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-collaborative-filtering.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-collaborative-filtering.html')
| -rw-r--r-- | site/docs/1.0.1/mllib-collaborative-filtering.html | 306 |
1 files changed, 306 insertions, 0 deletions
diff --git a/site/docs/1.0.1/mllib-collaborative-filtering.html b/site/docs/1.0.1/mllib-collaborative-filtering.html new file mode 100644 index 000000000..ad1983409 --- /dev/null +++ b/site/docs/1.0.1/mllib-collaborative-filtering.html @@ -0,0 +1,306 @@ +<!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>Collaborative Filtering - 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> - Collaborative Filtering</h1> + + + <ul id="markdown-toc"> + <li><a href="#collaborative-filtering">Collaborative filtering</a> <ul> + <li><a href="#explicit-vs-implicit-feedback">Explicit vs. implicit feedback</a></li> + </ul> + </li> + <li><a href="#examples">Examples</a></li> + <li><a href="#tutorial">Tutorial</a></li> +</ul> + +<h2 id="collaborative-filtering">Collaborative filtering</h2> + +<p><a href="http://en.wikipedia.org/wiki/Recommender_system#Collaborative_filtering">Collaborative filtering</a> +is commonly used for recommender systems. These techniques aim to fill in the +missing entries of a user-item association matrix. MLlib currently supports +model-based collaborative filtering, in which users and products are described +by a small set of latent factors that can be used to predict missing entries. +In particular, we implement the <a href="http://dl.acm.org/citation.cfm?id=1608614">alternating least squares +(ALS)</a> +algorithm to learn these latent factors. The implementation in MLlib has the +following parameters:</p> + +<ul> + <li><em>numBlocks</em> is the number of blocks used to parallelize computation (set to -1 to auto-configure).</li> + <li><em>rank</em> is the number of latent factors in our model.</li> + <li><em>iterations</em> is the number of iterations to run.</li> + <li><em>lambda</em> specifies the regularization parameter in ALS.</li> + <li><em>implicitPrefs</em> specifies whether to use the <em>explicit feedback</em> ALS variant or one adapted for +<em>implicit feedback</em> data.</li> + <li><em>alpha</em> is a parameter applicable to the implicit feedback variant of ALS that governs the +<em>baseline</em> confidence in preference observations.</li> +</ul> + +<h3 id="explicit-vs-implicit-feedback">Explicit vs. implicit feedback</h3> + +<p>The standard approach to matrix factorization based collaborative filtering treats +the entries in the user-item matrix as <em>explicit</em> preferences given by the user to the item.</p> + +<p>It is common in many real-world use cases to only have access to <em>implicit feedback</em> (e.g. views, +clicks, purchases, likes, shares etc.). The approach used in MLlib to deal with such data is taken +from +<a href="http://dx.doi.org/10.1109/ICDM.2008.22">Collaborative Filtering for Implicit Feedback Datasets</a>. +Essentially instead of trying to model the matrix of ratings directly, this approach treats the data +as a combination of binary preferences and <em>confidence values</em>. The ratings are then related to the +level of confidence in observed user preferences, rather than explicit ratings given to items. The +model then tries to find latent factors that can be used to predict the expected preference of a +user for an item.</p> + +<h2 id="examples">Examples</h2> + +<div class="codetabs"> + +<div data-lang="scala"> + <p>In the following example we load rating data. Each row consists of a user, a product and a rating. +We use the default <a href="api/scala/index.html#org.apache.spark.mllib.recommendation.ALS$">ALS.train()</a> +method which assumes ratings are explicit. We evaluate the +recommendation model by measuring the Mean Squared Error of rating prediction.</p> + + <div class="highlight"><pre><code class="scala"><span class="k">import</span> <span class="nn">org.apache.spark.mllib.recommendation.ALS</span> +<span class="k">import</span> <span class="nn">org.apache.spark.mllib.recommendation.Rating</span> + +<span class="c1">// Load and parse the data</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/als/test.data"</span><span class="o">)</span> +<span class="k">val</span> <span class="n">ratings</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="k">_</span><span class="o">.</span><span class="n">split</span><span class="o">(</span><span class="sc">','</span><span class="o">)</span> <span class="k">match</span> <span class="o">{</span> <span class="k">case</span> <span class="nc">Array</span><span class="o">(</span><span class="n">user</span><span class="o">,</span> <span class="n">item</span><span class="o">,</span> <span class="n">rate</span><span class="o">)</span> <span class="k">=></span> + <span class="nc">Rating</span><span class="o">(</span><span class="n">user</span><span class="o">.</span><span class="n">toInt</span><span class="o">,</span> <span class="n">item</span><span class="o">.</span><span class="n">toInt</span><span class="o">,</span> <span class="n">rate</span><span class="o">.