| |
| <!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 - spark.ml - Spark 1.6.2 Documentation</title> |
| |
| |
| |
| |
| <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-32518208-2']); |
| _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">1.6.2</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">DataFrames, Datasets and 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> |
| <li><a href="sparkr.html">SparkR (R 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">Scala</a></li> |
| <li><a href="api/java/index.html">Java</a></li> |
| <li><a href="api/python/index.html">Python</a></li> |
| <li><a href="api/R/index.html">R</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="spark-standalone.html">Spark Standalone</a></li> |
| <li><a href="running-on-mesos.html">Mesos</a></li> |
| <li><a href="running-on-yarn.html">YARN</a></li> |
| <li class="divider"></li> |
| <li><a href="ec2-scripts.html">Amazon EC2</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 class="divider"></li> |
| <li><a href="building-spark.html">Building Spark</a></li> |
| <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li> |
| <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Supplemental+Spark+Projects">Supplemental Projects</a></li> |
| </ul> |
| </li> |
| </ul> |
| <!--<p class="navbar-text pull-right"><span class="version-text">v1.6.2</span></p>--> |
| </div> |
| </div> |
| </div> |
| |
| <div class="container-wrapper"> |
| |
| |
| <div class="left-menu-wrapper"> |
| <div class="left-menu"> |
| <h3><a href="ml-guide.html">spark.ml package</a></h3> |
| |
| <ul> |
| |
| <li> |
| <a href="ml-guide.html"> |
| |
| Overview: estimators, transformers and pipelines |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="ml-features.html"> |
| |
| Extracting, transforming and selecting features |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="ml-classification-regression.html"> |
| |
| Classification and Regression |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="ml-clustering.html"> |
| |
| <b>Clustering</b> |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="ml-advanced.html"> |
| |
| Advanced topics |
| |
| </a> |
| </li> |
| |
| |
| </ul> |
| |
| <h3><a href="mllib-guide.html">spark.mllib package</a></h3> |
| |
| <ul> |
| |
| <li> |
| <a href="mllib-data-types.html"> |
| |
| Data types |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-statistics.html"> |
| |
| Basic statistics |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-classification-regression.html"> |
| |
| Classification and regression |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-collaborative-filtering.html"> |
| |
| Collaborative filtering |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-clustering.html"> |
| |
| Clustering |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-dimensionality-reduction.html"> |
| |
| Dimensionality reduction |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-feature-extraction.html"> |
| |
| Feature extraction and transformation |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-frequent-pattern-mining.html"> |
| |
| Frequent pattern mining |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-evaluation-metrics.html"> |
| |
| Evaluation metrics |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-pmml-model-export.html"> |
| |
| PMML model export |
| |
| </a> |
| </li> |
| |
| |
| <li> |
| <a href="mllib-optimization.html"> |
| |
| Optimization (developer) |
| |
| </a> |
| </li> |
| |
| |
| </ul> |
| |
| </div> |
| </div> |
| <input id="nav-trigger" class="nav-trigger" checked type="checkbox"> |
| <label for="nav-trigger"></label> |
| <div class="content-with-sidebar" id="content"> |
| |
| <h1 class="title">Clustering - spark.ml</h1> |
| |
| |
| <p>In this section, we introduce the pipeline API for <a href="mllib-clustering.html">clustering in mllib</a>.</p> |
| |
| <p><strong>Table of Contents</strong></p> |
| |
| <ul id="markdown-toc"> |
| <li><a href="#k-means" id="markdown-toc-k-means">K-means</a> <ul> |
| <li><a href="#input-columns" id="markdown-toc-input-columns">Input Columns</a></li> |
| <li><a href="#output-columns" id="markdown-toc-output-columns">Output Columns</a></li> |
| <li><a href="#example" id="markdown-toc-example">Example</a></li> |
| </ul> |
| </li> |
| <li><a href="#latent-dirichlet-allocation-lda" id="markdown-toc-latent-dirichlet-allocation-lda">Latent Dirichlet allocation (LDA)</a></li> |
| </ul> |
| |
| <h2 id="k-means">K-means</h2> |
| |
| <p><a href="http://en.wikipedia.org/wiki/K-means_clustering">k-means</a> is one of the |
| most commonly used clustering algorithms that clusters the data points into a |
| 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>.</p> |
| |
| <p><code>KMeans</code> is implemented as an <code>Estimator</code> and generates a <code>KMeansModel</code> as the base model.</p> |
| |
| <h3 id="input-columns">Input Columns</h3> |
| |
| <table class="table"> |
| <thead> |
| <tr> |
| <th align="left">Param name</th> |
| <th align="left">Type(s)</th> |
| <th align="left">Default</th> |
| <th align="left">Description</th> |
| </tr> |
| </thead> |
| <tbody> |
| <tr> |
| <td>featuresCol</td> |
| <td>Vector</td> |
| <td>"features"</td> |
| <td>Feature vector</td> |
| </tr> |
| </tbody> |
| </table> |
