| |
| <!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>MLlib: Main Guide - Spark 2.4.4 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="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 --> |
| |
| <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">2.4.4</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="rdd-programming-guide.html">RDDs, Accumulators, Broadcasts Vars</a></li> |
| <li><a href="sql-programming-guide.html">SQL, DataFrames, and Datasets</a></li> |
| <li><a href="structured-streaming-programming-guide.html">Structured Streaming</a></li> |
| <li><a href="streaming-programming-guide.html">Spark Streaming (DStreams)</a></li> |
| <li><a href="ml-guide.html">MLlib (Machine Learning)</a></li> |
| <li><a href="graphx-programming-guide.html">GraphX (Graph Processing)</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> |
| <li><a href="api/sql/index.html">SQL, Built-in Functions</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><a href="running-on-kubernetes.html">Kubernetes</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 class="divider"></li> |
| <li><a href="building-spark.html">Building Spark</a></li> |
| <li><a href="https://spark.apache.org/contributing.html">Contributing to Spark</a></li> |
| <li><a href="https://spark.apache.org/third-party-projects.html">Third Party Projects</a></li> |
| </ul> |
| </li> |
| </ul> |
| <!--<p class="navbar-text pull-right"><span class="version-text">v2.4.4</span></p>--> |
| </div> |
| </div> |
| </div> |
| |
| <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"> |
| |
| 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> |
| |
| |
| |
| <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" id="content"> |
| |
| <h1 class="title">Machine Learning Library (MLlib) Guide</h1> |
| |
| |
| <p>MLlib is Spark’s machine learning (ML) library. |
| Its goal is to make practical machine learning scalable and easy. |
| At a high level, it provides tools such as:</p> |
| |
| <ul> |
| <li>ML Algorithms: common learning algorithms such as classification, regression, clustering, and collaborative filtering</li> |
| <li>Featurization: feature extraction, transformation, dimensionality reduction, and selection</li> |
| <li>Pipelines: tools for constructing, evaluating, and tuning ML Pipelines</li> |
| <li>Persistence: saving and load algorithms, models, and Pipelines</li> |
| <li>Utilities: linear algebra, statistics, data handling, etc.</li> |
| </ul> |
| |
| <h1 id="announcement-dataframe-based-api-is-primary-api">Announcement: DataFrame-based API is primary API</h1> |
| |
| <p><strong>The MLlib RDD-based API is now in maintenance mode.</strong></p> |
| |
| <p>As of Spark 2.0, the <a href="rdd-programming-guide.html#resilient-distributed-datasets-rdds">RDD</a>-based APIs in the <code>spark.mllib</code> package have entered maintenance mode. |
| The primary Machine Learning API for Spark is now the <a href="sql-programming-guide.html">DataFrame</a>-based API in the <code>spark.ml</code> package.</p> |
| |
| <p><em>What are the implications?</em></p> |
| |
| <ul> |
| <li>MLlib will still support the RDD-based API in <code>spark.mllib</code> with bug fixes.</li> |
| <li>MLlib will not add new features to the RDD-based API.</li> |
| <li>In the Spark 2.x releases, MLlib will add features to the DataFrames-based API to reach feature parity with the RDD-based API.</li> |
| <li>After reaching feature parity (roughly estimated for Spark 2.3), the RDD-based API will be deprecated.</li> |
| <li>The RDD-based API is expected to be removed in Spark 3.0.</li> |
| </ul> |
| |
| <p><em>Why is MLlib switching to the DataFrame-based API?</em></p> |
| |
| <ul> |
| <li>DataFrames provide a more user-friendly API than RDDs. The many benefits of DataFrames include Spark Datasources, SQL/DataFrame queries, Tungsten and Catalyst optimizations, and uniform APIs across languages.</li> |
| <li>The DataFrame-based API for MLlib provides a uniform API across ML algorithms and across multiple languages.</li> |
| <li>DataFrames facilitate practical ML Pipelines, particularly feature transformations. See the <a href="ml-pipeline.html">Pipelines guide</a> for details.</li> |
| </ul> |
| |
| <p><em>What is “Spark ML”?</em></p> |
| |
| <ul> |