</span><span class="n">toDouble</span><span class="o">)</span> + <span class="o">})</span> + +<span class="c1">// Build the recommendation model using ALS</span> +<span class="k">val</span> <span class="n">rank</span> <span class="k">=</span> <span class="mi">10</span> +<span class="k">val</span> <span class="n">numIterations</span> <span class="k">=</span> <span class="mi">20</span> +<span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="nc">ALS</span><span class="o">.</span><span class="n">train</span><span class="o">(</span><span class="n">ratings</span><span class="o">,</span> <span class="n">rank</span><span class="o">,</span> <span class="n">numIterations</span><span class="o">,</span> <span class="mf">0.01</span><span class="o">)</span> + +<span class="c1">// Evaluate the model on rating data</span> +<span class="k">val</span> <span class="n">usersProducts</span> <span class="k">=</span> <span class="n">ratings</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="k">case</span> <span class="nc">Rating</span><span class="o">(</span><span class="n">user</span><span class="o">,</span> <span class="n">product</span><span class="o">,</span> <span class="n">rate</span><span class="o">)</span> <span class="k">=></span> + <span class="o">(</span><span class="n">user</span><span class="o">,</span> <span class="n">product</span><span class="o">)</span> +<span class="o">}</span> +<span class="k">val</span> <span class="n">predictions</span> <span class="k">=</span> + <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="o">(</span><span class="n">usersProducts</span><span class="o">).</span><span class="n">map</span> <span class="o">{</span> <span class="k">case</span> <span class="nc">Rating</span><span class="o">(</span><span class="n">user</span><span class="o">,</span> <span class="n">product</span><span class="o">,</span> <span class="n">rate</span><span class="o">)</span> <span class="k">=></span> + <span class="o">((</span><span class="n">user</span><span class="o">,</span> <span class="n">product</span><span class="o">),</span> <span class="n">rate</span><span class="o">)</span> + <span class="o">}</span> +<span class="k">val</span> <span class="n">ratesAndPreds</span> <span class="k">=</span> <span class="n">ratings</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="k">case</span> <span class="nc">Rating</span><span class="o">(</span><span class="n">user</span><span class="o">,</span> <span class="n">product</span><span class="o">,</span> <span class="n">rate</span><span class="o">)</span> <span class="k">=></span> + <span class="o">((</span><span class="n">user</span><span class="o">,</span> <span class="n">product</span><span class="o">),</span> <span class="n">rate</span><span class="o">)</span> +<span class="o">}.</span><span class="n">join</span><span class="o">(</span><span class="n">predictions</span><span class="o">)</span> +<span class="k">val</span> <span class="nc">MSE</span> <span class="k">=</span> <span class="n">ratesAndPreds</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="k">case</span> <span class="o">((</span><span class="n">user</span><span class="o">,</span> <span class="n">product</span><span class="o">),</span> <span class="o">(</span><span class="n">r1</span><span class="o">,</span> <span class="n">r2</span><span class="o">))</span> <span class="k">=></span> + <span class="k">val</span> <span class="n">err</span> <span class="k">=</span> <span class="o">(</span><span class="n">r1</span> <span class="o">-</span> <span class="n">r2</span><span class="o">)</span> + <span class="n">err</span> <span class="o">*</span> <span class="n">err</span> +<span class="o">}.</span><span class="n">mean</span><span class="o">()</span> +<span class="n">println</span><span class="o">(</span><span class="s">"Mean Squared Error = "</span> <span class="o">+</span> <span class="nc">MSE</span><span class="o">)</span> +</code></pre></div> + + <p>If the rating matrix is derived from other source of information (i.e., it is inferred from +other signals), you can use the trainImplicit method to get better results.</p> + + <div class="highlight"><pre><code class="scala"><span class="k">val</span> <span class="n">alpha</span> <span class="k">=</span> <span class="mf">0.01</span> +<span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="nc">ALS</span><span class="o">.</span><span class="n">trainImplicit</span><span class="o">(</span><span class="n">ratings</span><span class="o">,</span> <span class="n">rank</span><span class="o">,</span> <span class="n">numIterations</span><span class="o">,</span> <span class="n">alpha</span><span class="o">)</span> +</code></pre></div> + + </div> + +<div data-lang="java"> + <p>All of MLlib’s methods use Java-friendly types, so you can import and call them there the same +way you do in Scala. The only caveat is that the methods take Scala RDD objects, while the +Spark Java API uses a separate <code>JavaRDD</code> class. You can convert a Java RDD to a Scala one by +calling <code>.rdd()</code> on your <code>JavaRDD</code> object.