| <!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>Decision Trees - SparkML - Spark 1.5.2 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">1.5.2</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 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><a href="hadoop-third-party-distributions.html">3<sup>rd</sup>-Party Hadoop Distros</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">v1.5.2</span></p>--> |
| </div> |
| </div> |
| </div> |
| |
| <div class="container" id="content"> |
| |
| <h1 class="title"><a href="ml-guide.html">ML</a> - Decision Trees</h1> |
| |
| |
| <p><strong>Table of Contents</strong></p> |
| |
| <ul id="markdown-toc"> |
| <li><a href="#overview" id="markdown-toc-overview">Overview</a></li> |
| <li><a href="#inputs-and-outputs" id="markdown-toc-inputs-and-outputs">Inputs and Outputs</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="#examples" id="markdown-toc-examples">Examples</a> <ul> |
| <li><a href="#classification" id="markdown-toc-classification">Classification</a></li> |
| <li><a href="#regression" id="markdown-toc-regression">Regression</a></li> |
| </ul> |
| </li> |
| </ul> |
| |
| <h1 id="overview">Overview</h1> |
| |
| <p><a href="http://en.wikipedia.org/wiki/Decision_tree_learning">Decision trees</a> |
| and their ensembles are popular methods for the machine learning tasks of |
| classification and regression. Decision trees are widely used since they are easy to interpret, |
| handle categorical features, extend to the multiclass classification setting, do not require |
| feature scaling, and are able to capture non-linearities and feature interactions. Tree ensemble |
| algorithms such as random forests and boosting are among the top performers for classification and |
| regression tasks.</p> |
| |
| <p>MLlib supports decision trees for binary and multiclass classification and for regression, |
| using both continuous and categorical features. The implementation partitions data by rows, |
| allowing distributed training with millions or even billions of instances.</p> |
| |
| <p>Users can find more information about the decision tree algorithm in the <a href="mllib-decision-tree.html">MLlib Decision Tree guide</a>. In this section, we demonstrate the Pipelines API for Decision Trees.</p> |
| |
| <p>The Pipelines API for Decision Trees offers a bit more functionality than the original API. In particular, for classification, users can get the predicted probability of each class (a.k.a. class conditional probabilities).</p> |
| |
| <p>Ensembles of trees (Random Forests and Gradient-Boosted Trees) are described in the <a href="ml-ensembles.html">Ensembles guide</a>.</p> |
| |
| <h1 id="inputs-and-outputs">Inputs and Outputs</h1> |
| |
| <p>We list the input and output (prediction) column types here. |
| All output columns are optional; to exclude an output column, set its corresponding Param to an empty string.</p> |
| |
| <h2 id="input-columns">Input Columns</h2> |
| |
| <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>labelCol</td> |
| <td>Double</td> |
| <td>"label"</td> |
| <td>Label to predict</td> |
| </tr> |
| <tr> |
| <td>featuresCol</td> |
| <td>Vector</td> |
| <td>"features"</td> |
| <td>Feature vector</td> |
| </tr> |
| </tbody> |
| </table> |
| |
| <h2 id="output-columns">Output Columns</h2> |
| |
| <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> |
| <th align="left">Notes</th> |
| </tr> |
| </thead> |
| <tbody> |
| <tr> |
| <td>predictionCol</td> |
| <td>Double</td> |
| <td>"prediction"</td> |
| <td>Predicted label</td> |
| <td></td> |
| </tr> |
| <tr> |
| <td>rawPredictionCol</td> |
| <td>Vector</td> |
| <td>"rawPrediction"</td> |
| <td>Vector of length # classes, with the counts of training instance labels at the tree node which makes the prediction</td> |
| <td>Classification only</td> |
| </tr> |
| <tr> |
| <td>probabilityCol</td> |
| <td>Vector</td> |
| <td>"probability"</td> |
| <td>Vector of length # classes equal to rawPrediction normalized to a multinomial distribution</td> |
| <td>Classification only</td> |
| </tr> |
| </tbody> |
| </table> |
| |
| <h1 id="examples">Examples</h1> |
| |
| <p>The below examples demonstrate the Pipelines API for Decision Trees. The main differences between this API and the <a href="mllib-decision-tree.html">original MLlib Decision Tree API</a> are:</p> |
| |
| <ul> |
| <li>support for ML Pipelines</li> |
| <li>separation of Decision Trees for classification vs. regression</li> |
| <li>use of DataFrame metadata to distinguish continuous and categorical features</li> |
| </ul> |
| |
| <h2 id="classification">Classification</h2> |
| |
| <p>The following examples load a dataset in LibSVM format, split it into training and test sets, train on the first dataset, and then evaluate on the held-out test set. |
| We use two feature transformers to prepare the data; these help index categories for the label and categorical features, adding metadata to the <code>DataFrame</code> which the Decision Tree algorithm can recognize.</p> |
| |
| <div class="codetabs"> |
| <div data-lang="scala"> |
| |
| <p>More details on parameters can be found in the <a href="api/scala/index.html#org.apache.spark.ml.classification.DecisionTreeClassifier">Scala API documentation</a>.</p> |
| |