| <li>“Spark ML” is not an official name but occasionally used to refer to the MLlib DataFrame-based API. |
| This is majorly due to the <code>org.apache.spark.ml</code> Scala package name used by the DataFrame-based API, |
| and the “Spark ML Pipelines” term we used initially to emphasize the pipeline concept.</li> |
| </ul> |
| |
| <p><em>Is MLlib deprecated?</em></p> |
| |
| <ul> |
| <li>No. MLlib includes both the RDD-based API and the DataFrame-based API. |
| The RDD-based API is now in maintenance mode. |
| But neither API is deprecated, nor MLlib as a whole.</li> |
| </ul> |
| |
| <h1 id="dependencies">Dependencies</h1> |
| |
| <p>MLlib uses the linear algebra package <a href="http://www.scalanlp.org/">Breeze</a>, which depends on |
| <a href="https://github.com/fommil/netlib-java">netlib-java</a> for optimised numerical processing. |
| If native libraries<sup id="fnref:1"><a href="#fn:1" class="footnote">1</a></sup> are not available at runtime, you will see a warning message and a pure JVM |
| implementation will be used instead.</p> |
| |
| <p>Due to licensing issues with runtime proprietary binaries, we do not include <code>netlib-java</code>’s native |
| proxies by default. |
| To configure <code>netlib-java</code> / Breeze to use system optimised binaries, include |
| <code>com.github.fommil.netlib:all:1.1.2</code> (or build Spark with <code>-Pnetlib-lgpl</code>) as a dependency of your |
| project and read the <a href="https://github.com/fommil/netlib-java">netlib-java</a> documentation for your |
| platform’s additional installation instructions.</p> |
| |
| <p>The most popular native BLAS such as <a href="https://software.intel.com/en-us/mkl">Intel MKL</a>, <a href="http://www.openblas.net">OpenBLAS</a>, can use multiple threads in a single operation, which can conflict with Spark’s execution model.</p> |
| |
| <p>Configuring these BLAS implementations to use a single thread for operations may actually improve performance (see <a href="https://issues.apache.org/jira/browse/SPARK-21305">SPARK-21305</a>). It is usually optimal to match this to the number of cores each Spark task is configured to use, which is 1 by default and typically left at 1.</p> |
| |
| <p>Please refer to resources like the following to understand how to configure the number of threads these BLAS implementations use: <a href="https://software.intel.com/en-us/articles/recommended-settings-for-calling-intel-mkl-routines-from-multi-threaded-applications">Intel MKL</a> and <a href="https://github.com/xianyi/OpenBLAS/wiki/faq#multi-threaded">OpenBLAS</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> |
| |
| <h1 id="highlights-in-23">Highlights in 2.3</h1> |
| |
| <p>The list below highlights some of the new features and enhancements added to MLlib in the <code>2.3</code> |
| release of Spark:</p> |
| |
| <ul> |
| <li>Built-in support for reading images into a <code>DataFrame</code> was added |
| (<a href="https://issues.apache.org/jira/browse/SPARK-21866">SPARK-21866</a>).</li> |
| <li><a href="ml-features.html#onehotencoderestimator"><code>OneHotEncoderEstimator</code></a> was added, and should be |
| used instead of the existing <code>OneHotEncoder</code> transformer. The new estimator supports |
| transforming multiple columns.</li> |
| <li>Multiple column support was also added to <code>QuantileDiscretizer</code> and <code>Bucketizer</code> |
| (<a href="https://issues.apache.org/jira/browse/SPARK-22397">SPARK-22397</a> and |
| <a href="https://issues.apache.org/jira/browse/SPARK-20542">SPARK-20542</a>)</li> |
| <li>A new <a href="ml-features.html#featurehasher"><code>FeatureHasher</code></a> transformer was added |
| (<a href="https://issues.apache.org/jira/browse/SPARK-13969">SPARK-13969</a>).</li> |
| <li>Added support for evaluating multiple models in parallel when performing cross-validation using |
| <a href="ml-tuning.html"><code>TrainValidationSplit</code> or <code>CrossValidator</code></a> |
| (<a href="https://issues.apache.org/jira/browse/SPARK-19357">SPARK-19357</a>).</li> |
| <li>Improved support for custom pipeline components in Python (see |
| <a href="https://issues.apache.org/jira/browse/SPARK-21633">SPARK-21633</a> and |
| <a href="https://issues.apache.org/jira/browse/SPARK-21542">SPARK-21542</a>).</li> |
| <li><code>DataFrame</code> functions for descriptive summary statistics over vector columns |
