDD[K, V, C]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">ShuffledAggregatedRDD</span><span class="params">(<span name="parent">parent: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>, <span name="aggregator">aggregator: <a name="spark.Aggregator" class="extype" href="../Aggregator.html">Aggregator</a>[K, V, C]</span>, <span name="part">part: <a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a></span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[(K, C)]):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, (K, C)) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, (K, C)) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[((K, C), U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[((K, C), U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledAggregatedRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledAggregatedRDD" class="extype" href="">ShuffledAggregatedRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[(K, C), Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[(K, C), <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[(K, C), BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[(K, C), <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#dep" data-isabs="false"> + <a id="dep:ShuffleDependency[K, V, C]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dep</span><span class="result">: <a name="spark.ShuffleDependency" class="extype" href="../ShuffleDependency.html">ShuffleDependency</a>[K, V, C]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[ShuffleDependency[K, V, C]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[<a name="spark.ShuffleDependency" class="extype" href="../ShuffleDependency.html">ShuffleDependency</a>[K, V, C]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter(((K, C)) ⇒ Boolean):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: ((K, C)) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():(K, C)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: (K, C)</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U](((K, C)) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, C)) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold((K, C))(((K, C), (K, C)) ⇒ (K, C)):(K, C)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: (K, C)</span>)</span><span class="params">(<span name="op">op: ((K, C), (K, C)) ⇒ (K, C)</span>)</span><span class="result">: (K, C)</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach(((K, C)) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: ((K, C)) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[(K, C)]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[(K, C)]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, C)) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[(K, C)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, C)) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, C)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, C)) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[(K, C)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, C)) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, C)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U](((K, C)) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, C)) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[(K, C)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[(K, C)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[(K, C)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[(K, C)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#partitioner" data-isabs="false"> + <a id="partitioner:Some[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Some" class="extype">Some</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):scala.collection.immutable.Nil.type"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: scala.collection.immutable.Nil.type</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce(((K, C), (K, C)) ⇒ (K, C)):(K, C)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: ((K, C), (K, C)) ⇒ (K, C)</span>)</span><span class="result">: (K, C)</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#splits_" data-isabs="false"> + <a id="splits_:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, C)]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[(K, C)]):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.rdd.ShuffledRDD" class="parent"> + <h3>Inherited from <a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a>[K, V, C]</h3> + </div><div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/ShuffledRDD.html b/site/docs/0.6.1/api/core/spark/rdd/ShuffledRDD.html new file mode 100644 index 000000000..1b81d6b56 --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/ShuffledRDD.html @@ -0,0 +1,983 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.ShuffledRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>ShuffledRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier">abstract </span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">ShuffledRDD</span><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>, <span name="C">C</span>]</span><span class="result"> extends <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="comment cmt"><p>The resulting RDD from a shuffle (e.g. repartitioning of data). +</p></div><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div><div class="toggleContainer block"> + <span class="toggle">Known Subclasses</span> + <div class="subClasses hiddenContent"><a name="spark.rdd.RepartitionShuffledRDD" class="extype" href="RepartitionShuffledRDD.html">RepartitionShuffledRDD</a>, <a name="spark.rdd.ShuffledAggregatedRDD" class="extype" href="ShuffledAggregatedRDD.html">ShuffledAggregatedRDD</a>, <a name="spark.rdd.ShuffledSortedRDD" class="extype" href="ShuffledSortedRDD.html">ShuffledSortedRDD</a></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.ShuffledRDD" class="in"><span>ShuffledRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.ShuffledRDD#this" data-isabs="false"> + <a id="this:ShuffledRDD[K, V, C]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">ShuffledRDD</span><span class="params">(<span name="parent">parent: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>, <span name="aggregator">aggregator: <span name="scala.Option" class="extype">Option</span>[<a name="spark.Aggregator" class="extype" href="../Aggregator.html">Aggregator</a>[K, V, C]]</span>, <span name="part">part: <a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a></span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + <div class="values members" id="values"> + <h3>Abstract Value Members</h3> + <ol><li visbl="pub" name="spark.RDD#compute" data-isabs="true"> + <a id="compute(Split):Iterator[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">abstract </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li></ol> + </div> + + <div