Updating docs for 1.0.1 release

author: Patrick Wendell <pwendell@apache.org> 2014-07-11 17:23:23 +0000
committer: Patrick Wendell <pwendell@apache.org> 2014-07-11 17:23:23 +0000
commit: 0beac4e243f85e71554fe04093b09eb1745fea82 (patch)
tree: bc20d10426c5d57e2f189305865dc2bbec447923 /site/docs/1.0.1/mllib-clustering.html
parent: ddec2123ba6ab95543d1b250d4f20fb811c48f09 (diff)
download: spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.tar.gz
spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.tar.bz2
spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.zip
1 files changed, 264 insertions, 0 deletions
diff --git a/site/docs/1.0.1/mllib-clustering.html b/site/docs/1.0.1/mllib-clustering.html
new file mode 100644
index 000000000..f1830f268
--- /dev/null
+++ b/site/docs/1.0.1/mllib-clustering.html
@@ -0,0 +1,264 @@
+<!DOCTYPE html>
+<!--[if lt IE 7]>      <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
+<!--[if IE 7]>         <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
+<!--[if IE 8]>         <html class="no-js lt-ie9"> <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
+    <head>
+        <meta charset="utf-8">
+        <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
+        <title>Clustering - MLlib - Spark 1.0.1 Documentation</title>
+        <meta name="description" content="">
+
+        
+
+        <link rel="stylesheet" href="css/bootstrap.min.css">
+        <style>
+            body {
+                padding-top: 60px;
+                padding-bottom: 40px;
+            }
+        </style>
+        <meta name="viewport" content="width=device-width">
+        <link rel="stylesheet" href="css/bootstrap-responsive.min.css">
+        <link rel="stylesheet" href="css/main.css">
+
+        <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script>
+
+        <link rel="stylesheet" href="css/pygments-default.css">
+
+        
+        <!-- Google analytics script -->
+        <script type="text/javascript">
+          var _gaq = _gaq || [];
+          _gaq.push(['_setAccount', 'UA-32518208-1']);
+          _gaq.push(['_trackPageview']);
+
+          (function() {
+            var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+            ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+            var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+          })();
+        </script>
+        
+
+    </head>
+    <body>
+        <!--[if lt IE 7]>
+            <p class="chromeframe">You are using an outdated browser. <a href="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
+        <![endif]-->
+
+        <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
+
+        <div class="navbar navbar-fixed-top" id="topbar">
+            <div class="navbar-inner">
+                <div class="container">
+                    <div class="brand"><a href="index.html">
+                      <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">1.0.1</span>
+                    </div>
+                    <ul class="nav">
+                        <!--TODO(andyk): Add class="active" attribute to li some how.-->
+                        <li><a href="index.html">Overview</a></li>
+
+                        <li class="dropdown">
+                            <a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="quick-start.html">Quick Start</a></li>
+                                <li><a href="programming-guide.html">Spark Programming Guide</a></li>
+                                <li class="divider"></li>
+                                <li><a href="streaming-programming-guide.html">Spark Streaming</a></li>
+                                <li><a href="sql-programming-guide.html">Spark SQL</a></li>
+                                <li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li>
+                                <li><a href="graphx-programming-guide.html">GraphX (Graph Processing)</a></li>
+                                <li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li>
+                            </ul>
+                        </li>
+
+                        <li class="dropdown">
+                            <a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="api/scala/index.html#org.apache.spark.package">Scaladoc</a></li>
+                                <li><a href="api/java/index.html">Javadoc</a></li>
+                                <li><a href="api/python/index.html">Python API</a></li>
+                            </ul>
+                        </li>
+
+                        <li class="dropdown">
+                            <a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="cluster-overview.html">Overview</a></li>
+                                <li><a href="submitting-applications.html">Submitting Applications</a></li>
+                                <li class="divider"></li>
+                                <li><a href="ec2-scripts.html">Amazon EC2</a></li>
+                                <li><a href="spark-standalone.html">Standalone Mode</a></li>
+                                <li><a href="running-on-mesos.html">Mesos</a></li>
+                                <li><a href="running-on-yarn.html">YARN</a></li>
+                            </ul>
+                        </li>
+
+                        <li class="dropdown">
+                            <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="configuration.html">Configuration</a></li>
+                                <li><a href="monitoring.html">Monitoring</a></li>
+                                <li><a href="tuning.html">Tuning Guide</a></li>
+                                <li><a href="job-scheduling.html">Job Scheduling</a></li>
+                                <li><a href="security.html">Security</a></li>
+                                <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
+                                <li><a href="hadoop-third-party-distributions.html">3<sup>rd</sup>-Party Hadoop Distros</a></li>
+                                <li class="divider"></li>
+                                <li><a href="building-with-maven.html">Building Spark with Maven</a></li>
+                                <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li>
+                            </ul>
+                        </li>
+                    </ul>
+                    <!--<p class="navbar-text pull-right"><span class="version-text">v1.0.1</span></p>-->
+                </div>
+            </div>
+        </div>
+
+        <div class="container" id="content">
+          
+            <h1 class="title"><a href="mllib-guide.html">MLlib</a> - Clustering</h1>
+          
+
+          <ul id="markdown-toc">
+  <li><a href="#clustering">Clustering</a></li>
+  <li><a href="#examples">Examples</a></li>
+</ul>
+
+<h2 id="clustering">Clustering</h2>
+
+<p>Clustering is an unsupervised learning problem whereby we aim to group subsets
+of entities with one another based on some notion of similarity.  Clustering is
+often used for exploratory analysis and/or as a component of a hierarchical
+supervised learning pipeline (in which distinct classifiers or regression
+models are trained for each cluster). </p>
+
+<p>MLlib supports
+<a href="http://en.wikipedia.org/wiki/K-means_clustering">k-means</a> clustering, one of
+the most commonly used clustering algorithms that clusters the data points into
+predefined number of clusters. The MLlib implementation includes a parallelized
+variant of the <a href="http://en.wikipedia.org/wiki/K-means%2B%2B">k-means++</a> method
+called <a href="http://theory.stanford.edu/~sergei/papers/vldb12-kmpar.pdf">kmeans||</a>.
