diff options
| author | Patrick Wendell <pwendell@apache.org> | 2014-07-11 17:23:23 +0000 |
|---|---|---|
| committer | Patrick Wendell <pwendell@apache.org> | 2014-07-11 17:23:23 +0000 |
| commit | 0beac4e243f85e71554fe04093b09eb1745fea82 (patch) | |
| tree | bc20d10426c5d57e2f189305865dc2bbec447923 /site/docs/1.0.1/mllib-naive-bayes.html | |
| parent | ddec2123ba6ab95543d1b250d4f20fb811c48f09 (diff) | |
| download | spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.tar.gz spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.tar.bz2 spark-website-0beac4e243f85e71554fe04093b09eb1745fea82.zip | |
Updating docs for 1.0.1 release
Diffstat (limited to 'site/docs/1.0.1/mllib-naive-bayes.html')
| -rw-r--r-- | site/docs/1.0.1/mllib-naive-bayes.html | 287 |
1 files changed, 287 insertions, 0 deletions
diff --git a/site/docs/1.0.1/mllib-naive-bayes.html b/site/docs/1.0.1/mllib-naive-bayes.html new file mode 100644 index 000000000..7cc589e40 --- /dev/null +++ b/site/docs/1.0.1/mllib-naive-bayes.html @@ -0,0 +1,287 @@ +<!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>Naive Bayes - MLlib - Spark 1.0.1 Documentation</title> + <meta name="description" content=""> + + + + <link rel="stylesheet" href="css/bootstrap.min.css"> + <style> + body { + padding-top: 60px; + padding-bottom: 40px; + } + </style> + <meta name="viewport" content="width=device-width"> + <link rel="stylesheet" href="css/bootstrap-responsive.min.css"> + <link rel="stylesheet" href="css/main.css"> + + <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script> + + <link rel="stylesheet" href="css/pygments-default.css"> + + + <!-- Google analytics script --> + <script type="text/javascript"> + var _gaq = _gaq || []; + _gaq.push(['_setAccount', 'UA-32518208-1']); + _gaq.push(['_trackPageview']); + + (function() { + var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; + ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; + var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); + })(); + </script> + + + </head> + <body> + <!--[if lt IE 7]> + <p class="chromeframe">You are using an outdated browser. <a href="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p> + <![endif]--> + + <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html --> + + <div class="navbar navbar-fixed-top" id="topbar"> + <div class="navbar-inner"> + <div class="container"> + <div class="brand"><a href="index.html"> + <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">1.0.1</span> + </div> + <ul class="nav"> + <!--TODO(andyk): Add class="active" attribute to li some how.--> + <li><a href="index.html">Overview</a></li> + + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a> + <ul class="dropdown-menu"> + <li><a href="quick-start.html">Quick Start</a></li> + <li><a href="programming-guide.html">Spark Programming Guide</a></li> + <li class="divider"></li> + <li><a href="streaming-programming-guide.html">Spark Streaming</a></li> + <li><a href="sql-programming-guide.html">Spark SQL</a></li> + <li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li> + <li><a href="graphx-programming-guide.html">GraphX (Graph Processing)</a></li> + <li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li> + </ul> + </li> + + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a> + <ul class="dropdown-menu"> + <li><a href="api/scala/index.html#org.apache.spark.package">Scaladoc</a></li> + <li><a href="api/java/index.html">Javadoc</a></li> + <li><a href="api/python/index.html">Python API</a></li> + </ul> + </li> + + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a> + <ul class="dropdown-menu"> + <li><a href="cluster-overview.html">Overview</a></li> + <li><a href="submitting-applications.html">Submitting Applications</a></li> + <li class="divider"></li> + <li><a href="ec2-scripts.html">Amazon EC2</a></li> + <li><a href="spark-standalone.html">Standalone Mode</a></li> + <li><a href="running-on-mesos.html">Mesos</a></li> + <li><a href="running-on-yarn.html">YARN</a></li> + </ul> + </li> + + <li class="dropdown"> + <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a> + <ul class="dropdown-menu"> + <li><a href="configuration.html">Configuration</a></li> + <li><a href="monitoring.html">Monitoring</a></li> + <li><a href="tuning.html">Tuning Guide</a></li> + <li><a href="job-scheduling.html">Job Scheduling</a></li> + <li><a href="security.html">Security</a></li> + <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li> + <li><a href="hadoop-third-party-distributions.html">3<sup>rd</sup>-Party Hadoop Distros</a></li> + <li class="divider"></li> + <li><a href="building-with-maven.html">Building Spark with Maven</a></li> + <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li> + </ul> + </li> + </ul> + <!--<p class="navbar-text pull-right"><span class="version-text">v1.0.1</span></p>--> + </div> + </div> + </div> + + <div class="container" id="content"> + + <h1 class="title"><a href="mllib-guide.html">MLlib</a> - Naive Bayes</h1> + + + <p>Naive Bayes 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’ theorem to compute the conditional probability distribution of label +given an observation and use it for prediction. For more details, please visit the Wikipedia page +<a href="http://en.wikipedia.org/wiki/Naive_Bayes_classifier">Naive Bayes classifier</a>.