Google Git
Sign in
apache / spark-website / 28656f2c00baf1bc2d26570a16b4f96f9a890723 / . / site / docs / 3.0.0-preview2 / ml-datasource.html
blob: 8020828530efacf54555c32a5eb2876e17279872 [file] [log] [blame]
<!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>Data sources - Spark 3.0.0-preview2 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">3.0.0-preview2</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><a href="migration-guide.html">Migration Guide</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">v3.0.0-preview2</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.html">
<b>Data sources</b>
</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">Data sources</h1>
<p>In this section, we introduce how to use data source in ML to load data.
Besides some general data sources such as Parquet, CSV, JSON and JDBC, we also provide some specific data sources for ML.</p>
<p><strong>Table of Contents</strong></p>
<ul id="markdown-toc">
<li><a href="#image-data-source" id="markdown-toc-image-data-source">Image data source</a></li>
<li><a href="#libsvm-data-source" id="markdown-toc-libsvm-data-source">LIBSVM data source</a></li>
</ul>
<h2 id="image-data-source">Image data source</h2>
<p>This image data source is used to load image files from a directory, it can load compressed image (jpeg, png, etc.) into raw image representation via <code class="highlighter-rouge">ImageIO</code> in Java library.
The loaded DataFrame has one <code class="highlighter-rouge">StructType</code> column: &#8220;image&#8221;, containing image data stored as image schema.
The schema of the <code class="highlighter-rouge">image</code> column is:</p>
<ul>
<li>origin: <code class="highlighter-rouge">StringType</code> (represents the file path of the image)</li>
<li>height: <code class="highlighter-rouge">IntegerType</code> (height of the image)</li>
<li>width: <code class="highlighter-rouge">IntegerType</code> (width of the image)</li>
<li>nChannels: <code class="highlighter-rouge">IntegerType</code> (number of image channels)</li>
<li>mode: <code class="highlighter-rouge">IntegerType</code> (OpenCV-compatible type)</li>
<li>data: <code class="highlighter-rouge">BinaryType</code> (Image bytes in OpenCV-compatible order: row-wise BGR in most cases)</li>
</ul>
<div class="codetabs">
<div data-lang="scala">
<p><a href="api/scala/index.html#org.apache.spark.ml.source.image.ImageDataSource"><code class="highlighter-rouge">ImageDataSource</code></a>
implements a Spark SQL data source API for loading image data as a DataFrame.</p>
<figure class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="n">scala</span><span class="o">&gt;</span> <span class="k">val</span> <span class="nv">df</span> <span class="k">=</span> <span class="nv">spark</span><span class="o">.</span><span class="py">read</span><span class="o">.</span><span class="py">format</span><span class="o">(</span><span class="s">"image"</span><span class="o">).</span><span class="py">option</span><span class="o">(</span><span class="s">"dropInvalid"</span><span class="o">,</span> <span class="kc">true</span><span class="o">).</span><span class="py">load</span><span class="o">(</span><span class="s">"data/mllib/images/origin/kittens"</span><span class="o">)</span>
<span class="n">df</span><span class="k">:</span> <span class="kt">org.apache.spark.sql.DataFrame</span> <span class="o">=</span> <span class="o">[</span><span class="kt">image:</span> <span class="kt">struct&lt;origin:</span> <span class="kt">string</span>, <span class="kt">height:</span> <span class="kt">int</span> <span class="kt">...</span> <span class="err">4</span> <span class="kt">more</span> <span class="kt">fields&gt;</span><span class="o">]</span>
<span class="n">scala</span><span class="o">&gt;</span> <span class="nv">df</span><span class="o">.</span><span class="py">select</span><span class="o">(</span><span class="s">"image.origin"</span><span class="o">,</span> <span class="s">"image.width"</span><span class="o">,</span> <span class="s">"image.height"</span><span class="o">).</span><span class="py">show</span><span class="o">(</span><span class="n">truncate</span><span class="k">=</span><span class="kc">false</span><span class="o">)</span>
<span class="o">+-----------------------------------------------------------------------+-----+------+</span>
<span class="o">|</span><span class="n">origin</span> <span class="o">|</span><span class="n">width</span><span class="o">|</span><span class="n">height</span><span class="o">|</span>
<span class="o">+-----------------------------------------------------------------------+-----+------+</span>
