http://git-wip-us.apache.org/repos/asf/mahout/blob/5112e9ec/docs/latest/algorithms/map-reduce/clustering/k-means-clustering.html ---------------------------------------------------------------------- diff --git a/docs/latest/algorithms/map-reduce/clustering/k-means-clustering.html b/docs/latest/algorithms/map-reduce/clustering/k-means-clustering.html index 89529fe..983400e 100644 --- a/docs/latest/algorithms/map-reduce/clustering/k-means-clustering.html +++ b/docs/latest/algorithms/map-reduce/clustering/k-means-clustering.html @@ -1,312 +1,169 @@ - - <!DOCTYPE html> -<html lang="en"> +<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"> - <title>(Deprecated) K-Means Clustering</title> - - <meta name="author" content="Apache Mahout"> - - <!-- Enable responsive viewport --> - <meta name="viewport" content="width=device-width, initial-scale=1.0"> - - <!-- Bootstrap styles --> - <link href="/assets/themes/mahout3/css/bootstrap.min.css" rel="stylesheet"> - <!-- Optional theme --> - <link href="/assets/themes/mahout3/css/bootstrap-theme.min.css" rel="stylesheet"> - <!-- Sticky Footer --> - <link href="/assets/themes/mahout3/css/bs-sticky-footer.css" rel="stylesheet"> - - <!-- Custom styles --> - <link href="/assets/themes/mahout3/css/style.css" rel="stylesheet" type="text/css" media="all"> - - <!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries --> - <!-- WARNING: Respond.js doesn't work if you view the page via file:// --> - <!--[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]--> - - <!-- Fav and touch icons --> - <!-- Update these with your own images - <link rel="shortcut icon" href="images/favicon.ico"> - <link rel="apple-touch-icon" href="images/apple-touch-icon.png"> - <link rel="apple-touch-icon" sizes="72x72" href="images/apple-touch-icon-72x72.png"> - <link rel="apple-touch-icon" sizes="114x114" href="images/apple-touch-icon-114x114.png"> - --> - - <!-- atom & rss feed --> - <link href="/atom.xml" type="application/atom+xml" rel="alternate" title="Sitewide ATOM Feed"> - <link href="/rss.xml" type="application/rss+xml" rel="alternate" title="Sitewide RSS Feed"> - <script type="text/x-mathjax-config"> - MathJax.Hub.Config({ - tex2jax: { - skipTags: ['script', 'noscript', 'style', 'textarea', 'pre'] - } - }); - MathJax.Hub.Queue(function() { - var all = MathJax.Hub.getAllJax(), i; - for(i = 0; i < all.length; i += 1) { - all[i].SourceElement().parentNode.className += ' has-jax'; - } - }); - </script> - <script type="text/javascript"> - var mathjax = document.createElement('script'); - mathjax.type = 'text/javascript'; - mathjax.async = true; - - mathjax.src = ('https:' == document.location.protocol) ? - 'https://c328740.ssl.cf1.rackcdn.com/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML' : - 'http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML'; - - var s = document.getElementsByTagName('script')[0]; - s.parentNode.insertBefore(mathjax, s); - </script> -</head> - -<nav class="navbar navbar-default navbar-fixed-top"> - <div class="container-fluid"> - <!-- Brand and toggle get grouped for better mobile display --> - <div class="navbar-header"> - <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#bs-example-navbar-collapse-1" aria-expanded="false"> - <span class="sr-only">Toggle navigation</span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - </button> - <a class="navbar-brand" href="/"> - <img src="/assets/img/Mahout-logo-82x100.png" height="30" alt="I'm mahout"> - </a> - </div> - + <title> + (Deprecated) K-Means Clustering + </title> + <meta name="description" content="Distributed Linear Algebra"> -<!-- Collect the nav links, forms, and other content for toggling --> -<div class="collapse navbar-collapse" id="main-navbar"> - <ul class="nav navbar-nav"> - - <!-- Quick Start --> - <li id="quickstart"> - <a href="/index.html" >Mahout Overview</a> - </li> - - <li id="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Key Concepts<span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><a href="/index.html">Mahout Overview</a></li> - <li><span><b> Scala DSL</b><span></li> - <li><a href="/mahout-samsara/in-core-reference.html">In-core Reference</a></li> - <li><a href="/mahout-samsara/out-of-core-reference.html">Out-of-core Reference</a></li> - <li><a href="/mahout-samsara/faq.html">Samsara FAQ</a></li> - <li role="separator" class="divider"></li> - <li><span> <b>Bindings</b><span></li> - <li><a href="/distributed/spark-bindings/">Spark Bindings</a></li> - <li><a href="/distributed/flink-bindings.html">Flink Bindings</a></li> - <li><a href="/distributed/flink-bindings.html">H20 Bindings</a></li> - <!