summaryrefslogblamecommitdiff
path: root/site/docs/1.5.0/api/java/org/apache/spark/mllib/clustering/StreamingKMeansModel.html
blob: a4258a4bc2d4bc512cc737b0e295289e0b3f497b (plain) (tree)
1
2
3
4
5
6
7



                                                                                                      
                                                                                
                                   
                                       






























                                                                                                                                                                                      
                   






















































































































































































































































































                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       
                   








































                                                                                                                                                                                               
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<!-- NewPage -->
<html lang="en">
<head>
<!-- Generated by javadoc (version 1.7.0_51) on Wed Sep 16 10:26:32 PDT 2015 -->
<title>StreamingKMeansModel</title>
<meta name="date" content="2015-09-16">
<link rel="stylesheet" type="text/css" href="../../../../../stylesheet.css" title="Style">
</head>
<body>
<script type="text/javascript"><!--
    if (location.href.indexOf('is-external=true') == -1) {
        parent.document.title="StreamingKMeansModel";
    }
//-->
</script>
<noscript>
<div>JavaScript is disabled on your browser.</div>
</noscript>
<!-- ========= START OF TOP NAVBAR ======= -->
<div class="topNav"><a name="navbar_top">
<!--   -->
</a><a href="#skip-navbar_top" title="Skip navigation links"></a><a name="navbar_top_firstrow">
<!--   -->
</a>
<ul class="navList" title="Navigation">
<li><a href="../../../../../overview-summary.html">Overview</a></li>
<li><a href="package-summary.html">Package</a></li>
<li class="navBarCell1Rev">Class</li>
<li><a href="package-tree.html">Tree</a></li>
<li><a href="../../../../../deprecated-list.html">Deprecated</a></li>
<li><a href="../../../../../index-all.html">Index</a></li>
<li><a href="../../../../../help-doc.html">Help</a></li>
</ul>
</div>
<div class="subNav">
<ul class="navList">
<li><a href="../../../../../org/apache/spark/mllib/clustering/StreamingKMeans.html" title="class in org.apache.spark.mllib.clustering"><span class="strong">Prev Class</span></a></li>
<li>Next Class</li>
</ul>
<ul class="navList">
<li><a href="../../../../../index.html?org/apache/spark/mllib/clustering/StreamingKMeansModel.html" target="_top">Frames</a></li>
<li><a href="StreamingKMeansModel.html" target="_top">No Frames</a></li>
</ul>
<ul class="navList" id="allclasses_navbar_top">
<li><a href="../../../../../allclasses-noframe.html">All Classes</a></li>
</ul>
<div>
<script type="text/javascript"><!--
  allClassesLink = document.getElementById("allclasses_navbar_top");
  if(window==top) {
    allClassesLink.style.display = "block";
  }
  else {
    allClassesLink.style.display = "none";
  }
  //-->
</script>
</div>
<div>
<ul class="subNavList">