class="values members" id="values"> + <h3>Concrete Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[(K, C)]):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, (K, C)) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, (K, C)) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[((K, C), U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[((K, C), U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[(K, C), Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[(K, C), <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[(K, C), BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[(K, C), <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#dep" data-isabs="false"> + <a id="dep:ShuffleDependency[K, V, C]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dep</span><span class="result">: <a name="spark.ShuffleDependency" class="extype" href="../ShuffleDependency.html">ShuffleDependency</a>[K, V, C]</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[ShuffleDependency[K, V, C]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[<a name="spark.ShuffleDependency" class="extype" href="../ShuffleDependency.html">ShuffleDependency</a>[K, V, C]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter(((K, C)) ⇒ Boolean):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: ((K, C)) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():(K, C)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: (K, C)</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U](((K, C)) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, C)) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold((K, C))(((K, C), (K, C)) ⇒ (K, C)):(K, C)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: (K, C)</span>)</span><span class="params">(<span name="op">op: ((K, C), (K, C)) ⇒ (K, C)</span>)</span><span class="result">: (K, C)</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach(((K, C)) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: ((K, C)) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[(K, C)]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[(K, C)]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, C)) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[(K, C)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, C)) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, C)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, C)) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[(K, C)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, C)) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, C)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U](((K, C)) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, C)) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[(K, C)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[(K, C)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[(K, C)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[(K, C)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#partitioner" data-isabs="false"> + <a id="partitioner:Some[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Some" class="extype">Some</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):scala.collection.immutable.Nil.type"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: scala.collection.immutable.Nil.type</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce(((K, C), (K, C)) ⇒ (K, C)):(K, C)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: ((K, C), (K, C)) ⇒ (K, C)</span>)</span><span class="result">: (K, C)</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#splits_" data-isabs="false"> + <a id="splits_:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, C)]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[(K, C)]):RDD[(K, C)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, C)]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/ShuffledSortedRDD.html b/site/docs/0.6.1/api/core/spark/rdd/ShuffledSortedRDD.html new file mode 100644 index 000000000..bbe0dbfc6 --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/ShuffledSortedRDD.html @@ -0,0 +1,982 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.ShuffledSortedRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>ShuffledSortedRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">ShuffledSortedRDD</span><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>]</span><span class="result"> extends <a name="spark.rdd.RepartitionShuffledRDD" class="extype" href="RepartitionShuffledRDD.html">RepartitionShuffledRDD</a>[K, V]</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="comment cmt"><p>A sort-based shuffle (that doesn't apply aggregation). It does so by first +repartitioning the RDD by range, and then sort within each range. +</p></div><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.rdd.RepartitionShuffledRDD" class="extype" href="RepartitionShuffledRDD.html">RepartitionShuffledRDD</a>[K, V], <a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a>[K, V, V], <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.ShuffledSortedRDD" class="in"><span>ShuffledSortedRDD</span></li><li name="spark.rdd.RepartitionShuffledRDD" class="in"><span>RepartitionShuffledRDD</span></li><li name="spark.rdd.ShuffledRDD" class="in"><span>ShuffledRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.ShuffledSortedRDD#this" data-isabs="false"> + <a id="this:ShuffledSortedRDD[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">ShuffledSortedRDD</span><span class="params">(<span name="parent">parent: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>, <span name="ascending">ascending: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: (K) ⇒ Ordered[K]</span>, <span name="arg1">arg1: ClassManifest[K]</span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[(K, V)]):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, (K, V)) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, (K, V)) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[((K, V), U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[((K, V), U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledSortedRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledSortedRDD" class="extype" href="">ShuffledSortedRDD</a> → <a name="spark.rdd.RepartitionShuffledRDD" class="extype" href="RepartitionShuffledRDD.html">RepartitionShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[(K, V), Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[(K, V), <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[(K, V), BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[(K, V), <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#dep" data-isabs="false"> + <a id="dep:ShuffleDependency[K, V, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dep</span><span class="result">: <a