| |
| <!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 - RDD-based API - Spark 3.3.0 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/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"> |
| <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/docsearch.js@2/dist/cdn/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> |
| <!--[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 fixed-top navbar-expand-md navbar-light bg-light" id="topbar"> |
| <div class="container"> |
| <div class="navbar-header"> |
| <div class="navbar-brand"><a href="index.html"> |
| <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">3.3.0</span> |
| </div> |
| </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"> |
| <!--TODO(andyk): Add class="active" attribute to li some how.--> |
| <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">v3.3.0</span></span>--> |
| </div> |
| </div> |
| </nav> |
| |
| <div class="container-wrapper"> |
| |
| |
| |
| <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> |
| |
| |
| |
| <ul> |
| |
| <li> |
| <a href="mllib-collaborative-filtering.html#collaborative-filtering"> |
| |
| alternating least squares (ALS) |
| |
| </a> |
| </li> |
| |
| |
| |
| </ul> |
| |
| |
| |
| <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">Collaborative Filtering - RDD-based API</h1> |
| |
| |
| <ul id="markdown-toc"> |
| <li><a href="#collaborative-filtering" id="markdown-toc-collaborative-filtering">Collaborative filtering</a> <ul> |
| <li><a href="#explicit-vs-implicit-feedback" id="markdown-toc-explicit-vs-implicit-feedback">Explicit vs. implicit feedback</a></li> |
| <li><a href="#scaling-of-the-regularization-parameter" id="markdown-toc-scaling-of-the-regularization-parameter">Scaling of the regularization parameter</a></li> |
| </ul> |
| </li> |
| <li><a href="#examples" id="markdown-toc-examples">Examples</a></li> |
| <li><a href="#tutorial" id="markdown-toc-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. <code class="language-plaintext highlighter-rouge">spark.mllib</code> 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. |
| <code class="language-plaintext highlighter-rouge">spark.mllib</code> uses 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 <code class="language-plaintext highlighter-rouge">spark.mllib</code> 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 features to use (also referred to as the number of latent factors).</li> |
| <li><em>iterations</em> is the number of iterations of ALS to run. ALS typically converges to a reasonable |
| solution in 20 iterations or less.</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, |
| for example, users giving ratings to movies.</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 <code class="language-plaintext highlighter-rouge">spark.mllib</code> to deal with such data is taken |
| from <a href="https://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 numbers representing the <em>strength</em> in observations of user actions (such as the number of clicks, |
| or the cumulative duration someone spent viewing a movie). Those numbers 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> |
| |
| <h3 id="scaling-of-the-regularization-parameter">Scaling of the regularization parameter</h3> |
| |
| <p>Since v1.1, we scale the regularization parameter <code class="language-plaintext highlighter-rouge">lambda</code> in solving each least squares problem by |
| the number of ratings the user generated in updating user factors, |
| or the number of ratings the product received in updating product factors. |
| This approach is named “ALS-WR” and discussed in the paper |
| “<a href="https://doi.org/10.1007/978-3-540-68880-8_32">Large-Scale Parallel Collaborative Filtering for the Netflix Prize</a>”. |
| It makes <code class="language-plaintext highlighter-rouge">lambda</code> less dependent on the scale of the dataset, so we can apply the |
| best parameter learned from a sampled subset to the full dataset and expect similar performance.</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/org/apache/spark/mllib/recommendation/ALS$.html">ALS.train()</a> |
| method which assumes ratings are explicit. We evaluate the |
| recommendation model by measuring the Mean Squared Error of rating prediction.</p> |
| |
| <p>Refer to the <a href="api/scala/org/apache/spark/mllib/recommendation/ALS.html"><code class="language-plaintext highlighter-rouge">ALS</code> Scala docs</a> for more details on the API.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><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.MatrixFactorizationModel</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="nv">data</span> <span class="k">=</span> <span class="nv">sc</span><span class="o">.</span><span class="py">textFile</span><span class="o">(</span><span class="s">"data/mllib/als/test.data"</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">ratings</span> <span class="k">=</span> <span class="nv">data</span><span class="o">.</span><span class="py">map</span><span class="o">(</span><span class="nv">_</span><span class="o">.</span><span class="py">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="nv">user</span><span class="o">.</span><span class="py">toInt</span><span class="o">,</span> <span class="nv">item</span><span class="o">.</span><span class="py">toInt</span><span class="o">,</span> <span class="nv">rate</span><span class="o">.</span><span class="py">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="nv">rank</span> <span class="k">=</span> <span class="mi">10</span> |
