Spark 1.4.1 docs

author: Patrick Wendell <pwendell@apache.org> 2015-07-15 04:17:01 +0000
committer: Patrick Wendell <pwendell@apache.org> 2015-07-15 04:17:01 +0000
commit: 8c2ee8d4aa3eb7fdc66536019d86793e1db2b135 (patch)
tree: 07beeb27472248193736185dfa7567fc078426fa /site/docs/1.4.1/ml-ensembles.html
parent: 7378439da1198903bbb855218de3d050c611a057 (diff)
download: spark-website-8c2ee8d4aa3eb7fdc66536019d86793e1db2b135.tar.gz
spark-website-8c2ee8d4aa3eb7fdc66536019d86793e1db2b135.tar.bz2
spark-website-8c2ee8d4aa3eb7fdc66536019d86793e1db2b135.zip
1 files changed, 292 insertions, 0 deletions
diff --git a/site/docs/1.4.1/ml-ensembles.html b/site/docs/1.4.1/ml-ensembles.html
new file mode 100644
index 000000000..14b82e395
--- /dev/null
+++ b/site/docs/1.4.1/ml-ensembles.html
@@ -0,0 +1,292 @@
+<!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>Ensembles - Spark 1.4.1 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="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
+        <![endif]-->
+
+        <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
+
+        <div class="navbar navbar-fixed-top" id="topbar">
+            <div class="navbar-inner">
+                <div class="container">
+                    <div class="brand"><a href="index.html">
+                      <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">1.4.1</span>
+                    </div>
+                    <ul class="nav">
+                        <!--TODO(andyk): Add class="active" attribute to li some how.-->
+                        <li><a href="index.html">Overview</a></li>
+
+                        <li class="dropdown">
+                            <a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="quick-start.html">Quick Start</a></li>
+                                <li><a href="programming-guide.html">Spark Programming Guide</a></li>
+                                <li class="divider"></li>
+                                <li><a href="streaming-programming-guide.html">Spark Streaming</a></li>
+                                <li><a href="sql-programming-guide.html">DataFrames and SQL</a></li>
+                                <li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li>
+                                <li><a href="graphx-programming-guide.html">GraphX (Graph Processing)</a></li>
+                                <li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li>
+                                <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>
+                            </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 class="divider"></li>
+                                <li><a href="ec2-scripts.html">Amazon EC2</a></li>
+                            </ul>
+                        </li>
+
+                        <li class="dropdown">
+                            <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="configuration.html">Configuration</a></li>
+                                <li><a href="monitoring.html">Monitoring</a></li>
+                                <li><a href="tuning.html">Tuning Guide</a></li>
+                                <li><a href="job-scheduling.html">Job Scheduling</a></li>
+                                <li><a href="security.html">Security</a></li>
+                                <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
+                                <li><a href="hadoop-third-party-distributions.html">3<sup>rd</sup>-Party Hadoop Distros</a></li>
+                                <li class="divider"></li>
+                                <li><a href="building-spark.html">Building Spark</a></li>
+                                <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li>
+                                <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Supplemental+Spark+Projects">Supplemental Projects</a></li>
+                            </ul>
+                        </li>
+                    </ul>
+                    <!--<p class="navbar-text pull-right"><span class="version-text">v1.4.1</span></p>-->
+                </div>
+            </div>
+        </div>
+
+        <div class="container" id="content">
+          
+            <h1 class="title"><a href="ml-guide.html">ML</a> - Ensembles</h1>
+          
+
+          <p><strong>Table of Contents</strong></p>
+
+<ul id="markdown-toc">
+  <li><a href="#onevsrest" id="markdown-toc-onevsrest">OneVsRest</a>    <ul>
+      <li><a href="#example" id="markdown-toc-example">Example</a></li>
+    </ul>
+  </li>
+</ul>
+
+<p>An <a href="http://en.wikipedia.org/wiki/Ensemble_learning">ensemble method</a>
+is a learning algorithm which creates a model composed of a set of other base models.