name="spark.ShuffleDependency" class="extype" href="../ShuffleDependency.html">ShuffleDependency</a>[K, V, V]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[ShuffleDependency[K, V, V]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[<a name="spark.ShuffleDependency" class="extype" href="../ShuffleDependency.html">ShuffleDependency</a>[K, V, V]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter(((K, V)) ⇒ Boolean):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: ((K, V)) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U](((K, V)) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold((K, V))(((K, V), (K, V)) ⇒ (K, V)):(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: (K, V)</span>)</span><span class="params">(<span name="op">op: ((K, V), (K, V)) ⇒ (K, V)</span>)</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach(((K, V)) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: ((K, V)) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[(K, V)]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[(K, V)]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, V)) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[(K, V)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, V)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K](((K, V)) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[(K, V)])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[(K, V)])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U](((K, V)) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: ((K, V)) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[(K, V)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[(K, V)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[(K, V)]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[(K, V)]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#partitioner" data-isabs="false"> + <a id="partitioner:Some[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Some" class="extype">Some</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):scala.collection.immutable.Nil.type"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: scala.collection.immutable.Nil.type</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce(((K, V), (K, V)) ⇒ (K, V)):(K, V)"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: ((K, V), (K, V)) ⇒ (K, V)</span>)</span><span class="result">: (K, V)</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD#splits_" data-isabs="false"> + <a id="splits_:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[(K, V)]):RDD[(K, V)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.rdd.RepartitionShuffledRDD" class="parent"> + <h3>Inherited from <a name="spark.rdd.RepartitionShuffledRDD" class="extype" href="RepartitionShuffledRDD.html">RepartitionShuffledRDD</a>[K, V]</h3> + </div><div name="spark.rdd.ShuffledRDD" class="parent"> + <h3>Inherited from <a name="spark.rdd.ShuffledRDD" class="extype" href="ShuffledRDD.html">ShuffledRDD</a>[K, V, V]</h3> + </div><div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, V)]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/UnionRDD.html b/site/docs/0.6.1/api/core/spark/rdd/UnionRDD.html new file mode 100644 index 000000000..0bb390183 --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/UnionRDD.html @@ -0,0 +1,964 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd.UnionRDD</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="type"> + <div id="definition"> + <img src="../../lib/class_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a>.<a name="spark.rdd" class="extype" href="package.html">rdd</a></p> + <h1>UnionRDD</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <span class="name">UnionRDD</span><span class="tparams">[<span name="T">T</span>]</span><span class="result"> extends <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T] with <span name="scala.Serializable" class="extype">Serializable</span></span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"><div class="toggleContainer block"> + <span class="toggle">Linear Supertypes</span> + <div class="superTypes hiddenContent"><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T], <span name="scala.Serializable" class="extype">Serializable</span>, <span name="java.io.Serializable" class="extype">Serializable</span>, AnyRef, <span name="scala.Any" class="extype">Any</span></div> + </div></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + <div id="order"> + <span class="filtertype">Ordering</span> + <ol><li class="alpha in"><span>Alphabetic</span></li><li class="inherit out"><span>By inheritance</span></li></ol> + </div> + <div id="ancestors"> + <span class="filtertype">Inherited</span> + <ol><li class="hideall out"><span>Hide All</span></li> + <li class="showall in"><span>Show all</span></li></ol> + <ol id="linearization"><li name="spark.rdd.UnionRDD" class="in"><span>UnionRDD</span></li><li name="spark.RDD" class="in"><span>RDD</span></li><li name="scala.Serializable" class="in"><span>Serializable</span></li><li name="java.io.Serializable" class="in"><span>Serializable</span></li><li name="scala.AnyRef" class="in"><span>AnyRef</span></li><li name="scala.Any" class="in"><span>Any</span></li></ol> + </div> + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + <div class="members" id="constructors"> + <h3>Instance Constructors</h3> + <ol><li visbl="pub" name="spark.rdd.UnionRDD#this" data-isabs="false"> + <a id="this:UnionRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">new</span> + </span> + <span class="symbol"> + <span class="name">UnionRDD</span><span class="params">(<span name="sc">sc: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span>, <span name="rdds">rdds: Seq[<a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[T]</span>)</span> + </span> + </h4> + + </li></ol> + </div> + + + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="scala.AnyRef#!=" data-isabs="false"> + <a id="!=(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#!=" data-isabs="false"> + <a id="!=(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $bang$eq">!=</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef###" data-isabs="false"> + <a id="##():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $hash$hash">##</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#++" data-isabs="false"> + <a id="++(RDD[T]):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $plus$plus">++</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#==" data-isabs="false"> + <a id="==(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.Any#==" data-isabs="false"> + <a id="==(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name" title="gt4s: $eq$eq">==</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#aggregate" data-isabs="false"> + <a id="aggregate[U](U)((U, T) ⇒ U,(U, U) ⇒ U)(ClassManifest[U]):U"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">aggregate</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="zeroValue">zeroValue: U</span>)</span><span class="params">(<span name="seqOp">seqOp: (U, T) ⇒ U</span>, <span name="combOp">combOp: (U, U) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: U</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using +given combine functions and a neutral "zero value". This function can return a different result +type, U, than the type of this RDD, T. Thus, we need one operation for merging a T into an U +and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are +allowed to modify and return their first argument instead of creating a new U to avoid memory +allocation. