diff options
author | Tathagata Das <tdas@apache.org> | 2014-08-05 23:40:54 +0000 |
---|---|---|
committer | Tathagata Das <tdas@apache.org> | 2014-08-05 23:40:54 +0000 |
commit | a8baa06017eef8d0fa3adefd595cd5aa3f22083a (patch) | |
tree | 88b8198f81e4d7de0363f2be0508fcc1a817ddd7 /site/docs/1.0.2/mllib-guide.html | |
parent | bb63580d440750ccbe9b1ee8a24256076a9a1acb (diff) | |
download | spark-website-a8baa06017eef8d0fa3adefd595cd5aa3f22083a.tar.gz spark-website-a8baa06017eef8d0fa3adefd595cd5aa3f22083a.tar.bz2 spark-website-a8baa06017eef8d0fa3adefd595cd5aa3f22083a.zip |
Adding Spark 1.0.2
Diffstat (limited to 'site/docs/1.0.2/mllib-guide.html')
-rw-r--r-- | site/docs/1.0.2/mllib-guide.html | 298 |
1 files changed, 298 insertions, 0 deletions
diff --git a/site/docs/1.0.2/mllib-guide.html b/site/docs/1.0.2/mllib-guide.html new file mode 100644 index 000000000..197bc8979 --- /dev/null +++ b/site/docs/1.0.2/mllib-guide.html @@ -0,0 +1,298 @@ +<!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>Machine Learning Library (MLlib) - Spark 1.0.2 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">1.0.2</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">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">v1.0.2</span></p>--> + </div> + </div> + </div> + + <div class="container" id="content"> + + <h1 class="title">Machine Learning Library (MLlib)</h1> + + + <p>MLlib is a Spark implementation of some common machine learning algorithms and utilities, +including classification, regression, clustering, collaborative +filtering, dimensionality reduction, as well as underlying optimization primitives:</p> + +<ul> + <li><a href="mllib-basics.html">Basics</a> + <ul> + <li>data types </li> + <li>summary statistics</li> + </ul> + </li> + <li>Classification and regression + <ul> + <li><a href="mllib-linear-methods.html#linear-support-vector-machine-svm">linear support vector machine (SVM)</a></li> + <li><a href="mllib-linear-methods.html#logistic-regression">logistic regression</a></li> + <li><a href="mllib-linear-methods.html#linear-least-squares-lasso-and-ridge-regression">linear least squares, Lasso, and ridge regression</a></li> + <li><a href="mllib-decision-tree.html">decision tree</a></li> + <li><a href="mllib-naive-bayes.html">naive Bayes</a></li> + </ul> + </li> + <li><a href="mllib-collaborative-filtering.html">Collaborative filtering</a> + <ul> + <li>alternating least squares (ALS)</li> + </ul> + </li> + <li><a href="mllib-clustering.html">Clustering</a> + <ul> + <li>k-means</li> + </ul> + </li> + <li><a href="mllib-dimensionality-reduction.html">Dimensionality reduction</a> + <ul> + <li>singular value decomposition (SVD)</li> + <li>principal component analysis (PCA)</li> + </ul> + </li> + <li><a href="mllib-optimization.html">Optimization</a> + <ul> + <li>stochastic gradient descent</li> + <li>limited-memory BFGS (L-BFGS)</li> + </ul> + </li> +</ul> + +<p>MLlib is a new component under active development. +The APIs marked <code>Experimental</code>/<code>DeveloperApi</code> may change in future releases, +and we will provide migration guide between releases.</p> + +<h1 id="dependencies">Dependencies</h1> + +<p>MLlib uses linear algebra packages <a href="http://www.scalanlp.org/">Breeze</a>, which depends on +<a href="https://github.com/fommil/netlib-java">netlib-java</a>, and +<a href="https://github.com/mikiobraun/jblas">jblas</a>. +<code>netlib-java</code> and <code>jblas</code> depend on native Fortran routines. +You need to install the +<a href="https://github.com/mikiobraun/jblas/wiki/Missing-Libraries">gfortran runtime library</a> if it is not +already present on your nodes. MLlib will throw a linking error if it cannot detect these libraries +automatically. Due to license issues, we do not include <code>netlib-java</code>’s native libraries in MLlib’s +dependency set. If no native library is available at runtime, you will see a warning message. To +use native libraries from <code>netlib-java</code>, please include artifact +<code>com.github.fommil.netlib:all:1.1.2</code> as a dependency of your project or build your own (see +<a href="https://github.com/fommil/netlib-java/blob/master/README.md#machine-optimised-system-libraries">instructions</a>).</p> + +<p>To use MLlib in Python, you will need <a href="http://www.numpy.org">NumPy</a> version 1.4 or newer.</p> + +<hr /> + +<h1 id="migration-guide">Migration Guide</h1> + +<h2 id="from-09-to-10">From 0.9 to 1.0</h2> + +<p>In MLlib v1.0, we support both dense and sparse input in a unified way, which introduces a few +breaking changes. If your data is sparse, please store it in a sparse format instead of dense to +take advantage of sparsity in both storage and computation.