| |
| <!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"> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>Clustering - Spark 3.5.0 Documentation</title> |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="css/bootstrap.min.css"> |
| <link rel="preconnect" href="https://fonts.googleapis.com"> |
| <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> |
| <link href="https://fonts.googleapis.com/css2?family=DM+Sans:ital,wght@0,400;0,500;0,700;1,400;1,500;1,700&Courier+Prime:wght@400;700&display=swap" rel="stylesheet"> |
| <link href="css/custom.css" rel="stylesheet"> |
| <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script> |
| |
| <link rel="stylesheet" href="css/pygments-default.css"> |
| <link rel="stylesheet" href="css/docsearch.min.css" /> |
| <link rel="stylesheet" href="css/docsearch.css"> |
| |
| <!-- Matomo --> |
| <script type="text/javascript"> |
| var _paq = window._paq = window._paq || []; |
| /* tracker methods like "setCustomDimension" should be called before "trackPageView" */ |
| _paq.push(["disableCookies"]); |
| _paq.push(['trackPageView']); |
| _paq.push(['enableLinkTracking']); |
| (function() { |
| var u="https://analytics.apache.org/"; |
| _paq.push(['setTrackerUrl', u+'matomo.php']); |
| _paq.push(['setSiteId', '40']); |
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0]; |
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s); |
| })(); |
| </script> |
| <!-- End Matomo Code --> |
| </head> |
| <body class="global"> |
| <!--[if lt IE 7]> |
| <p class="chromeframe">You are using an outdated browser. <a href="https://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 --> |
| |
| <nav class="navbar navbar-expand-lg navbar-dark p-0 px-4 fixed-top" style="background: #1d6890;" id="topbar"> |
| <div class="navbar-brand"><a href="index.html"> |
| <img src="img/spark-logo-rev.svg" width="141" height="72"/></a><span class="version">3.5.0</span> |
| </div> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" |
| data-target="#navbarCollapse" aria-controls="navbarCollapse" |
| aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| <div class="collapse navbar-collapse" id="navbarCollapse"> |
| <ul class="navbar-nav me-auto"> |
| <li class="nav-item"><a href="index.html" class="nav-link">Overview</a></li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarQuickStart" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Programming Guides</a> |
| <div class="dropdown-menu" aria-labelledby="navbarQuickStart"> |
| <a class="dropdown-item" href="quick-start.html">Quick Start</a> |
| <a class="dropdown-item" href="rdd-programming-guide.html">RDDs, Accumulators, Broadcasts Vars</a> |
| <a class="dropdown-item" href="sql-programming-guide.html">SQL, DataFrames, and Datasets</a> |
| <a class="dropdown-item" href="structured-streaming-programming-guide.html">Structured Streaming</a> |
| <a class="dropdown-item" href="streaming-programming-guide.html">Spark Streaming (DStreams)</a> |
| <a class="dropdown-item" href="ml-guide.html">MLlib (Machine Learning)</a> |
| <a class="dropdown-item" href="graphx-programming-guide.html">GraphX (Graph Processing)</a> |
| <a class="dropdown-item" href="sparkr.html">SparkR (R on Spark)</a> |
| <a class="dropdown-item" href="api/python/getting_started/index.html">PySpark (Python on Spark)</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarAPIDocs" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">API Docs</a> |
| <div class="dropdown-menu" aria-labelledby="navbarAPIDocs"> |
| <a class="dropdown-item" href="api/scala/org/apache/spark/index.html">Scala</a> |
| <a class="dropdown-item" href="api/java/index.html">Java</a> |
| <a class="dropdown-item" href="api/python/index.html">Python</a> |
| <a class="dropdown-item" href="api/R/index.html">R</a> |
| <a class="dropdown-item" href="api/sql/index.html">SQL, Built-in Functions</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarDeploying" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Deploying</a> |
| <div class="dropdown-menu" aria-labelledby="navbarDeploying"> |
| <a class="dropdown-item" href="cluster-overview.html">Overview</a> |
| <a class="dropdown-item" href="submitting-applications.html">Submitting Applications</a> |
| <div class="dropdown-divider"></div> |
| <a class="dropdown-item" href="spark-standalone.html">Spark Standalone</a> |
| <a class="dropdown-item" href="running-on-mesos.html">Mesos</a> |
| <a class="dropdown-item" href="running-on-yarn.html">YARN</a> |
| <a class="dropdown-item" href="running-on-kubernetes.html">Kubernetes</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarMore" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">More</a> |
| <div class="dropdown-menu" aria-labelledby="navbarMore"> |
| <a class="dropdown-item" href="configuration.html">Configuration</a> |
| <a class="dropdown-item" href="monitoring.html">Monitoring</a> |
| <a class="dropdown-item" href="tuning.html">Tuning Guide</a> |
| <a class="dropdown-item" href="job-scheduling.html">Job Scheduling</a> |
| <a class="dropdown-item" href="security.html">Security</a> |
| <a class="dropdown-item" href="hardware-provisioning.html">Hardware Provisioning</a> |
| <a class="dropdown-item" href="migration-guide.html">Migration Guide</a> |
| <div class="dropdown-divider"></div> |
| <a class="dropdown-item" href="building-spark.html">Building Spark</a> |
| <a class="dropdown-item" href="https://spark.apache.org/contributing.html">Contributing to Spark</a> |
| <a class="dropdown-item" href="https://spark.apache.org/third-party-projects.html">Third Party Projects</a> |
| </div> |
| </li> |
| |
| <li class="nav-item"> |
| <input type="text" id="docsearch-input" placeholder="Search the docs…"> |
| </li> |
| </ul> |
| <!--<span class="navbar-text navbar-right"><span class="version-text">v3.5.0</span></span>--> |
| </div> |
| </nav> |
| |
| |
| |
| <div class="container"> |
| |
| |
| |
| <div class="left-menu-wrapper"> |
| <div class="left-menu"> |
| <h3><a href="ml-guide.html">MLlib: Main Guide</a></h3> |
| |
| <ul> |
| |
| <li> |
| <a href="ml-statistics.html"> |
| |
| Basic statistics |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-datasource.html"> |
| |
| Data sources |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-pipeline.html"> |
| |
| 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"> |
| |
| Clustering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-collaborative-filtering.html"> |
| |
| Collaborative filtering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-frequent-pattern-mining.html"> |
| |
| Frequent Pattern Mining |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-tuning.html"> |
| |
| Model selection and tuning |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-advanced.html"> |
| |
| Advanced topics |
| |
| </a> |
| </li> |
| |
| |
| |
| </ul> |
| |
| <h3><a href="mllib-guide.html">MLlib: RDD-based API Guide</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 mr-3" id="content"> |
| |
| <h1 class="title">Clustering</h1> |
| |
| |
| <p>This page describes clustering algorithms in MLlib. |
| The <a href="mllib-clustering.html">guide for clustering in the RDD-based API</a> also has relevant information |
| about these algorithms.</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> |
| </ul> |
| </li> |
| <li><a href="#latent-dirichlet-allocation-lda" id="markdown-toc-latent-dirichlet-allocation-lda">Latent Dirichlet allocation (LDA)</a></li> |
| <li><a href="#bisecting-k-means" id="markdown-toc-bisecting-k-means">Bisecting k-means</a></li> |
| <li><a href="#gaussian-mixture-model-gmm" id="markdown-toc-gaussian-mixture-model-gmm">Gaussian Mixture Model (GMM)</a> <ul> |
| <li><a href="#input-columns-1" id="markdown-toc-input-columns-1">Input Columns</a></li> |
| <li><a href="#output-columns-1" id="markdown-toc-output-columns-1">Output Columns</a></li> |
| </ul> |
| </li> |
| <li><a href="#power-iteration-clustering-pic" id="markdown-toc-power-iteration-clustering-pic">Power Iteration Clustering (PIC)</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 class="language-plaintext highlighter-rouge">KMeans</code> is implemented as an <code class="language-plaintext highlighter-rouge">Estimator</code> and generates a <code class="language-plaintext highlighter-rouge">KMeansModel</code> as the base model.</p> |
| |
| <h3 id="input-columns">Input Columns</h3> |
| |
| <table class="table table-striped"> |
| <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 table-striped"> |
| <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> |
| |