<li>Summary:&nbsp;</li>
<li>Nested&nbsp;|&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li><a href="#constructor_summary">Constr</a>&nbsp;|&nbsp;</li>
<li><a href="#method_summary">Method</a></li>
</ul>
<ul class="subNavList">
<li>Detail:&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li><a href="#constructor_detail">Constr</a>&nbsp;|&nbsp;</li>
<li><a href="#method_detail">Method</a></li>
</ul>
</div>
<a name="skip-navbar_top">
<!--   -->
</a></div>
<!-- ========= END OF TOP NAVBAR ========= -->
<!-- ======== START OF CLASS DATA ======== -->
<div class="header">
<div class="subTitle">org.apache.spark.mllib.clustering</div>
<h2 title="Class StreamingKMeansModel" class="title">Class StreamingKMeansModel</h2>
</div>
<div class="contentContainer">
<ul class="inheritance">
<li>java.lang.Object</li>
<li>
<ul class="inheritance">
<li><a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html" title="class in org.apache.spark.mllib.clustering">org.apache.spark.mllib.clustering.KMeansModel</a></li>
<li>
<ul class="inheritance">
<li>org.apache.spark.mllib.clustering.StreamingKMeansModel</li>
</ul>
</li>
</ul>
</li>
</ul>
<div class="description">
<ul class="blockList">
<li class="blockList">
<dl>
<dt>All Implemented Interfaces:</dt>
<dd>java.io.Serializable, <a href="../../../../../org/apache/spark/Logging.html" title="interface in org.apache.spark">Logging</a>, <a href="../../../../../org/apache/spark/mllib/pmml/PMMLExportable.html" title="interface in org.apache.spark.mllib.pmml">PMMLExportable</a>, <a href="../../../../../org/apache/spark/mllib/util/Saveable.html" title="interface in org.apache.spark.mllib.util">Saveable</a></dd>
</dl>
<hr>
<br>
<pre>public class <span class="strong">StreamingKMeansModel</span>
extends <a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html" title="class in org.apache.spark.mllib.clustering">KMeansModel</a>
implements <a href="../../../../../org/apache/spark/Logging.html" title="interface in org.apache.spark">Logging</a></pre>
<div class="block">:: Experimental ::
 <p>
 StreamingKMeansModel extends MLlib's KMeansModel for streaming
 algorithms, so it can keep track of a continuously updated weight
 associated with each cluster, and also update the model by
 doing a single iteration of the standard k-means algorithm.
 <p>
 The update algorithm uses the "mini-batch" KMeans rule,
 generalized to incorporate forgetfullness (i.e. decay).
 The update rule (for each cluster) is:
 <p>
 <pre><code>
 c_t+1 = [(c_t * n_t * a) + (x_t * m_t)] / [n_t + m_t]
 n_t+t = n_t * a + m_t
 </code></pre>
 <p>
 Where c_t is the previously estimated centroid for that cluster,
 n_t is the number of points assigned to it thus far, x_t is the centroid
 estimated on the current batch, and m_t is the number of points assigned
 to that centroid in the current batch.
 <p>
 The decay factor 'a' scales the contribution of the clusters as estimated thus far,
 by applying a as a discount weighting on the current point when evaluating
 new incoming data. If a=1, all batches are weighted equally. If a=0, new centroids
 are determined entirely by recent data. Lower values correspond to
 more forgetting.
 <p>
 Decay can optionally be specified by a half life and associated
 time unit. The time unit can either be a batch of data or a single
 data point. Considering data arrived at time t, the half life h is defined
 such that at time t + h the discount applied to the data from t is 0.5.