--<li role="separator" class="divider"></li> - <li><span> <b>Native Solvers</b><span></li> - <li><a href="/native-solvers/viennacl.html">ViennaCL</a></li> - <li><a href="/native-solvers/viennacl-omp.html">ViennaCL-OMP</a></li> - <li><a href="/native-solvers/cuda.html">CUDA</a></li>--> - </ul> - </li> - - <li id="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Tutorials<span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><span> <b>Reccomenders</b><span></li> - <li><a href="/tutorials/cco-lastfm">CCO Example with Last.FM Data</a></li> - <li><a href="/tutorials/intro-cooccurrence-spark">Introduction to Cooccurrence in Spark</a></li> - <li role="separator" class="divider"></li> - <li><span> <b>Mahout Samsara</b><span></li> - <li><a href="/tutorials/samsara/play-with-shell.html">Playing with Samsara in Spark Shell</a></li> - <li><a href="/tutorials/samsara/playing-with-samsara-flink-batch.html">Playing with Samsara in Flink Batch</a></li> - <li><a href="/tutorials/samsara/classify-a-doc-from-the-shell.html">Text Classification (Shell)</a></li> - <li><a href="/tutorials/samsara/spark-naive-bayes.html">Spark Naive Bayes</a></li> - <li role="separator" class="divider"></li> - <li><span> <b>Misc</b><span></li> - <li><a href="/tutorials/misc/mahout-in-zeppelin">Mahout in Apache Zeppelin</a></li> - <li><a href="/tutorials/misc/contributing-algos">How To Contribute a New Algorithm</a></li> - <li><a href="/tutorials/misc/how-to-build-an-app.html">How To Build An App</a></li> - <li role="separator" class="divider"></li> - <li><span> <b>Deprecated</b><span></li> - <li><a href="/tutorials/map-reduce">MapReduce</a></li> - </ul> - </li> - - - <!-- Algorithms (Samsara / MR) --> - <li id="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Algorithms<span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><a href="/algorithms/linear-algebra">Distributed Linear Algebra</a></li> - <li><a href="/algorithms/preprocessors">Preprocessors</a></li> - <li><a href="/algorithms/regression">Regression</a></li> - <li><a href="/algorithms/reccomenders">Reccomenders</a></li> - <li role="separator" class="divider"></li> - <li><a href="/algorithms/map-reduce">MapReduce <i>(deprecated)</i></a></li> - </ul> - <!--<li><a href="/algorithms/reccomenders/recommender-overview.html">Reccomender Overview</a></li> Do we still need? seems like short version of next post--> - <!-- - <li><a href="/algorithms/reccomenders/intro-cooccurrence-spark.html">Intro to Coocurrence With Spark</a></li> - <li role="separator" class="divider"></li> - <li><span> <a href="/algorithms/map-reduce"><b>MapReduce</b> (deprecated)</a><span></li> + <link rel="stylesheet" href="/assets/css/main.css"> + <!-- Font Awesome --> + <link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.7.0/css/font-awesome.min.css" rel="stylesheet" integrity="sha384-wvfXpqpZZVQGK6TAh5PVlGOfQNHSoD2xbE+QkPxCAFlNEevoEH3Sl0sibVcOQVnN" crossorigin="anonymous"> - --> - </li> + <!-- Google Fonts --> + <link href="https://fonts.googleapis.com/css?family=Maven+Pro:400,500" rel="stylesheet"> + <link href="https://fonts.googleapis.com/css?family=Muli:400,400i,700,700i" rel="stylesheet"> - <!-- Scala Docs --> - <li id="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">API Docs<span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><a href="/0.13.0/api/index.html">0.13.0</a></li> - </ul> - </li> - - - </ul> - <form class="navbar-form navbar-left"> - <div class="form-group"> - <input type="text" class="form-control" placeholder="Search"> - </div> - <button type="submit" class="btn btn-default">Submit</button> - </form> - <ul class="nav navbar-nav navbar-right"> - <li><a href="http://github.com/apache/mahout">Github</a></li> - - <!