| <p><strong>Examples</strong></p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="python"> |
| <p>Refer to the <a href="api/python/reference/api/pyspark.ml.clustering.KMeans.html">Python API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.ml.clustering</span> <span class="kn">import</span> <span class="n">KMeans</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.evaluation</span> <span class="kn">import</span> <span class="n">ClusteringEvaluator</span> |
| |
| <span class="c1"># Loads data. |
| </span><span class="n">dataset</span> <span class="o">=</span> <span class="n">spark</span><span class="p">.</span><span class="n">read</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="s">"libsvm"</span><span class="p">).</span><span class="n">load</span><span class="p">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="p">)</span> |
| |
| <span class="c1"># Trains a k-means model. |
| </span><span class="n">kmeans</span> <span class="o">=</span> <span class="n">KMeans</span><span class="p">().</span><span class="n">setK</span><span class="p">(</span><span class="mi">2</span><span class="p">).</span><span class="n">setSeed</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">kmeans</span><span class="p">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| |
| <span class="c1"># Make predictions |
| </span><span class="n">predictions</span> <span class="o">=</span> <span class="n">model</span><span class="p">.</span><span class="n">transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| |
| <span class="c1"># Evaluate clustering by computing Silhouette score |
| </span><span class="n">evaluator</span> <span class="o">=</span> <span class="n">ClusteringEvaluator</span><span class="p">()</span> |
| |
| <span class="n">silhouette</span> <span class="o">=</span> <span class="n">evaluator</span><span class="p">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">predictions</span><span class="p">)</span> |
| <span class="k">print</span><span class="p">(</span><span class="s">"Silhouette with squared euclidean distance = "</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">silhouette</span><span class="p">))</span> |
| |
| <span class="c1"># Shows the result. |
| </span><span class="n">centers</span> <span class="o">=</span> <span class="n">model</span><span class="p">.</span><span class="n">clusterCenters</span><span class="p">()</span> |
| <span class="k">print</span><span class="p">(</span><span class="s">"Cluster Centers: "</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">center</span> <span class="ow">in</span> <span class="n">centers</span><span class="p">:</span> |
| <span class="k">print</span><span class="p">(</span><span class="n">center</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/ml/kmeans_example.py" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="scala"> |
| <p>Refer to the <a href="api/scala/org/apache/spark/ml/clustering/KMeans.html">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><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.ml.evaluation.ClusteringEvaluator</span> |
| |
| <span class="c1">// Loads data.</span> |
| <span class="k">val</span> <span class="nv">dataset</span> <span class="k">=</span> <span class="nv">spark</span><span class="o">.</span><span class="py">read</span><span class="o">.</span><span class="py">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">).</span><span class="py">load</span><span class="o">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="o">)</span> |
| |
| <span class="c1">// Trains a k-means model.</span> |
| <span class="k">val</span> <span class="nv">kmeans</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">KMeans</span><span class="o">().</span><span class="py">setK</span><span class="o">(</span><span class="mi">2</span><span class="o">).</span><span class="py">setSeed</span><span class="o">(</span><span class="mi">1L</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="nv">kmeans</span><span class="o">.</span><span class="py">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="c1">// Make predictions</span> |
| <span class="k">val</span> <span class="nv">predictions</span> <span class="k">=</span> <span class="nv">model</span><span class="o">.</span><span class="py">transform</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="c1">// Evaluate clustering by computing Silhouette score</span> |
| <span class="k">val</span> <span class="nv">evaluator</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">ClusteringEvaluator</span><span class="o">()</span> |
| |
| <span class="k">val</span> <span class="nv">silhouette</span> <span class="k">=</span> <span class="nv">evaluator</span><span class="o">.</span><span class="py">evaluate</span><span class="o">(</span><span class="n">predictions</span><span class="o">)</span> |
| <span class="nf">println</span><span class="o">(</span><span class="n">s</span><span class="s">"Silhouette with squared euclidean distance = $silhouette"</span><span class="o">)</span> |
| |
| <span class="c1">// Shows the result.</span> |
| <span class="nf">println</span><span class="o">(</span><span class="s">"Cluster Centers: "</span><span class="o">)</span> |
| <span class="nv">model</span><span class="o">.</span><span class="py">clusterCenters</span><span class="o">.</span><span class="py">foreach</span><span class="o">(</span><span class="n">println</span><span class="o">)</span></code></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 class="codehilite"><code><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.ml.evaluation.ClusteringEvaluator</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.linalg.Vector</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Dataset</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="c1">// Loads data.</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">dataset</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">read</span><span class="o">().</span><span class="na">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">).</span><span class="na">load</span><span class="o">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="o">);</span> |
| |
| <span class="c1">// Trains a k-means model.</span> |
| <span class="nc">KMeans</span> <span class="n">kmeans</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">KMeans</span><span class="o">().</span><span class="na">setK</span><span class="o">(</span><span class="mi">2</span><span class="o">).</span><span class="na">setSeed</span><span class="o">(</span><span class="mi">1L</span><span class="o">);</span> |
| <span class="nc">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">// Make predictions</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">predictions</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="c1">// Evaluate clustering by computing Silhouette score</span> |
| <span class="nc">ClusteringEvaluator</span> <span class="n">evaluator</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">ClusteringEvaluator</span><span class="o">();</span> |
| |
| <span class="kt">double</span> <span class="n">silhouette</span> <span class="o">=</span> <span class="n">evaluator</span><span class="o">.</span><span class="na">evaluate</span><span class="o">(</span><span class="n">predictions</span><span class="o">);</span> |
| <span class="nc">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">"Silhouette with squared euclidean distance = "</span> <span class="o">+</span> <span class="n">silhouette</span><span class="o">);</span> |
| |
| <span class="c1">// Shows the result.</span> |
| <span class="nc">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="nc">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="nc">Vector</span> <span class="nl">center:</span> <span class="n">centers</span><span class="o">)</span> <span class="o">{</span> |
| <span class="nc">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></code></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 data-lang="r"> |
| |
| <p>Refer to the <a href="api/R/reference/spark.kmeans.html">R API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="c1"># Fit a k-means model with spark.kmeans</span><span class="w"> |
| </span><span class="n">t</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">as.data.frame</span><span class="p">(</span><span class="n">Titanic</span><span class="p">)</span><span class="w"> |
| </span><span class="n">training</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">t</span><span class="p">)</span><span class="w"> |