<span class="o">|</span><span class="n">file</span><span class="o">:///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="mf">54893.</span><span class="n">jpg</span> <span class="o">|</span><span class="mi">300</span> <span class="o">|</span><span class="mi">311</span> <span class="o">|</span>
<span class="o">|</span><span class="n">file</span><span class="o">:///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="nv">DP802813</span><span class="o">.</span><span class="py">jpg</span> <span class="o">|</span><span class="mi">199</span> <span class="o">|</span><span class="mi">313</span> <span class="o">|</span>
<span class="o">|</span><span class="n">file</span><span class="o">:///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="mf">29.5</span><span class="o">.</span><span class="py">a_b_EGDP022204</span><span class="o">.</span><span class="py">jpg</span> <span class="o">|</span><span class="mi">300</span> <span class="o">|</span><span class="mi">200</span> <span class="o">|</span>
<span class="o">|</span><span class="n">file</span><span class="o">:///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="nv">DP153539</span><span class="o">.</span><span class="py">jpg</span> <span class="o">|</span><span class="mi">300</span> <span class="o">|</span><span class="mi">296</span> <span class="o">|</span>
<span class="o">+-----------------------------------------------------------------------+-----+------+</span></code></pre></figure>
</div>
<div data-lang="java">
<p><a href="api/java/org/apache/spark/ml/source/image/ImageDataSource.html"><code class="highlighter-rouge">ImageDataSource</code></a>
implements Spark SQL data source API for loading image data as a DataFrame.</p>
<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="nc">Dataset</span><span class="o">&lt;</span><span class="nc">Row</span><span class="o">&gt;</span> <span class="n">imagesDF</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">read</span><span class="o">().</span><span class="na">format</span><span class="o">(</span><span class="s">"image"</span><span class="o">).</span><span class="na">option</span><span class="o">(</span><span class="s">"dropInvalid"</span><span class="o">,</span> <span class="kc">true</span><span class="o">).</span><span class="na">load</span><span class="o">(</span><span class="s">"data/mllib/images/origin/kittens"</span><span class="o">);</span>
<span class="n">imageDF</span><span class="o">.</span><span class="na">select</span><span class="o">(</span><span class="s">"image.origin"</span><span class="o">,</span> <span class="s">"image.width"</span><span class="o">,</span> <span class="s">"image.height"</span><span class="o">).</span><span class="na">show</span><span class="o">(</span><span class="kc">false</span><span class="o">);</span>
<span class="cm">/*
Will output:
+-----------------------------------------------------------------------+-----+------+
|origin |width|height|
+-----------------------------------------------------------------------+-----+------+
|file:///spark/data/mllib/images/origin/kittens/54893.jpg |300 |311 |
|file:///spark/data/mllib/images/origin/kittens/DP802813.jpg |199 |313 |
|file:///spark/data/mllib/images/origin/kittens/29.5.a_b_EGDP022204.jpg |300 |200 |
|file:///spark/data/mllib/images/origin/kittens/DP153539.jpg |300 |296 |
+-----------------------------------------------------------------------+-----+------+
*/</span></code></pre></figure>
</div>
<div data-lang="python">
<p>In PySpark we provide Spark SQL data source API for loading image data as a DataFrame.</p>
<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="o">&gt;&gt;&gt;</span> <span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">read</span><span class="o">.</span><span class="nb">format</span><span class="p">(</span><span class="s">"image"</span><span class="p">)</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="s">"dropInvalid"</span><span class="p">,</span> <span class="n">true</span><span class="p">)</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="s">"data/mllib/images/origin/kittens"</span><span class="p">)</span>
<span class="o">&gt;&gt;&gt;</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s">"image.origin"</span><span class="p">,</span> <span class="s">"image.width"</span><span class="p">,</span> <span class="s">"image.height"</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">(</span><span class="n">truncate</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
<span class="o">+-----------------------------------------------------------------------+-----+------+</span>
<span class="o">|</span><span class="n">origin</span> <span class="o">|</span><span class="n">width</span><span class="o">|</span><span class="n">height</span><span class="o">|</span>
<span class="o">+-----------------------------------------------------------------------+-----+------+</span>