| <div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.ml.Pipeline</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.classification.DecisionTreeClassifier</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.classification.DecisionTreeClassificationModel</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.feature.</span><span class="o">{</span><span class="nc">StringIndexer</span><span class="o">,</span> <span class="nc">IndexToString</span><span class="o">,</span> <span class="nc">VectorIndexer</span><span class="o">}</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span> |
| |
| <span class="c1">// Load and parse the data file, converting it to a DataFrame.</span> |
| <span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="nc">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">).</span><span class="n">toDF</span><span class="o">()</span> |
| |
| <span class="c1">// Index labels, adding metadata to the label column.</span> |
| <span class="c1">// Fit on whole dataset to include all labels in index.</span> |
| <span class="k">val</span> <span class="n">labelIndexer</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">StringIndexer</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setInputCol</span><span class="o">(</span><span class="s">"label"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setOutputCol</span><span class="o">(</span><span class="s">"indexedLabel"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">data</span><span class="o">)</span> |
| <span class="c1">// Automatically identify categorical features, and index them.</span> |
| <span class="k">val</span> <span class="n">featureIndexer</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">VectorIndexer</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setInputCol</span><span class="o">(</span><span class="s">"features"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setOutputCol</span><span class="o">(</span><span class="s">"indexedFeatures"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setMaxCategories</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span> <span class="c1">// features with > 4 distinct values are treated as continuous</span> |
| <span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">data</span><span class="o">)</span> |
| |
| <span class="c1">// Split the data into training and test sets (30% held out for testing)</span> |
| <span class="k">val</span> <span class="nc">Array</span><span class="o">(</span><span class="n">trainingData</span><span class="o">,</span> <span class="n">testData</span><span class="o">)</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">randomSplit</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="mf">0.7</span><span class="o">,</span> <span class="mf">0.3</span><span class="o">))</span> |
| |
| <span class="c1">// Train a DecisionTree model.</span> |
| <span class="k">val</span> <span class="n">dt</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">DecisionTreeClassifier</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setLabelCol</span><span class="o">(</span><span class="s">"indexedLabel"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setFeaturesCol</span><span class="o">(</span><span class="s">"indexedFeatures"</span><span class="o">)</span> |
| |
| <span class="c1">// Convert indexed labels back to original labels.</span> |
| <span class="k">val</span> <span class="n">labelConverter</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">IndexToString</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setInputCol</span><span class="o">(</span><span class="s">"prediction"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setOutputCol</span><span class="o">(</span><span class="s">"predictedLabel"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setLabels</span><span class="o">(</span><span class="n">labelIndexer</span><span class="o">.</span><span class="n">labels</span><span class="o">)</span> |
| |
| <span class="c1">// Chain indexers and tree in a Pipeline</span> |
| <span class="k">val</span> <span class="n">pipeline</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">Pipeline</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setStages</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="n">labelIndexer</span><span class="o">,</span> <span class="n">featureIndexer</span><span class="o">,</span> <span class="n">dt</span><span class="o">,</span> <span class="n">labelConverter</span><span class="o">))</span> |
| |
| <span class="c1">// Train model. This also runs the indexers.</span> |
| <span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="n">pipeline</span><span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">trainingData</span><span class="o">)</span> |
| |
| <span class="c1">// Make predictions.</span> |
| <span class="k">val</span> <span class="n">predictions</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">testData</span><span class="o">)</span> |
| |
| <span class="c1">// Select example rows to display.</span> |
| <span class="n">predictions</span><span class="o">.</span><span class="n">select</span><span class="o">(</span><span class="s">"predictedLabel"</span><span class="o">,</span> <span class="s">"label"</span><span class="o">,</span> <span class="s">"features"</span><span class="o">).</span><span class="n">show</span><span class="o">(</span><span class="mi">5</span><span class="o">)</span> |
| |
| <span class="c1">// Select (prediction, true label) and compute test error</span> |
| <span class="k">val</span> <span class="n">evaluator</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">MulticlassClassificationEvaluator</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setLabelCol</span><span class="o">(</span><span class="s">"indexedLabel"</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="o">.</span><span class="n">setMetricName</span><span class="o">(</span><span class="s">"precision"</span><span class="o">)</span> |