</p> + +<div class="codetabs"> +<div data-lang="scala"> + + <p>We used to represent a feature vector by <code>Array[Double]</code>, which is replaced by +<a href="api/scala/index.html#org.apache.spark.mllib.linalg.Vector"><code>Vector</code></a> in v1.0. Algorithms that used +to accept <code>RDD[Array[Double]]</code> now take +<code>RDD[Vector]</code>. <a href="api/scala/index.html#org.apache.spark.mllib.regression.LabeledPoint"><code>LabeledPoint</code></a> +is now a wrapper of <code>(Double, Vector)</code> instead of <code>(Double, Array[Double])</code>. Converting +<code>Array[Double]</code> to <code>Vector</code> is straightforward:</p> + + <div class="highlight"><pre><code class="scala"><span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.</span><span class="o">{</span><span class="nc">Vector</span><span class="o">,</span> <span class="nc">Vectors</span><span class="o">}</span> + +<span class="k">val</span> <span class="n">array</span><span class="k">:</span> <span class="kt">Array</span><span class="o">[</span><span class="kt">Double</span><span class="o">]</span> <span class="k">=</span> <span class="o">...</span> <span class="c1">// a double array</span> +<span class="k">val</span> <span class="n">vector</span><span class="k">:</span> <span class="kt">Vector</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">array</span><span class="o">)</span> <span class="c1">// a dense vector</span> +</code></pre></div> + + <p><a href="api/scala/index.html#org.apache.spark.mllib.linalg.Vectors$"><code>Vectors</code></a> provides factory methods to create sparse vectors.</p> + + <p><em>Note</em>. Scala imports <code>scala.collection.immutable.Vector</code> by default, so you have to import <code>org.apache.spark.mllib.linalg.Vector</code> explicitly to use MLlib’s <code>Vector</code>.</p> + + </div> + +<div data-lang="java"> + + <p>We used to represent a feature vector by <code>double[]</code>, which is replaced by +<a href="api/java/index.html?org/apache/spark/mllib/linalg/Vector.html"><code>Vector</code></a> in v1.0. Algorithms that used +to accept <code>RDD<double[]></code> now take +<code>RDD<Vector></code>. <a href="api/java/index.html?org/apache/spark/mllib/regression/LabeledPoint.html"><code>LabeledPoint</code></a> +is now a wrapper of <code>(double, Vector)</code> instead of <code>(double, double[])</code>. Converting <code>double[]</code> to +<code>Vector</code> is straightforward:</p> + + <div class="highlight"><pre><code class="java"><span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vector</span><span class="o">;</span> +<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span><span class="o">;</span> + +<span class="kt">double</span><span class="o">[]</span> <span class="n">array</span> <span class="o">=</span> <span class="o">...</span> <span class="c1">// a double array</span> +<span class="n">Vector</span> <span class="n">vector</span> <span class="o">=</span> <span class="n">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="n">array</span><span class="o">);</span> <span class="c1">// a dense vector</span> +</code></pre></div> + + <p><a href="api/scala/index.html#org.apache.spark.mllib.linalg.Vectors$"><code>Vectors</code></a> provides factory methods to +create sparse vectors.</p> + + </div> + +<div data-lang="python"> + + <p>We used to represent a labeled feature vector in a NumPy array, where the first entry corresponds to +the label and the rest are features. This representation is replaced by class +<a href="api/python/pyspark.mllib.regression.LabeledPoint-class.html"><code>LabeledPoint</code></a>, which takes both +dense and sparse feature vectors.</p> + + <div class="highlight"><pre><code class="python"><span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">SparseVector</span> +<span class="kn">from</span> <span class="nn">pyspark.mllib.regression</span> <span class="kn">import</span> <span class="n">LabeledPoint</span> + +<span class="c"># Create a labeled point with a positive label and a dense feature vector.</span> +<span class="n">pos</span> <span class="o">=</span> <span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">1.0</span><span class="p">,</span> <span class="p">[</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">])</span> + +<span class="c"># Create a labeled point with a negative label and a sparse feature vector.</span> +<span class="n">neg</span> <span class="o">=</span> <span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span> <span class="p">[</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">3.0</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> |