| </span><span class="n">df_list</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">randomSplit</span><span class="p">(</span><span class="n">training</span><span class="p">,</span><span class="w"> </span><span class="nf">c</span><span class="p">(</span><span class="m">7</span><span class="p">,</span><span class="m">3</span><span class="p">),</span><span class="w"> </span><span class="m">2</span><span class="p">)</span><span class="w"> |
| </span><span class="n">kmeansDF</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">df_list</span><span class="p">[[</span><span class="m">1</span><span class="p">]]</span><span class="w"> |
| </span><span class="n">kmeansTestDF</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">df_list</span><span class="p">[[</span><span class="m">2</span><span class="p">]]</span><span class="w"> |
| </span><span class="n">kmeansModel</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.kmeans</span><span class="p">(</span><span class="n">kmeansDF</span><span class="p">,</span><span class="w"> </span><span class="o">~</span><span class="w"> </span><span class="n">Class</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="n">Sex</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="n">Age</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="n">Freq</span><span class="p">,</span><span class="w"> |
| </span><span class="n">k</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">3</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Model summary</span><span class="w"> |
| </span><span class="n">summary</span><span class="p">(</span><span class="n">kmeansModel</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Get fitted result from the k-means model</span><span class="w"> |
| </span><span class="n">head</span><span class="p">(</span><span class="n">fitted</span><span class="p">(</span><span class="n">kmeansModel</span><span class="p">))</span><span class="w"> |
| |
| </span><span class="c1"># Prediction</span><span class="w"> |
| </span><span class="n">kmeansPredictions</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">predict</span><span class="p">(</span><span class="n">kmeansModel</span><span class="p">,</span><span class="w"> </span><span class="n">kmeansTestDF</span><span class="p">)</span><span class="w"> |
| </span><span class="n">head</span><span class="p">(</span><span class="n">kmeansPredictions</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/r/ml/kmeans.R" in the Spark repo.</small></div> |
| </div> |
| |
| </div> |
| |
| <h2 id="latent-dirichlet-allocation-lda">Latent Dirichlet allocation (LDA)</h2> |
| |
| <p><code class="language-plaintext highlighter-rouge">LDA</code> is implemented as an <code class="language-plaintext highlighter-rouge">Estimator</code> that supports both <code class="language-plaintext highlighter-rouge">EMLDAOptimizer</code> and <code class="language-plaintext highlighter-rouge">OnlineLDAOptimizer</code>, |
| and generates a <code class="language-plaintext highlighter-rouge">LDAModel</code> as the base model. Expert users may cast a <code class="language-plaintext highlighter-rouge">LDAModel</code> generated by |
| <code class="language-plaintext highlighter-rouge">EMLDAOptimizer</code> to a <code class="language-plaintext highlighter-rouge">DistributedLDAModel</code> if needed.</p> |
| |
| <p><strong>Examples</strong></p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="python"> |
| |
| <p>Refer to the <a href="api/python/reference/api/pyspark.ml.clustering.LDA.html">Python API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.ml.clustering</span> <span class="kn">import</span> <span class="n">LDA</span> |
| |
| <span class="c1"># Loads data. |
| </span><span class="n">dataset</span> <span class="o">=</span> <span class="n">spark</span><span class="p">.</span><span class="n">read</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="s">"libsvm"</span><span class="p">).</span><span class="n">load</span><span class="p">(</span><span class="s">"data/mllib/sample_lda_libsvm_data.txt"</span><span class="p">)</span> |
| |
| <span class="c1"># Trains a LDA model. |
| </span><span class="n">lda</span> <span class="o">=</span> <span class="n">LDA</span><span class="p">(</span><span class="n">k</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">lda</span><span class="p">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| |
| <span class="n">ll</span> <span class="o">=</span> <span class="n">model</span><span class="p">.</span><span class="n">logLikelihood</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="n">lp</span> <span class="o">=</span> <span class="n">model</span><span class="p">.</span><span class="n">logPerplexity</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="k">print</span><span class="p">(</span><span class="s">"The lower bound on the log likelihood of the entire corpus: "</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">ll</span><span class="p">))</span> |
| <span class="k">print</span><span class="p">(</span><span class="s">"The upper bound on perplexity: "</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">lp</span><span class="p">))</span> |
| |
| <span class="c1"># Describe topics. |
| </span><span class="n">topics</span> <span class="o">=</span> <span class="n">model</span><span class="p">.</span><span class="n">describeTopics</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span> |
| <span class="k">print</span><span class="p">(</span><span class="s">"The topics described by their top-weighted terms:"</span><span class="p">)</span> |
| <span class="n">topics</span><span class="p">.</span><span class="n">show</span><span class="p">(</span><span class="n">truncate</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span> |
| |
| <span class="c1"># Shows the result |
| </span><span class="n">transformed</span> <span class="o">=</span> <span class="n">model</span><span class="p">.</span><span class="n">transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| <span class="n">transformed</span><span class="p">.</span><span class="n">show</span><span class="p">(</span><span class="n">truncate</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/ml/lda_example.py" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="scala"> |
| |
| <p>Refer to the <a href="api/scala/org/apache/spark/ml/clustering/LDA.html">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.ml.clustering.LDA</span> |
| |
| <span class="c1">// Loads data.</span> |
| <span class="k">val</span> <span class="nv">dataset</span> <span class="k">=</span> <span class="nv">spark</span><span class="o">.</span><span class="py">read</span><span class="o">.</span><span class="py">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">)</span> |
| <span class="o">.</span><span class="py">load</span><span class="o">(</span><span class="s">"data/mllib/sample_lda_libsvm_data.txt"</span><span class="o">)</span> |
| |
| <span class="c1">// Trains a LDA model.</span> |
| <span class="k">val</span> <span class="nv">lda</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">LDA</span><span class="o">().</span><span class="py">setK</span><span class="o">(</span><span class="mi">10</span><span class="o">).</span><span class="py">setMaxIter</span><span class="o">(</span><span class="mi">10</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="nv">lda</span><span class="o">.</span><span class="py">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="k">val</span> <span class="nv">ll</span> <span class="k">=</span> <span class="nv">model</span><span class="o">.</span><span class="py">logLikelihood</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">lp</span> <span class="k">=</span> <span class="nv">model</span><span class="o">.</span><span class="py">logPerplexity</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| <span class="nf">println</span><span class="o">(</span><span class="n">s</span><span class="s">"The lower bound on the log likelihood of the entire corpus: $ll"</span><span class="o">)</span> |
| <span class="nf">println</span><span class="o">(</span><span class="n">s</span><span class="s">"The upper bound on perplexity: $lp"</span><span class="o">)</span> |
| |
| <span class="c1">// Describe topics.</span> |
| <span class="k">val</span> <span class="nv">topics</span> <span class="k">=</span> <span class="nv">model</span><span class="o">.</span><span class="py">describeTopics</span><span class="o">(</span><span class="mi">3</span><span class="o">)</span> |