| <span class="k">val</span> <span class="n">accuracy</span> <span class="k">=</span> <span class="n">evaluator</span><span class="o">.</span><span class="n">evaluate</span><span class="o">(</span><span class="n">predictions</span><span class="o">)</span> |
| <span class="n">println</span><span class="o">(</span><span class="s">"Test Error = "</span> <span class="o">+</span> <span class="o">(</span><span class="mf">1.0</span> <span class="o">-</span> <span class="n">accuracy</span><span class="o">))</span> |
| |
| <span class="k">val</span> <span class="n">treeModel</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">stages</span><span class="o">(</span><span class="mi">2</span><span class="o">).</span><span class="n">asInstanceOf</span><span class="o">[</span><span class="kt">DecisionTreeClassificationModel</span><span class="o">]</span> |
| <span class="n">println</span><span class="o">(</span><span class="s">"Learned classification tree model:\n"</span> <span class="o">+</span> <span class="n">treeModel</span><span class="o">.</span><span class="n">toDebugString</span><span class="o">)</span></code></pre></div> |
| |
| </div> |
| |
| <div data-lang="java"> |
| |
| <p>More details on parameters can be found in the <a href="api/java/org/apache/spark/ml/classification/DecisionTreeClassifier.html">Java API documentation</a>.</p> |
| |
| <div class="highlight"><pre><code class="language-java" data-lang="java"><span class="kn">import</span> <span class="nn">org.apache.spark.ml.Pipeline</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.PipelineModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.PipelineStage</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.classification.DecisionTreeClassifier</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.classification.DecisionTreeClassificationModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.feature.*</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.rdd.RDD</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="c1">// Load and parse the data file, converting it to a DataFrame.</span> |
| <span class="n">RDD</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">></span> <span class="n">rdd</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="o">.</span><span class="na">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">.</span><span class="na">sc</span><span class="o">(),</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">);</span> |
| <span class="n">DataFrame</span> <span class="n">data</span> <span class="o">=</span> <span class="n">jsql</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">rdd</span><span class="o">,</span> <span class="n">LabeledPoint</span><span class="o">.</span><span class="na">class</span><span class="o">);</span> |
| |
| <span class="c1">// Index labels, adding metadata to the label column.</span> |
| <span class="c1">// Fit on whole dataset to include all labels in index.</span> |
| <span class="n">StringIndexerModel</span> <span class="n">labelIndexer</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">StringIndexer</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setInputCol</span><span class="o">(</span><span class="s">"label"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setOutputCol</span><span class="o">(</span><span class="s">"indexedLabel"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">data</span><span class="o">);</span> |
| <span class="c1">// Automatically identify categorical features, and index them.</span> |
| <span class="n">VectorIndexerModel</span> <span class="n">featureIndexer</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">VectorIndexer</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setInputCol</span><span class="o">(</span><span class="s">"features"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setOutputCol</span><span class="o">(</span><span class="s">"indexedFeatures"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setMaxCategories</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span> <span class="c1">// features with > 4 distinct values are treated as continuous</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">data</span><span class="o">);</span> |
| |
| <span class="c1">// Split the data into training and test sets (30% held out for testing)</span> |
| <span class="n">DataFrame</span><span class="o">[]</span> <span class="n">splits</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="na">randomSplit</span><span class="o">(</span><span class="k">new</span> <span class="kt">double</span><span class="o">[]</span> <span class="o">{</span><span class="mf">0.7</span><span class="o">,</span> <span class="mf">0.3</span><span class="o">});</span> |
| <span class="n">DataFrame</span> <span class="n">trainingData</span> <span class="o">=</span> <span class="n">splits</span><span class="o">[</span><span class="mi">0</span><span class="o">];</span> |
| <span class="n">DataFrame</span> <span class="n">testData</span> <span class="o">=</span> <span class="n">splits</span><span class="o">[</span><span class="mi">1</span><span class="o">];</span> |
| |
| <span class="c1">// Train a DecisionTree model.</span> |
| <span class="n">DecisionTreeClassifier</span> <span class="n">dt</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">DecisionTreeClassifier</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setLabelCol</span><span class="o">(</span><span class="s">"indexedLabel"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setFeaturesCol</span><span class="o">(</span><span class="s">"indexedFeatures"</span><span class="o">);</span> |