-- Apache --> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache <span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><a href="http://www.apache.org/foundation/how-it-works.html">Apache Software Foundation</a></li> - <li><a href="http://www.apache.org/licenses/">Apache License</a></li> - <li><a href="http://www.apache.org/foundation/sponsorship.html">Sponsorship</a></li> - <li><a href="http://www.apache.org/foundation/thanks.html">Thanks</a></li> - </ul> - </li> + <link rel="canonical" href="http://mahout.apache.org//docs/latest/algorithms/map-reduce/clustering/k-means-clustering.html"> + <link rel="alternate" type="application/rss+xml" title="Apache Mahout" href="/%20/feed.xml"> - </ul> -</div><!-- /.navbar-collapse --> - </div><!-- /.container-fluid --> -</nav> +</head> + <body> -<div id="wrap"> - <body class=""> + <nav class="navbar navbar-expand-lg navbar-light bg-light navbar-mahout"> + + <div class="container"> + + <a class="navbar-brand" href="/"> + <img src="/assets/mahout-logo-blue.svg" alt=""> + </a> + + <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbarSupportedContent" aria-controls="navbarSupportedContent" aria-expanded="false" aria-label="Toggle navigation"> + <span class="navbar-toggler-icon"></span> + </button> + + <div class="collapse navbar-collapse" id="navbarSupportedContent"> + + <div class="navbar-nav ml-auto"> + + <!-- Quick Start --> + <li class="nav-item"> + <a class="nav-link" href="//docs/latest/" >Mahout Overview</a> + </li> + + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Key Concepts</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <a class="dropdown-item" href="/docs/latest/index.html">Mahout Overview</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Scala DSL</h6> + <a class="dropdown-item" href="/docs/latest/mahout-samsara/in-core-reference.html">In-core Reference</a> + <a class="dropdown-item" href="/docs/latest/mahout-samsara/out-of-core-reference.html">Out-of-core Reference</a> + <a class="dropdown-item" href="/docs/latest/mahout-samsara/faq.html">Samsara FAQ</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Distributed Engine Bindings</h6> + <a class="dropdown-item" href="/docs/latest/distributed/spark-bindings/">Spark Bindings</a> + <a class="dropdown-item" href="/docs/latest/distributed/flink-bindings.html">Flink Bindings</a> + <a class="dropdown-item" href="/docs/latest/distributed/flink-bindings.html">H20 Bindings</a> + <!--<div class="dropdown-divider"></div> + <h6 class="dropdown-header">Native Solvers</h6> + <a class="dropdown-item" href="/docs/latest/native-solvers/viennacl.html">ViennaCL</a></li> + <a class="dropdown-item" href="/docs/latest/native-solvers/viennacl-omp.html">ViennaCL-OMP</a></li> + <a class="dropdown-item" href="/docs/latest/native-solvers/cuda.html">CUDA</a></li>--> + </div> + </li> + + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Tutorial</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Reccomenders</h6> + <a class="dropdown-item" href="/docs/latest/tutorials/cco-lastfm">CCO Example with Last.FM Data</a> + <a class="dropdown-item" href="/docs/latest/tutorials/intro-cooccurrence-spark">Introduction to Cooccurrence in Spark</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Mahout Samsara</h6> + <a class="dropdown-item" href="/docs/latest/tutorials/samsara/play-with-shell.html">Playing with Samsara in Spark Shell</a> + <a class="dropdown-item" href="/docs/latest/tutorials/samsara/playing-with-samsara-flink-batch.html">Playing with Samsara in Flink Batch</a> + <a class="dropdown-item" href="/docs/latest/tutorials/samsara/classify-a-doc-from-the-shell.html">Text Classification (Shell)</a> + <a class="dropdown-item" href="/docs/latest/tutorials/samsara/spark-naive-bayes.html">Spark Naive Bayes</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Misc</h6> + <a class="dropdown-item" href="/docs/latest/tutorials/misc/mahout-in-zeppelin">Mahout in Apache Zeppelin</a> + <a class="dropdown-item" href="/docs/latest/tutorials/misc/contributing-algos">How To Contribute a New Algorithm</a> + <a class="dropdown-item" href="/docs/latest/tutorials/misc/how-to-build-an-app.html">How To Build An App</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Deprecated</h6> + <a class="dropdown-item" href="/docs/latest/tutorials/map-reduce">MapReduce</a> + </div> + </li> + + + <!