diff options
author | Reynold Xin <rxin@apache.org> | 2015-09-27 22:59:57 +0000 |
---|---|---|
committer | Reynold Xin <rxin@apache.org> | 2015-09-27 22:59:57 +0000 |
commit | 3a384df51131aa4c17aa0b6e613790d05b1cea35 (patch) | |
tree | effc2ebccbe2b43e55504c75df9833f72408d6f7 /site/docs/1.5.1/ml-ann.html | |
parent | 09067be9a1ac977b6f7d7e57a9c7aa9684d2c49f (diff) | |
download | spark-website-3a384df51131aa4c17aa0b6e613790d05b1cea35.tar.gz spark-website-3a384df51131aa4c17aa0b6e613790d05b1cea35.tar.bz2 spark-website-3a384df51131aa4c17aa0b6e613790d05b1cea35.zip |
Add 1.5.1 docs
Diffstat (limited to 'site/docs/1.5.1/ml-ann.html')
-rw-r--r-- | site/docs/1.5.1/ml-ann.html | 278 |
1 files changed, 278 insertions, 0 deletions
diff --git a/site/docs/1.5.1/ml-ann.html b/site/docs/1.5.1/ml-ann.html new file mode 100644 index 000000000..4d644d6c0 --- /dev/null +++ b/site/docs/1.5.1/ml-ann.html @@ -0,0 +1,278 @@ +<!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>Multilayer perceptron classifier - ML - Spark 1.5.1 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">1.5.1</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">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">v1.5.1</span></p>--> + </div> + </div> + </div> + + <div class="container" id="content"> + + <h1 class="title"><a href="ml-guide.html">ML</a> - Multilayer perceptron classifier</h1> + + + <p><code>\[ +\newcommand{\R}{\mathbb{R}} +\newcommand{\E}{\mathbb{E}} +\newcommand{\x}{\mathbf{x}} +\newcommand{\y}{\mathbf{y}} +\newcommand{\wv}{\mathbf{w}} +\newcommand{\av}{\mathbf{\alpha}} +\newcommand{\bv}{\mathbf{b}} +\newcommand{\N}{\mathbb{N}} +\newcommand{\id}{\mathbf{I}} +\newcommand{\ind}{\mathbf{1}} +\newcommand{\0}{\mathbf{0}} +\newcommand{\unit}{\mathbf{e}} +\newcommand{\one}{\mathbf{1}} +\newcommand{\zero}{\mathbf{0}} +\]</code></p> + +<p>Multilayer perceptron classifier (MLPC) is a classifier based on the <a href="https://en.wikipedia.org/wiki/Feedforward_neural_network">feedforward artificial neural network</a>. +MLPC consists of multiple layers of nodes. +Each layer is fully connected to the next layer in the network. Nodes in the input layer represent the input data. All other nodes maps inputs to the outputs +by performing linear combination of the inputs with the node’s weights <code>$\wv$</code> and bias <code>$\bv$</code> and applying an activation function. +It can be written in matrix form for MLPC with <code>$K+1$</code> layers as follows: +<code>\[ +\mathrm{y}(\x) = \mathrm{f_K}(...\mathrm{f_2}(\wv_2^T\mathrm{f_1}(\wv_1^T \x+b_1)+b_2)...+b_K) +\]</code> +Nodes in intermediate layers use sigmoid (logistic) function: +<code>\[ +\mathrm{f}(z_i) = \frac{1}{1 + e^{-z_i}} +\]</code> +Nodes in the output layer use softmax function: +<code>\[ +\mathrm{f}(z_i) = \frac{e^{z_i}}{\sum_{k=1}^N e^{z_k}} +\]</code> +The number of nodes <code>$N$</code> in the output layer corresponds to the number of classes.</p> + +<p>MLPC employes backpropagation for learning the model. We use logistic loss function for optimization and L-BFGS as optimization routine.</p> + +<p><strong>Examples</strong></p> + +<div class="codetabs"> + +<div data-lang="scala"> + + <div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.ml.classification.MultilayerPerceptronClassifier</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="k">import</span> <span class="nn">org.apache.spark.sql.Row</span> + +<span class="c1">// Load training data</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_multiclass_classification_data.txt"</span><span class="o">).</span><span class="n">toDF</span><span class="o">()</span> +<span class="c1">// Split the data into train and test</span> +<span class="k">val</span> <span class="n">splits</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">0.6</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">1234L</span><span class="o">)</span> +<span class="k">val</span> <span class="n">train</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="c1">// specify layers for the neural network: </span> +<span class="c1">// input layer of size 4 (features), two intermediate of size 5 and 4 and output of size 3 (classes)</span> +<span class="k">val</span> <span class="n">layers</span> <span class="k">=</span> <span class="nc">Array</span><span class="o">[</span><span class="kt">Int</span><span class="o">](</span><span class="mi">4</span><span class="o">,</span> <span class="mi">5</span><span class="o">,</span> <span class="mi">4</span><span class="o">,</span> <span class="mi">3</span><span class="o">)</span> +<span class="c1">// create the trainer and set its parameters</span> +<span class="k">val</span> <span class="n">trainer</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">MultilayerPerceptronClassifier</span><span class="o">()</span> + <span class="o">.</span><span class="n">setLayers</span><span class="o">(</span><span class="n">layers</span><span class="o">)</span> + <span class="o">.</span><span class="n">setBlockSize</span><span class="o">(</span><span class="mi">128</span><span class="o">)</span> + <span class="o">.</span><span class="n">setSeed</span><span class="o">(</span><span class="mi">1234L</span><span class="o">)</span> + <span class="o">.