| |
| <span class="c1">// Convert indexed labels back to original labels.</span> |
| <span class="n">IndexToString</span> <span class="n">labelConverter</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">IndexToString</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setInputCol</span><span class="o">(</span><span class="s">"prediction"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setOutputCol</span><span class="o">(</span><span class="s">"predictedLabel"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setLabels</span><span class="o">(</span><span class="n">labelIndexer</span><span class="o">.</span><span class="na">labels</span><span class="o">());</span> |
| |
| <span class="c1">// Chain indexers and tree in a Pipeline</span> |
| <span class="n">Pipeline</span> <span class="n">pipeline</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">Pipeline</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setStages</span><span class="o">(</span><span class="k">new</span> <span class="n">PipelineStage</span><span class="o">[]</span> <span class="o">{</span><span class="n">labelIndexer</span><span class="o">,</span> <span class="n">featureIndexer</span><span class="o">,</span> <span class="n">dt</span><span class="o">,</span> <span class="n">labelConverter</span><span class="o">});</span> |
| |
| <span class="c1">// Train model. This also runs the indexers.</span> |
| <span class="n">PipelineModel</span> <span class="n">model</span> <span class="o">=</span> <span class="n">pipeline</span><span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">trainingData</span><span class="o">);</span> |
| |
| <span class="c1">// Make predictions.</span> |
| <span class="n">DataFrame</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">testData</span><span class="o">);</span> |
| |
| <span class="c1">// Select example rows to display.</span> |
| <span class="n">predictions</span><span class="o">.</span><span class="na">select</span><span class="o">(</span><span class="s">"predictedLabel"</span><span class="o">,</span> <span class="s">"label"</span><span class="o">,</span> <span class="s">"features"</span><span class="o">).</span><span class="na">show</span><span class="o">(</span><span class="mi">5</span><span class="o">);</span> |
| |
| <span class="c1">// Select (prediction, true label) and compute test error</span> |
| <span class="n">MulticlassClassificationEvaluator</span> <span class="n">evaluator</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">MulticlassClassificationEvaluator</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setLabelCol</span><span class="o">(</span><span class="s">"indexedLabel"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setPredictionCol</span><span class="o">(</span><span class="s">"prediction"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setMetricName</span><span class="o">(</span><span class="s">"precision"</span><span class="o">);</span> |
| <span class="kt">double</span> <span class="n">accuracy</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="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">"Test Error = "</span> <span class="o">+</span> <span class="o">(</span><span class="mf">1.0</span> <span class="o">-</span> <span class="n">accuracy</span><span class="o">));</span> |
| |
| <span class="n">DecisionTreeClassificationModel</span> <span class="n">treeModel</span> <span class="o">=</span> |
| <span class="o">(</span><span class="n">DecisionTreeClassificationModel</span><span class="o">)(</span><span class="n">model</span><span class="o">.</span><span class="na">stages</span><span class="o">()[</span><span class="mi">2</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">"Learned classification tree model:\n"</span> <span class="o">+</span> <span class="n">treeModel</span><span class="o">.</span><span class="na">toDebugString</span><span class="o">());</span></code></pre></div> |
| |
| </div> |
| |
| <div data-lang="python"> |
| |
| <p>More details on parameters can be found in the <a href="api/python/pyspark.ml.html#pyspark.ml.classification.DecisionTreeClassifier">Python API documentation</a>.</p> |
| |
| <div class="highlight"><pre><code class="language-python" data-lang="python"><span class="kn">from</span> <span class="nn">pyspark.ml</span> <span class="kn">import</span> <span class="n">Pipeline</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.classification</span> <span class="kn">import</span> <span class="n">DecisionTreeClassifier</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.feature</span> <span class="kn">import</span> <span class="n">StringIndexer</span><span class="p">,</span> <span class="n">VectorIndexer</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.evaluation</span> <span class="kn">import</span> <span class="n">MulticlassClassificationEvaluator</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">MLUtils</span> |
| |
| <span class="c"># Load and parse the data file, converting it to a DataFrame.</span> |
| <span class="n">data</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="p">)</span><span class="o">.</span><span class="n">toDF</span><span class="p">()</span> |
| |
| <span class="c"># Index labels, adding metadata to the label column.</span> |
| <span class="c"># Fit on whole dataset to include all labels in index.</span> |