<span class="o">|</span><span class="nb">file</span><span class="p">:</span><span class="o">///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="mf">54893.j</span><span class="n">pg</span> <span class="o">|</span><span class="mi">300</span> <span class="o">|</span><span class="mi">311</span> <span class="o">|</span>
<span class="o">|</span><span class="nb">file</span><span class="p">:</span><span class="o">///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="n">DP802813</span><span class="o">.</span><span class="n">jpg</span> <span class="o">|</span><span class="mi">199</span> <span class="o">|</span><span class="mi">313</span> <span class="o">|</span>
<span class="o">|</span><span class="nb">file</span><span class="p">:</span><span class="o">///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="mf">29.5</span><span class="o">.</span><span class="n">a_b_EGDP022204</span><span class="o">.</span><span class="n">jpg</span> <span class="o">|</span><span class="mi">300</span> <span class="o">|</span><span class="mi">200</span> <span class="o">|</span>
<span class="o">|</span><span class="nb">file</span><span class="p">:</span><span class="o">///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="n">DP153539</span><span class="o">.</span><span class="n">jpg</span> <span class="o">|</span><span class="mi">300</span> <span class="o">|</span><span class="mi">296</span> <span class="o">|</span>
<span class="o">+-----------------------------------------------------------------------+-----+------+</span></code></pre></figure>
</div>
<div data-lang="r">
<p>In SparkR we provide Spark SQL data source API for loading image data as a DataFrame.</p>
<figure class="highlight"><pre><code class="language-r" data-lang="r"><span class="o">&gt;</span><span class="w"> </span><span class="n">df</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">read.df</span><span class="p">(</span><span class="s2">"data/mllib/images/origin/kittens"</span><span class="p">,</span><span class="w"> </span><span class="s2">"image"</span><span class="p">)</span><span class="w">
</span><span class="o">&gt;</span><span class="w"> </span><span class="n">head</span><span class="p">(</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="p">,</span><span class="w"> </span><span class="n">df</span><span class="o">$</span><span class="n">image.origin</span><span class="p">,</span><span class="w"> </span><span class="n">df</span><span class="o">$</span><span class="n">image.width</span><span class="p">,</span><span class="w"> </span><span class="n">df</span><span class="o">$</span><span class="n">image.height</span><span class="p">))</span><span class="w">
</span><span class="m">1</span><span class="w"> </span><span class="n">file</span><span class="o">:///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="m">54893</span><span class="n">.jpg</span><span class="w">
</span><span class="m">2</span><span class="w"> </span><span class="n">file</span><span class="o">:///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="n">DP802813.jpg</span><span class="w">
</span><span class="m">3</span><span class="w"> </span><span class="n">file</span><span class="o">:///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="m">29.5</span><span class="n">.a_b_EGDP022204.jpg</span><span class="w">
</span><span class="m">4</span><span class="w"> </span><span class="n">file</span><span class="o">:///</span><span class="n">spark</span><span class="o">/</span><span class="n">data</span><span class="o">/</span><span class="n">mllib</span><span class="o">/</span><span class="n">images</span><span class="o">/</span><span class="n">origin</span><span class="o">/</span><span class="n">kittens</span><span class="o">/</span><span class="n">DP153539.jpg</span><span class="w">
</span><span class="n">width</span><span class="w"> </span><span class="n">height</span><span class="w">
</span><span class="m">1</span><span class="w"> </span><span class="m">300</span><span class="w"> </span><span class="m">311</span><span class="w">
</span><span class="m">2</span><span class="w"> </span><span class="m">199</span><span class="w"> </span><span class="m">313</span><span class="w">
</span><span class="m">3</span><span class="w"> </span><span class="m">300</span><span class="w"> </span><span class="m">200</span><span class="w">
</span><span class="m">4</span><span class="w"> </span><span class="m">300</span><span class="w"> </span><span class="m">296</span></code></pre></figure>
</div>
</div>
<h2 id="libsvm-data-source">LIBSVM data source</h2>
<p>This <code class="highlighter-rouge">LIBSVM</code> data source is used to load &#8216;libsvm&#8217; type files from a directory.