| <span class="nf">println</span><span class="o">(</span><span class="s">"The topics described by their top-weighted terms:"</span><span class="o">)</span> |
| <span class="nv">topics</span><span class="o">.</span><span class="py">show</span><span class="o">(</span><span class="kc">false</span><span class="o">)</span> |
| |
| <span class="c1">// Shows the result.</span> |
| <span class="k">val</span> <span class="nv">transformed</span> <span class="k">=</span> <span class="nv">model</span><span class="o">.</span><span class="py">transform</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| <span class="nv">transformed</span><span class="o">.</span><span class="py">show</span><span class="o">(</span><span class="kc">false</span><span class="o">)</span></code></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 class="codehilite"><code><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.sql.Dataset</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.SparkSession</span><span class="o">;</span> |
| |
| <span class="c1">// Loads data.</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">dataset</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">read</span><span class="o">().</span><span class="na">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">load</span><span class="o">(</span><span class="s">"data/mllib/sample_lda_libsvm_data.txt"</span><span class="o">);</span> |
| |
| <span class="c1">// Trains a LDA model.</span> |
| <span class="no">LDA</span> <span class="n">lda</span> <span class="o">=</span> <span class="k">new</span> <span class="no">LDA</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="na">setMaxIter</span><span class="o">(</span><span class="mi">10</span><span class="o">);</span> |
| <span class="nc">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="kt">double</span> <span class="n">ll</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="kt">double</span> <span class="n">lp</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="nc">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">"The lower bound on the log likelihood of the entire corpus: "</span> <span class="o">+</span> <span class="n">ll</span><span class="o">);</span> |
| <span class="nc">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">"The upper bound on perplexity: "</span> <span class="o">+</span> <span class="n">lp</span><span class="o">);</span> |
| |
| <span class="c1">// Describe topics.</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></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="nc">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">"The topics described by their top-weighted terms:"</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="c1">// Shows the result.</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">transformed</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="n">transformed</span><span class="o">.</span><span class="na">show</span><span class="o">(</span><span class="kc">false</span><span class="o">);</span></code></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 data-lang="r"> |
| |
| <p>Refer to the <a href="api/R/reference/spark.lda.html">R API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="c1"># Load training data</span><span class="w"> |
| </span><span class="n">df</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">read.df</span><span class="p">(</span><span class="s2">"data/mllib/sample_lda_libsvm_data.txt"</span><span class="p">,</span><span class="w"> </span><span class="n">source</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s2">"libsvm"</span><span class="p">)</span><span class="w"> |
| </span><span class="n">training</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">df</span><span class="w"> |
| </span><span class="n">test</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">df</span><span class="w"> |
| |
| </span><span class="c1"># Fit a latent dirichlet allocation model with spark.lda</span><span class="w"> |
| </span><span class="n">model</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.lda</span><span class="p">(</span><span class="n">training</span><span class="p">,</span><span class="w"> </span><span class="n">k</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">10</span><span class="p">,</span><span class="w"> </span><span class="n">maxIter</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">10</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Model summary</span><span class="w"> |
| </span><span class="n">summary</span><span class="p">(</span><span class="n">model</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Posterior probabilities</span><span class="w"> |
| </span><span class="n">posterior</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.posterior</span><span class="p">(</span><span class="n">model</span><span class="p">,</span><span class="w"> </span><span class="n">test</span><span class="p">)</span><span class="w"> |
| </span><span class="n">head</span><span class="p">(</span><span class="n">posterior</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># The log perplexity of the LDA model</span><span class="w"> |
| </span><span class="n">logPerplexity</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.perplexity</span><span class="p">(</span><span class="n">model</span><span class="p">,</span><span class="w"> </span><span class="n">test</span><span class="p">)</span><span class="w"> |
| </span><span class="n">print</span><span class="p">(</span><span class="n">paste0</span><span class="p">(</span><span class="s2">"The upper bound bound on perplexity: "</span><span class="p">,</span><span class="w"> </span><span class="n">logPerplexity</span><span class="p">))</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/r/ml/lda.R" in the Spark repo.</small></div> |
| </div> |
| |
| </div> |
| |
| <h2 id="bisecting-k-means">Bisecting k-means</h2> |
| |
| <p>Bisecting k-means is a kind of <a href="https://en.wikipedia.org/wiki/Hierarchical_clustering">hierarchical clustering</a> using a |
| divisive (or “top-down”) approach: all observations start in one cluster, and splits are performed recursively as one |
| moves down the hierarchy.</p> |
| |
| <p>Bisecting K-means can often be much faster than regular K-means, but it will generally produce a different clustering.</p> |
| |
| <p><code class="language-plaintext highlighter-rouge">BisectingKMeans</code> is implemented as an <code class="language-plaintext highlighter-rouge">Estimator</code> and generates a <code class="language-plaintext highlighter-rouge">BisectingKMeansModel</code> as the base model.</p> |
| |
| <p><strong>Examples</strong></p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="python"> |
| <p>Refer to the <a href="api/python/reference/api/pyspark.ml.clustering.BisectingKMeans.html">Python API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.ml.clustering</span> <span class="kn">import</span> <span class="n">BisectingKMeans</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.evaluation</span> <span class="kn">import</span> <span class="n">ClusteringEvaluator</span> |
| |
| <span class="c1"># Loads data. |
| </span><span class="n">dataset</span> <span class="o">=</span> <span class="n">spark</span><span class="p">.</span><span class="n">read</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="s">"libsvm"</span><span class="p">).</span><span class="n">load</span><span class="p">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="p">)</span> |
| |
| <span class="c1"># Trains a bisecting k-means model. |
| </span><span class="n">bkm</span> <span class="o">=</span> <span class="n">BisectingKMeans</span><span class="p">().</span><span class="n">setK</span><span class="p">(</span><span class="mi">2</span><span class="p">).</span><span class="n">setSeed</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">bkm</span><span class="p">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| |
| <span class="c1"># Make predictions |
| </span><span class="n">predictions</span> <span class="o">=</span> <span class="n">model</span><span class="p">.</span><span class="n">transform</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| |
| <span class="c1"># Evaluate clustering by computing Silhouette score |
| </span><span class="n">evaluator</span> <span class="o">=</span> <span class="n">ClusteringEvaluator</span><span class="p">()</span> |
| |
| <span class="n">silhouette</span> <span class="o">=</span> <span class="n">evaluator</span><span class="p">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">predictions</span><span class="p">)</span> |