| |
| <h3 id="output-columns">Output Columns</h3> |
| |
| <table class="table"> |
| <thead> |
| <tr> |
| <th align="left">Param name</th> |
| <th align="left">Type(s)</th> |
| <th align="left">Default</th> |
| <th align="left">Description</th> |
| </tr> |
| </thead> |
| <tbody> |
| <tr> |
| <td>predictionCol</td> |
| <td>Int</td> |
| <td>"prediction"</td> |
| <td>Predicted cluster center</td> |
| </tr> |
| </tbody> |
| </table> |
| |
| <h3 id="example">Example</h3> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="scala"> |
| <p>Refer to the <a href="api/scala/index.html#org.apache.spark.ml.clustering.KMeans">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre><span class="k">import</span> <span class="nn">org.apache.spark.ml.clustering.KMeans</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span> |
| |
| <span class="c1">// Crates a DataFrame</span> |
| <span class="k">val</span> <span class="n">dataset</span><span class="k">:</span> <span class="kt">DataFrame</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="o">(</span><span class="nc">Seq</span><span class="o">(</span> |
| <span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">0.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">)),</span> |
| <span class="o">(</span><span class="mi">2</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">0.1</span><span class="o">,</span> <span class="mf">0.1</span><span class="o">,</span> <span class="mf">0.1</span><span class="o">)),</span> |
| <span class="o">(</span><span class="mi">3</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">0.2</span><span class="o">,</span> <span class="mf">0.2</span><span class="o">,</span> <span class="mf">0.2</span><span class="o">)),</span> |
| <span class="o">(</span><span class="mi">4</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">9.0</span><span class="o">,</span> <span class="mf">9.0</span><span class="o">,</span> <span class="mf">9.0</span><span class="o">)),</span> |
| <span class="o">(</span><span class="mi">5</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">9.1</span><span class="o">,</span> <span class="mf">9.1</span><span class="o">,</span> <span class="mf">9.1</span><span class="o">)),</span> |
| <span class="o">(</span><span class="mi">6</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="mf">9.2</span><span class="o">,</span> <span class="mf">9.2</span><span class="o">,</span> <span class="mf">9.2</span><span class="o">))</span> |
| <span class="o">)).</span><span class="n">toDF</span><span class="o">(</span><span class="s">"id"</span><span class="o">,</span> <span class="s">"features"</span><span class="o">)</span> |
| |
| <span class="c1">// Trains a k-means model</span> |
| <span class="k">val</span> <span class="n">kmeans</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">KMeans</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setK</span><span class="o">(</span><span class="mi">2</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setFeaturesCol</span><span class="o">(</span><span class="s">"features"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setPredictionCol</span><span class="o">(</span><span class="s">"prediction"</span><span class="o">)</span> |
| <span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="n">kmeans</span><span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="c1">// Shows the result</span> |
| <span class="n">println</span><span class="o">(</span><span class="s">"Final Centers: "</span><span class="o">)</span> |
| <span class="n">model</span><span class="o">.</span><span class="n">clusterCenters</span><span class="o">.</span><span class="n">foreach</span><span class="o">(</span><span class="n">println</span><span class="o">)</span> |
| </pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/ml/KMeansExample.scala" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="java"> |
| <p>Refer to the <a href="api/java/org/apache/spark/ml/clustering/KMeans.html">Java API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre><span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.KMeansModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.KMeans</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vector</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.VectorUDT</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.DataFrame</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Row</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.Metadata</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.StructField</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.StructType</span><span class="o">;</span> |
| |
| <span class="c1">// Loads data</span> |
| <span class="n">JavaRDD</span><span class="o"><</span><span class="n">Row</span><span class="o">></span> <span class="n">points</span> <span class="o">=</span> <span class="n">jsc</span><span class="o">.</span><span class="na">textFile</span><span class="o">(</span><span class="n">inputFile</span><span class="o">).</span><span class="na">map</span><span class="o">(</span><span class="k">new</span> <span class="nf">ParsePoint</span><span class="o">());</span> |