</p> + +<p>In MLlib, we implemented multinomial naive Bayes, which is typically used for document +classification. Within that context, each observation is a document, each feature represents a term, +whose value is the frequency of the term. For its formulation, please visit the Wikipedia page +<a href="http://en.wikipedia.org/wiki/Naive_Bayes_classifier#Multinomial_naive_Bayes">Multinomial Naive Bayes</a> +or the section +<a href="http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html">Naive Bayes text classification</a> +from the book Introduction to Information +Retrieval. <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. Please supply sparse vectors 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="scala"> + + <p><a href="api/scala/index.html#org.apache.spark.mllib.classification.NaiveBayes$">NaiveBayes</a> implements +multinomial naive Bayes. It takes an RDD of +<a href="api/scala/index.html#org.apache.spark.mllib.regression.LabeledPoint">LabeledPoint</a> and an optional +smoothing parameter <code>lambda</code> as input, and output a +<a href="api/scala/index.html#org.apache.spark.mllib.classification.NaiveBayesModel">NaiveBayesModel</a>, which +can be used for evaluation and prediction.</p> + + <div class="highlight"><pre><code class="scala"><span class="k">import</span> <span class="nn">org.apache.spark.mllib.classification.NaiveBayes</span> +<span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span> +<span class="k">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span> + +<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"mllib/data/sample_naive_bayes_data.txt"</span><span class="o">)</span> +<span class="k">val</span> <span class="n">parsedData</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="n">line</span> <span class="k">=></span> + <span class="k">val</span> <span class="n">parts</span> <span class="k">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="o">(</span><span class="sc">','</span><span class="o">)</span> + <span class="nc">LabeledPoint</span><span class="o">(</span><span class="n">parts</span><span class="o">(</span><span class="mi">0</span><span class="o">).</span><span class="n">toDouble</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="n">parts</span><span class="o">(</span><span class="mi">1</span><span class="o">).</span><span class="n">split</span><span class="o">(</span><span class="sc">' '</span><span class="o">).</span><span class="n">map</span><span class="o">(</span><span class="k">_</span><span class="o">.</span><span class="n">toDouble</span><span class="o">)))</span> +<span class="o">}</span> +<span class="c1">// Split data into training (60%) and test (40%).</span> +<span class="k">val</span> <span class="n">splits</span> <span class="k">=</span> <span class="n">parsedData</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">0.6</span><span class="o">,</span> <span class="mf">0.4</span><span class="o">),</span> <span class="n">seed</span> <span class="k">=</span> <span class="mi">11L</span><span class="o">)</span> +<span class="k">val</span> <span class="n">training</span> <span class="k">=</span> <span class="n">splits</span><span class="o">(</span><span class="mi">0</span><span class="o">)</span> +<span class="k">val</span> <span class="n">test</span> <span class="k">=</span> <span class="n">splits</span><span class="o">(</span><span class="mi">1</span><span class="o">)</span> + +<span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="nc">NaiveBayes</span><span class="o">.</span><span class="n">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="k">val</span> <span class="n">prediction</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="o">(</span><span class="n">test</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="k">_</span><span class="o">.</span><span class="n">features</span><span class="o">))</span> + +<span class="k">val</span> <span class="n">predictionAndLabel</span> <span class="k">=</span> <span class="n">prediction</span><span class="o">.</span><span class="n">zip</span><span class="o">(</span><span class="n">test</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="k">_</span><span class="o">.</span><span class="n">label</span><span class="o">))</span> +<span class="k">val</span> <span class="n">accuracy</span> <span class="k">=</span> <span class="mf">1.0</span> <span class="o">*</span> <span class="n">predictionAndLabel</span><span class="o">.</span><span class="n">filter</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="n">x</span><span class="o">.</span><span class="n">_1</span> <span class="o">==</span> <span class="n">x</span><span class="o">.</span><span class="n">_2</span><span class="o">).</span><span class="n">count</span><span class="o">()</span> <span class="o">/</span> <span class="n">test</span><span class="o">.</span><span class="n">count</span><span class="o">()</span> +</code></pre></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>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> + + <div class="highlight"><pre><code class="java"><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.function.Function</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">scala.Tuple2</span><span class="o">;</span> + +<span class="n">JavaRDD</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">></span> <span class="n">training</span> <span class="o">=</span> <span class="o">...</span> <span class="c1">// training set</span> +<span class="n">JavaRDD</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">></span> <span class="n">test</span> <span class="o">=</span> <span class="o">...</span> <span class="c1">// test set</span> + +<span class="kd">final</span> <span class="n">NaiveBayesModel</span> <span class="n">model</span> <span class="o">=</span> <span class="n">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="n">JavaRDD</span><span class="o"><</span><span class="n">Double</span><span class="o">></span> <span class="n">prediction</span> <span class="o">=</span> + <span class="n">test</span><span class="o">.