</p> + </div> + +<div data-lang="python"> + <p>In the following example we load rating data. Each row consists of a user, a product and a rating. +We use the default ALS.train() method which assumes ratings are explicit. We evaluate the +recommendation by measuring the Mean Squared Error of rating prediction.</p> + + <div class="highlight"><pre><code class="python"><span class="kn">from</span> <span class="nn">pyspark.mllib.recommendation</span> <span class="kn">import</span> <span class="n">ALS</span> +<span class="kn">from</span> <span class="nn">numpy</span> <span class="kn">import</span> <span class="n">array</span> + +<span class="c"># Load and parse the data</span> +<span class="n">data</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="s">"mllib/data/als/test.data"</span><span class="p">)</span> +<span class="n">ratings</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">line</span><span class="p">:</span> <span class="n">array</span><span class="p">([</span><span class="nb">float</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">','</span><span class="p">)]))</span> + +<span class="c"># Build the recommendation model using Alternating Least Squares</span> +<span class="n">rank</span> <span class="o">=</span> <span class="mi">10</span> +<span class="n">numIterations</span> <span class="o">=</span> <span class="mi">20</span> +<span class="n">model</span> <span class="o">=</span> <span class="n">ALS</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">ratings</span><span class="p">,</span> <span class="n">rank</span><span class="p">,</span> <span class="n">numIterations</span><span class="p">)</span> + +<span class="c"># Evaluate the model on training data</span> +<span class="n">testdata</span> <span class="o">=</span> <span class="n">ratings</span><span class="o">.</span><span class="n">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="nb">int</span><span class="p">(</span><span class="n">p</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span> <span class="nb">int</span><span class="p">(</span><span class="n">p</span><span class="p">[</span><span class="mi">1</span><span class="p">])))</span> +<span class="n">predictions</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predictAll</span><span class="p">(</span><span class="n">testdata</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">r</span><span class="p">:</span> <span class="p">((</span><span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">r</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span> <span class="n">r</span><span class="p">[</span><span class="mi">2</span><span class="p">]))</span> +<span class="n">ratesAndPreds</span> <span class="o">=</span> <span class="n">ratings</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">r</span><span class="p">:</span> <span class="p">((</span><span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">r</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span> <span class="n">r</span><span class="p">[</span><span class="mi">2</span><span class="p">]))</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">predictions</span><span class="p">)</span> +<span class="n">MSE</span> <span class="o">=</span> <span class="n">ratesAndPreds</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">r</span><span class="p">:</span> <span class="p">(</span><span class="n">r</span><span class="p">[</span><span class="mi">1</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> <span class="o">-</span> <span class="n">r</span><span class="p">[</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">])</span><span class="o">**</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">reduce</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">:</span> <span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="p">)</span><span class="o">/</span><span class="n">ratesAndPreds</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> +<span class="k">print</span><span class="p">(</span><span class="s">"Mean Squared Error = "</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">MSE</span><span class="p">))</span> +</code></pre></div> + + <p>If the rating matrix is derived from other source of information (i.e., it is inferred from other +signals), you can use the trainImplicit method to get better results.</p> + + <div class="highlight"><pre><code class="python"><span class="c"># Build the recommendation model using Alternating Least Squares based on implicit ratings</span> +<span class="n">model</span> <span class="o">=</span> <span class="n">ALS</span><span class="o">.</span><span class="n">trainImplicit</span><span class="p">(</span><span class="n">ratings</span><span class="p">,</span> <span class="n">rank</span><span class="p">,</span> <span class="n">numIterations</span><span class="p">,</span> <span class="n">alpha</span> <span class="o">=</span> <span class="mf">0.01</span><span class="p">)</span> +</code></pre></div> + + </div> + +</div> + +<h2 id="tutorial">Tutorial</h2> + +<p><a href="http://ampcamp.berkeley.edu/">AMP Camp</a> provides a hands-on tutorial for +<a href="http://ampcamp.berkeley.edu/big-data-mini-course/movie-recommendation-with-mllib.html">personalized movie recommendation with MLlib</a>.</p> + + + </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> |