| <span class="n">labelIndexer</span> <span class="o">=</span> <span class="n">StringIndexer</span><span class="p">(</span><span class="n">inputCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">outputCol</span><span class="o">=</span><span class="s">"indexedLabel"</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> |
| <span class="c"># Automatically identify categorical features, and index them.</span> |
| <span class="c"># We specify maxCategories so features with > 4 distinct values are treated as continuous.</span> |
| <span class="n">featureIndexer</span> <span class="o">=</span>\ |
| <span class="n">VectorIndexer</span><span class="p">(</span><span class="n">inputCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">outputCol</span><span class="o">=</span><span class="s">"indexedFeatures"</span><span class="p">,</span> <span class="n">maxCategories</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> |
| |
| <span class="c"># Split the data into training and test sets (30% held out for testing)</span> |
| <span class="p">(</span><span class="n">trainingData</span><span class="p">,</span> <span class="n">testData</span><span class="p">)</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">randomSplit</span><span class="p">([</span><span class="mf">0.7</span><span class="p">,</span> <span class="mf">0.3</span><span class="p">])</span> |
| |
| <span class="c"># Train a DecisionTree model.</span> |
| <span class="n">dt</span> <span class="o">=</span> <span class="n">DecisionTreeClassifier</span><span class="p">(</span><span class="n">labelCol</span><span class="o">=</span><span class="s">"indexedLabel"</span><span class="p">,</span> <span class="n">featuresCol</span><span class="o">=</span><span class="s">"indexedFeatures"</span><span class="p">)</span> |
| |
| <span class="c"># Chain indexers and tree in a Pipeline</span> |
| <span class="n">pipeline</span> <span class="o">=</span> <span class="n">Pipeline</span><span class="p">(</span><span class="n">stages</span><span class="o">=</span><span class="p">[</span><span class="n">labelIndexer</span><span class="p">,</span> <span class="n">featureIndexer</span><span class="p">,</span> <span class="n">dt</span><span class="p">])</span> |
| |
| <span class="c"># Train model. This also runs the indexers.</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">pipeline</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">trainingData</span><span class="p">)</span> |
| |
| <span class="c"># Make predictions.</span> |
| <span class="n">predictions</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">testData</span><span class="p">)</span> |
| |
| <span class="c"># Select example rows to display.</span> |
| <span class="n">predictions</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s">"prediction"</span><span class="p">,</span> <span class="s">"indexedLabel"</span><span class="p">,</span> <span class="s">"features"</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">(</span><span class="mi">5</span><span class="p">)</span> |
| |
| <span class="c"># Select (prediction, true label) and compute test error</span> |
| <span class="n">evaluator</span> <span class="o">=</span> <span class="n">MulticlassClassificationEvaluator</span><span class="p">(</span> |
| <span class="n">labelCol</span><span class="o">=</span><span class="s">"indexedLabel"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span> <span class="n">metricName</span><span class="o">=</span><span class="s">"precision"</span><span class="p">)</span> |
| <span class="n">accuracy</span> <span class="o">=</span> <span class="n">evaluator</span><span class="o">.</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="s">"Test Error = </span><span class="si">%g</span><span class="s">"</span> <span class="o">%</span> <span class="p">(</span><span class="mf">1.0</span> <span class="o">-</span> <span class="n">accuracy</span><span class="p">)</span> |
| |
| <span class="n">treeModel</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">stages</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span> |
| <span class="k">print</span> <span class="n">treeModel</span> <span class="c"># summary only</span></code></pre></div> |
| |
| </div> |
| |
| </div> |
| |
| <h2 id="regression">Regression</h2> |
| |
| <p>The following examples load a dataset in LibSVM format, split it into training and test sets, train on the first dataset, and then evaluate on the held-out test set. |
| We use a feature transformer to index categorical features, adding metadata to the <code>DataFrame</code> which the Decision Tree algorithm can recognize.</p> |
| |
| <div class="codetabs"> |
| <div data-lang="scala"> |
| |
| <p>More details on parameters can be found in the <a href="api/scala/index.html#org.apache.spark.ml.regression.DecisionTreeRegressor">Scala API documentation</a>.</p> |
| |
| <div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.ml.Pipeline</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.regression.DecisionTreeRegressor</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.regression.DecisionTreeRegressionModel</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.feature.VectorIndexer</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.ml.evaluation.RegressionEvaluator</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span> |
| |
| <span class="c1">// Load and parse the data file, converting it to a DataFrame.</span> |
| <span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="nc">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">).</span><span class="n">toDF</span><span class="o">()</span> |