| (<a href="https://issues.apache.org/jira/browse/SPARK-19634">SPARK-19634</a>).</li> |
| <li>Robust linear regression with Huber loss |
| (<a href="https://issues.apache.org/jira/browse/SPARK-3181">SPARK-3181</a>).</li> |
| </ul> |
| |
| <h1 id="migration-guide">Migration guide</h1> |
| |
| <p>MLlib is under active development. |
| The APIs marked <code>Experimental</code>/<code>DeveloperApi</code> may change in future releases, |
| and the migration guide below will explain all changes between releases.</p> |
| |
| <h2 id="from-22-to-23">From 2.2 to 2.3</h2> |
| |
| <h3 id="breaking-changes">Breaking changes</h3> |
| |
| <ul> |
| <li>The class and trait hierarchy for logistic regression model summaries was changed to be cleaner |
| and better accommodate the addition of the multi-class summary. This is a breaking change for user |
| code that casts a <code>LogisticRegressionTrainingSummary</code> to a |
| <code>BinaryLogisticRegressionTrainingSummary</code>. Users should instead use the <code>model.binarySummary</code> |
| method. See <a href="https://issues.apache.org/jira/browse/SPARK-17139">SPARK-17139</a> for more detail |
| (<em>note</em> this is an <code>Experimental</code> API). This <em>does not</em> affect the Python <code>summary</code> method, which |
| will still work correctly for both multinomial and binary cases.</li> |
| </ul> |
| |
| <h3 id="deprecations-and-changes-of-behavior">Deprecations and changes of behavior</h3> |
| |
| <p><strong>Deprecations</strong></p> |
| |
| <ul> |
| <li><code>OneHotEncoder</code> has been deprecated and will be removed in <code>3.0</code>. It has been replaced by the |
| new <a href="ml-features.html#onehotencoderestimator"><code>OneHotEncoderEstimator</code></a> |
| (see <a href="https://issues.apache.org/jira/browse/SPARK-13030">SPARK-13030</a>). <strong>Note</strong> that |
| <code>OneHotEncoderEstimator</code> will be renamed to <code>OneHotEncoder</code> in <code>3.0</code> (but |
| <code>OneHotEncoderEstimator</code> will be kept as an alias).</li> |
| </ul> |
| |
| <p><strong>Changes of behavior</strong></p> |
| |
| <ul> |
| <li><a href="https://issues.apache.org/jira/browse/SPARK-21027">SPARK-21027</a>: |
| The default parallelism used in <code>OneVsRest</code> is now set to 1 (i.e. serial). In <code>2.2</code> and |
| earlier versions, the level of parallelism was set to the default threadpool size in Scala.</li> |
| <li><a href="https://issues.apache.org/jira/browse/SPARK-22156">SPARK-22156</a>: |
| The learning rate update for <code>Word2Vec</code> was incorrect when <code>numIterations</code> was set greater than |
| <code>1</code>. This will cause training results to be different between <code>2.3</code> and earlier versions.</li> |
| <li><a href="https://issues.apache.org/jira/browse/SPARK-21681">SPARK-21681</a>: |
| Fixed an edge case bug in multinomial logistic regression that resulted in incorrect coefficients |
| when some features had zero variance.</li> |
| <li><a href="https://issues.apache.org/jira/browse/SPARK-16957">SPARK-16957</a>: |
| Tree algorithms now use mid-points for split values. This may change results from model training.</li> |
| <li><a href="https://issues.apache.org/jira/browse/SPARK-14657">SPARK-14657</a>: |
| Fixed an issue where the features generated by <code>RFormula</code> without an intercept were inconsistent |
| with the output in R. This may change results from model training in this scenario.</li> |
| </ul> |
| |
| <h2 id="previous-spark-versions">Previous Spark versions</h2> |
| |
| <p>Earlier migration guides are archived <a href="ml-migration-guides.html">on this page</a>.</p> |
| |
| <hr /> |
| <div class="footnotes"> |
| <ol> |
| <li id="fn:1"> |
| <p>To learn more about the benefits and background of system optimised natives, you may wish to |
| watch Sam Halliday’s ScalaX talk on <a href="http://fommil.github.io/scalax14/#/">High Performance Linear Algebra in Scala</a>. <a href="#fnref:1" class="reversefootnote">↩</a></p> |
| </li> |
| </ol> |
| </div> |
| |
| |
| </div> |
| |
| <!-- /container --> |
| </div> |
| |
| <script src="js/vendor/jquery-1.12.4.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://') + |
| '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> |
