site/docs/3.5.0/mllib-naive-bayes.html - spark-website - Git at Google


 <!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>Naive Bayes - RDD-based API - 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">Naive Bayes - RDD-based API</h1>


                     <p><a href="http://en.wikipedia.org/wiki/Naive_Bayes_classifier">Naive Bayes</a> is a simple
 multiclass classification algorithm with the assumption of independence between
 every pair of features. Naive Bayes can be trained very efficiently. Within a
 single pass to the training data, it computes the conditional probability
 distribution of each feature given label, and then it applies Bayes&#8217; theorem to
 compute the conditional probability distribution of label given an observation
 and use it for prediction.</p>

 <p><code class="language-plaintext highlighter-rouge">spark.mllib</code> supports <a href="http://en.wikipedia.org/wiki/Naive_Bayes_classifier#Multinomial_naive_Bayes">multinomial naive
 Bayes</a>
 and <a href="http://nlp.stanford.edu/IR-book/html/htmledition/the-bernoulli-model-1.html">Bernoulli naive Bayes</a>.
 These models are typically used for <a href="http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html">document classification</a>.
 Within that context, each observation is a document and each
 feature represents a term whose value is the frequency of the term (in multinomial naive Bayes) or
 a zero or one indicating whether the term was found in the document (in Bernoulli naive Bayes).
 Feature values must be nonnegative. The model type is selected with an optional parameter
 &#8220;multinomial&#8221; or &#8220;bernoulli&#8221; with &#8220;multinomial&#8221; as the default.
 <a href="http://en.wikipedia.org/wiki/Lidstone_smoothing">Additive smoothing</a> can be used by
 setting the parameter $\lambda$ (default to $1.0$). For document classification, the input feature
 vectors are usually sparse, and sparse vectors should be supplied as input to take advantage of
 sparsity. Since the training data is only used once, it is not necessary to cache it.</p>

 <h2 id="examples">Examples</h2>

 <div class="codetabs">

 <div data-lang="python">

     <p><a href="api/python/reference/api/pyspark.mllib.classification.NaiveBayes.html">NaiveBayes</a> implements multinomial
 naive Bayes. It takes an RDD of
 <a href="api/python/reference/api/pyspark.mllib.regression.LabeledPoint.html">LabeledPoint</a> and an optionally
 smoothing parameter <code class="language-plaintext highlighter-rouge">lambda</code> as input, and output a
 <a href="api/python/reference/api/pyspark.mllib.classification.NaiveBayesModel.html">NaiveBayesModel</a>, which can be
 used for evaluation and prediction.</p>

     <p>Note that the Python API does not yet support model save/load but will in the future.</p>

     <p>Refer to the <a href="api/python/reference/api/pyspark.mllib.classification.NaiveBayes.html"><code class="language-plaintext highlighter-rouge">NaiveBayes</code> Python docs</a> and <a href="api/python/reference/api/pyspark.mllib.classification.NaiveBayesModel.html"><code class="language-plaintext highlighter-rouge">NaiveBayesModel</code> Python docs</a> for more details on the API.</p>

     <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.mllib.classification</span> <span class="kn">import</span> <span class="n">NaiveBayes</span><span class="p">,</span> <span class="n">NaiveBayesModel</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="c1"># Load and parse the data file.
 </span><span class="n">data</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="p">.</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="c1"># Split data approximately into training (60%) and test (40%)
 </span><span class="n">training</span><span class="p">,</span> <span class="n">test</span> <span class="o">=</span> <span class="n">data</span><span class="p">.</span><span class="n">randomSplit</span><span class="p">([</span><span class="mf">0.6</span><span class="p">,</span> <span class="mf">0.4</span><span class="p">])</span>

 <span class="c1"># Train a naive Bayes model.
 </span><span class="n">model</span> <span class="o">=</span> <span class="n">NaiveBayes</span><span class="p">.</span><span class="n">train</span><span class="p">(</span><span class="n">training</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span>