| <span class="k">print</span><span class="p">(</span><span class="s">"Silhouette with squared euclidean distance = "</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">silhouette</span><span class="p">))</span> |
| |
| <span class="c1"># Shows the result. |
| </span><span class="k">print</span><span class="p">(</span><span class="s">"Cluster Centers: "</span><span class="p">)</span> |
| <span class="n">centers</span> <span class="o">=</span> <span class="n">model</span><span class="p">.</span><span class="n">clusterCenters</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">center</span> <span class="ow">in</span> <span class="n">centers</span><span class="p">:</span> |
| <span class="k">print</span><span class="p">(</span><span class="n">center</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/ml/bisecting_k_means_example.py" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="scala"> |
| <p>Refer to the <a href="api/scala/org/apache/spark/ml/clustering/BisectingKMeans.html">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.ml.clustering.BisectingKMeans</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.evaluation.ClusteringEvaluator</span> |
| |
| <span class="c1">// Loads data.</span> |
| <span class="k">val</span> <span class="nv">dataset</span> <span class="k">=</span> <span class="nv">spark</span><span class="o">.</span><span class="py">read</span><span class="o">.</span><span class="py">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">).</span><span class="py">load</span><span class="o">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="o">)</span> |
| |
| <span class="c1">// Trains a bisecting k-means model.</span> |
| <span class="k">val</span> <span class="nv">bkm</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">BisectingKMeans</span><span class="o">().</span><span class="py">setK</span><span class="o">(</span><span class="mi">2</span><span class="o">).</span><span class="py">setSeed</span><span class="o">(</span><span class="mi">1</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="nv">bkm</span><span class="o">.</span><span class="py">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="c1">// Make predictions</span> |
| <span class="k">val</span> <span class="nv">predictions</span> <span class="k">=</span> <span class="nv">model</span><span class="o">.</span><span class="py">transform</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="c1">// Evaluate clustering by computing Silhouette score</span> |
| <span class="k">val</span> <span class="nv">evaluator</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">ClusteringEvaluator</span><span class="o">()</span> |
| |
| <span class="k">val</span> <span class="nv">silhouette</span> <span class="k">=</span> <span class="nv">evaluator</span><span class="o">.</span><span class="py">evaluate</span><span class="o">(</span><span class="n">predictions</span><span class="o">)</span> |
| <span class="nf">println</span><span class="o">(</span><span class="n">s</span><span class="s">"Silhouette with squared euclidean distance = $silhouette"</span><span class="o">)</span> |
| |
| <span class="c1">// Shows the result.</span> |
| <span class="nf">println</span><span class="o">(</span><span class="s">"Cluster Centers: "</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">centers</span> <span class="k">=</span> <span class="nv">model</span><span class="o">.</span><span class="py">clusterCenters</span> |
| <span class="nv">centers</span><span class="o">.</span><span class="py">foreach</span><span class="o">(</span><span class="n">println</span><span class="o">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.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/BisectingKMeans.html">Java API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.BisectingKMeans</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.BisectingKMeansModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.evaluation.ClusteringEvaluator</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.linalg.Vector</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Dataset</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="c1">// Loads data.</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">dataset</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">read</span><span class="o">().</span><span class="na">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">).</span><span class="na">load</span><span class="o">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="o">);</span> |
| |
| <span class="c1">// Trains a bisecting k-means model.</span> |
| <span class="nc">BisectingKMeans</span> <span class="n">bkm</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">BisectingKMeans</span><span class="o">().</span><span class="na">setK</span><span class="o">(</span><span class="mi">2</span><span class="o">).</span><span class="na">setSeed</span><span class="o">(</span><span class="mi">1</span><span class="o">);</span> |
| <span class="nc">BisectingKMeansModel</span> <span class="n">model</span> <span class="o">=</span> <span class="n">bkm</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">// Make predictions</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">predictions</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="c1">// Evaluate clustering by computing Silhouette score</span> |
| <span class="nc">ClusteringEvaluator</span> <span class="n">evaluator</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">ClusteringEvaluator</span><span class="o">();</span> |
| |
| <span class="kt">double</span> <span class="n">silhouette</span> <span class="o">=</span> <span class="n">evaluator</span><span class="o">.</span><span class="na">evaluate</span><span class="o">(</span><span class="n">predictions</span><span class="o">);</span> |
| <span class="nc">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">"Silhouette with squared euclidean distance = "</span> <span class="o">+</span> <span class="n">silhouette</span><span class="o">);</span> |
| |
| <span class="c1">// Shows the result.</span> |
| <span class="nc">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="nc">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="k">for</span> <span class="o">(</span><span class="nc">Vector</span> <span class="n">center</span> <span class="o">:</span> <span class="n">centers</span><span class="o">)</span> <span class="o">{</span> |
| <span class="nc">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></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="r"> |
| |
| <p>Refer to the <a href="api/R/reference/spark.bisectingKmeans.html">R API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="n">t</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">as.data.frame</span><span class="p">(</span><span class="n">Titanic</span><span class="p">)</span><span class="w"> |
| </span><span class="n">training</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">t</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Fit bisecting k-means model with four centers</span><span class="w"> |
| </span><span class="n">model</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.bisectingKmeans</span><span class="p">(</span><span class="n">training</span><span class="p">,</span><span class="w"> </span><span class="n">Class</span><span class="w"> </span><span class="o">~</span><span class="w"> </span><span class="n">Survived</span><span class="p">,</span><span class="w"> </span><span class="n">k</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">4</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># get fitted result from a bisecting k-means model</span><span class="w"> |
| </span><span class="n">fitted.model</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">fitted</span><span class="p">(</span><span class="n">model</span><span class="p">,</span><span class="w"> </span><span class="s2">"centers"</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Model summary</span><span class="w"> |
| </span><span class="n">head</span><span class="p">(</span><span class="n">summary</span><span class="p">(</span><span class="n">fitted.model</span><span class="p">))</span><span class="w"> |
| |
| </span><span class="c1"># fitted values on training data</span><span class="w"> |
| </span><span class="n">fitted</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">predict</span><span class="p">(</span><span class="n">model</span><span class="p">,</span><span class="w"> </span><span class="n">training</span><span class="p">)</span><span class="w"> |