| <span class="n">StructField</span><span class="o">[]</span> <span class="n">fields</span> <span class="o">=</span> <span class="o">{</span><span class="k">new</span> <span class="nf">StructField</span><span class="o">(</span><span class="s">"features"</span><span class="o">,</span> <span class="k">new</span> <span class="nf">VectorUDT</span><span class="o">(),</span> <span class="kc">false</span><span class="o">,</span> <span class="n">Metadata</span><span class="o">.</span><span class="na">empty</span><span class="o">())};</span> |
| <span class="n">StructType</span> <span class="n">schema</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">StructType</span><span class="o">(</span><span class="n">fields</span><span class="o">);</span> |
| <span class="n">DataFrame</span> <span class="n">dataset</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">points</span><span class="o">,</span> <span class="n">schema</span><span class="o">);</span> |
| |
| <span class="c1">// Trains a k-means model</span> |
| <span class="n">KMeans</span> <span class="n">kmeans</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">KMeans</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setK</span><span class="o">(</span><span class="n">k</span><span class="o">);</span> |
| <span class="n">KMeansModel</span> <span class="n">model</span> <span class="o">=</span> <span class="n">kmeans</span><span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">);</span> |
| |
| <span class="c1">// Shows the result</span> |
| <span class="n">Vector</span><span class="o">[]</span> <span class="n">centers</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="na">clusterCenters</span><span class="o">();</span> |
| <span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">println</span><span class="o">(</span><span class="s">"Cluster Centers: "</span><span class="o">);</span> |
| <span class="k">for</span> <span class="o">(</span><span class="n">Vector</span> <span class="nl">center:</span> <span class="n">centers</span><span class="o">)</span> <span class="o">{</span> |
| <span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">println</span><span class="o">(</span><span class="n">center</span><span class="o">);</span> |
| <span class="o">}</span> |
| </pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java" in the Spark repo.</small></div> |
| </div> |
| |
| </div> |
| |
| <h2 id="latent-dirichlet-allocation-lda">Latent Dirichlet allocation (LDA)</h2> |
| |
| <p><code>LDA</code> is implemented as an <code>Estimator</code> that supports both <code>EMLDAOptimizer</code> and <code>OnlineLDAOptimizer</code>, |
| and generates a <code>LDAModel</code> as the base models. Expert users may cast a <code>LDAModel</code> generated by |
| <code>EMLDAOptimizer</code> to a <code>DistributedLDAModel</code> if needed.</p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="scala"> |
| |
| <p>Refer to the <a href="api/scala/index.html#org.apache.spark.ml.clustering.LDA">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre><span class="k">import</span> <span class="nn">org.apache.spark.ml.clustering.LDA</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.sql.</span><span class="o">{</span><span class="nc">Row</span><span class="o">,</span> <span class="nc">SQLContext</span><span class="o">}</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.sql.types.</span><span class="o">{</span><span class="nc">StructField</span><span class="o">,</span> <span class="nc">StructType</span><span class="o">}</span> |
| |
| <span class="c1">// Loads data</span> |
| <span class="k">val</span> <span class="n">rowRDD</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="n">input</span><span class="o">).</span><span class="n">filter</span><span class="o">(</span><span class="k">_</span><span class="o">.</span><span class="n">nonEmpty</span><span class="o">)</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">split</span><span class="o">(</span><span class="s">" "</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="n">map</span><span class="o">(</span><span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">).</span><span class="n">map</span><span class="o">(</span><span class="nc">Row</span><span class="o">(</span><span class="k">_</span><span class="o">))</span> |
| <span class="k">val</span> <span class="n">schema</span> <span class="k">=</span> <span class="nc">StructType</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="nc">StructField</span><span class="o">(</span><span class="nc">FEATURES_COL</span><span class="o">,</span> <span class="k">new</span> <span class="nc">VectorUDT</span><span class="o">,</span> <span class="kc">false</span><span class="o">)))</span> |
| <span class="k">val</span> <span class="n">dataset</span> <span class="k">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="o">(</span><span class="n">rowRDD</span><span class="o">,</span> <span class="n">schema</span><span class="o">)</span> |
| |
| <span class="c1">// Trains a LDA model</span> |
| <span class="k">val</span> <span class="n">lda</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">LDA</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setK</span><span class="o">(</span><span class="mi">10</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setMaxIter</span><span class="o">(</span><span class="mi">10</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setFeaturesCol</span><span class="o">(</span><span class="nc">FEATURES_COL</span><span class="o">)</span> |