 <span class="c1"># Make prediction and test accuracy.
 </span><span class="n">predictionAndLabel</span> <span class="o">=</span> <span class="n">test</span><span class="p">.</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">p</span><span class="p">:</span> <span class="p">(</span><span class="n">model</span><span class="p">.</span><span class="n">predict</span><span class="p">(</span><span class="n">p</span><span class="p">.</span><span class="n">features</span><span class="p">),</span> <span class="n">p</span><span class="p">.</span><span class="n">label</span><span class="p">))</span>
 <span class="n">accuracy</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">*</span> <span class="n">predictionAndLabel</span><span class="p">.</span><span class="nb">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">pl</span><span class="p">:</span> <span class="n">pl</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="n">pl</span><span class="p">[</span><span class="mi">1</span><span class="p">]).</span><span class="n">count</span><span class="p">()</span> <span class="o">/</span> <span class="n">test</span><span class="p">.</span><span class="n">count</span><span class="p">()</span>
 <span class="k">print</span><span class="p">(</span><span class="s">'model accuracy {}'</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="n">accuracy</span><span class="p">))</span>

 <span class="c1"># Save and load model
 </span><span class="n">output_dir</span> <span class="o">=</span> <span class="s">'target/tmp/myNaiveBayesModel'</span>
 <span class="n">shutil</span><span class="p">.</span><span class="n">rmtree</span><span class="p">(</span><span class="n">output_dir</span><span class="p">,</span> <span class="n">ignore_errors</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
 <span class="n">model</span><span class="p">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">output_dir</span><span class="p">)</span>
 <span class="n">sameModel</span> <span class="o">=</span> <span class="n">NaiveBayesModel</span><span class="p">.</span><span class="n">load</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">output_dir</span><span class="p">)</span>
 <span class="n">predictionAndLabel</span> <span class="o">=</span> <span class="n">test</span><span class="p">.</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">p</span><span class="p">:</span> <span class="p">(</span><span class="n">sameModel</span><span class="p">.</span><span class="n">predict</span><span class="p">(</span><span class="n">p</span><span class="p">.</span><span class="n">features</span><span class="p">),</span> <span class="n">p</span><span class="p">.</span><span class="n">label</span><span class="p">))</span>
 <span class="n">accuracy</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">*</span> <span class="n">predictionAndLabel</span><span class="p">.</span><span class="nb">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">pl</span><span class="p">:</span> <span class="n">pl</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="n">pl</span><span class="p">[</span><span class="mi">1</span><span class="p">]).</span><span class="n">count</span><span class="p">()</span> <span class="o">/</span> <span class="n">test</span><span class="p">.</span><span class="n">count</span><span class="p">()</span>
 <span class="k">print</span><span class="p">(</span><span class="s">'sameModel accuracy {}'</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="n">accuracy</span><span class="p">))</span></code></pre></div>
     <div><small>Find full example code at "examples/src/main/python/mllib/naive_bayes_example.py" in the Spark repo.</small></div>
   </div>

 <div data-lang="scala">

     <p><a href="api/scala/org/apache/spark/mllib/classification/NaiveBayes$.html">NaiveBayes</a> implements
 multinomial naive Bayes. It takes an RDD of
 <a href="api/scala/org/apache/spark/mllib/regression/LabeledPoint.html">LabeledPoint</a> and an optional
 smoothing parameter <code class="language-plaintext highlighter-rouge">lambda</code> as input, an optional model type parameter (default is &#8220;multinomial&#8221;), and outputs a
 <a href="api/scala/org/apache/spark/mllib/classification/NaiveBayesModel.html">NaiveBayesModel</a>, which
 can be used for evaluation and prediction.</p>

     <p>Refer to the <a href="api/scala/org/apache/spark/mllib/classification/NaiveBayes$.html"><code class="language-plaintext highlighter-rouge">NaiveBayes</code> Scala docs</a> and <a href="api/scala/org/apache/spark/mllib/classification/NaiveBayesModel.html"><code class="language-plaintext highlighter-rouge">NaiveBayesModel</code> Scala docs</a> for details on the API.</p>