-- Algorithms (Samsara / MR) --> + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Algorithms</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <a class="dropdown-item" href="/docs/latest/algorithms/linear-algebra">Distributed Linear Algebra</a> + <a class="dropdown-item" href="/docs/latest/algorithms/preprocessors">Preprocessors</a> + <a class="dropdown-item" href="/docs/latest/algorithms/regression">Regression</a> + <a class="dropdown-item" href="/docs/latest/algorithms/reccomenders">Reccomenders</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Deprecated</h6> + <a class="dropdown-item" href="/docs/latest/algorithms/map-reduce">MapReduce <i>(deprecated)</i></a> + </div> + <!--<a class="dropdown-item" href="/docs/latest/algorithms/reccomenders/recommender-overview.html">Reccomender Overview</a></li> Do we still need? seems like short version of next post--> + <!-- + <a class="dropdown-item" href="/docs/latest/algorithms/reccomenders/intro-cooccurrence-spark.html">Intro to Coocurrence With Spark</a></li> + <li role="separator" class="divider"></li> + <li><span> <a href="/docs/latest/algorithms/map-reduce"><b>MapReduce</b> (deprecated)</a><span></li> + + + --> + </li> + + <!-- Scala /docs --> + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">API /docs</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <a class="dropdown-item" href="/docs/latest/0.13.0/api/index.html">0.13.0</a> + </div> + </li> + + <!-- Apache --> + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Apache</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <a class="dropdown-item" href="http://www.apache.org/foundation/how-it-works.html">Apache Software Foundation</a> + <a class="dropdown-item" href="http://www.apache.org/licenses/">Apache License</a> + <a class="dropdown-item" href="http://www.apache.org/foundation/sponsorship.html">Sponsorship</a> + <a class="dropdown-item" href="http://www.apache.org/foundation/thanks.html">Thanks</a> + </div> + </li> - <div class="container"> - + </ul> + + <!--<form class="navbar-form navbar-left">--> + <!--<div class="form-group">--> + <!--<input type="text" class="form-control" placeholder="Search">--> + <!--</div>--> + <!--<button type="submit" class="btn btn-default">Submit</button>--> + <!--</form>--> + <!--<ul class="nav navbar-nav navbar-right">--> + <!--<a class="dropdown-item" href="http://github.com/apache/mahout">Github</a></li>--> -<div class="row"> - <div class="col-md-3"> - <div id="AlgoMenu"> - <span><b>Mahout-Samsara Algorithms</b></span> - <div class="list-group panel"> - <a href="#linalg" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Linear Algebra</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="linalg"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/linear-algebra/d-qr.html">Distributed QR Decomposition</a></li> - <li> <a href="/algorithms/linear-algebra/d-spca.html">Distributed Stochastic Principal Component Analysis</a></li> - <li> <a href="/algorithms/linear-algebra/d-ssvd.html">Distributed Stochastic Singular Value Decomposition</a></li> - </ul> - </div> - <a href="#clustering" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Clustering</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="clustering"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/clustering">Clustering Algorithms</a></li> - <li> <a href="/algorithms/clustering/distance-metrics.html">Distance Metrics</a></li> - <li> <a href="/algorithms/clustering/canopy">Canopy Clustering</a></li> - </ul> - </div> - <a href="#preprocessors" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Preprocessors</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="preprocessors"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/preprocessors/AsFactor.html">AsFactor (a.k.a. One-Hot-Encoding)</a></li> - <li> <a href="/algorithms/preprocessors/StandardScaler.html">StandardScaler</a></li> - <li> <a href="/algorithms/preprocessors/MeanCenter.html">MeanCenter</a></li> - </ul> - </div> - <a href="#regression" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Regression</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="regression"> - <ul class="nav sidebar-nav"> - <a href="#serial-correlation" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#regression"><b>• Serial