| <span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="n">lda</span><span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| <span class="k">val</span> <span class="n">transformed</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="k">val</span> <span class="n">ll</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">logLikelihood</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| <span class="k">val</span> <span class="n">lp</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">logPerplexity</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="c1">// describeTopics</span> |
| <span class="k">val</span> <span class="n">topics</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">describeTopics</span><span class="o">(</span><span class="mi">3</span><span class="o">)</span> |
| |
| <span class="c1">// Shows the result</span> |
| <span class="n">topics</span><span class="o">.</span><span class="n">show</span><span class="o">(</span><span class="kc">false</span><span class="o">)</span> |
| <span class="n">transformed</span><span class="o">.</span><span class="n">show</span><span class="o">(</span><span class="kc">false</span><span class="o">)</span> |
| </pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/ml/LDAExample.scala" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="java"> |
| |
| <p>Refer to the <a href="api/java/org/apache/spark/ml/clustering/LDA.html">Java API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre><span class="kn">import</span> <span class="nn">java.util.regex.Pattern</span><span class="o">;</span> |
| |
| <span class="kn">import</span> <span class="nn">org.apache.spark.SparkConf</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaRDD</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaSparkContext</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.function.Function</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.LDA</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.LDAModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vector</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.VectorUDT</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.DataFrame</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Row</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.SQLContext</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.catalyst.expressions.GenericRow</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.Metadata</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.StructField</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.StructType</span><span class="o">;</span> |
| |
| <span class="kd">private</span> <span class="kd">static</span> <span class="kd">class</span> <span class="nc">ParseVector</span> <span class="kd">implements</span> <span class="n">Function</span><span class="o"><</span><span class="n">String</span><span class="o">,</span> <span class="n">Row</span><span class="o">></span> <span class="o">{</span> |
| <span class="kd">private</span> <span class="kd">static</span> <span class="kd">final</span> <span class="n">Pattern</span> <span class="n">separator</span> <span class="o">=</span> <span class="n">Pattern</span><span class="o">.</span><span class="na">compile</span><span class="o">(</span><span class="s">" "</span><span class="o">);</span> |
| |
| <span class="nd">@Override</span> |
| <span class="kd">public</span> <span class="n">Row</span> <span class="nf">call</span><span class="o">(</span><span class="n">String</span> <span class="n">line</span><span class="o">)</span> <span class="o">{</span> |
| <span class="n">String</span><span class="o">[]</span> <span class="n">tok</span> <span class="o">=</span> <span class="n">separator</span><span class="o">.</span><span class="na">split</span><span class="o">(</span><span class="n">line</span><span class="o">);</span> |
| <span class="kt">double</span><span class="o">[]</span> <span class="n">point</span> <span class="o">=</span> <span class="k">new</span> <span class="kt">double</span><span class="o">[</span><span class="n">tok</span><span class="o">.</span><span class="na">length</span><span class="o">];</span> |
| <span class="k">for</span> <span class="o">(</span><span class="kt">int</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="o">;</span> <span class="n">i</span> <span class="o"><</span> <span class="n">tok</span><span class="o">.</span><span class="na">length</span><span class="o">;</span> <span class="o">++</span><span class="n">i</span><span class="o">)</span> <span class="o">{</span> |
| <span class="n">point</span><span class="o">[</span><span class="n">i</span><span class="o">]</span> <span class="o">=</span> <span class="n">Double</span><span class="o">.</span><span class="na">parseDouble</span><span class="o">(</span><span class="n">tok</span><span class="o">[</span><span class="n">i</span><span class="o">]);</span> |
| <span class="o">}</span> |
| <span class="n">Vector</span><span class="o">[]</span> <span class="n">points</span> <span class="o">=</span> <span class="o">{</span><span class="n">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="n">point</span><span class="o">)};</span> |