     <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.mllib.classification.</span><span class="o">{</span><span class="nc">NaiveBayes</span><span class="o">,</span> <span class="nc">NaiveBayesModel</span><span class="o">}</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.</span>
 <span class="k">val</span> <span class="nv">data</span> <span class="k">=</span> <span class="nv">MLUtils</span><span class="o">.</span><span class="py">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="c1">// Split data into training (60%) and test (40%).</span>
 <span class="k">val</span> <span class="nv">Array</span><span class="o">(</span><span class="n">training</span><span class="o">,</span> <span class="n">test</span><span class="o">)</span> <span class="k">=</span> <span class="nv">data</span><span class="o">.</span><span class="py">randomSplit</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="mf">0.6</span><span class="o">,</span> <span class="mf">0.4</span><span class="o">))</span>

 <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="nv">NaiveBayes</span><span class="o">.</span><span class="py">train</span><span class="o">(</span><span class="n">training</span><span class="o">,</span> <span class="n">lambda</span> <span class="k">=</span> <span class="mf">1.0</span><span class="o">,</span> <span class="n">modelType</span> <span class="k">=</span> <span class="s">"multinomial"</span><span class="o">)</span>

 <span class="k">val</span> <span class="nv">predictionAndLabel</span> <span class="k">=</span> <span class="nv">test</span><span class="o">.</span><span class="py">map</span><span class="o">(</span><span class="n">p</span> <span class="k">=&gt;</span> <span class="o">(</span><span class="nv">model</span><span class="o">.</span><span class="py">predict</span><span class="o">(</span><span class="nv">p</span><span class="o">.</span><span class="py">features</span><span class="o">),</span> <span class="nv">p</span><span class="o">.</span><span class="py">label</span><span class="o">))</span>
 <span class="k">val</span> <span class="nv">accuracy</span> <span class="k">=</span> <span class="mf">1.0</span> <span class="o">*</span> <span class="nv">predictionAndLabel</span><span class="o">.</span><span class="py">filter</span><span class="o">(</span><span class="n">x</span> <span class="k">=&gt;</span> <span class="nv">x</span><span class="o">.</span><span class="py">_1</span> <span class="o">==</span> <span class="nv">x</span><span class="o">.</span><span class="py">_2</span><span class="o">).</span><span class="py">count</span><span class="o">()</span> <span class="o">/</span> <span class="nv">test</span><span class="o">.</span><span class="py">count</span><span class="o">()</span>

 <span class="c1">// Save and load model</span>
 <span class="nv">model</span><span class="o">.</span><span class="py">save</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"target/tmp/myNaiveBayesModel"</span><span class="o">)</span>
 <span class="k">val</span> <span class="nv">sameModel</span> <span class="k">=</span> <span class="nv">NaiveBayesModel</span><span class="o">.</span><span class="py">load</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> <span class="s">"target/tmp/myNaiveBayesModel"</span><span class="o">)</span></code></pre></div>
     <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala" in the Spark repo.</small></div>
   </div>
 <div data-lang="java">

     <p><a href="api/java/org/apache/spark/mllib/classification/NaiveBayes.html">NaiveBayes</a> implements
 multinomial naive Bayes. It takes a Scala RDD of
 <a href="api/java/org/apache/spark/mllib/regression/LabeledPoint.html">LabeledPoint</a> and an
 optionally smoothing parameter <code class="language-plaintext highlighter-rouge">lambda</code> as input, and output a
 <a href="api/java/org/apache/spark/mllib/classification/NaiveBayesModel.html">NaiveBayesModel</a>, which
 can be used for evaluation and prediction.</p>

     <p>Refer to the <a href="api/java/org/apache/spark/mllib/classification/NaiveBayes.html"><code class="language-plaintext highlighter-rouge">NaiveBayes</code> Java docs</a> and <a href="api/java/org/apache/spark/mllib/classification/NaiveBayesModel.html"><code class="language-plaintext highlighter-rouge">NaiveBayesModel</code> Java docs</a> for details on the API.</p>