+The implementation in MLlib has the following parameters:  </p>
+
+<ul>
+  <li><em>k</em> is the number of desired clusters.</li>
+  <li><em>maxIterations</em> is the maximum number of iterations to run.</li>
+  <li><em>initializationMode</em> specifies either random initialization or
+initialization via k-means||.</li>
+  <li><em>runs</em> is the number of times to run the k-means algorithm (k-means is not
+guaranteed to find a globally optimal solution, and when run multiple times on
+a given dataset, the algorithm returns the best clustering result).</li>
+  <li><em>initializationSteps</em> determines the number of steps in the k-means|| algorithm.</li>
+  <li><em>epsilon</em> determines the distance threshold within which we consider k-means to have converged. </li>
+</ul>
+
+<h2 id="examples">Examples</h2>
+
+<div class="codetabs">
+<div data-lang="scala">
+    <p>Following code snippets can be executed in <code>spark-shell</code>.</p>
+
+    <p>In the following example after loading and parsing data, we use the
+<a href="api/scala/index.html#org.apache.spark.mllib.clustering.KMeans"><code>KMeans</code></a> object to cluster the data
+into two clusters. The number of desired clusters is passed to the algorithm. We then compute Within
+Set Sum of Squared Error (WSSSE). You can reduce this error measure by increasing <em>k</em>. In fact the
+optimal <em>k</em> is usually one where there is an &#8220;elbow&#8221; in the WSSSE graph.</p>
+
+    <div class="highlight"><pre><code class="scala"><span class="k">import</span> <span class="nn">org.apache.spark.mllib.clustering.KMeans</span>
+<span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span>
+
+<span class="c1">// Load and parse the data</span>
+<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">&quot;data/kmeans_data.txt&quot;</span><span class="o">)</span>
+<span class="k">val</span> <span class="n">parsedData</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">s</span> <span class="k">=&gt;</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="n">s</span><span class="o">.</span><span class="n">split</span><span class="o">(</span><span class="sc">&#39; &#39;</span><span class="o">).</span><span class="n">map</span><span class="o">(</span><span class="k">_</span><span class="o">.</span><span class="n">toDouble</span><span class="o">)))</span>
+
+<span class="c1">// Cluster the data into two classes using KMeans</span>
+<span class="k">val</span> <span class="n">numClusters</span> <span class="k">=</span> <span class="mi">2</span>
+<span class="k">val</span> <span class="n">numIterations</span> <span class="k">=</span> <span class="mi">20</span>
+<span class="k">val</span> <span class="n">clusters</span> <span class="k">=</span> <span class="nc">KMeans</span><span class="o">.</span><span class="n">train</span><span class="o">(</span><span class="n">parsedData</span><span class="o">,</span> <span class="n">numClusters</span><span class="o">,</span> <span class="n">numIterations</span><span class="o">)</span>
+
+<span class="c1">// Evaluate clustering by computing Within Set Sum of Squared Errors</span>
+<span class="k">val</span> <span class="nc">WSSSE</span> <span class="k">=</span> <span class="n">clusters</span><span class="o">.</span><span class="n">computeCost</span><span class="o">(</span><span class="n">parsedData</span><span class="o">)</span>
+<span class="n">println</span><span class="o">(</span><span class="s">&quot;Within Set Sum of Squared Errors = &quot;</span> <span class="o">+</span> <span class="nc">WSSSE</span><span class="o">)</span>
+</code></pre></div>
+
+  </div>
+
+<div data-lang="java">
+    <p>All of MLlib&#8217;s methods use Java-friendly types, so you can import and call them there the same
+way you do in Scala. The only caveat is that the methods take Scala RDD objects, while the
+Spark Java API uses a separate <code>JavaRDD</code> class. You can convert a Java RDD to a Scala one by
+calling <code>.rdd()</code> on your <code>JavaRDD</code> object.</p>
+  </div>
+
+<div data-lang="python">
+    <p>Following examples can be tested in the PySpark shell.</p>
+
+    <p>In the following example after loading and parsing data, we use the KMeans object to cluster the
+data into two clusters. The number of desired clusters is passed to the algorithm. We then compute
+Within Set Sum of Squared Error (WSSSE). You can reduce this error measure by increasing <em>k</em>. In
+fact the optimal <em>k</em> is usually one where there is an &#8220;elbow&#8221; in the WSSSE graph.</p>
+
+    <div class="highlight"><pre><code class="python"><span class="kn">from</span> <span class="nn">pyspark.mllib.clustering</span> <span class="kn">import</span> <span class="n">KMeans</span>
+<span class="kn">from</span> <span class="nn">numpy</span> <span class="kn">import</span> <span class="n">array</span>