| <span class="k">val</span> <span class="nv">numIterations</span> <span class="k">=</span> <span class="mi">10</span> |
| <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="nv">ALS</span><span class="o">.</span><span class="py">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="nv">usersProducts</span> <span class="k">=</span> <span class="nv">ratings</span><span class="o">.</span><span class="py">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="nv">predictions</span> <span class="k">=</span> |
| <span class="nv">model</span><span class="o">.</span><span class="py">predict</span><span class="o">(</span><span class="n">usersProducts</span><span class="o">).</span><span class="py">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="nv">ratesAndPreds</span> <span class="k">=</span> <span class="nv">ratings</span><span class="o">.</span><span class="py">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="py">join</span><span class="o">(</span><span class="n">predictions</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">MSE</span> <span class="k">=</span> <span class="nv">ratesAndPreds</span><span class="o">.</span><span class="py">map</span> <span class="o">{</span> <span class="nf">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="nv">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="py">mean</span><span class="o">()</span> |
| <span class="nf">println</span><span class="o">(</span><span class="n">s</span><span class="s">"Mean Squared Error = $MSE"</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/myCollaborativeFilter"</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">sameModel</span> <span class="k">=</span> <span class="nv">MatrixFactorizationModel</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/myCollaborativeFilter"</span><span class="o">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/mllib/RecommendationExample.scala" in the Spark repo.</small></div> |
| |
| <p>If the rating matrix is derived from another source of information (i.e. it is inferred from |
| other signals), you can use the <code class="language-plaintext highlighter-rouge">trainImplicit</code> method to get better results.</p> |
| |
| <figure class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="nv">alpha</span> <span class="k">=</span> <span class="mf">0.01</span> |
| <span class="k">val</span> <span class="nv">lambda</span> <span class="k">=</span> <span class="mf">0.01</span> |
| <span class="k">val</span> <span class="nv">model</span> <span class="k">=</span> <span class="nv">ALS</span><span class="o">.</span><span class="py">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">lambda</span><span class="o">,</span> <span class="n">alpha</span><span class="o">)</span></code></pre></figure> |
| |
| </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 class="language-plaintext highlighter-rouge">JavaRDD</code> class. You can convert a Java RDD to a Scala one by |
| calling <code class="language-plaintext highlighter-rouge">.rdd()</code> on your <code class="language-plaintext highlighter-rouge">JavaRDD</code> object. A self-contained application example |
| that is equivalent to the provided example in Scala is given below:</p> |
| |
| <p>Refer to the <a href="api/java/org/apache/spark/mllib/recommendation/ALS.html"><code class="language-plaintext highlighter-rouge">ALS</code> Java docs</a> for more 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.*</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.recommendation.ALS</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.recommendation.MatrixFactorizationModel</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.recommendation.Rating</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.SparkConf</span><span class="o">;</span> |
| |
| <span class="nc">SparkConf</span> <span class="n">conf</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">SparkConf</span><span class="o">().</span><span class="na">setAppName</span><span class="o">(</span><span class="s">"Java Collaborative Filtering Example"</span><span class="o">);</span> |
| <span class="nc">JavaSparkContext</span> <span class="n">jsc</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">JavaSparkContext</span><span class="o">(</span><span class="n">conf</span><span class="o">);</span> |
| |
| <span class="c1">// Load and parse the data</span> |
| <span class="nc">String</span> <span class="n">path</span> <span class="o">=</span> <span class="s">"data/mllib/als/test.data"</span><span class="o">;</span> |
| <span class="nc">JavaRDD</span><span class="o"><</span><span class="nc">String</span><span class="o">></span> <span class="n">data</span> <span class="o">=</span> <span class="n">jsc</span><span class="o">.</span><span class="na">textFile</span><span class="o">(</span><span class="n">path</span><span class="o">);</span> |
| <span class="nc">JavaRDD</span><span class="o"><</span><span class="nc">Rating</span><span class="o">></span> <span class="n">ratings</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="na">map</span><span class="o">(</span><span class="n">s</span> <span class="o">-></span> <span class="o">{</span> |