     <div class="highlight"><pre class="codehilite"><code><span class="kn">import</span> <span class="nn">scala.Tuple2</span><span class="o">;</span>
 <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaPairRDD</span><span class="o">;</span>
 <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaRDD</span><span class="o">;</span>
 <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaSparkContext</span><span class="o">;</span>
 <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.classification.NaiveBayes</span><span class="o">;</span>
 <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.classification.NaiveBayesModel</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="nc">String</span> <span class="n">path</span> <span class="o">=</span> <span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">;</span>
 <span class="nc">JavaRDD</span><span class="o">&lt;</span><span class="nc">LabeledPoint</span><span class="o">&gt;</span> <span class="n">inputData</span> <span class="o">=</span> <span class="nc">MLUtils</span><span class="o">.</span><span class="na">loadLibSVMFile</span><span class="o">(</span><span class="n">jsc</span><span class="o">.</span><span class="na">sc</span><span class="o">(),</span> <span class="n">path</span><span class="o">).</span><span class="na">toJavaRDD</span><span class="o">();</span>
 <span class="nc">JavaRDD</span><span class="o">&lt;</span><span class="nc">LabeledPoint</span><span class="o">&gt;[]</span> <span class="n">tmp</span> <span class="o">=</span> <span class="n">inputData</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="mf">0.6</span><span class="o">,</span> <span class="mf">0.4</span><span class="o">});</span>
 <span class="nc">JavaRDD</span><span class="o">&lt;</span><span class="nc">LabeledPoint</span><span class="o">&gt;</span> <span class="n">training</span> <span class="o">=</span> <span class="n">tmp</span><span class="o">[</span><span class="mi">0</span><span class="o">];</span> <span class="c1">// training set</span>
 <span class="nc">JavaRDD</span><span class="o">&lt;</span><span class="nc">LabeledPoint</span><span class="o">&gt;</span> <span class="n">test</span> <span class="o">=</span> <span class="n">tmp</span><span class="o">[</span><span class="mi">1</span><span class="o">];</span> <span class="c1">// test set</span>
 <span class="nc">NaiveBayesModel</span> <span class="n">model</span> <span class="o">=</span> <span class="nc">NaiveBayes</span><span class="o">.</span><span class="na">train</span><span class="o">(</span><span class="n">training</span><span class="o">.</span><span class="na">rdd</span><span class="o">(),</span> <span class="mf">1.0</span><span class="o">);</span>
 <span class="nc">JavaPairRDD</span><span class="o">&lt;</span><span class="nc">Double</span><span class="o">,</span> <span class="nc">Double</span><span class="o">&gt;</span> <span class="n">predictionAndLabel</span> <span class="o">=</span>
   <span class="n">test</span><span class="o">.</span><span class="na">mapToPair</span><span class="o">(</span><span class="n">p</span> <span class="o">-&gt;</span> <span class="k">new</span> <span class="nc">Tuple2</span><span class="o">&lt;&gt;(</span><span class="n">model</span><span class="o">.</span><span class="na">predict</span><span class="o">(</span><span class="n">p</span><span class="o">.</span><span class="na">features</span><span class="o">()),</span> <span class="n">p</span><span class="o">.</span><span class="na">label</span><span class="o">()));</span>
 <span class="kt">double</span> <span class="n">accuracy</span> <span class="o">=</span>
   <span class="n">predictionAndLabel</span><span class="o">.</span><span class="na">filter</span><span class="o">(</span><span class="n">pl</span> <span class="o">-&gt;</span> <span class="n">pl</span><span class="o">.</span><span class="na">_1</span><span class="o">().</span><span class="na">equals</span><span class="o">(</span><span class="n">pl</span><span class="o">.</span><span class="na">_2</span><span class="o">())).</span><span class="na">count</span><span class="o">()</span> <span class="o">/</span> <span class="o">(</span><span class="kt">double</span><span class="o">)</span> <span class="n">test</span><span class="o">.</span><span class="na">count</span><span class="o">();</span>

 <span class="c1">// Save and load model</span>
 <span class="n">model</span><span class="o">.</span><span class="na">save</span><span class="o">(</span><span class="n">jsc</span><span class="o">.</span><span class="na">sc</span><span class="o">(),</span> <span class="s">"target/tmp/myNaiveBayesModel"</span><span class="o">);</span>
 <span class="nc">NaiveBayesModel</span> <span class="n">sameModel</span> <span class="o">=</span> <span class="nc">NaiveBayesModel</span><span class="o">.</span><span class="na">load</span><span class="o">(</span><span class="n">jsc</span><span class="o">.</span><span class="na">sc</span><span class="o">(),</span> <span class="s">"target/tmp/myNaiveBayesModel"</span><span class="o">);</span></code></pre></div>
     <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/mllib/JavaNaiveBayesExample.java" 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>