+The Pipelines API supports the following ensemble algorithms: <a href="api/scala/index.html#org.apache.spark.ml.classifier.OneVsRest"><code>OneVsRest</code></a></p>
+
+<h2 id="onevsrest">OneVsRest</h2>
+
+<p><a href="http://en.wikipedia.org/wiki/Multiclass_classification#One-vs.-rest">OneVsRest</a> is an example of a machine learning reduction for performing multiclass classification given a base classifier that can perform binary classification efficiently.</p>
+
+<p><code>OneVsRest</code> is implemented as an <code>Estimator</code>. For the base classifier it takes instances of <code>Classifier</code> and creates a binary classification problem for each of the k classes. The classifier for class i is trained to predict whether the label is i or not, distinguishing class i from all other classes.</p>
+
+<p>Predictions are done by evaluating each binary classifier and the index of the most confident classifier is output as label.</p>
+
+<h3 id="example">Example</h3>
+
+<p>The example below demonstrates how to load the
+<a href="http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/iris.scale">Iris dataset</a>, parse it as a DataFrame and perform multiclass classification using <code>OneVsRest</code>. The test error is calculated to measure the algorithm accuracy.</p>
+
+<div class="codetabs">
+<div data-lang="scala">
+
+    <div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">import</span> <span class="nn">org.apache.spark.ml.classification.</span><span class="o">{</span><span class="nc">LogisticRegression</span><span class="o">,</span> <span class="nc">OneVsRest</span><span class="o">}</span>
+<span class="k">import</span> <span class="nn">org.apache.spark.mllib.evaluation.MulticlassMetrics</span>
+<span class="k">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span>
+<span class="k">import</span> <span class="nn">org.apache.spark.sql.</span><span class="o">{</span><span class="nc">Row</span><span class="o">,</span> <span class="nc">SQLContext</span><span class="o">}</span>
+
+<span class="k">val</span> <span class="n">sqlContext</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">SQLContext</span><span class="o">(</span><span class="n">sc</span><span class="o">)</span>
+
+<span class="c1">// parse data into dataframe</span>
+<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="nc">MLUtils</span><span class="o">.</span><span class="n">loadLibSVMFile</span><span class="o">(</span><span class="n">sc</span><span class="o">,</span> 
+  <span class="s">&quot;data/mllib/sample_multiclass_classification_data.txt&quot;</span><span class="o">)</span>
+<span class="k">val</span> <span class="nc">Array</span><span class="o">(</span><span class="n">train</span><span class="o">,</span> <span class="n">test</span><span class="o">)</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">toDF</span><span class="o">().</span><span class="n">randomSplit</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span><span class="mf">0.7</span><span class="o">,</span> <span class="mf">0.3</span><span class="o">))</span>
+
+<span class="c1">// instantiate multiclass learner and train</span>
+<span class="k">val</span> <span class="n">ovr</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">OneVsRest</span><span class="o">().</span><span class="n">setClassifier</span><span class="o">(</span><span class="k">new</span> <span class="nc">LogisticRegression</span><span class="o">)</span>
+
+<span class="k">val</span> <span class="n">ovrModel</span> <span class="k">=</span> <span class="n">ovr</span><span class="o">.</span><span class="n">fit</span><span class="o">(</span><span class="n">train</span><span class="o">)</span>
+
+<span class="c1">// score model on test data</span>
+<span class="k">val</span> <span class="n">predictions</span> <span class="k">=</span> <span class="n">ovrModel</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">test</span><span class="o">).</span><span class="n">select</span><span class="o">(</span><span class="s">&quot;prediction&quot;</span><span class="o">,</span> <span class="s">&quot;label&quot;</span><span class="o">)</span>
+<span class="k">val</span> <span class="n">predictionsAndLabels</span> <span class="k">=</span> <span class="n">predictions</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span><span class="k">case</span> <span class="nc">Row</span><span class="o">(</span><span class="n">p</span><span class="k">:</span> <span class="kt">Double</span><span class="o">,</span> <span class="n">l</span><span class="k">:</span> <span class="kt">Double</span><span class="o">)</span> <span class="k">=&gt;</span> <span class="o">(</span><span class="n">p</span><span class="o">,</span> <span class="n">l</span><span class="o">)}</span>
+
+<span class="c1">// compute confusion matrix</span>