</span><span class="n">setMaxIter</span><span class="o">(</span><span class="mi">100</span><span class="o">)</span> +<span class="c1">// train the model</span> +<span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="n">trainer</span><span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">train</span><span class="o">)</span> +<span class="c1">// compute precision on the test set</span> +<span class="k">val</span> <span class="n">result</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">test</span><span class="o">)</span> +<span class="k">val</span> <span class="n">predictionAndLabels</span> <span class="k">=</span> <span class="n">result</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="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">setMetricName</span><span class="o">(</span><span class="s">"precision"</span><span class="o">)</span> +<span class="n">println</span><span class="o">(</span><span class="s">"Precision:"</span> <span class="o">+</span> <span class="n">evaluator</span><span class="o">.</span><span class="n">evaluate</span><span class="o">(</span><span class="n">predictionAndLabels</span><span class="o">))</span></code></pre></div> + + </div> + +<div data-lang="java"> + + <div class="highlight"><pre><code class="language-java" data-lang="java"><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.ml.classification.MultilayerPerceptronClassificationModel</span><span class="o">;</span> +<span class="kn">import</span> <span class="nn">org.apache.spark.ml.classification.MultilayerPerceptronClassifier</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.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="c1">// Load training data</span> +<span class="n">String</span> <span class="n">path</span> <span class="o">=</span> <span class="s">"data/mllib/sample_multiclass_classification_data.txt"</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">data</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="n">path</span><span class="o">).</span><span class="na">toJavaRDD</span><span class="o">();</span> +<span class="n">DataFrame</span> <span class="n">dataFrame</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">data</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">// Split the data into train and test</span> +<span class="n">DataFrame</span><span class="o">[]</span> <span class="n">splits</span> <span class="o">=</span> <span class="n">dataFrame</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="mi">1234L</span><span class="o">);</span> +<span class="n">DataFrame</span> <span class="n">train</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">test</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">// specify layers for the neural network:</span> +<span class="c1">// input layer of size 4 (features), two intermediate of size 5 and 4 and output of size 3 (classes)</span> +<span class="kt">int</span><span class="o">[]</span> <span class="n">layers</span> <span class="o">=</span> <span class="k">new</span> <span class="kt">int</span><span class="o">[]</span> <span class="o">{</span><span class="mi">4</span><span class="o">,</span> <span class="mi">5</span><span class="o">,</span> <span class="mi">4</span><span class="o">,</span> <span class="mi">3</span><span class="o">};</span> +<span class="c1">// create the trainer and set its parameters</span> +<span class="n">MultilayerPerceptronClassifier</span> <span class="n">trainer</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">MultilayerPerceptronClassifier</span><span class="o">()</span> + <span class="o">.</span><span class="na">setLayers</span><span class="o">(</span><span class="n">layers</span><span class="o">)</span> + <span class="o">.</span><span class="na">setBlockSize</span><span class="o">(</span><span class="mi">128</span><span class="o">)</span> + <span class="o">.</span><span class="na">setSeed</span><span class="o">(</span><span class="mi">1234L</span><span class="o">)</span> + <span class="o">.</span><span class="na">setMaxIter</span><span class="o">(</span><span class="mi">100</span><span class="o">);</span> +<span class="c1">// train the model</span> +<span class="n">MultilayerPerceptronClassificationModel</span> <span class="n">model</span> <span class="o">=</span> <span class="n">trainer</span><span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">train</span><span class="o">);</span> +<span class="c1">// compute precision on the test set</span> +<span class="n">DataFrame</span> <span class="n">result</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">test</span><span class="o">);</span> +<span class="n">DataFrame</span> <span class="n">predictionAndLabels</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="na">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="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">setMetricName</span><span class="o">(</span><span class="s">"precision"</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">"Precision = "</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">predictionAndLabels</span><span class="o">));</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> |