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#asInstanceOf" data-isabs="false"> + <a id="asInstanceOf[T0]:T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">asInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cache" data-isabs="false"> + <a id="cache():RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cache</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#cartesian" data-isabs="false"> + <a id="cartesian[U](RDD[U])(ClassManifest[U]):RDD[(T, U)]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">cartesian</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(T, U)]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>.</p><div class="fullcomment"><div class="comment cmt"><p>Return the Cartesian product of this RDD and another one, that is, the RDD of all pairs of +elements (a, b) where a is in <code>this</code> and b is in <code>other</code>. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#clone" data-isabs="false"> + <a id="clone():AnyRef"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">clone</span><span class="params">()</span><span class="result">: AnyRef</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#collect" data-isabs="false"> + <a id="collect():Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">collect</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.UnionRDD#compute" data-isabs="false"> + <a id="compute(Split):Iterator[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">compute</span><span class="params">(<span name="s">s: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Function for computing a given partition.</p><div class="fullcomment"><div class="comment cmt"><p>Function for computing a given partition.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.UnionRDD" class="extype" href="">UnionRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#context" data-isabs="false"> + <a id="context:SparkContext"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">context</span><span class="result">: <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a></span> + </span> + </h4> + <p class="shortcomment cmt">The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p><div class="fullcomment"><div class="comment cmt"><p>The <a name="spark.SparkContext" class="extype" href="../SparkContext.html">SparkContext</a> that this RDD was created on.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#count" data-isabs="false"> + <a id="count():Long"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">count</span><span class="params">()</span><span class="result">: <span name="scala.Long" class="extype">Long</span></span> + </span> + </h4> + <p class="shortcomment cmt">Return the number of elements in the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the number of elements in the RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countApprox" data-isabs="false"> + <a id="countApprox(Long,Double):PartialResult[BoundedDouble]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished.</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of count() that returns a potentially incomplete result +within a timeout, even if not all tasks have finished. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValue" data-isabs="false"> + <a id="countByValue():Map[T, Long]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValue</span><span class="params">()</span><span class="result">: <span name="scala.collection.Map" class="extype">Map</span>[T, <span name="scala.Long" class="extype">Long</span>]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the count of each unique value in this RDD as a map of (value, count) pairs.</p><div class="fullcomment"><div class="comment cmt"><p>Return the count of each unique value in this RDD as a map of (value, count) pairs. The final +combine step happens locally on the master, equivalent to running a single reduce task. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#countByValueApprox" data-isabs="false"> + <a id="countByValueApprox(Long,Double):PartialResult[Map[T, BoundedDouble]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">countByValueApprox</span><span class="params">(<span name="timeout">timeout: <span name="scala.Long" class="extype">Long</span></span>, <span name="confidence">confidence: <span name="scala.Double" class="extype">Double</span> = <span class="symbol">0.95</span></span>)</span><span class="result">: <a name="spark.partial.PartialResult" class="extype" href="../partial/PartialResult.html">PartialResult</a>[<span name="scala.collection.Map" class="extype">Map</span>[T, <a name="spark.partial.BoundedDouble" class="extype" href="../partial/BoundedDouble.html">BoundedDouble</a>]]</span> + </span> + </h4> + <p class="shortcomment cmt">(Experimental) Approximate version of countByValue().</p><div class="fullcomment"><div class="comment cmt"><p>(Experimental) Approximate version of countByValue(). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.UnionRDD#dependencies" data-isabs="false"> + <a id="dependencies:List[spark.Dependency[_]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">dependencies</span><span class="result">: <span name="scala.collection.immutable.List" class="extype">List</span>[spark.Dependency[_]]</span> + </span> + </h4> + <p class="shortcomment cmt">How this RDD depends on any parent RDDs.</p><div class="fullcomment"><div class="comment cmt"><p>How this RDD depends on any parent RDDs.