+<span class="k">val</span> <span class="n">metrics</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">MulticlassMetrics</span><span class="o">(</span><span class="n">predictionsAndLabels</span><span class="o">)</span>
+<span class="n">println</span><span class="o">(</span><span class="n">metrics</span><span class="o">.</span><span class="n">confusionMatrix</span><span class="o">)</span>
+
+<span class="c1">// the Iris DataSet has three classes</span>
+<span class="k">val</span> <span class="n">numClasses</span> <span class="k">=</span> <span class="mi">3</span>
+
+<span class="n">println</span><span class="o">(</span><span class="s">&quot;label\tfpr\n&quot;</span><span class="o">)</span>
+<span class="o">(</span><span class="mi">0</span> <span class="n">until</span> <span class="n">numClasses</span><span class="o">).</span><span class="n">foreach</span> <span class="o">{</span> <span class="n">index</span> <span class="k">=&gt;</span>
+  <span class="k">val</span> <span class="n">label</span> <span class="k">=</span> <span class="n">index</span><span class="o">.</span><span class="n">toDouble</span>
+  <span class="n">println</span><span class="o">(</span><span class="n">label</span> <span class="o">+</span> <span class="s">&quot;\t&quot;</span> <span class="o">+</span> <span class="n">metrics</span><span class="o">.</span><span class="n">falsePositiveRate</span><span class="o">(</span><span class="n">label</span><span class="o">))</span>
+<span class="o">}</span></code></pre></div>
+
+  </div>
+<div data-lang="java">
+
+    <div class="highlight"><pre><code class="language-java" data-lang="java"><span class="kn">import</span> <span class="nn">org.apache.spark.SparkConf</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaSparkContext</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.ml.classification.LogisticRegression</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.ml.classification.OneVsRest</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.ml.classification.OneVsRestModel</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.evaluation.MulticlassMetrics</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Matrix</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.mllib.util.MLUtils</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.rdd.RDD</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.sql.DataFrame</span><span class="o">;</span>
+<span class="kn">import</span> <span class="nn">org.apache.spark.sql.SQLContext</span><span class="o">;</span>
+
+<span class="n">SparkConf</span> <span class="n">conf</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">SparkConf</span><span class="o">().</span><span class="na">setAppName</span><span class="o">(</span><span class="s">&quot;JavaOneVsRestExample&quot;</span><span class="o">);</span>
+<span class="n">JavaSparkContext</span> <span class="n">jsc</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">JavaSparkContext</span><span class="o">(</span><span class="n">conf</span><span class="o">);</span>
+<span class="n">SQLContext</span> <span class="n">jsql</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">SQLContext</span><span class="o">(</span><span class="n">jsc</span><span class="o">);</span>
+
+<span class="n">RDD</span><span class="o">&lt;</span><span class="n">LabeledPoint</span><span class="o">&gt;</span> <span class="n">data</span> <span class="o">=</span> <span class="n">MLUtils</span><span class="o">.</span><span class="na">loadLibSVMFile</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">&quot;data/mllib/sample_multiclass_classification_data.txt&quot;</span><span class="o">);</span>
+
+<span class="n">DataFrame</span> <span class="n">dataFrame</span> <span class="o">=</span> <span class="n">jsql</span><span class="o">.</span><span class="na">createDataFrame</span><span class="o">(</span><span class="n">data</span><span class="o">,</span> <span class="n">LabeledPoint</span><span class="o">.</span><span class="na">class</span><span class="o">);</span>
+<span class="n">DataFrame</span><span class="o">[]</span> <span class="n">splits</span> <span class="o">=</span> <span class="n">dataFrame</span><span class="o">.</span><span class="na">randomSplit</span><span class="o">(</span><span class="k">new</span> <span class="kt">double</span><span class="o">[]{</span><span class="mf">0.7</span><span class="o">,</span> <span class="mf">0.3</span><span class="o">},</span> <span class="mi">12345</span><span class="o">);</span>
+<span class="n">DataFrame</span> <span class="n">train</span> <span class="o">=</span> <span class="n">splits</span><span class="o">[</span><span class="mi">0</span><span class="o">];</span>
+<span class="n">DataFrame</span> <span class="n">test</span> <span class="o">=</span> <span class="n">splits</span><span class="o">[</span><span class="mi">1</span><span class="o">];</span>