| </span><span class="n">head</span><span class="p">(</span><span class="n">select</span><span class="p">(</span><span class="n">fitted</span><span class="p">,</span><span class="w"> </span><span class="s2">"Class"</span><span class="p">,</span><span class="w"> </span><span class="s2">"prediction"</span><span class="p">))</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/r/ml/bisectingKmeans.R" in the Spark repo.</small></div> |
| </div> |
| </div> |
| |
| <h2 id="gaussian-mixture-model-gmm">Gaussian Mixture Model (GMM)</h2> |
| |
| <p>A <a href="http://en.wikipedia.org/wiki/Mixture_model#Multivariate_Gaussian_mixture_model">Gaussian Mixture Model</a> |
| represents a composite distribution whereby points are drawn from one of <em>k</em> Gaussian sub-distributions, |
| each with its own probability. The <code class="language-plaintext highlighter-rouge">spark.ml</code> implementation uses the |
| <a href="http://en.wikipedia.org/wiki/Expectation%E2%80%93maximization_algorithm">expectation-maximization</a> |
| algorithm to induce the maximum-likelihood model given a set of samples.</p> |
| |
| <p><code class="language-plaintext highlighter-rouge">GaussianMixture</code> is implemented as an <code class="language-plaintext highlighter-rouge">Estimator</code> and generates a <code class="language-plaintext highlighter-rouge">GaussianMixtureModel</code> as the base |
| model.</p> |
| |
| <h3 id="input-columns-1">Input Columns</h3> |
| |
| <table class="table table-striped"> |
| <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-1">Output Columns</h3> |
| |
| <table class="table table-striped"> |
| <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> |
| <tr> |
| <td>probabilityCol</td> |
| <td>Vector</td> |
| <td>"probability"</td> |
| <td>Probability of each cluster</td> |
| </tr> |
| </tbody> |
| </table> |
| |
| <p><strong>Examples</strong></p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="python"> |
| <p>Refer to the <a href="api/python/reference/api/pyspark.ml.clustering.GaussianMixture.html">Python API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.ml.clustering</span> <span class="kn">import</span> <span class="n">GaussianMixture</span> |
| |
| <span class="c1"># loads data |
| </span><span class="n">dataset</span> <span class="o">=</span> <span class="n">spark</span><span class="p">.</span><span class="n">read</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="s">"libsvm"</span><span class="p">).</span><span class="n">load</span><span class="p">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="p">)</span> |
| |
| <span class="n">gmm</span> <span class="o">=</span> <span class="n">GaussianMixture</span><span class="p">().</span><span class="n">setK</span><span class="p">(</span><span class="mi">2</span><span class="p">).</span><span class="n">setSeed</span><span class="p">(</span><span class="mi">538009335</span><span class="p">)</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">gmm</span><span class="p">.</span><span class="n">fit</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span> |
| |
| <span class="k">print</span><span class="p">(</span><span class="s">"Gaussians shown as a DataFrame: "</span><span class="p">)</span> |
| <span class="n">model</span><span class="p">.</span><span class="n">gaussiansDF</span><span class="p">.</span><span class="n">show</span><span class="p">(</span><span class="n">truncate</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/ml/gaussian_mixture_example.py" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="scala"> |
| <p>Refer to the <a href="api/scala/org/apache/spark/ml/clustering/GaussianMixture.html">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.ml.clustering.GaussianMixture</span> |
| |
| <span class="c1">// Loads data</span> |
| <span class="k">val</span> <span class="nv">dataset</span> <span class="k">=</span> <span class="nv">spark</span><span class="o">.</span><span class="py">read</span><span class="o">.</span><span class="py">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">).</span><span class="py">load</span><span class="o">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="o">)</span> |
| |
| <span class="c1">// Trains Gaussian Mixture Model</span> |
| <span class="k">val</span> <span class="nv">gmm</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">GaussianMixture</span><span class="o">()</span> |
| <span class="o">.</span><span class="py">setK</span><span class="o">(</span><span class="mi">2</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="nv">gmm</span><span class="o">.</span><span class="py">fit</span><span class="o">(</span><span class="n">dataset</span><span class="o">)</span> |
| |
| <span class="c1">// output parameters of mixture model model</span> |
| <span class="nf">for</span> <span class="o">(</span><span class="n">i</span> <span class="k"><-</span> <span class="mi">0</span> <span class="n">until</span> <span class="nv">model</span><span class="o">.</span><span class="py">getK</span><span class="o">)</span> <span class="o">{</span> |
| <span class="nf">println</span><span class="o">(</span><span class="n">s</span><span class="s">"Gaussian $i:\nweight=${model.weights(i)}\n"</span> <span class="o">+</span> |
| <span class="n">s</span><span class="s">"mu=${model.gaussians(i).mean}\nsigma=\n${model.gaussians(i).cov}\n"</span><span class="o">)</span> |
| <span class="o">}</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/ml/GaussianMixtureExample.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/GaussianMixture.html">Java API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.GaussianMixture</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.GaussianMixtureModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Dataset</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="c1">// Loads data</span> |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">dataset</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">read</span><span class="o">().</span><span class="na">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">).</span><span class="na">load</span><span class="o">(</span><span class="s">"data/mllib/sample_kmeans_data.txt"</span><span class="o">);</span> |
| |
| <span class="c1">// Trains a GaussianMixture model</span> |
| <span class="nc">GaussianMixture</span> <span class="n">gmm</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">GaussianMixture</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setK</span><span class="o">(</span><span class="mi">2</span><span class="o">);</span> |
| <span class="nc">GaussianMixtureModel</span> <span class="n">model</span> <span class="o">=</span> <span class="n">gmm</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">// Output the parameters of the mixture model</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">model</span><span class="o">.</span><span class="na">getK</span><span class="o">();</span> <span class="n">i</span><span class="o">++)</span> <span class="o">{</span> |
| <span class="nc">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">printf</span><span class="o">(</span><span class="s">"Gaussian %d:\nweight=%f\nmu=%s\nsigma=\n%s\n\n"</span><span class="o">,</span> |
| <span class="n">i</span><span class="o">,</span> <span class="n">model</span><span class="o">.</span><span class="na">weights</span><span class="o">()[</span><span class="n">i</span><span class="o">],</span> <span class="n">model</span><span class="o">.</span><span class="na">gaussians</span><span class="o">()[</span><span class="n">i</span><span class="o">].</span><span class="na">mean</span><span class="o">(),</span> <span class="n">model</span><span class="o">.</span><span class="na">gaussians</span><span class="o">()[</span><span class="n">i</span><span class="o">].</span><span class="na">cov</span><span class="o">());</span> |
| <span class="o">}</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/ml/JavaGaussianMixtureExample.java" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="r"> |
| |
| <p>Refer to the <a href="api/R/reference/spark.gaussianMixture.html">R API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="c1"># Load training data</span><span class="w"> |
| </span><span class="n">df</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">read.df</span><span class="p">(</span><span class="s2">"data/mllib/sample_kmeans_data.txt"</span><span class="p">,</span><span class="w"> </span><span class="n">source</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s2">"libsvm"</span><span class="p">)</span><span class="w"> |