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.UnionRDD" class="extype" href="">UnionRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#distinct" data-isabs="false"> + <a id="distinct(Int):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">distinct</span><span class="params">(<span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span> = <span class="symbol"><span class="name"><a href="../RDD.html#splits:Array[Split]">splits.size</a></span></span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing the distinct elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing the distinct elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#eq" data-isabs="false"> + <a id="eq(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">eq</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#equals" data-isabs="false"> + <a id="equals(Any):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">equals</span><span class="params">(<span name="arg0">arg0: <span name="scala.Any" class="extype">Any</span></span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#filter" data-isabs="false"> + <a id="filter((T) ⇒ Boolean):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">filter</span><span class="params">(<span name="f">f: (T) ⇒ <span name="scala.Boolean" class="extype">Boolean</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD containing only the elements that satisfy a predicate.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD containing only the elements that satisfy a predicate. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="prt" name="scala.AnyRef#finalize" data-isabs="false"> + <a id="finalize():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">finalize</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Attributes</dt><dd>protected[<a name="java.lang" class="extype" href="../../java/lang/package.html">lang</a>] </dd><dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="spark.RDD#first" data-isabs="false"> + <a id="first():T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">first</span><span class="params">()</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Return the first element in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return the first element in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#flatMap" data-isabs="false"> + <a id="flatMap[U]((T) ⇒ TraversableOnce[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">flatMap</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (T) ⇒ TraversableOnce[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt"> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results.</p><div class="fullcomment"><div class="comment cmt"><p> Return a new RDD by first applying a function to all elements of this + RDD, and then flattening the results. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#fold" data-isabs="false"> + <a id="fold(T)((T, T) ⇒ T):T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">fold</span><span class="params">(<span name="zeroValue">zeroValue: T</span>)</span><span class="params">(<span name="op">op: (T, T) ⇒ T</span>)</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value".</p><div class="fullcomment"><div class="comment cmt"><p>Aggregate the elements of each partition, and then the results for all the partitions, using a +given associative function and a neutral "zero value". The function op(t1, t2) is allowed to +modify t1 and return it as its result value to avoid object allocation; however, it should not +modify t2. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#foreach" data-isabs="false"> + <a id="foreach((T) ⇒ Unit):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">foreach</span><span class="params">(<span name="f">f: (T) ⇒ <span name="scala.Unit" class="extype">Unit</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Applies a function f to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Applies a function f to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#getClass" data-isabs="false"> + <a id="getClass():java.lang.Class[_]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getClass</span><span class="params">()</span><span class="result">: java.lang.Class[_]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#getStorageLevel" data-isabs="false"> + <a id="getStorageLevel:StorageLevel"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">getStorageLevel</span><span class="result">: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span> + </span> + </h4> + <p class="shortcomment cmt">Get the RDD's current storage level, or StorageLevel.</p><div class="fullcomment"><div class="comment cmt"><p>Get the RDD's current storage level, or StorageLevel.NONE if none is set.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#glom" data-isabs="false"> + <a id="glom():RDD[Array[T]]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">glom</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[<span name="scala.Array" class="extype">Array</span>[T]]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by coalescing all elements within each partition into an array.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by coalescing all elements within each partition into an array. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K]((T) ⇒ K)(ClassManifest[K]):RDD[(K, Seq[T])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: (T) ⇒ K</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[T])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped items.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped items. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#groupBy" data-isabs="false"> + <a id="groupBy[K]((T) ⇒ K,Int)(ClassManifest[K]):RDD[(K, Seq[T])]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">groupBy</span><span class="tparams">[<span name="K">K</span>]</span><span class="params">(<span name="f">f: (T) ⇒ K</span>, <span name="numSplits">numSplits: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[K]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[(K, Seq[T])]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD of grouped elements.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD of grouped elements. Each group consists of a key and a sequence of elements +mapping to that key. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#hashCode" data-isabs="false"> + <a id="hashCode():Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">hashCode</span><span class="params">()</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#id" data-isabs="false"> + <a id="id:Int"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">id</span><span class="result">: <span name="scala.Int" class="extype">Int</span></span> + </span> + </h4> + <p class="shortcomment cmt">A unique ID for this RDD (within its SparkContext).</p><div class="fullcomment"><div class="comment cmt"><p>A unique ID for this RDD (within its SparkContext).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.Any#isInstanceOf" data-isabs="false"> + <a id="isInstanceOf[T0]:Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">isInstanceOf</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#iterator" data-isabs="false"> + <a id="iterator(Split):Iterator[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">iterator</span><span class="params">(<span name="split">split: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Iterator[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Internal method to this RDD; will read from cache if applicable, or otherwise compute it.