+
+<span class="c1">// instantiate the One Vs Rest Classifier</span>
+<span class="n">OneVsRest</span> <span class="n">ovr</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">OneVsRest</span><span class="o">().</span><span class="na">setClassifier</span><span class="o">(</span><span class="k">new</span> <span class="nf">LogisticRegression</span><span class="o">());</span>
+
+<span class="c1">// train the multiclass model</span>
+<span class="n">OneVsRestModel</span> <span class="n">ovrModel</span> <span class="o">=</span> <span class="n">ovr</span><span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">train</span><span class="o">.</span><span class="na">cache</span><span class="o">());</span>
+
+<span class="c1">// score the model on test data</span>
+<span class="n">DataFrame</span> <span class="n">predictions</span> <span class="o">=</span> <span class="n">ovrModel</span>
+  <span class="o">.</span><span class="na">transform</span><span class="o">(</span><span class="n">test</span><span class="o">)</span>
+  <span class="o">.</span><span class="na">select</span><span class="o">(</span><span class="s">&quot;prediction&quot;</span><span class="o">,</span> <span class="s">&quot;label&quot;</span><span class="o">);</span>
+
+<span class="c1">// obtain metrics</span>
+<span class="n">MulticlassMetrics</span> <span class="n">metrics</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">MulticlassMetrics</span><span class="o">(</span><span class="n">predictions</span><span class="o">);</span>
+<span class="n">Matrix</span> <span class="n">confusionMatrix</span> <span class="o">=</span> <span class="n">metrics</span><span class="o">.</span><span class="na">confusionMatrix</span><span class="o">();</span>
+
+<span class="c1">// output the Confusion Matrix</span>
+<span class="n">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">&quot;Confusion Matrix&quot;</span><span class="o">);</span>
+<span class="n">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="n">confusionMatrix</span><span class="o">);</span>
+
+<span class="c1">// compute the false positive rate per label</span>
+<span class="n">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="n">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">&quot;label\tfpr\n&quot;</span><span class="o">);</span>
+
+<span class="c1">// the Iris DataSet has three classes</span>
+<span class="kt">int</span> <span class="n">numClasses</span> <span class="o">=</span> <span class="mi">3</span><span class="o">;</span>
+<span class="k">for</span> <span class="o">(</span><span class="kt">int</span> <span class="n">index</span> <span class="o">=</span> <span class="mi">0</span><span class="o">;</span> <span class="n">index</span> <span class="o">&lt;</span> <span class="n">numClasses</span><span class="o">;</span> <span class="n">index</span><span class="o">++)</span> <span class="o">{</span>
+  <span class="kt">double</span> <span class="n">label</span> <span class="o">=</span> <span class="o">(</span><span class="kt">double</span><span class="o">)</span> <span class="n">index</span><span class="o">;</span>
+  <span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">print</span><span class="o">(</span><span class="n">label</span><span class="o">);</span>
+  <span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">print</span><span class="o">(</span><span class="s">&quot;\t&quot;</span><span class="o">);</span>
+  <span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">print</span><span class="o">(</span><span class="n">metrics</span><span class="o">.</span><span class="na">falsePositiveRate</span><span class="o">(</span><span class="n">label</span><span class="o">));</span>
+  <span class="n">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="o">}</span></code></pre></div>
+
+  </div>
+</div>
+
+
+        </div> <!-- /container -->
+
+        <script src="js/vendor/jquery-1.8.0.min.js"></script>
+        <script src="js/vendor/bootstrap.min.js"></script>
+        <script src="js/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://') +
+                    'cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML';
+                d.getElementsByTagName('head')[0].appendChild(script);
+            }(document));
+        </script>
+    </body>
+</html>
author	Patrick Wendell <pwendell@apache.org>	2015-07-15 04:17:01 +0000
committer	Patrick Wendell <pwendell@apache.org>	2015-07-15 04:17:01 +0000
commit	8c2ee8d4aa3eb7fdc66536019d86793e1db2b135 (patch)
tree	07beeb27472248193736185dfa7567fc078426fa /site/docs/1.4.1/ml-ensembles.html
parent	7378439da1198903bbb855218de3d050c611a057 (diff)
download	spark-website-8c2ee8d4aa3eb7fdc66536019d86793e1db2b135.tar.gz spark-website-8c2ee8d4aa3eb7fdc66536019d86793e1db2b135.tar.bz2 spark-website-8c2ee8d4aa3eb7fdc66536019d86793e1db2b135.zip