diff options
Diffstat (limited to 'site/mllib/index.html')
| -rw-r--r-- | site/mllib/index.html | 314 |
1 files changed, 314 insertions, 0 deletions
diff --git a/site/mllib/index.html b/site/mllib/index.html new file mode 100644 index 000000000..f369755c7 --- /dev/null +++ b/site/mllib/index.html @@ -0,0 +1,314 @@ +<!DOCTYPE html> +<html lang="en"> +<head> + <meta charset="utf-8"> + <meta http-equiv="X-UA-Compatible" content="IE=edge"> + <meta name="viewport" content="width=device-width, initial-scale=1.0"> + + <title> + MLlib | Apache Spark + + </title> + + + + <!-- Bootstrap core CSS --> + <link href="/css/cerulean.min.css" rel="stylesheet"> + <link href="/css/custom.css" rel="stylesheet"> + + <script type="text/javascript"> + <!-- Google Analytics initialization --> + 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); + })(); + + <!-- Adds slight delay to links to allow async reporting --> + function trackOutboundLink(link, category, action) { + try { + _gaq.push(['_trackEvent', category , action]); + } catch(err){} + + setTimeout(function() { + document.location.href = link.href; + }, 100); + } + </script> + + <!-- HTML5 shim and Respond.js IE8 support of HTML5 elements and media queries --> + <!--[if lt IE 9]> + <script src="https://oss.maxcdn.com/libs/html5shiv/3.7.0/html5shiv.js"></script> + <script src="https://oss.maxcdn.com/libs/respond.js/1.3.0/respond.min.js"></script> + <![endif]--> +</head> + +<body> + +<div class="container" style="max-width: 1200px;"> + +<div class="masthead"> + + <p class="lead"> + <a href="/"> + <img src="/images/spark-logo.png" + style="height:100px; width:auto; vertical-align: bottom; margin-top: 20px;"></a> + <a href="#"><span class="subproject"> + MLlib + </span></a> + </p> + +</div> + +<nav class="navbar navbar-default" role="navigation"> + <!-- Brand and toggle get grouped for better mobile display --> + <div class="navbar-header"> + <button type="button" class="navbar-toggle" data-toggle="collapse" + data-target="#navbar-collapse-1"> + <span class="sr-only">Toggle navigation</span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + <span class="icon-bar"></span> + </button> + </div> + + <!-- Collect the nav links, forms, and other content for toggling --> + <div class="collapse navbar-collapse" id="navbar-collapse-1"> + <ul class="nav navbar-nav"> + <li><a href="/downloads.html">Download</a></li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown"> + Related Projects <b class="caret"></b> + </a> + <ul class="dropdown-menu"> + <li><a href="http://shark.cs.berkeley.edu">Shark (SQL)</a></li> + <li><a href="/streaming/">Spark Streaming</a></li> + <li><a href="/mllib/">MLlib (machine learning)</a></li> + <li><a href="http://amplab.github.io/graphx/">GraphX (graph)</a></li> + </ul> + </li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown"> + Documentation <b class="caret"></b> + </a> + <ul class="dropdown-menu"> + <li><a href="/documentation.html">Overview</a></li> + <li><a href="/docs/latest/">Latest Release</a></li> + <li><a href="/examples.html">Examples</a></li> + </ul> + </li> + <li class="dropdown"> + <a href="#" class="dropdown-toggle" data-toggle="dropdown"> + Community <b class="caret"></b> + </a> + <ul class="dropdown-menu"> + <li><a href="/community.html">Mailing Lists</a></li> + <li><a href="/community.html#events">Events and Meetups</a></li> + <li><a href="/community.html#history">Project History</a></li> + <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Powered+By+Spark">Powered By</a></li> + </ul> + </li> + <li><a href="/faq.html">FAQ</a></li> + </ul> + </div> + <!