| </span><span class="n">training</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">df</span><span class="w"> |
| </span><span class="n">test</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">df</span><span class="w"> |
| |
| </span><span class="c1"># Fit a gaussian mixture clustering model with spark.gaussianMixture</span><span class="w"> |
| </span><span class="n">model</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.gaussianMixture</span><span class="p">(</span><span class="n">training</span><span class="p">,</span><span class="w"> </span><span class="o">~</span><span class="w"> </span><span class="n">features</span><span class="p">,</span><span class="w"> </span><span class="n">k</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">2</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Model summary</span><span class="w"> |
| </span><span class="n">summary</span><span class="p">(</span><span class="n">model</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="c1"># Prediction</span><span class="w"> |
| </span><span class="n">predictions</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">predict</span><span class="p">(</span><span class="n">model</span><span class="p">,</span><span class="w"> </span><span class="n">test</span><span class="p">)</span><span class="w"> |
| </span><span class="n">head</span><span class="p">(</span><span class="n">predictions</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/r/ml/gaussianMixture.R" in the Spark repo.</small></div> |
| </div> |
| |
| </div> |
| |
| <h2 id="power-iteration-clustering-pic">Power Iteration Clustering (PIC)</h2> |
| |
| <p>Power Iteration Clustering (PIC) is a scalable graph clustering algorithm |
| developed by <a href="http://www.cs.cmu.edu/~frank/papers/icml2010-pic-final.pdf">Lin and Cohen</a>. |
| From the abstract: PIC finds a very low-dimensional embedding of a dataset |
| using truncated power iteration on a normalized pair-wise similarity matrix of the data.</p> |
| |
| <p><code class="language-plaintext highlighter-rouge">spark.ml</code>’s PowerIterationClustering implementation takes the following parameters:</p> |
| |
| <ul> |
| <li><code class="language-plaintext highlighter-rouge">k</code>: the number of clusters to create</li> |
| <li><code class="language-plaintext highlighter-rouge">initMode</code>: param for the initialization algorithm</li> |
| <li><code class="language-plaintext highlighter-rouge">maxIter</code>: param for maximum number of iterations</li> |
| <li><code class="language-plaintext highlighter-rouge">srcCol</code>: param for the name of the input column for source vertex IDs</li> |
| <li><code class="language-plaintext highlighter-rouge">dstCol</code>: name of the input column for destination vertex IDs</li> |
| <li><code class="language-plaintext highlighter-rouge">weightCol</code>: Param for weight column name</li> |
| </ul> |
| |
| <p><strong>Examples</strong></p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="python"> |
| <p>Refer to the <a href="api/python/reference/api/pyspark.ml.clustering.PowerIterationClustering.html">Python API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.ml.clustering</span> <span class="kn">import</span> <span class="n">PowerIterationClustering</span> |
| |
| <span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="p">.</span><span class="n">createDataFrame</span><span class="p">([</span> |
| <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> |
| <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> |
| <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> |
| <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> |
| <span class="p">(</span><span class="mi">4</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">)</span> |
| <span class="p">],</span> <span class="p">[</span><span class="s">"src"</span><span class="p">,</span> <span class="s">"dst"</span><span class="p">,</span> <span class="s">"weight"</span><span class="p">])</span> |
| |
| <span class="n">pic</span> <span class="o">=</span> <span class="n">PowerIterationClustering</span><span class="p">(</span><span class="n">k</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">initMode</span><span class="o">=</span><span class="s">"degree"</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="s">"weight"</span><span class="p">)</span> |
| |
| <span class="c1"># Shows the cluster assignment |
| </span><span class="n">pic</span><span class="p">.</span><span class="n">assignClusters</span><span class="p">(</span><span class="n">df</span><span class="p">).</span><span class="n">show</span><span class="p">()</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/ml/power_iteration_clustering_example.py" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="scala"> |
| <p>Refer to the <a href="api/scala/org/apache/spark/ml/clustering/PowerIterationClustering.html">Scala API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.ml.clustering.PowerIterationClustering</span> |
| |
| <span class="k">val</span> <span class="nv">dataset</span> <span class="k">=</span> <span class="nv">spark</span><span class="o">.</span><span class="py">createDataFrame</span><span class="o">(</span><span class="nc">Seq</span><span class="o">(</span> |
| <span class="o">(</span><span class="mi">0L</span><span class="o">,</span> <span class="mi">1L</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> |
| <span class="o">(</span><span class="mi">0L</span><span class="o">,</span> <span class="mi">2L</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> |
| <span class="o">(</span><span class="mi">1L</span><span class="o">,</span> <span class="mi">2L</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> |
| <span class="o">(</span><span class="mi">3L</span><span class="o">,</span> <span class="mi">4L</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> |
| <span class="o">(</span><span class="mi">4L</span><span class="o">,</span> <span class="mi">0L</span><span class="o">,</span> <span class="mf">0.1</span><span class="o">)</span> |
| <span class="o">)).</span><span class="py">toDF</span><span class="o">(</span><span class="s">"src"</span><span class="o">,</span> <span class="s">"dst"</span><span class="o">,</span> <span class="s">"weight"</span><span class="o">)</span> |
| |
| <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">PowerIterationClustering</span><span class="o">().</span> |
| <span class="nf">setK</span><span class="o">(</span><span class="mi">2</span><span class="o">).</span> |
| <span class="nf">setMaxIter</span><span class="o">(</span><span class="mi">20</span><span class="o">).</span> |
| <span class="nf">setInitMode</span><span class="o">(</span><span class="s">"degree"</span><span class="o">).</span> |
| <span class="nf">setWeightCol</span><span class="o">(</span><span class="s">"weight"</span><span class="o">)</span> |
| |
| <span class="k">val</span> <span class="nv">prediction</span> <span class="k">=</span> <span class="nv">model</span><span class="o">.</span><span class="py">assignClusters</span><span class="o">(</span><span class="n">dataset</span><span class="o">).</span><span class="py">select</span><span class="o">(</span><span class="s">"id"</span><span class="o">,</span> <span class="s">"cluster"</span><span class="o">)</span> |
| |
| <span class="c1">// Shows the cluster assignment</span> |
| <span class="nv">prediction</span><span class="o">.</span><span class="py">show</span><span class="o">(</span><span class="kc">false</span><span class="o">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/ml/PowerIterationClusteringExample.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/PowerIterationClustering.html">Java API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">import</span> <span class="nn">java.util.Arrays</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">java.util.List</span><span class="o">;</span> |
| |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.clustering.PowerIterationClustering</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.Dataset</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.RowFactory</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.SparkSession</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.sql.types.DataTypes</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="nc">List</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">data</span> <span class="o">=</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="mi">0L</span><span class="o">,</span> <span class="mi">1L</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="mi">0L</span><span class="o">,</span> <span class="mi">2L</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="mi">1L</span><span class="o">,</span> <span class="mi">2L</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="mi">3L</span><span class="o">,</span> <span class="mi">4L</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> |