 The definition remains the same whether the time unit is given
 as batches or points.</div>
<dl><dt><span class="strong">See Also:</span></dt><dd><a href="../../../../../serialized-form.html#org.apache.spark.mllib.clustering.StreamingKMeansModel">Serialized Form</a></dd></dl>
</li>
</ul>
</div>
<div class="summary">
<ul class="blockList">
<li class="blockList">
<!-- ======== CONSTRUCTOR SUMMARY ======== -->
<ul class="blockList">
<li class="blockList"><a name="constructor_summary">
<!--   -->
</a>
<h3>Constructor Summary</h3>
<table class="overviewSummary" border="0" cellpadding="3" cellspacing="0" summary="Constructor Summary table, listing constructors, and an explanation">
<caption><span>Constructors</span><span class="tabEnd">&nbsp;</span></caption>
<tr>
<th class="colOne" scope="col">Constructor and Description</th>
</tr>
<tr class="altColor">
<td class="colOne"><code><strong><a href="../../../../../org/apache/spark/mllib/clustering/StreamingKMeansModel.html#StreamingKMeansModel(org.apache.spark.mllib.linalg.Vector[], double[])">StreamingKMeansModel</a></strong>(<a href="../../../../../org/apache/spark/mllib/linalg/Vector.html" title="interface in org.apache.spark.mllib.linalg">Vector</a>[]&nbsp;clusterCenters,
                    double[]&nbsp;clusterWeights)</code>&nbsp;</td>
</tr>
</table>
</li>
</ul>
<!-- ========== METHOD SUMMARY =========== -->
<ul class="blockList">
<li class="blockList"><a name="method_summary">
<!--   -->
</a>
<h3>Method Summary</h3>
<table class="overviewSummary" border="0" cellpadding="3" cellspacing="0" summary="Method Summary table, listing methods, and an explanation">
<caption><span>Methods</span><span class="tabEnd">&nbsp;</span></caption>
<tr>
<th class="colFirst" scope="col">Modifier and Type</th>
<th class="colLast" scope="col">Method and Description</th>
</tr>
<tr class="altColor">
<td class="colFirst"><code><a href="../../../../../org/apache/spark/mllib/linalg/Vector.html" title="interface in org.apache.spark.mllib.linalg">Vector</a>[]</code></td>
<td class="colLast"><code><strong><a href="../../../../../org/apache/spark/mllib/clustering/StreamingKMeansModel.html#clusterCenters()">clusterCenters</a></strong>()</code>&nbsp;</td>
</tr>
<tr class="rowColor">
<td class="colFirst"><code>double[]</code></td>
<td class="colLast"><code><strong><a href="../../../../../org/apache/spark/mllib/clustering/StreamingKMeansModel.html#clusterWeights()">clusterWeights</a></strong>()</code>&nbsp;</td>
</tr>
<tr class="altColor">
<td class="colFirst"><code><a href="../../../../../org/apache/spark/mllib/clustering/StreamingKMeansModel.html" title="class in org.apache.spark.mllib.clustering">StreamingKMeansModel</a></code></td>
<td class="colLast"><code><strong><a href="../../../../../org/apache/spark/mllib/clustering/StreamingKMeansModel.html#update(org.apache.spark.rdd.RDD, double, java.lang.String)">update</a></strong>(<a href="../../../../../org/apache/spark/rdd/RDD.html" title="class in org.apache.spark.rdd">RDD</a>&lt;<a href="../../../../../org/apache/spark/mllib/linalg/Vector.html" title="interface in org.apache.spark.mllib.linalg">Vector</a>&gt;&nbsp;data,
      double&nbsp;decayFactor,
      java.lang.String&nbsp;timeUnit)</code>
<div class="block">Perform a k-means update on a batch of data.</div>
</td>
</tr>
</table>
<ul class="blockList">
<li class="blockList"><a name="methods_inherited_from_class_org.apache.spark.mllib.clustering.KMeansModel">
<!--   -->
</a>
<h3>Methods inherited from class&nbsp;org.apache.spark.mllib.clustering.<a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html" title="class in org.apache.spark.mllib.clustering">KMeansModel</a></h3>
<code><a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#computeCost(org.apache.spark.rdd.RDD)">computeCost</a>, <a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#formatVersion()">formatVersion</a>, <a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#k()">k</a>, <a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#load(org.apache.spark.SparkContext, java.lang.String)">load</a>, <a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#predict(org.apache.spark.api.java.JavaRDD)">predict</a>, <a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#predict(org.apache.spark.rdd.RDD)">predict</a>, <a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#predict(org.apache.spark.mllib.linalg.Vector)">predict</a>, <a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#save(org.apache.spark.SparkContext, java.lang.String)">save</a></code></li>