</span><span class="na">map</span><span class="o">(</span><span class="k">new</span> <span class="n">Function</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">,</span> <span class="n">Double</span><span class="o">>()</span> <span class="o">{</span> + <span class="nd">@Override</span> <span class="kd">public</span> <span class="n">Double</span> <span class="n">call</span><span class="o">(</span><span class="n">LabeledPoint</span> <span class="n">p</span><span class="o">)</span> <span class="o">{</span> + <span class="k">return</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="o">}</span> + <span class="o">});</span> +<span class="n">JavaPairRDD</span><span class="o"><</span><span class="n">Double</span><span class="o">,</span> <span class="n">Double</span><span class="o">></span> <span class="n">predictionAndLabel</span> <span class="o">=</span> + <span class="n">prediction</span><span class="o">.</span><span class="na">zip</span><span class="o">(</span><span class="n">test</span><span class="o">.</span><span class="na">map</span><span class="o">(</span><span class="k">new</span> <span class="n">Function</span><span class="o"><</span><span class="n">LabeledPoint</span><span class="o">,</span> <span class="n">Double</span><span class="o">>()</span> <span class="o">{</span> + <span class="nd">@Override</span> <span class="kd">public</span> <span class="n">Double</span> <span class="n">call</span><span class="o">(</span><span class="n">LabeledPoint</span> <span class="n">p</span><span class="o">)</span> <span class="o">{</span> + <span class="k">return</span> <span class="n">p</span><span class="o">.</span><span class="na">label</span><span class="o">();</span> + <span class="o">}</span> + <span class="o">}));</span> +<span class="kt">double</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="o">.</span><span class="na">filter</span><span class="o">(</span><span class="k">new</span> <span class="n">Function</span><span class="o"><</span><span class="n">Tuple2</span><span class="o"><</span><span class="n">Double</span><span class="o">,</span> <span class="n">Double</span><span class="o">>,</span> <span class="n">Boolean</span><span class="o">>()</span> <span class="o">{</span> + <span class="nd">@Override</span> <span class="kd">public</span> <span class="n">Boolean</span> <span class="n">call</span><span class="o">(</span><span class="n">Tuple2</span><span class="o"><</span><span class="n">Double</span><span class="o">,</span> <span class="n">Double</span><span class="o">></span> <span class="n">pl</span><span class="o">)</span> <span class="o">{</span> + <span class="k">return</span> <span class="n">pl</span><span class="o">.</span><span class="na">_1</span><span class="o">()</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="o">}</span> + <span class="o">}).</span><span class="na">count</span><span class="o">()</span> <span class="o">/</span> <span class="n">test</span><span class="o">.</span><span class="na">count</span><span class="o">();</span> +</code></pre></div> + + </div> + +<div data-lang="python"> + + <p><a href="api/python/pyspark.mllib.classification.NaiveBayes-class.html">NaiveBayes</a> implements multinomial +naive Bayes. It takes an RDD of +<a href="api/python/pyspark.mllib.regression.LabeledPoint-class.html">LabeledPoint</a> and an optionally +smoothing parameter <code>lambda</code> as input, and output a +<a href="api/python/pyspark.mllib.classification.NaiveBayesModel-class.html">NaiveBayesModel</a>, which can be +used for evaluation and prediction.</p> + + <!-- TODO: Make Python's example consistent with Scala's and Java's. --> + + <div class="highlight"><pre><code class="python"><span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="n">LabeledPoint</span> +<span class="kn">from</span> <span class="nn">pyspark.mllib.classification</span> <span class="kn">import</span> <span class="n">NaiveBayes</span> + +<span class="c"># an RDD of LabeledPoint</span> +<span class="n">data</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span> + <span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">])</span> + <span class="o">...</span> <span class="c"># more labeled points</span> +<span class="p">])</span> + +<span class="c"># Train a naive Bayes model.</span> +<span class="n">model</span> <span class="o">=</span> <span class="n">NaiveBayes</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span> + +<span class="c"># Make prediction.</span> +<span class="n">prediction</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="p">([</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">])</span> +</code></pre></div> + + </div> +</div> + + + </div> <!-- /container --> + + <script src="js/vendor/jquery-1.8.0.min.js"></script> + <script src="js/vendor/bootstrap.min.js"></script> + <script src="js/main.js"></script> + + <!-- MathJax Section --> + <script type="text/x-mathjax-config"> + MathJax.Hub.Config({ + TeX: { equationNumbers: { autoNumber: "AMS" } } + }); + </script> + <script> + // Note that we load MathJax this way to work with local file (file://), HTTP and HTTPS. + // We could use "//cdn.mathjax...", but that won't support "file://". + (function(d, script) { + script = d.createElement('script'); + script.type = 'text/javascript'; + script.async = true; + script.onload = function(){ + MathJax.Hub.Config({ + tex2jax: { + inlineMath: [ ["$", "$"], ["\\\\(","\\\\)"] ], + displayMath: [ ["$$","$$"], ["\\[", "\\]"] ], + processEscapes: true, + skipTags: ['script', 'noscript', 'style', 'textarea', 'pre'] + } + }); + }; + script.src = ('https:' == document.location.protocol ? 'https://' : 'http://') + + 'cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML'; + d.getElementsByTagName('head')[0].appendChild(script); + }(document)); + </script> + </body> +</html> |