The loaded DataFrame has two columns: label containing labels stored as doubles and features containing feature vectors stored as Vectors.
The schemas of the columns are:</p>
<ul>
<li>label: <code class="highlighter-rouge">DoubleType</code> (represents the instance label)</li>
<li>features: <code class="highlighter-rouge">VectorUDT</code> (represents the feature vector)</li>
</ul>
<div class="codetabs">
<div data-lang="scala">
<p><a href="api/scala/index.html#org.apache.spark.ml.source.libsvm.LibSVMDataSource"><code class="highlighter-rouge">LibSVMDataSource</code></a>
implements a Spark SQL data source API for loading <code class="highlighter-rouge">LIBSVM</code> data as a DataFrame.</p>
<figure class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="n">scala</span><span class="o">&gt;</span> <span class="k">val</span> <span class="nv">df</span> <span class="k">=</span> <span class="nv">spark</span><span class="o">.</span><span class="py">read</span><span class="o">.</span><span class="py">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">).</span><span class="py">option</span><span class="o">(</span><span class="s">"numFeatures"</span><span class="o">,</span> <span class="s">"780"</span><span class="o">).</span><span class="py">load</span><span class="o">(</span><span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">)</span>
<span class="n">df</span><span class="k">:</span> <span class="kt">org.apache.spark.sql.DataFrame</span> <span class="o">=</span> <span class="o">[</span><span class="kt">label:</span> <span class="kt">double</span>, <span class="kt">features:</span> <span class="kt">vector</span><span class="o">]</span>
<span class="n">scala</span><span class="o">&gt;</span> <span class="nv">df</span><span class="o">.</span><span class="py">show</span><span class="o">(</span><span class="mi">10</span><span class="o">)</span>
<span class="o">+-----+--------------------+</span>
<span class="o">|</span><span class="n">label</span><span class="o">|</span> <span class="n">features</span><span class="o">|</span>
<span class="o">+-----+--------------------+</span>
<span class="o">|</span> <span class="mf">0.0</span><span class="o">|(</span><span class="mi">780</span><span class="o">,[</span><span class="err">127</span>,<span class="err">128</span>,<span class="err">129</span><span class="kt">...|</span>
<span class="kt">|</span> <span class="err">1</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">158</span>,<span class="err">159</span>,<span class="err">160</span><span class="kt">...|</span>
<span class="kt">|</span> <span class="err">1</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">124</span>,<span class="err">125</span>,<span class="err">126</span><span class="kt">...|</span>
<span class="kt">|</span> <span class="err">1</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">152</span>,<span class="err">153</span>,<span class="err">154</span><span class="kt">...|</span>
<span class="kt">|</span> <span class="err">1</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">151</span>,<span class="err">152</span>,<span class="err">153</span><span class="kt">...|</span>
<span class="kt">|</span> <span class="err">0</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">129</span>,<span class="err">130</span>,<span class="err">131</span><span class="kt">...|</span>
<span class="kt">|</span> <span class="err">1</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">158</span>,<span class="err">159</span>,<span class="err">160</span><span class="kt">...|</span>
<span class="kt">|</span> <span class="err">1</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">99</span>,<span class="err">100</span>,<span class="err">101</span>,<span class="kt">...|</span>
<span class="kt">|</span> <span class="err">0</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">154</span>,<span class="err">155</span>,<span class="err">156</span><span class="kt">...|</span>
<span class="kt">|</span> <span class="err">0</span><span class="kt">.</span><span class="err">0</span><span class="kt">|</span><span class="o">(</span><span class="err">780</span>,<span class="o">[</span><span class="err">127</span>,<span class="err">128</span>,<span class="err">129</span><span class="kt">...|</span>