| <span class="k">return</span> <span class="k">new</span> <span class="nf">GenericRow</span><span class="o">(</span><span class="n">points</span><span class="o">);</span> |
| <span class="o">}</span> |
| <span class="o">}</span> |
| |
| <span class="kd">public</span> <span class="kd">static</span> <span class="kt">void</span> <span class="nf">main</span><span class="o">(</span><span class="n">String</span><span class="o">[]</span> <span class="n">args</span><span class="o">)</span> <span class="o">{</span> |
| |
| <span class="n">String</span> <span class="n">inputFile</span> <span class="o">=</span> <span class="s">"data/mllib/sample_lda_data.txt"</span><span class="o">;</span> |
| |
| <span class="c1">// Parses the arguments</span> |
| <span class="n">SparkConf</span> <span class="n">conf</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">SparkConf</span><span class="o">().</span><span class="na">setAppName</span><span class="o">(</span><span class="s">"JavaLDAExample"</span><span class="o">);</span> |
| <span class="n">JavaSparkContext</span> <span class="n">jsc</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">JavaSparkContext</span><span class="o">(</span><span class="n">conf</span><span class="o">);</span> |
| <span class="n">SQLContext</span> <span class="n">sqlContext</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">SQLContext</span><span class="o">(</span><span class="n">jsc</span><span class="o">);</span> |
| |
| <span class="c1">// Loads data</span> |
| <span class="n">JavaRDD</span><span class="o"><</span><span class="n">Row</span><span class="o">></span> <span class="n">points</span> <span class="o">=</span> <span class="n">jsc</span><span class="o">.</span><span class="na">textFile</span><span class="o">(</span><span class="n">inputFile</span><span class="o">).</span><span class="na">map</span><span class="o">(</span><span class="k">new</span> <span class="nf">ParseVector</span><span class="o">());</span> |
| <span class="n">StructField</span><span class="o">[]</span> <span class="n">fields</span> <span class="o">=</span> <span class="o">{</span><span class="k">new</span> <span class="nf">StructField</span><span class="o">(</span><span class="s">"features"</span><span class="o">,</span> <span class="k">new</span> <span class="nf">VectorUDT</span><span class="o">(),</span> <span class="kc">false</span><span class="o">,</span> <span class="n">Metadata</span><span class="o">.</span><span class="na">empty</span><span class="o">())};</span> |
| <span class="n">StructType</span> <span class="n">schema</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">StructType</span><span class="o">(</span><span class="n">fields</span><span class="o">);</span> |
| <span class="n">DataFrame</span> <span class="n">dataset</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">points</span><span class="o">,</span> <span class="n">schema</span><span class="o">);</span> |
| |
| <span class="c1">// Trains a LDA model</span> |
| <span class="n">LDA</span> <span class="n">lda</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">LDA</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setK</span><span class="o">(</span><span class="mi">10</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setMaxIter</span><span class="o">(</span><span class="mi">10</span><span class="o">);</span> |
| <span class="n">LDAModel</span> <span class="n">model</span> <span class="o">=</span> <span class="n">lda</span><span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">);</span> |
| |
| <span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">println</span><span class="o">(</span><span class="n">model</span><span class="o">.</span><span class="na">logLikelihood</span><span class="o">(</span><span class="n">dataset</span><span class="o">));</span> |
| <span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">println</span><span class="o">(</span><span class="n">model</span><span class="o">.</span><span class="na">logPerplexity</span><span class="o">(</span><span class="n">dataset</span><span class="o">));</span> |
| |
| <span class="c1">// Shows the result</span> |
| <span class="n">DataFrame</span> <span class="n">topics</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="na">describeTopics</span><span class="o">(</span><span class="mi">3</span><span class="o">);</span> |
| <span class="n">topics</span><span class="o">.</span><span class="na">show</span><span class="o">(</span><span class="kc">false</span><span class="o">);</span> |
| <span class="n">model</span><span class="o">.</span><span class="na">transform</span><span class="o">(</span><span class="n">dataset</span><span class="o">).</span><span class="na">show</span><span class="o">(</span><span class="kc">false</span><span class="o">);</span> |
| |
| <span class="n">jsc</span><span class="o">.</span><span class="na">stop</span><span class="o">();</span> |
| <span class="o">}</span> |
| </pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java" in the Spark repo.</small></div> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| |
| <!-- /container --> |
| </div> |
| |
| <script src="js/vendor/jquery-1.8.0.min.js"></script> |
| <script src="js/vendor/bootstrap.min.js"></script> |
| <script src="js/vendor/anchor.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> |