| <span class="nc">String</span><span class="o">[]</span> <span class="n">sarray</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="na">split</span><span class="o">(</span><span class="s">","</span><span class="o">);</span> |
| <span class="k">return</span> <span class="k">new</span> <span class="nf">Rating</span><span class="o">(</span><span class="nc">Integer</span><span class="o">.</span><span class="na">parseInt</span><span class="o">(</span><span class="n">sarray</span><span class="o">[</span><span class="mi">0</span><span class="o">]),</span> |
| <span class="nc">Integer</span><span class="o">.</span><span class="na">parseInt</span><span class="o">(</span><span class="n">sarray</span><span class="o">[</span><span class="mi">1</span><span class="o">]),</span> |
| <span class="nc">Double</span><span class="o">.</span><span class="na">parseDouble</span><span class="o">(</span><span class="n">sarray</span><span class="o">[</span><span class="mi">2</span><span class="o">]));</span> |
| <span class="o">});</span> |
| |
| <span class="c1">// Build the recommendation model using ALS</span> |
| <span class="kt">int</span> <span class="n">rank</span> <span class="o">=</span> <span class="mi">10</span><span class="o">;</span> |
| <span class="kt">int</span> <span class="n">numIterations</span> <span class="o">=</span> <span class="mi">10</span><span class="o">;</span> |
| <span class="nc">MatrixFactorizationModel</span> <span class="n">model</span> <span class="o">=</span> <span class="no">ALS</span><span class="o">.</span><span class="na">train</span><span class="o">(</span><span class="nc">JavaRDD</span><span class="o">.</span><span class="na">toRDD</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="nc">JavaRDD</span><span class="o"><</span><span class="nc">Tuple2</span><span class="o"><</span><span class="nc">Object</span><span class="o">,</span> <span class="nc">Object</span><span class="o">>></span> <span class="n">userProducts</span> <span class="o">=</span> |
| <span class="n">ratings</span><span class="o">.</span><span class="na">map</span><span class="o">(</span><span class="n">r</span> <span class="o">-></span> <span class="k">new</span> <span class="nc">Tuple2</span><span class="o"><>(</span><span class="n">r</span><span class="o">.</span><span class="na">user</span><span class="o">(),</span> <span class="n">r</span><span class="o">.</span><span class="na">product</span><span class="o">()));</span> |
| <span class="nc">JavaPairRDD</span><span class="o"><</span><span class="nc">Tuple2</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Integer</span><span class="o">>,</span> <span class="nc">Double</span><span class="o">></span> <span class="n">predictions</span> <span class="o">=</span> <span class="nc">JavaPairRDD</span><span class="o">.</span><span class="na">fromJavaRDD</span><span class="o">(</span> |
| <span class="n">model</span><span class="o">.</span><span class="na">predict</span><span class="o">(</span><span class="nc">JavaRDD</span><span class="o">.</span><span class="na">toRDD</span><span class="o">(</span><span class="n">userProducts</span><span class="o">)).</span><span class="na">toJavaRDD</span><span class="o">()</span> |
| <span class="o">.</span><span class="na">map</span><span class="o">(</span><span class="n">r</span> <span class="o">-></span> <span class="k">new</span> <span class="nc">Tuple2</span><span class="o"><>(</span><span class="k">new</span> <span class="nc">Tuple2</span><span class="o"><>(</span><span class="n">r</span><span class="o">.</span><span class="na">user</span><span class="o">(),</span> <span class="n">r</span><span class="o">.</span><span class="na">product</span><span class="o">()),</span> <span class="n">r</span><span class="o">.</span><span class="na">rating</span><span class="o">()))</span> |
| <span class="o">);</span> |
| <span class="nc">JavaRDD</span><span class="o"><</span><span class="nc">Tuple2</span><span class="o"><</span><span class="nc">Double</span><span class="o">,</span> <span class="nc">Double</span><span class="o">>></span> <span class="n">ratesAndPreds</span> <span class="o">=</span> <span class="nc">JavaPairRDD</span><span class="o">.</span><span class="na">fromJavaRDD</span><span class="o">(</span> |
| <span class="n">ratings</span><span class="o">.</span><span class="na">map</span><span class="o">(</span><span class="n">r</span> <span class="o">-></span> <span class="k">new</span> <span class="nc">Tuple2</span><span class="o"><>(</span><span class="k">new</span> <span class="nc">Tuple2</span><span class="o"><>(</span><span class="n">r</span><span class="o">.</span><span class="na">user</span><span class="o">(),</span> <span class="n">r</span><span class="o">.</span><span class="na">product</span><span class="o">()),</span> <span class="n">r</span><span class="o">.</span><span class="na">rating</span><span class="o">())))</span> |
| <span class="o">.</span><span class="na">join</span><span class="o">(</span><span class="n">predictions</span><span class="o">).</span><span class="na">values</span><span class="o">();</span> |
| <span class="kt">double</span> <span class="no">MSE</span> <span class="o">=</span> <span class="n">ratesAndPreds</span><span class="o">.</span><span class="na">mapToDouble</span><span class="o">(</span><span class="n">pair</span> <span class="o">-></span> <span class="o">{</span> |