| |
| <span class="c1">// Automatically identify categorical features, and index them.</span> |
| <span class="c1">// Here, we treat features with > 4 distinct values as continuous.</span> |
| <span class="k">val</span> <span class="n">featureIndexer</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">VectorIndexer</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setInputCol</span><span class="o">(</span><span class="s">"features"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setOutputCol</span><span class="o">(</span><span class="s">"indexedFeatures"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setMaxCategories</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">data</span><span class="o">)</span> |
| |
| <span class="c1">// Split the data into training and test sets (30% held out for testing)</span> |
| <span class="k">val</span> <span class="nc">Array</span><span class="o">(</span><span class="n">trainingData</span><span class="o">,</span> <span class="n">testData</span><span class="o">)</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">randomSplit</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="mf">0.7</span><span class="o">,</span> <span class="mf">0.3</span><span class="o">))</span> |
| |
| <span class="c1">// Train a DecisionTree model.</span> |
| <span class="k">val</span> <span class="n">dt</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">DecisionTreeRegressor</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setLabelCol</span><span class="o">(</span><span class="s">"label"</span><span class="o">)</span> |
| <span class="o">.</span><span class="n">setFeaturesCol</span><span class="o">(</span><span class="s">"indexedFeatures"</span><span class="o">)</span> |
| |
| <span class="c1">// Chain indexer and tree in a Pipeline</span> |
| <span class="k">val</span> <span class="n">pipeline</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">Pipeline</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setStages</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="n">featureIndexer</span><span class="o">,</span> <span class="n">dt</span><span class="o">))</span> |
| |
| <span class="c1">// Train model. This also runs the indexer.</span> |
| <span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="n">pipeline</span><span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">trainingData</span><span class="o">)</span> |
| |
| <span class="c1">// Make predictions.</span> |
| <span class="k">val</span> <span class="n">predictions</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">testData</span><span class="o">)</span> |
| |
| <span class="c1">// Select example rows to display.</span> |
| <span class="n">predictions</span><span class="o">.</span><span class="n">select</span><span class="o">(</span><span class="s">"prediction"</span><span class="o">,</span> <span class="s">"label"</span><span class="o">,</span> <span class="s">"features"</span><span class="o">).</span><span class="n">show</span><span class="o">(</span><span class="mi">5</span><span class="o">)</span> |
| |
| <span class="c1">// Select (prediction, true label) and compute test error</span> |
| <span class="k">val</span> <span class="n">evaluator</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">RegressionEvaluator</span><span class="o">()</span> |
| <span class="o">.</span><span class="n">setLabelCol</span><span class="o">(</span><span class="s">"label"</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="o">.</span><span class="n">setMetricName</span><span class="o">(</span><span class="s">"rmse"</span><span class="o">)</span> |
| <span class="k">val</span> <span class="n">rmse</span> <span class="k">=</span> <span class="n">evaluator</span><span class="o">.</span><span class="n">evaluate</span><span class="o">(</span><span class="n">predictions</span><span class="o">)</span> |
| <span class="n">println</span><span class="o">(</span><span class="s">"Root Mean Squared Error (RMSE) on test data = "</span> <span class="o">+</span> <span class="n">rmse</span><span class="o">)</span> |
| |
| <span class="k">val</span> <span class="n">treeModel</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">stages</span><span class="o">(</span><span class="mi">1</span><span class="o">).</span><span class="n">asInstanceOf</span><span class="o">[</span><span class="kt">DecisionTreeRegressionModel</span><span class="o">]</span> |
| <span class="n">println</span><span class="o">(</span><span class="s">"Learned regression tree model:\n"</span> <span class="o">+</span> <span class="n">treeModel</span><span class="o">.</span><span class="n">toDebugString</span><span class="o">)</span></code></pre></div> |
| |
| </div> |
| |
| <div data-lang="java"> |
| |
| <p>More details on parameters can be found in the <a href="api/java/org/apache/spark/ml/regression/DecisionTreeRegressor.html">Java API documentation</a>.</p> |
| |
| <div class="highlight"><pre><code class="language-java" data-lang="java"><span class="kn">import</span> <span class="nn">org.apache.spark.ml.Pipeline</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.PipelineModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.PipelineStage</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.evaluation.RegressionEvaluator</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.feature.VectorIndexer</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.feature.VectorIndexerModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.regression.DecisionTreeRegressionModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.ml.regression.DecisionTreeRegressor</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.rdd.RDD</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="c1">// Load and parse the data file, converting it to a DataFrame.</span> |