| <span class="nc">RowFactory</span><span class="o">.</span><span class="na">create</span><span class="o">(</span><span class="mi">4L</span><span class="o">,</span> <span class="mi">0L</span><span class="o">,</span> <span class="mf">0.1</span><span class="o">)</span> |
| <span class="o">);</span> |
| |
| <span class="nc">StructType</span> <span class="n">schema</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">StructType</span><span class="o">(</span><span class="k">new</span> <span class="nc">StructField</span><span class="o">[]{</span> |
| <span class="k">new</span> <span class="nf">StructField</span><span class="o">(</span><span class="s">"src"</span><span class="o">,</span> <span class="nc">DataTypes</span><span class="o">.</span><span class="na">LongType</span><span class="o">,</span> <span class="kc">false</span><span class="o">,</span> <span class="nc">Metadata</span><span class="o">.</span><span class="na">empty</span><span class="o">()),</span> |
| <span class="k">new</span> <span class="nf">StructField</span><span class="o">(</span><span class="s">"dst"</span><span class="o">,</span> <span class="nc">DataTypes</span><span class="o">.</span><span class="na">LongType</span><span class="o">,</span> <span class="kc">false</span><span class="o">,</span> <span class="nc">Metadata</span><span class="o">.</span><span class="na">empty</span><span class="o">()),</span> |
| <span class="k">new</span> <span class="nf">StructField</span><span class="o">(</span><span class="s">"weight"</span><span class="o">,</span> <span class="nc">DataTypes</span><span class="o">.</span><span class="na">DoubleType</span><span class="o">,</span> <span class="kc">false</span><span class="o">,</span> <span class="nc">Metadata</span><span class="o">.</span><span class="na">empty</span><span class="o">())</span> |
| <span class="o">});</span> |
| |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">data</span><span class="o">,</span> <span class="n">schema</span><span class="o">);</span> |
| |
| <span class="nc">PowerIterationClustering</span> <span class="n">model</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">PowerIterationClustering</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setK</span><span class="o">(</span><span class="mi">2</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="o">.</span><span class="na">setInitMode</span><span class="o">(</span><span class="s">"degree"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setWeightCol</span><span class="o">(</span><span class="s">"weight"</span><span class="o">);</span> |
| |
| <span class="nc">Dataset</span><span class="o"><</span><span class="nc">Row</span><span class="o">></span> <span class="n">result</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="na">assignClusters</span><span class="o">(</span><span class="n">df</span><span class="o">);</span> |
| <span class="n">result</span><span class="o">.</span><span class="na">show</span><span class="o">(</span><span class="kc">false</span><span class="o">);</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/ml/JavaPowerIterationClusteringExample.java" in the Spark repo.</small></div> |
| </div> |
| |
| <div data-lang="r"> |
| |
| <p>Refer to the <a href="api/R/reference/spark.powerIterationClustering.html">R API docs</a> for more details.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="n">df</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">createDataFrame</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="nf">list</span><span class="p">(</span><span class="m">0L</span><span class="p">,</span><span class="w"> </span><span class="m">1L</span><span class="p">,</span><span class="w"> </span><span class="m">1.0</span><span class="p">),</span><span class="w"> </span><span class="nf">list</span><span class="p">(</span><span class="m">0L</span><span class="p">,</span><span class="w"> </span><span class="m">2L</span><span class="p">,</span><span class="w"> </span><span class="m">1.0</span><span class="p">),</span><span class="w"> |
| </span><span class="nf">list</span><span class="p">(</span><span class="m">1L</span><span class="p">,</span><span class="w"> </span><span class="m">2L</span><span class="p">,</span><span class="w"> </span><span class="m">1.0</span><span class="p">),</span><span class="w"> </span><span class="nf">list</span><span class="p">(</span><span class="m">3L</span><span class="p">,</span><span class="w"> </span><span class="m">4L</span><span class="p">,</span><span class="w"> </span><span class="m">1.0</span><span class="p">),</span><span class="w"> |
| </span><span class="nf">list</span><span class="p">(</span><span class="m">4L</span><span class="p">,</span><span class="w"> </span><span class="m">0L</span><span class="p">,</span><span class="w"> </span><span class="m">0.1</span><span class="p">)),</span><span class="w"> |
| </span><span class="n">schema</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="nf">c</span><span class="p">(</span><span class="s2">"src"</span><span class="p">,</span><span class="w"> </span><span class="s2">"dst"</span><span class="p">,</span><span class="w"> </span><span class="s2">"weight"</span><span class="p">))</span><span class="w"> |
| </span><span class="c1"># assign clusters</span><span class="w"> |
| </span><span class="n">clusters</span><span class="w"> </span><span class="o"><-</span><span class="w"> </span><span class="n">spark.assignClusters</span><span class="p">(</span><span class="n">df</span><span class="p">,</span><span class="w"> </span><span class="n">k</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">2L</span><span class="p">,</span><span class="w"> </span><span class="n">maxIter</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="m">20L</span><span class="p">,</span><span class="w"> |
| </span><span class="n">initMode</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s2">"degree"</span><span class="p">,</span><span class="w"> </span><span class="n">weightCol</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s2">"weight"</span><span class="p">)</span><span class="w"> |
| |
| </span><span class="n">showDF</span><span class="p">(</span><span class="n">arrange</span><span class="p">(</span><span class="n">clusters</span><span class="p">,</span><span class="w"> </span><span class="n">clusters</span><span class="o">$</span><span class="n">id</span><span class="p">))</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/r/ml/powerIterationClustering.R" in the Spark repo.</small></div> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| |
| <!-- /container --> |
| </div> |
| |
| <script src="js/vendor/jquery-3.5.1.min.js"></script> |
| <script src="js/vendor/bootstrap.bundle.min.js"></script> |
| |
| <script src="js/vendor/anchor.min.js"></script> |
| <script src="js/main.js"></script> |
| |
| <script type="text/javascript" src="js/vendor/docsearch.min.js"></script> |
| <script type="text/javascript"> |
| // DocSearch is entirely free and automated. DocSearch is built in two parts: |
| // 1. a crawler which we run on our own infrastructure every 24 hours. It follows every link |
| // in your website and extract content from every page it traverses. It then pushes this |
| // content to an Algolia index. |
| // 2. a JavaScript snippet to be inserted in your website that will bind this Algolia index |
| // to your search input and display its results in a dropdown UI. If you want to find more |
| // details on how works DocSearch, check the docs of DocSearch. |
| docsearch({ |
| apiKey: 'd62f962a82bc9abb53471cb7b89da35e', |
| appId: 'RAI69RXRSK', |
| indexName: 'apache_spark', |
| inputSelector: '#docsearch-input', |
| enhancedSearchInput: true, |
| algoliaOptions: { |
| 'facetFilters': ["version:3.5.0"] |
| }, |
| debug: false // Set debug to true if you want to inspect the dropdown |
| }); |
| |
| </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://') + |
| 'cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js' + |
| '?config=TeX-AMS-MML_HTMLorMML'; |
| d.getElementsByTagName('head')[0].appendChild(script); |
| }(document)); |
| </script> |
| </body> |
| </html> |