+<span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span>
+
+<span class="c"># Load and parse the data</span>
+<span class="n">data</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="s">&quot;data/kmeans_data.txt&quot;</span><span class="p">)</span>
+<span class="n">parsedData</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">line</span><span class="p">:</span> <span class="n">array</span><span class="p">([</span><span class="nb">float</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">&#39; &#39;</span><span class="p">)]))</span>
+
+<span class="c"># Build the model (cluster the data)</span>
+<span class="n">clusters</span> <span class="o">=</span> <span class="n">KMeans</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">parsedData</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="n">maxIterations</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
+        <span class="n">runs</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">initializationMode</span><span class="o">=</span><span class="s">&quot;random&quot;</span><span class="p">)</span>
+
+<span class="c"># Evaluate clustering by computing Within Set Sum of Squared Errors</span>
+<span class="k">def</span> <span class="nf">error</span><span class="p">(</span><span class="n">point</span><span class="p">):</span>
+    <span class="n">center</span> <span class="o">=</span> <span class="n">clusters</span><span class="o">.</span><span class="n">centers</span><span class="p">[</span><span class="n">clusters</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">point</span><span class="p">)]</span>
+    <span class="k">return</span> <span class="n">sqrt</span><span class="p">(</span><span class="nb">sum</span><span class="p">([</span><span class="n">x</span><span class="o">**</span><span class="mi">2</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="p">(</span><span class="n">point</span> <span class="o">-</span> <span class="n">center</span><span class="p">)]))</span>
+
+<span class="n">WSSSE</span> <span class="o">=</span> <span class="n">parsedData</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">point</span><span class="p">:</span> <span class="n">error</span><span class="p">(</span><span class="n">point</span><span class="p">))</span><span class="o">.</span><span class="n">reduce</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">:</span> <span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="p">)</span>
+<span class="k">print</span><span class="p">(</span><span class="s">&quot;Within Set Sum of Squared Error = &quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">WSSSE</span><span class="p">))</span>
+</code></pre></div>
+
+  </div>
+
+</div>
+
+
+        </div> <!-- /container -->
+
+        <script src="js/vendor/jquery-1.8.0.min.js"></script>
+        <script src="js/vendor/bootstrap.min.js"></script>
+        <script src="js/main.js"></script>
+
+        <!-- MathJax Section -->
+        <script type="text/x-mathjax-config">
+            MathJax.Hub.Config({
+                TeX: { equationNumbers: { autoNumber: "AMS" } }
+            });
+        </script>
+        <script>
+            // Note that we load MathJax this way to work with local file (file://), HTTP and HTTPS.
+            // We could use "//cdn.mathjax...", but that won't support "file://".
+            (function(d, script) {
+                script = d.createElement('script');
+                script.type = 'text/javascript';
+                script.async = true;
+                script.onload = function(){
+                    MathJax.Hub.Config({
+                        tex2jax: {
+                            inlineMath: [ ["$", "$"], ["\\\\(","\\\\)"] ],
+                            displayMath: [ ["$$","$$"], ["\\[", "\\]"] ], 
+                            processEscapes: true,
+                            skipTags: ['script', 'noscript', 'style', 'textarea', 'pre']
+                        }
+                    });
+                };
+                script.src = ('https:' == document.location.protocol ? 'https://' : 'http://') +
+                    'cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML';
+                d.getElementsByTagName('head')[0].appendChild(script);
+            }(document));
+        </script>
+    </body>
+</html>
author	Patrick Wendell <pwendell@apache.org>	2014-07-11 17:23:23 +0000
committer	Patrick Wendell <pwendell@apache.org>	2014-07-11 17:23:23 +0000
commit	0beac4e243f85e71554fe04093b09eb1745fea82 (patch)
tree	bc20d10426c5d57e2f189305865dc2bbec447923 /site/docs/1.0.1/mllib-clustering.html
parent	ddec2123ba6ab95543d1b250d4f20fb811c48f09 (diff)
download	spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.tar.gz spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.tar.bz2 spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.zip