Correlation</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="serial-correlation"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/regression/serial-correlation/cochrane-orcutt.html">Cochrane-Orcutt Procedure</a></li> - <li> <a href="/algorithms/regression/serial-correlation/dw-test.html">Durbin Watson Test</a></li> - </ul> - </div> - <li> <a href="/algorithms/regression/ols.html">Ordinary Least Squares (Closed Form)</a></li> - <li> <a href="/algorithms/regression/fittness-tests.html">Fitness Tests</a></li> - </ul> - </div> - <a href="#reccomenders" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Reccomenders</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="reccomenders"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/reccomenders">Reccomender Overview</a></li> - <li> <a href="/algorithms/reccomenders/cco.html">CCO</a></li> - <li> <a href="/algorithms/reccomenders/d-als.html">Distributed Alternating Least Squares</a></li> - </ul> - </div> - </div> - <span><b>Map Reduce Algorithms</b> (deprecated)</span> - <div class="list-group panel"> - <a href="#classification" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Classification</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="classification"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/map-reduce/classification/bayesian.html">Bayesian</a></li> - <li> <a href="/algorithms/map-reduce/classification/class-discovery.html">Class Discovery</a></li> - <li> <a href="/algorithms/map-reduce/classification/classifyingyourdata.html">Classifying Your Data</a></li> - <li> <a href="/algorithms/map-reduce/classification/collocations.html">Collocation</a></li> - <li> <a href="/algorithms/map-reduce/classification/gaussian-discriminative-analysis.html">Gaussian Discriminative Analysis</a></li> - <li> <a href="/algorithms/map-reduce/classification/hidden-markov-models.html">Hidden Markov Models</a></li> - <li> <a href="/algorithms/map-reduce/classification/independent-component-analysis.html">Independent Component Analysis</a></li> - <li> <a href="/algorithms/map-reduce/classification/locally-weighted-linear-regression.html">Locally Weighted Linear Regression</a></li> - <li> <a href="/algorithms/map-reduce/classification/logistic-regression.html">Logistic Regression</a></li> - <li> <a href="/algorithms/map-reduce/classification/mahout-collections.html">Mahout Collections</a></li> - <li> <a href="/algorithms/map-reduce/classification/mlp.html">Multilayer Perceptron</a></li> - <li> <a href="/algorithms/map-reduce/classification/naivebayes.html">Naive Bayes</a></li> - <li> <a href="/algorithms/map-reduce/classification/neural-network.html">Neural Networks</a></li> - <li> <a href="/algorithms/map-reduce/classification/partial-implementation.html">Partial Implementation</a></li> - <li> <a href="/algorithms/map-reduce/classification/random-forrests.html">Random Forrests</a></li> - <li> <a href="/algorithms/map-reduce/classification/restricted-boltzman-machines.html">Restricted Boltzman Machines</a></li> - <li> <a href="/algorithms/map-reduce/classification/support-vector-machines.html">Support Vector Machines</a></li> - </ul> - </div> - <a href="#mr-clustering" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Clustering</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="mr-clustering"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/map-reduce/clustering/canopy-clustering.html">Canopy Clustering</a></li> - <li> <a href="/algorithms/map-reduce/clustering/cluster-dumper.html">Cluster Dumper</a></li> - <li> <a href="/algorithms/map-reduce/clustering/expectation-maximization.html">Expectation Maximization</a></li> - <li> <a href="/algorithms/map-reduce/clustering/fuzzy-k-means.html">Fuzzy K-Means</a></li> - <li> <a href="/algorithms/map-reduce/clustering/hierarchical-clustering.html">Hierarchical Clustering</a></li> - <li> <a href="/algorithms/map-reduce/clustering/k-means-clustering.html">K-Means Clustering</a></li> - <li> <a href="/algorithms/map-reduce/clustering/latent-dirichlet-allocation.html">Latent Dirichlet Allocation</a></li> - <li> <a href="/algorithms/map-reduce/clustering/llr---log-likelihood-ratio.html">Log Likelihood Ratio</a></li> - <li> <a href="/algorithms/map-reduce/clustering/spectral-clustering.html">Spectral Clustering</a></li> - <li> <a href="/algorithms/map-reduce/clustering/streaming-k-means.html">Streaming K-Means</a></li> - </ul> - </div> - </div> -</div> + <!