-- /.navbar-collapse --> +</nav> + + +<div class="row"> + <div class="col-md-3 col-md-push-9"> + <div class="news" style="margin-bottom: 20px;"> + <h5>Latest News</h5> + <ul class="list-unstyled"> + + <li><a href="/news/spark-0-8-1-released.html">Spark 0.8.1 released</a> + <span class="small">(Dec 19, 2013)</span></li> + + <li><a href="/news/spark-summit-2013-is-a-wrap.html">Spark Summit 2013 is a Wrap</a> + <span class="small">(Dec 15, 2013)</span></li> + + <li><a href="/news/announcing-the-first-spark-summit.html">Announcing the first Spark Summit: December 2, 2013</a> + <span class="small">(Oct 08, 2013)</span></li> + + <li><a href="/news/spark-0-8-0-released.html">Spark 0.8.0 released</a> + <span class="small">(Sep 25, 2013)</span></li> + + </ul> + <p class="small" style="text-align: right;"><a href="/news/index.html">Archive</a></p> + </div> + <div class="hidden-xs hidden-sm"> + <a href="/downloads.html" class="btn btn-success btn-lg btn-block" style="margin-bottom: 30px;"> + Download Spark + </a> + <p style="font-size: 16px; font-weight: 500; color: #555;"> + Related Projects: + </p> + <ul class="list-narrow"> + <li><a href="http://shark.cs.berkeley.edu">Shark (SQL)</a></li> + <li><a href="/streaming/">Spark Streaming</a></li> + <li><a href="/mllib/">MLlib (machine learning)</a></li> + <li><a href="http://amplab.github.io/graphx/">GraphX (graph)</a></li> + </ul> + </div> + </div> + + <div class="col-md-9 col-md-pull-3"> + <div class="jumbotron"> + <b>MLlib</b> is Apache Spark's scalable machine learning library. +</div> + +<div class="row row-padded"> + <div class="col-md-7 col-sm-7"> + <h2>Ease of Use</h2> + <p class="lead"> + Usable in Java, Scala and Python. + </p> + <p> + MLlib fits into <a href="/">Spark</a>'s + APIs and interoperates with <a href="http://www.numpy.org">NumPy</a> in Python (starting in Spark 0.9). + You can use any Hadoop data source (e.g. HDFS, HBase, or local files), making it + easy to plug into Hadoop workflows. + </p> + </div> + <div class="col-md-5 col-sm-5 col-padded-top col-center"> + + <div style="margin-top: 15px; text-align: left; display: inline-block;"> + <div class="code"> + points = spark.textFile(<span class="string">"hdfs://..."</span>)<br /> + .<span class="sparkop">map</span>(<span class="closure">parsePoint</span>)<br /> + <br /> + model = KMeans.<span class="sparkop">train</span>(points) + </div> + <div class="caption">Calling MLlib in Scala</div> + </div> + </div> +</div> + +<div class="row row-padded"> + <div class="col-md-7 col-sm-7"> + <h2>Performance</h2> + <p class="lead"> + High-quality algorithms, 100x faster than MapReduce. + </p> + <p> + Spark excels at iterative computation, enabling MLlib to run fast. + At the same time, we care about algorithmic performance: + MLlib contains high-quality algorithms that leverage iteration, and + can yield better results than the one-pass approximations sometimes used on MapReduce. + </p> + </div> + <div class="col-md-5 col-sm-5 col-padded-top col-center"> + <div style="width: 100%; max-width: 272px; display: inline-block; text-align: center;"> + <img src="/images/logistic-regression.png" style="width: 100%; max-width: 250px;" /> + <div class="caption" style="min-width: 272px;">Logistic regression in Hadoop and Spark</div> + </div> + </div> +</div> + +<div class="row row-padded" style="margin-bottom: 15px;"> + <div class="col-md-7 col-sm-7"> + <h2>Easy to Deploy</h2> + <p class="lead"> + Runs on existing Hadoop clusters and data. + </p> + <p> + If you have a Hadoop 2 cluster, you can run Spark and MLlib without any pre-installation. + Otherwise, Spark is easy to run <a