</ul>
<ul class="blockList">
<li class="blockList"><a name="methods_inherited_from_class_java.lang.Object">
<!--   -->
</a>
<h3>Methods inherited from class&nbsp;java.lang.Object</h3>
<code>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</code></li>
</ul>
<ul class="blockList">
<li class="blockList"><a name="methods_inherited_from_class_org.apache.spark.Logging">
<!--   -->
</a>
<h3>Methods inherited from interface&nbsp;org.apache.spark.<a href="../../../../../org/apache/spark/Logging.html" title="interface in org.apache.spark">Logging</a></h3>
<code><a href="../../../../../org/apache/spark/Logging.html#initializeIfNecessary()">initializeIfNecessary</a>, <a href="../../../../../org/apache/spark/Logging.html#initializeLogging()">initializeLogging</a>, <a href="../../../../../org/apache/spark/Logging.html#isTraceEnabled()">isTraceEnabled</a>, <a href="../../../../../org/apache/spark/Logging.html#log_()">log_</a>, <a href="../../../../../org/apache/spark/Logging.html#log()">log</a>, <a href="../../../../../org/apache/spark/Logging.html#logDebug(scala.Function0)">logDebug</a>, <a href="../../../../../org/apache/spark/Logging.html#logDebug(scala.Function0, java.lang.Throwable)">logDebug</a>, <a href="../../../../../org/apache/spark/Logging.html#logError(scala.Function0)">logError</a>, <a href="../../../../../org/apache/spark/Logging.html#logError(scala.Function0, java.lang.Throwable)">logError</a>, <a href="../../../../../org/apache/spark/Logging.html#logInfo(scala.Function0)">logInfo</a>, <a href="../../../../../org/apache/spark/Logging.html#logInfo(scala.Function0, java.lang.Throwable)">logInfo</a>, <a href="../../../../../org/apache/spark/Logging.html#logName()">logName</a>, <a href="../../../../../org/apache/spark/Logging.html#logTrace(scala.Function0)">logTrace</a>, <a href="../../../../../org/apache/spark/Logging.html#logTrace(scala.Function0, java.lang.Throwable)">logTrace</a>, <a href="../../../../../org/apache/spark/Logging.html#logWarning(scala.Function0)">logWarning</a>, <a href="../../../../../org/apache/spark/Logging.html#logWarning(scala.Function0, java.lang.Throwable)">logWarning</a></code></li>
</ul>
<ul class="blockList">
<li class="blockList"><a name="methods_inherited_from_class_org.apache.spark.mllib.pmml.PMMLExportable">
<!--   -->
</a>
<h3>Methods inherited from interface&nbsp;org.apache.spark.mllib.pmml.<a href="../../../../../org/apache/spark/mllib/pmml/PMMLExportable.html" title="interface in org.apache.spark.mllib.pmml">PMMLExportable</a></h3>
<code><a href="../../../../../org/apache/spark/mllib/pmml/PMMLExportable.html#toPMML()">toPMML</a>, <a href="../../../../../org/apache/spark/mllib/pmml/PMMLExportable.html#toPMML(java.io.OutputStream)">toPMML</a>, <a href="../../../../../org/apache/spark/mllib/pmml/PMMLExportable.html#toPMML(org.apache.spark.SparkContext, java.lang.String)">toPMML</a>, <a href="../../../../../org/apache/spark/mllib/pmml/PMMLExportable.html#toPMML(javax.xml.transform.stream.StreamResult)">toPMML</a>, <a href="../../../../../org/apache/spark/mllib/pmml/PMMLExportable.html#toPMML(java.lang.String)">toPMML</a></code></li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
<div class="details">
<ul class="blockList">
<li class="blockList">
<!-- ========= CONSTRUCTOR DETAIL ======== -->
<ul class="blockList">
<li class="blockList"><a name="constructor_detail">
<!--   -->
</a>
<h3>Constructor Detail</h3>
<a name="StreamingKMeansModel(org.apache.spark.mllib.linalg.Vector[], double[])">
<!--   -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>StreamingKMeansModel</h4>
<pre>public&nbsp;StreamingKMeansModel(<a href="../../../../../org/apache/spark/mllib/linalg/Vector.html" title="interface in org.apache.spark.mllib.linalg">Vector</a>[]&nbsp;clusterCenters,
                    double[]&nbsp;clusterWeights)</pre>
</li>
</ul>
</li>
</ul>
<!-- ============ METHOD DETAIL ========== -->
<ul class="blockList">
<li class="blockList"><a name="method_detail">
<!--   -->
</a>
<h3>Method Detail</h3>