</p><div class="fullcomment"><div class="comment cmt"><p>Internal method to this RDD; will read from cache if applicable, or otherwise compute it. +This should <i>not</i> be called by users directly, but is available for implementors of custom +subclasses of RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#map" data-isabs="false"> + <a id="map[U]((T) ⇒ U)(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">map</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (T) ⇒ U</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to all elements of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to all elements of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitions" data-isabs="false"> + <a id="mapPartitions[U]((Iterator[T]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitions</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (Iterator[T]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#mapPartitionsWithSplit" data-isabs="false"> + <a id="mapPartitionsWithSplit[U]((Int, Iterator[T]) ⇒ Iterator[U])(ClassManifest[U]):RDD[U]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">mapPartitionsWithSplit</span><span class="tparams">[<span name="U">U</span>]</span><span class="params">(<span name="f">f: (<span name="scala.Int" class="extype">Int</span>, Iterator[T]) ⇒ Iterator[U]</span>)</span><span class="params">(<span class="implicit">implicit </span><span name="arg0">arg0: ClassManifest[U]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[U]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition.</p><div class="fullcomment"><div class="comment cmt"><p>Return a new RDD by applying a function to each partition of this RDD, while tracking the index +of the original partition. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#ne" data-isabs="false"> + <a id="ne(AnyRef):Boolean"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">ne</span><span class="params">(<span name="arg0">arg0: AnyRef</span>)</span><span class="result">: <span name="scala.Boolean" class="extype">Boolean</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notify" data-isabs="false"> + <a id="notify():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notify</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#notifyAll" data-isabs="false"> + <a id="notifyAll():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">notifyAll</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#partitioner" data-isabs="false"> + <a id="partitioner:Option[Partitioner]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">partitioner</span><span class="result">: <span name="scala.Option" class="extype">Option</span>[<a name="spark.Partitioner" class="extype" href="../Partitioner.html">Partitioner</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify how they are partitioned.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify how they are partitioned.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist():RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">()</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p><div class="fullcomment"><div class="comment cmt"><p>Persist this RDD with the default storage level (<code>MEMORY_ONLY</code>).</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#persist" data-isabs="false"> + <a id="persist(StorageLevel):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">persist</span><span class="params">(<span name="newLevel">newLevel: <a name="spark.storage.StorageLevel" class="extype" href="../storage/StorageLevel.html">StorageLevel</a></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Set this RDD's storage level to persist its values across operations after the first time +it is computed.</p><div class="fullcomment"><div class="comment cmt"><p>Set this RDD's storage level to persist its values across operations after the first time +it is computed. Can only be called once on each RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String],Map[String, String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>, <span name="env">env: <span name="scala.collection.Map" class="extype">Map</span>[String, String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(Seq[String]):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: Seq[String]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#pipe" data-isabs="false"> + <a id="pipe(String):RDD[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">pipe</span><span class="params">(<span name="command">command: String</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an RDD created by piping elements to a forked external process.</p><div class="fullcomment"><div class="comment cmt"><p>Return an RDD created by piping elements to a forked external process. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.UnionRDD#preferredLocations" data-isabs="false"> + <a id="preferredLocations(Split):Seq[String]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">preferredLocations</span><span class="params">(<span name="s">s: <a name="spark.Split" class="extype" href="../Split.html">Split</a></span>)</span><span class="result">: Seq[String]</span> + </span> + </h4> + <p class="shortcomment cmt">Optionally overridden by subclasses to specify placement preferences.</p><div class="fullcomment"><div class="comment cmt"><p>Optionally overridden by subclasses to specify placement preferences.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.UnionRDD" class="extype" href="">UnionRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#reduce" data-isabs="false"> + <a id="reduce((T, T) ⇒ T):T"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">reduce</span><span class="params">(<span name="f">f: (T, T) ⇒ T</span>)</span><span class="result">: T</span> + </span> + </h4> + <p class="shortcomment cmt">Reduces the elements of this RDD using the specified associative binary operator.</p><div class="fullcomment"><div class="comment cmt"><p>Reduces the elements of this RDD using the specified associative binary operator. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#sample" data-isabs="false"> + <a id="sample(Boolean,Double,Int):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">sample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="fraction">fraction: <span name="scala.Double" class="extype">Double</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return a sampled subset of this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return a sampled subset of this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsObjectFile" data-isabs="false"> + <a id="saveAsObjectFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsObjectFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a SequenceFile of serialized objects.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a SequenceFile of serialized objects. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#saveAsTextFile" data-isabs="false"> + <a id="saveAsTextFile(String):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">saveAsTextFile</span><span class="params">(<span name="path">path: String</span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <p class="shortcomment cmt">Save this RDD as a text file, using string representations of elements.</p><div class="fullcomment"><div class="comment cmt"><p>Save this RDD as a text file, using string representations of elements. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.UnionRDD#splits" data-isabs="false"> + <a id="splits:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">splits</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + <p class="shortcomment cmt">Set of partitions in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Set of partitions in this RDD.</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.rdd.UnionRDD" class="extype" href="">UnionRDD</a> → <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.rdd.UnionRDD#splits_" data-isabs="false"> + <a id="splits_:Array[Split]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">val</span> + </span> + <span class="symbol"> + <span class="name">splits_</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[<a name="spark.Split" class="extype" href="../Split.html">Split</a>]</span> + </span> + </h4> + + </li><li visbl="pub" name="scala.AnyRef#synchronized" data-isabs="false"> + <a id="synchronized[T0](⇒ T0):T0"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">synchronized</span><span class="tparams">[<span name="T0">T0</span>]</span><span class="params">(<span name="arg0">arg0: ⇒ T0</span>)</span><span class="result">: T0</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#take" data-isabs="false"> + <a id="take(Int):Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">take</span><span class="params">(<span name="num">num: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Take the first num elements of the RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Take the first num elements of the RDD. This currently scans the partitions *one by one*, so +it will be slow if a lot of partitions are required. In that case, use collect() to get the +whole RDD instead. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#takeSample" data-isabs="false"> + <a id="takeSample(Boolean,Int,Int):Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">takeSample</span><span class="params">(<span name="withReplacement">withReplacement: <span name="scala.Boolean" class="extype">Boolean</span></span>, <span name="num">num: <span name="scala.Int" class="extype">Int</span></span>, <span name="seed">seed: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="spark.RDD#toArray" data-isabs="false"> + <a id="toArray():Array[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toArray</span><span class="params">()</span><span class="result">: <span name="scala.Array" class="extype">Array</span>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return an array that contains all of the elements in this RDD.</p><div class="fullcomment"><div class="comment cmt"><p>Return an array that contains all of the elements in this RDD. +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#toString" data-isabs="false"> + <a id="toString():String"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">toString</span><span class="params">()</span><span class="result">: <span name="java.lang.String" class="extype">String</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef → Any</dd></dl></div> + </li><li visbl="pub" name="spark.RDD#union" data-isabs="false"> + <a id="union(RDD[T]):RDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">union</span><span class="params">(<span name="other">other: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span>)</span><span class="result">: <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</span> + </span> + </h4> + <p class="shortcomment cmt">Return the union of this RDD and another one.</p><div class="fullcomment"><div class="comment cmt"><p>Return the union of this RDD and another one. Any identical elements will appear multiple +times (use <code>.distinct()</code> to eliminate them). +</p></div><dl class="attributes block"> <dt>Definition Classes</dt><dd><a name="spark.RDD" class="extype" href="../RDD.html">RDD</a></dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait():Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">()</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long,Int):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>, <span name="arg1">arg1: <span name="scala.Int" class="extype">Int</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li><li visbl="pub" name="scala.AnyRef#wait" data-isabs="false"> + <a id="wait(Long):Unit"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">final </span> + <span class="kind">def</span> + </span> + <span class="symbol"> + <span class="name">wait</span><span class="params">(<span name="arg0">arg0: <span name="scala.Long" class="extype">Long</span></span>)</span><span class="result">: <span name="scala.Unit" class="extype">Unit</span></span> + </span> + </h4> + <div class="fullcomment"><dl class="attributes block"> <dt>Definition Classes</dt><dd>AnyRef</dd><dt>Annotations</dt><dd> + <span class="name">@throws</span><span class="args">()</span> + + </dd></dl></div> + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + <div name="spark.RDD" class="parent"> + <h3>Inherited from <a name="spark.RDD" class="extype" href="../RDD.html">RDD</a>[T]</h3> + </div><div name="scala.Serializable" class="parent"> + <h3>Inherited from <span name="scala.Serializable" class="extype">Serializable</span></h3> + </div><div name="java.io.Serializable" class="parent"> + <h3>Inherited from <span name="java.io.Serializable" class="extype">Serializable</span></h3> + </div><div name="scala.AnyRef" class="parent"> + <h3>Inherited from AnyRef</h3> + </div><div name="scala.Any" class="parent"> + <h3>Inherited from <span name="scala.Any" class="extype">Any</span></h3> + </div> + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file diff --git a/site/docs/0.6.1/api/core/spark/rdd/package.html b/site/docs/0.6.1/api/core/spark/rdd/package.html new file mode 100644 index 000000000..727c54a38 --- /dev/null +++ b/site/docs/0.6.1/api/core/spark/rdd/package.html @@ -0,0 +1,222 @@ +<?xml version='1.0' encoding='UTF-8'?