| <span class="n">RDD</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">></span> <span class="n">rdd</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="o">.</span><span class="na">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">.</span><span class="na">sc</span><span class="o">(),</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">);</span> |
| <span class="n">DataFrame</span> <span class="n">data</span> <span class="o">=</span> <span class="n">jsql</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">rdd</span><span class="o">,</span> <span class="n">LabeledPoint</span><span class="o">.</span><span class="na">class</span><span class="o">);</span> |
| |
| <span class="c1">// Automatically identify categorical features, and index them.</span> |
| <span class="c1">// Set maxCategories so features with > 4 distinct values are treated as continuous.</span> |
| <span class="n">VectorIndexerModel</span> <span class="n">featureIndexer</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">VectorIndexer</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setInputCol</span><span class="o">(</span><span class="s">"features"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setOutputCol</span><span class="o">(</span><span class="s">"indexedFeatures"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setMaxCategories</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">data</span><span class="o">);</span> |
| |
| <span class="c1">// Split the data into training and test sets (30% held out for testing)</span> |
| <span class="n">DataFrame</span><span class="o">[]</span> <span class="n">splits</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="na">randomSplit</span><span class="o">(</span><span class="k">new</span> <span class="kt">double</span><span class="o">[]</span> <span class="o">{</span><span class="mf">0.7</span><span class="o">,</span> <span class="mf">0.3</span><span class="o">});</span> |
| <span class="n">DataFrame</span> <span class="n">trainingData</span> <span class="o">=</span> <span class="n">splits</span><span class="o">[</span><span class="mi">0</span><span class="o">];</span> |
| <span class="n">DataFrame</span> <span class="n">testData</span> <span class="o">=</span> <span class="n">splits</span><span class="o">[</span><span class="mi">1</span><span class="o">];</span> |
| |
| <span class="c1">// Train a DecisionTree model.</span> |
| <span class="n">DecisionTreeRegressor</span> <span class="n">dt</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">DecisionTreeRegressor</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setFeaturesCol</span><span class="o">(</span><span class="s">"indexedFeatures"</span><span class="o">);</span> |
| |
| <span class="c1">// Chain indexer and tree in a Pipeline</span> |
| <span class="n">Pipeline</span> <span class="n">pipeline</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">Pipeline</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setStages</span><span class="o">(</span><span class="k">new</span> <span class="n">PipelineStage</span><span class="o">[]</span> <span class="o">{</span><span class="n">featureIndexer</span><span class="o">,</span> <span class="n">dt</span><span class="o">});</span> |
| |
| <span class="c1">// Train model. This also runs the indexer.</span> |
| <span class="n">PipelineModel</span> <span class="n">model</span> <span class="o">=</span> <span class="n">pipeline</span><span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">trainingData</span><span class="o">);</span> |
| |
| <span class="c1">// Make predictions.</span> |
| <span class="n">DataFrame</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">testData</span><span class="o">);</span> |
| |
| <span class="c1">// Select example rows to display.</span> |
| <span class="n">predictions</span><span class="o">.</span><span class="na">select</span><span class="o">(</span><span class="s">"label"</span><span class="o">,</span> <span class="s">"features"</span><span class="o">).</span><span class="na">show</span><span class="o">(</span><span class="mi">5</span><span class="o">);</span> |
| |
| <span class="c1">// Select (prediction, true label) and compute test error</span> |
| <span class="n">RegressionEvaluator</span> <span class="n">evaluator</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">RegressionEvaluator</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">setLabelCol</span><span class="o">(</span><span class="s">"label"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setPredictionCol</span><span class="o">(</span><span class="s">"prediction"</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">setMetricName</span><span class="o">(</span><span class="s">"rmse"</span><span class="o">);</span> |
| <span class="kt">double</span> <span class="n">rmse</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="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">"Root Mean Squared Error (RMSE) on test data = "</span> <span class="o">+</span> <span class="n">rmse</span><span class="o">);</span> |
| |
| <span class="n">DecisionTreeRegressionModel</span> <span class="n">treeModel</span> <span class="o">=</span> |