<a name="clusterCenters()">
<!--   -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>clusterCenters</h4>
<pre>public&nbsp;<a href="../../../../../org/apache/spark/mllib/linalg/Vector.html" title="interface in org.apache.spark.mllib.linalg">Vector</a>[]&nbsp;clusterCenters()</pre>
<dl>
<dt><strong>Overrides:</strong></dt>
<dd><code><a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html#clusterCenters()">clusterCenters</a></code>&nbsp;in class&nbsp;<code><a href="../../../../../org/apache/spark/mllib/clustering/KMeansModel.html" title="class in org.apache.spark.mllib.clustering">KMeansModel</a></code></dd>
</dl>
</li>
</ul>
<a name="clusterWeights()">
<!--   -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>clusterWeights</h4>
<pre>public&nbsp;double[]&nbsp;clusterWeights()</pre>
</li>
</ul>
<a name="update(org.apache.spark.rdd.RDD, double, java.lang.String)">
<!--   -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>update</h4>
<pre>public&nbsp;<a href="../../../../../org/apache/spark/mllib/clustering/StreamingKMeansModel.html" title="class in org.apache.spark.mllib.clustering">StreamingKMeansModel</a>&nbsp;update(<a href="../../../../../org/apache/spark/rdd/RDD.html" title="class in org.apache.spark.rdd">RDD</a>&lt;<a href="../../../../../org/apache/spark/mllib/linalg/Vector.html" title="interface in org.apache.spark.mllib.linalg">Vector</a>&gt;&nbsp;data,
                          double&nbsp;decayFactor,
                          java.lang.String&nbsp;timeUnit)</pre>
<div class="block">Perform a k-means update on a batch of data.</div>
<dl><dt><span class="strong">Parameters:</span></dt><dd><code>data</code> - (undocumented)</dd><dd><code>decayFactor</code> - (undocumented)</dd><dd><code>timeUnit</code> - (undocumented)</dd>
<dt><span class="strong">Returns:</span></dt><dd>(undocumented)</dd></dl>
</li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
</div>
<!-- ========= END OF CLASS DATA ========= -->
<!-- ======= START OF BOTTOM NAVBAR ====== -->
<div class="bottomNav"><a name="navbar_bottom">
<!--   -->
</a><a href="#skip-navbar_bottom" title="Skip navigation links"></a><a name="navbar_bottom_firstrow">
<!--   -->
</a>
<ul class="navList" title="Navigation">
<li><a href="../../../../../overview-summary.html">Overview</a></li>
<li><a href="package-summary.html">Package</a></li>
<li class="navBarCell1Rev">Class</li>
<li><a href="package-tree.html">Tree</a></li>
<li><a href="../../../../../deprecated-list.html">Deprecated</a></li>
<li><a href="../../../../../index-all.html">Index</a></li>
<li><a href="../../../../../help-doc.html">Help</a></li>
</ul>
</div>
<div class="subNav">
<ul class="navList">
<li><a href="../../../../../org/apache/spark/mllib/clustering/StreamingKMeans.html" title="class in org.apache.spark.mllib.clustering"><span class="strong">Prev Class</span></a></li>
<li>Next Class</li>
</ul>
<ul class="navList">
<li><a href="../../../../../index.html?org/apache/spark/mllib/clustering/StreamingKMeansModel.html" target="_top">Frames</a></li>
<li><a href="StreamingKMeansModel.html" target="_top">No Frames</a></li>
</ul>
<ul class="navList" id="allclasses_navbar_bottom">
<li><a href="../../../../../allclasses-noframe.html">All Classes</a></li>
</ul>
<div>
<script type="text/javascript"><!--
  allClassesLink = document.getElementById("allclasses_navbar_bottom");
  if(window==top) {
    allClassesLink.style.display = "block";
  }
  else {
    allClassesLink.style.display = "none";
  }
  //-->
</script>
</div>
<div>
<ul class="subNavList">
<li>Summary:&nbsp;</li>
<li>Nested&nbsp;|&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li><a href="#constructor_summary">Constr</a>&nbsp;|&nbsp;</li>
<li><a href="#method_summary">Method</a></li>
</ul>
<ul class="subNavList">
<li>Detail:&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li><a href="#constructor_detail">Constr</a>&nbsp;|&nbsp;</li>
<li><a href="#method_detail">Method</a></li>
</ul>
</div>
<a name="skip-navbar_bottom">
<!--   -->
</a></div>
<!-- ======== END OF BOTTOM NAVBAR ======= -->
<script defer="defer" type="text/javascript" src="../../../../../lib/jquery.js"></script><script defer="defer" type="text/javascript" src="../../../../../lib/api-javadocs.js"></script></body>
</html>