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> +<html> + <head> + <title>spark.rdd</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8" /> + + <link type="text/css" media="screen" rel="stylesheet" href="../../lib/template.css" /> + <script type="text/javascript" src="../../lib/jquery.js"></script> + <script type="text/javascript" src="../../lib/jquery-ui.js"></script> + <script type="text/javascript" src="../../lib/template.js"></script> + <script type="text/javascript" src="../../lib/tools.tooltip.js"></script> + + </head> + <body onload="sh_highlightDocument('../lib/', '.min.js');" class="value"> + <div id="definition"> + <img src="../../lib/package_big.png" /> + <p id="owner"><a name="spark" class="extype" href="../package.html">spark</a></p> + <h1>rdd</h1> + </div> + + <h4 class="signature" id="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">package</span> + </span> + <span class="symbol"> + <span class="name">rdd</span> + </span> + </h4> + + <div class="fullcommenttop" id="comment"></div> + + + <div id="mbrsel"> + <div id="textfilter"><span class="pre"></span><span class="input"><input accesskey="/" type="text" /></span><span class="post"></span></div> + + + <div id="visbl"> + <span class="filtertype">Visibility</span> + <ol><li class="public in"><span>Public</span></li><li class="all out"><span>All</span></li></ol> + </div> + </div> + + <div id="template"> + <div id="allMembers"> + + + <div class="types members" id="types"> + <h3>Type Members</h3> + <ol><li visbl="pub" name="spark.rdd.CoGroupedRDD" data-isabs="false"> + <a id="CoGroupedRDD:CoGroupedRDD[K]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="CoGroupedRDD.html"><span class="name">CoGroupedRDD</span></a><span class="tparams">[<span name="K">K</span>]</span><span class="result"> extends RDD[(K, Seq[Seq[_]])] with Logging</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.rdd.CoalescedRDD" data-isabs="false"> + <a id="CoalescedRDD:CoalescedRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="CoalescedRDD.html"><span class="name">CoalescedRDD</span></a><span class="tparams">[<span name="T">T</span>]</span><span class="result"> extends RDD[T]</span> + </span> + </h4> + <p class="comment cmt">Coalesce the partitions of a parent RDD (<code>prev</code>) into fewer partitions, so that each partition of +this RDD computes one or more of the parent ones.</p> + </li><li visbl="pub" name="spark.rdd.HadoopRDD" data-isabs="false"> + <a id="HadoopRDD:HadoopRDD[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="HadoopRDD.html"><span class="name">HadoopRDD</span></a><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>]</span><span class="result"> extends RDD[(K, V)]</span> + </span> + </h4> + <p class="comment cmt">An RDD that reads a Hadoop dataset as specified by a JobConf (e.</p> + </li><li visbl="pub" name="spark.rdd.NewHadoopRDD" data-isabs="false"> + <a id="NewHadoopRDD:NewHadoopRDD[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="NewHadoopRDD.html"><span class="name">NewHadoopRDD</span></a><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>]</span><span class="result"> extends RDD[(K, V)] with HadoopMapReduceUtil</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.rdd.PipedRDD" data-isabs="false"> + <a id="PipedRDD:PipedRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="PipedRDD.html"><span class="name">PipedRDD</span></a><span class="tparams">[<span name="T">T</span>]</span><span class="result"> extends RDD[String]</span> + </span> + </h4> + <p class="comment cmt">An RDD that pipes the contents of each parent partition through an external command +(printing them one per line) and returns the output as a collection of strings.</p> + </li><li visbl="pub" name="spark.rdd.RepartitionShuffledRDD" data-isabs="false"> + <a id="RepartitionShuffledRDD:RepartitionShuffledRDD[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="RepartitionShuffledRDD.html"><span class="name">RepartitionShuffledRDD</span></a><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>]</span><span class="result"> extends ShuffledRDD[K, V, V]</span> + </span> + </h4> + <p class="comment cmt">Repartition a key-value pair RDD.</p> + </li><li visbl="pub" name="spark.rdd.SampledRDD" data-isabs="false"> + <a id="SampledRDD:SampledRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="SampledRDD.html"><span class="name">SampledRDD</span></a><span class="tparams">[<span name="T">T</span>]</span><span class="result"> extends RDD[T]</span> + </span> + </h4> + + </li><li visbl="pub" name="spark.rdd.ShuffledAggregatedRDD" data-isabs="false"> + <a id="ShuffledAggregatedRDD:ShuffledAggregatedRDD[K, V, C]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="ShuffledAggregatedRDD.html"><span class="name">ShuffledAggregatedRDD</span></a><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>, <span name="C">C</span>]</span><span class="result"> extends ShuffledRDD[K, V, C]</span> + </span> + </h4> + <p class="comment cmt">The resulting RDD from shuffle and running (hash-based) aggregation.</p> + </li><li visbl="pub" name="spark.rdd.ShuffledRDD" data-isabs="true"> + <a id="ShuffledRDD:ShuffledRDD[K, V, C]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier">abstract </span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="ShuffledRDD.html"><span class="name">ShuffledRDD</span></a><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>, <span name="C">C</span>]</span><span class="result"> extends RDD[(K, C)]</span> + </span> + </h4> + <p class="comment cmt">The resulting RDD from a shuffle (e.</p> + </li><li visbl="pub" name="spark.rdd.ShuffledSortedRDD" data-isabs="false"> + <a id="ShuffledSortedRDD:ShuffledSortedRDD[K, V]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="ShuffledSortedRDD.html"><span class="name">ShuffledSortedRDD</span></a><span class="tparams">[<span name="K">K</span>, <span name="V">V</span>]</span><span class="result"> extends RepartitionShuffledRDD[K, V]</span> + </span> + </h4> + <p class="comment cmt">A sort-based shuffle (that doesn't apply aggregation).</p> + </li><li visbl="pub" name="spark.rdd.UnionRDD" data-isabs="false"> + <a id="UnionRDD:UnionRDD[T]"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">class</span> + </span> + <span class="symbol"> + <a href="UnionRDD.html"><span class="name">UnionRDD</span></a><span class="tparams">[<span name="T">T</span>]</span><span class="result"> extends RDD[T] with Serializable</span> + </span> + </h4> + + </li></ol> + </div> + + + + <div class="values members" id="values"> + <h3>Value Members</h3> + <ol><li visbl="pub" name="spark.rdd.PipedRDD" data-isabs="false"> + <a id="PipedRDD:PipedRDD"></a> + <h4 class="signature"> + <span class="modifier_kind"> + <span class="modifier"></span> + <span class="kind">object</span> + </span> + <span class="symbol"> + <a href="PipedRDD$.html"><span class="name">PipedRDD</span></a><span class="result"> extends Serializable</span> + </span> + </h4> + + </li></ol> + </div> + + + </div> + + <div id="inheritedMembers"> + + </div> + + </div> + + <div id="tooltip"></div> + + <div id="footer"> </div> + + + </body> + </html>
\ No newline at end of file |