| <span class="kt">double</span> <span class="n">err</span> <span class="o">=</span> <span class="n">pair</span><span class="o">.</span><span class="na">_1</span><span class="o">()</span> <span class="o">-</span> <span class="n">pair</span><span class="o">.</span><span class="na">_2</span><span class="o">();</span> |
| <span class="k">return</span> <span class="n">err</span> <span class="o">*</span> <span class="n">err</span><span class="o">;</span> |
| <span class="o">}).</span><span class="na">mean</span><span class="o">();</span> |
| <span class="nc">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">"Mean Squared Error = "</span> <span class="o">+</span> <span class="no">MSE</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/myCollaborativeFilter"</span><span class="o">);</span> |
| <span class="nc">MatrixFactorizationModel</span> <span class="n">sameModel</span> <span class="o">=</span> <span class="nc">MatrixFactorizationModel</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/myCollaborativeFilter"</span><span class="o">);</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/mllib/JavaRecommendationExample.java" in the Spark repo.</small></div> |
| </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> |
| |
| <p>Refer to the <a href="api/python/reference/api/pyspark.mllib.recommendation.ALS.html"><code class="language-plaintext highlighter-rouge">ALS</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.recommendation</span> <span class="kn">import</span> <span class="n">ALS</span><span class="p">,</span> <span class="n">MatrixFactorizationModel</span><span class="p">,</span> <span class="n">Rating</span> |
| |
| <span class="c1"># Load and parse the data |
| </span><span class="n">data</span> <span class="o">=</span> <span class="n">sc</span><span class="p">.</span><span class="n">textFile</span><span class="p">(</span><span class="s">"data/mllib/als/test.data"</span><span class="p">)</span> |
| <span class="n">ratings</span> <span class="o">=</span> <span class="n">data</span><span class="p">.</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">l</span><span class="p">:</span> <span class="n">l</span><span class="p">.</span><span class="n">split</span><span class="p">(</span><span class="s">','</span><span class="p">))</span>\ |
| <span class="p">.</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">l</span><span class="p">:</span> <span class="n">Rating</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">l</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">l</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span> <span class="nb">float</span><span class="p">(</span><span class="n">l</span><span class="p">[</span><span class="mi">2</span><span class="p">])))</span> |
| |
| <span class="c1"># 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">10</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">ALS</span><span class="p">.</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="c1"># Evaluate the model on training data |
| </span><span class="n">testdata</span> <span class="o">=</span> <span class="n">ratings</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">p</span><span class="p">[</span><span class="mi">0</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="p">.</span><span class="n">predictAll</span><span class="p">(</span><span class="n">testdata</span><span class="p">).</span><span class="nb">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="p">.</span><span class="nb">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">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="p">.</span><span class="nb">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="n">mean</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> |
| |
| <span class="c1"># Save and load model |
| </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="s">"target/tmp/myCollaborativeFilter"</span><span class="p">)</span> |
| <span class="n">sameModel</span> <span class="o">=</span> <span class="n">MatrixFactorizationModel</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="s">"target/tmp/myCollaborativeFilter"</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/mllib/recommendation_example.py" in the Spark repo.</small></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> |
| |
| <figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="c1"># 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="p">.</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></figure> |
| |
| </div> |
| |
| </div> |
| |
| <p>In order to run the above application, follow the instructions |
| provided in the <a href="quick-start.html#self-contained-applications">Self-Contained Applications</a> |
| section of the Spark |
| Quick Start guide. Be sure to also include <em>spark-mllib</em> to your build file as |
| a dependency.</p> |
| |
| <h2 id="tutorial">Tutorial</h2> |
| |
| <p>The <a href="https://github.com/databricks/spark-training">training exercises</a> from the Spark Summit 2014 include a hands-on tutorial for |
| <a href="https://github.com/databricks/spark-training/blob/master/website/movie-recommendation-with-mllib.md">personalized movie recommendation with <code class="language-plaintext highlighter-rouge">spark.mllib</code></a>.</p> |
| |
| |
| </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="https://cdn.jsdelivr.net/npm/docsearch.js@2/dist/cdn/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:3.3.0"] |
| }, |
| 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> |