| <span class="o">(</span><span class="n">DecisionTreeRegressionModel</span><span class="o">)(</span><span class="n">model</span><span class="o">.</span><span class="na">stages</span><span class="o">()[</span><span class="mi">1</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">"Learned regression tree model:\n"</span> <span class="o">+</span> <span class="n">treeModel</span><span class="o">.</span><span class="na">toDebugString</span><span class="o">());</span></code></pre></div> |
| |
| </div> |
| |
| <div data-lang="python"> |
| |
| <p>More details on parameters can be found in the <a href="api/python/pyspark.ml.html#pyspark.ml.regression.DecisionTreeRegressor">Python API documentation</a>.</p> |
| |
| <div class="highlight"><pre><code class="language-python" data-lang="python"><span class="kn">from</span> <span class="nn">pyspark.ml</span> <span class="kn">import</span> <span class="n">Pipeline</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.regression</span> <span class="kn">import</span> <span class="n">DecisionTreeRegressor</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.feature</span> <span class="kn">import</span> <span class="n">VectorIndexer</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.evaluation</span> <span class="kn">import</span> <span class="n">RegressionEvaluator</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">MLUtils</span> |
| |
| <span class="c"># Load and parse the data file, converting it to a DataFrame.</span> |
| <span class="n">data</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="p">)</span><span class="o">.</span><span class="n">toDF</span><span class="p">()</span> |
| |
| <span class="c"># Automatically identify categorical features, and index them.</span> |
| <span class="c"># We specify maxCategories so features with > 4 distinct values are treated as continuous.</span> |
| <span class="n">featureIndexer</span> <span class="o">=</span>\ |
| <span class="n">VectorIndexer</span><span class="p">(</span><span class="n">inputCol</span><span class="o">=</span><span class="s">"features"</span><span class="p">,</span> <span class="n">outputCol</span><span class="o">=</span><span class="s">"indexedFeatures"</span><span class="p">,</span> <span class="n">maxCategories</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> |
| |
| <span class="c"># Split the data into training and test sets (30% held out for testing)</span> |
| <span class="p">(</span><span class="n">trainingData</span><span class="p">,</span> <span class="n">testData</span><span class="p">)</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">randomSplit</span><span class="p">([</span><span class="mf">0.7</span><span class="p">,</span> <span class="mf">0.3</span><span class="p">])</span> |
| |
| <span class="c"># Train a DecisionTree model.</span> |
| <span class="n">dt</span> <span class="o">=</span> <span class="n">DecisionTreeRegressor</span><span class="p">(</span><span class="n">featuresCol</span><span class="o">=</span><span class="s">"indexedFeatures"</span><span class="p">)</span> |
| |
| <span class="c"># Chain indexer and tree in a Pipeline</span> |
| <span class="n">pipeline</span> <span class="o">=</span> <span class="n">Pipeline</span><span class="p">(</span><span class="n">stages</span><span class="o">=</span><span class="p">[</span><span class="n">featureIndexer</span><span class="p">,</span> <span class="n">dt</span><span class="p">])</span> |
| |
| <span class="c"># Train model. This also runs the indexer.</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">pipeline</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">trainingData</span><span class="p">)</span> |
| |
| <span class="c"># Make predictions.</span> |
| <span class="n">predictions</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">testData</span><span class="p">)</span> |
| |
| <span class="c"># Select example rows to display.</span> |
| <span class="n">predictions</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s">"prediction"</span><span class="p">,</span> <span class="s">"label"</span><span class="p">,</span> <span class="s">"features"</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">(</span><span class="mi">5</span><span class="p">)</span> |
| |
| <span class="c"># Select (prediction, true label) and compute test error</span> |
| <span class="n">evaluator</span> <span class="o">=</span> <span class="n">RegressionEvaluator</span><span class="p">(</span> |
| <span class="n">labelCol</span><span class="o">=</span><span class="s">"label"</span><span class="p">,</span> <span class="n">predictionCol</span><span class="o">=</span><span class="s">"prediction"</span><span class="p">,</span> <span class="n">metricName</span><span class="o">=</span><span class="s">"rmse"</span><span class="p">)</span> |
| <span class="n">rmse</span> <span class="o">=</span> <span class="n">evaluator</span><span class="o">.</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="s">"Root Mean Squared Error (RMSE) on test data = </span><span class="si">%g</span><span class="s">"</span> <span class="o">%</span> <span class="n">rmse</span> |
| |
| <span class="n">treeModel</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">stages</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
| <span class="k">print</span> <span class="n">treeModel</span> <span class="c"># summary only</span></code></pre></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| </div> <!-- /container --> |
| |
| <script src="js/vendor/jquery-1.8.0.min.js"></script> |
| <script src="js/vendor/bootstrap.min.js"></script> |
| <script src="js/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> |