<span class="kt">+-----+--------------------+</span>
<span class="kt">only</span> <span class="kt">showing</span> <span class="kt">top</span> <span class="err">10</span> <span class="kt">rows</span></code></pre></figure>
</div>
<div data-lang="java">
<p><a href="api/java/org/apache/spark/ml/source/libsvm/LibSVMDataSource.html"><code class="highlighter-rouge">LibSVMDataSource</code></a>
implements Spark SQL data source API for loading <code class="highlighter-rouge">LIBSVM</code> data as a DataFrame.</p>
<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="nc">Dataset</span><span class="o">&lt;</span><span class="nc">Row</span><span class="o">&gt;</span> <span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="na">read</span><span class="o">.</span><span class="na">format</span><span class="o">(</span><span class="s">"libsvm"</span><span class="o">).</span><span class="na">option</span><span class="o">(</span><span class="s">"numFeatures"</span><span class="o">,</span> <span class="s">"780"</span><span class="o">).</span><span class="na">load</span><span class="o">(</span><span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="o">);</span>
<span class="n">df</span><span class="o">.</span><span class="na">show</span><span class="o">(</span><span class="mi">10</span><span class="o">);</span>
<span class="cm">/*
Will output:
+-----+--------------------+
|label| features|
+-----+--------------------+
| 0.0|(780,[127,128,129...|
| 1.0|(780,[158,159,160...|
| 1.0|(780,[124,125,126...|
| 1.0|(780,[152,153,154...|
| 1.0|(780,[151,152,153...|
| 0.0|(780,[129,130,131...|
| 1.0|(780,[158,159,160...|
| 1.0|(780,[99,100,101,...|
| 0.0|(780,[154,155,156...|
| 0.0|(780,[127,128,129...|
+-----+--------------------+
only showing top 10 rows
*/</span></code></pre></figure>
</div>
<div data-lang="python">
<p>In PySpark we provide Spark SQL data source API for loading <code class="highlighter-rouge">LIBSVM</code> data as a DataFrame.</p>
<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="o">&gt;&gt;&gt;</span> <span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">read</span><span class="o">.</span><span class="nb">format</span><span class="p">(</span><span class="s">"libsvm"</span><span class="p">)</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="s">"numFeatures"</span><span class="p">,</span> <span class="s">"780"</span><span class="p">)</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="s">"data/mllib/sample_libsvm_data.txt"</span><span class="p">)</span>
<span class="o">&gt;&gt;&gt;</span> <span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span>
<span class="o">+-----+--------------------+</span>
<span class="o">|</span><span class="n">label</span><span class="o">|</span> <span class="n">features</span><span class="o">|</span>
<span class="o">+-----+--------------------+</span>
<span class="o">|</span> <span class="mf">0.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">127</span><span class="p">,</span><span class="mi">128</span><span class="p">,</span><span class="mf">129.</span><span class="o">..|</span>
<span class="o">|</span> <span class="mf">1.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">158</span><span class="p">,</span><span class="mi">159</span><span class="p">,</span><span class="mf">160.</span><span class="o">..|</span>
<span class="o">|</span> <span class="mf">1.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">124</span><span class="p">,</span><span class="mi">125</span><span class="p">,</span><span class="mf">126.</span><span class="o">..|</span>
<span class="o">|</span> <span class="mf">1.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">152</span><span class="p">,</span><span class="mi">153</span><span class="p">,</span><span class="mf">154.</span><span class="o">..|</span>
<span class="o">|</span> <span class="mf">1.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">151</span><span class="p">,</span><span class="mi">152</span><span class="p">,</span><span class="mf">153.</span><span class="o">..|</span>
<span class="o">|</span> <span class="mf">0.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">129</span><span class="p">,</span><span class="mi">130</span><span class="p">,</span><span class="mf">131.</span><span class="o">..|</span>