href="/docs/latest/spark-standalone.html">standalone</a> + or on <a href="/docs/latest/ec2-scripts.html">EC2</a> or <a href="http://mesos.apache.org">Mesos</a>. + You can read from <a href="http://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-hdfs/HdfsUserGuide.html">HDFS</a>, <a href="http://hbase.apache.org">HBase</a>, or any Hadoop data source. + </p> + </div> + <div class="col-md-5 col-sm-5 col-padded-top col-center"> + <img src="/images/hadoop.jpg" style="width: 100%; max-width: 280px;" /> + </div> +</div> + + + </div> +</div> + + + +<div class="row"> + <div class="col-md-4 col-padded"> + <h3>Algorithms</h3> + <p> + MLlib 0.8.1 contains the following algorithms: + </p> + <ul class="list-narrow"> + <li>K-means clustering with <a href="http://theory.stanford.edu/~sergei/papers/vldb12-kmpar.pdf">K-means|| initialization</a>.</li> + <li>L<sub>1</sub>- and L<sub>2</sub>-regularized <a href="http://en.wikipedia.org/wiki/Linear_regression">linear regression</a>.</li> + <li>L<sub>1</sub>- and L<sub>2</sub>-regularized <a href="http://en.wikipedia.org/wiki/Logistic_regression">logistic regression</a>.</li> + <li><a href="http://www.hpl.hp.com/personal/Robert_Schreiber/papers/2008%20AAIM%20Netflix/netflix_aaim08(submitted).pdf">Alternating least squares</a> collaborative filtering, with explicit + ratings or <a href="http://www2.research.att.com/~yifanhu/PUB/cf.pdf">implicit feedback</a>.</li> + <!--<li><a href="http://en.wikipedia.org/wiki/Naive_Bayes_classifier">Naive Bayes</a> multinomial classification.</li>--> + <li>Stochastic gradient descent.</li> + </ul> + <p>Refer to the <a href="/docs/latest/mllib-guide.html">MLlib guide</a> for usage examples.</p> + </div> + + <div class="col-md-4 col-padded"> + <h3>Community</h3> + <p> + MLlib is developed as part of the Apache Spark project. It thus gets + tested and updated with each Spark release. + </p> + <p> + If you have questions about the library, ask on the + <a href="/community.html#mailing-lists">Spark mailing lists</a>. + </p> + <p> + MLlib is still a young project and welcomes contributions. If you'd like to submit an algorithm to MLlib, + read <a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">how to + contribute to Spark</a> and send us a patch! + </p> + </div> + + <div class="col-md-4 col-padded"> + <h3>Getting Started</h3> + <p> + To get started with MLlib: + </p> + <ul class="list-narrow"> + <li><a href="/downloads.html">Download Spark</a>. MLlib is included as a module.</li> + <li>Read the <a href="/docs/latest/mllib-guide.html">MLlib guide</a>, which includes + various usage examples.</li> + <li>Learn how to <a href="/docs/latest/#launching-on-a-cluster">deploy</a> Spark on a cluster + if you'd like to run in distributed mode. You can also run locally on a multicore machine + without any setup. + </li> + </ul> + </div> +</div> + +<div class="row"> + <div class="col-sm-12 col-center"> + <a href="/downloads.html" class="btn btn-success btn-lg btn-multiline"> + Download Spark<br /><span class="small">Includes MLlib</span> + </a> + </div> +</div> + + + + +<footer class="small"> + <hr> + Apache Spark is an effort undergoing incubation at The Apache Software Foundation. + <a href="http://incubator.apache.org/" style="border: none;"> + <img style="vertical-align: middle; float: right; margin-bottom: 15px;" + src="/images/incubator-logo.png" alt="Apache Incubator" title="Apache Incubator" /> + </a> +</footer> + +</div> + +<script src="https://code.jquery.com/jquery.js"></script> +<script src="//netdna.bootstrapcdn.com/bootstrap/3.0.3/js/bootstrap.min.js"></script> +<script src="/js/lang-tabs.js"></script> + +</body> +</html> |