<span class="o">|</span> <span class="mf">1.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">158</span><span class="p">,</span><span class="mi">159</span><span class="p">,</span><span class="mf">160.</span><span class="o">..|</span>
<span class="o">|</span> <span class="mf">1.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">99</span><span class="p">,</span><span class="mi">100</span><span class="p">,</span><span class="mi">101</span><span class="p">,</span><span class="o">...|</span>
<span class="o">|</span> <span class="mf">0.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">154</span><span class="p">,</span><span class="mi">155</span><span class="p">,</span><span class="mf">156.</span><span class="o">..|</span>
<span class="o">|</span> <span class="mf">0.0</span><span class="o">|</span><span class="p">(</span><span class="mi">780</span><span class="p">,[</span><span class="mi">127</span><span class="p">,</span><span class="mi">128</span><span class="p">,</span><span class="mf">129.</span><span class="o">..|</span>
<span class="o">+-----+--------------------+</span>
<span class="n">only</span> <span class="n">showing</span> <span class="n">top</span> <span class="mi">10</span> <span class="n">rows</span></code></pre></figure>
</div>
<div data-lang="r">
<p>In SparkR we provide Spark SQL data source API for loading <code class="highlighter-rouge">LIBSVM</code> data as a DataFrame.</p>
<figure class="highlight"><pre><code class="language-r" data-lang="r"><span class="o">&gt;</span><span class="w"> </span><span class="n">df</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">read.df</span><span class="p">(</span><span class="s2">"data/mllib/sample_libsvm_data.txt"</span><span class="p">,</span><span class="w"> </span><span class="s2">"libsvm"</span><span class="p">)</span><span class="w">
</span><span class="o">&gt;</span><span class="w"> </span><span class="n">head</span><span class="p">(</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="p">,</span><span class="w"> </span><span class="n">df</span><span class="o">$</span><span class="n">label</span><span class="p">,</span><span class="w"> </span><span class="n">df</span><span class="o">$</span><span class="n">features</span><span class="p">),</span><span class="w"> </span><span class="m">10</span><span class="p">)</span><span class="w">
</span><span class="n">label</span><span class="w"> </span><span class="n">features</span><span class="w">
</span><span class="m">1</span><span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d35366e8</span><span class="o">&gt;</span><span class="w">
</span><span class="m">2</span><span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d353bf78</span><span class="o">&gt;</span><span class="w">
</span><span class="m">3</span><span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d3541840</span><span class="o">&gt;</span><span class="w">
</span><span class="m">4</span><span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d3545108</span><span class="o">&gt;</span><span class="w">
</span><span class="m">5</span><span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d354c8e0</span><span class="o">&gt;</span><span class="w">
</span><span class="m">6</span><span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d35501a8</span><span class="o">&gt;</span><span class="w">
</span><span class="m">7</span><span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d3555a70</span><span class="o">&gt;</span><span class="w">
</span><span class="m">8</span><span class="w"> </span><span class="m">1</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d3559338</span><span class="o">&gt;</span><span class="w">
</span><span class="m">9</span><span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d355cc00</span><span class="o">&gt;</span><span class="w">
</span><span class="m">10</span><span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="o">&lt;</span><span class="n">environment</span><span class="o">:</span><span class="w"> </span><span class="mh">0x7fe6d35643d8</span><span class="o">&gt;</span></code></pre></figure>
</div>
</div>
</div>
<!-- /container -->
</div>
<script src="js/vendor/jquery-3.4.1.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>