--</ul>--> + </div><!-- /.navbar-collapse --> </div> +</nav> - <div class="col-md-8"> - <div class="page-header"> - <h1>(Deprecated) K-Means Clustering </h1> - </div> - <h1 id="k-means-clustering---basics">k-Means clustering - basics</h1> + <div class="container mt-5 pb-4"> + + <div class="row"> + + <div class="col-lg-8"> + <h1 id="k-means-clustering---basics">k-Means clustering - basics</h1> <p><a href="http://en.wikipedia.org/wiki/Kmeans">k-Means</a> is a simple but well-known algorithm for grouping objects, clustering. All objects need to be represented as a set of numerical features. In addition, the user has to specify the @@ -365,7 +222,7 @@ clustering and convergence values.</p> <p>Canopy clustering can be used to compute the initial clusters for k-KMeans:</p> -<pre><code>// run the CanopyDriver job +<div class="highlighter-rouge"><pre class="highlight"><code>// run the CanopyDriver job CanopyDriver.runJob("testdata", "output" ManhattanDistanceMeasure.class.getName(), (float) 3.1, (float) 2.1, false); @@ -373,6 +230,7 @@ ManhattanDistanceMeasure.class.getName(), (float) 3.1, (float) 2.1, false); KMeansDriver.runJob("testdata", "output/clusters-0", "output", EuclideanDistanceMeasure.class.getName(), "0.001", "10", true); </code></pre> +</div> <p>In the above example, the input data points are stored in âtestdataâ and the CanopyDriver is configured to output to the âoutput/clusters-0â @@ -393,7 +251,7 @@ on KMeansDriver.main or by making a Java call to KMeansDriver.runJob().</p> <p>Invocation using the command line takes the form:</p> -<pre><code>bin/mahout kmeans \ +<div class="highlighter-rouge"><pre class="highlight"><code>bin/mahout kmeans \ -i <input vectors directory> \ -c <input clusters directory> \ -o <output working directory> \ @@ -405,6 +263,7 @@ on KMeansDriver.main or by making a Java call to KMeansDriver.runJob().</p> -cl <run input vector clustering after computing Canopies> -xm <execution method: sequential or mapreduce> </code></pre> +</div> <p>Note: if the -k argument is supplied, any clusters in the -c directory will be overwritten and -k random points will be sampled from the input @@ -486,32 +345,25 @@ K-Means does a fair job handling this data set as well.</p> <p><img src="../../images/2dKMeans.png" alt="2d kmeans" /></p> </div> -</div> - </div> - - -</div> -<div id="footer"> - <div class="container"> - <p>© 2017 Apache Mahout - with help from <a href="http://jekyllbootstrap.com" target="_blank" title="The Definitive Jekyll Blogging Framework">Jekyll Bootstrap</a> - and <a href="http://getbootstrap.com" target="_blank">Bootstrap</a> - </p> </div> -</div> - - +</div> + <footer class="footer bg-light"> + <div class="container text-center small"> + Copyright © 2014-2017 The Apache Software Foundation, Licensed under the Apache License, Version 2.0. + </div> +</footer> + <script src="/assets/vendor/jquery/jquery-slim.min.js"></script> + <script src="/assets/vendor/popper/popper.min.js"></script> + <script src="/assets/vendor/bootstrap/js/bootstrap.min.js"></script> + <script src="/assets/header.js"></script> + <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script> -<!-- Latest compiled and minified JavaScript, requires jQuery 1.x (2.x not supported in IE8) --> -<!-- Placed at the end of the document so the pages load faster --> -<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script> -<script src="/assets/themes/mahout3/js/bootstrap.min.js"></script> </body> -</html> +</html>
http://git-wip-us.apache.org/repos/asf/mahout/blob/5112e9ec/docs/latest/algorithms/map-reduce/clustering/latent-dirichlet-allocation.html ---------------------------------------------------------------------- diff --git a/docs/latest/algorithms/map-reduce/clustering/latent-dirichlet-allocation.html b/docs/latest/algorithms/map-reduce/clustering/latent-dirichlet-allocation.html index a1d4a6b..38b74fc 100644 --- a/docs/latest/algorithms/map-reduce/clustering/latent-dirichlet-allocation.html +++ b/docs/latest/algorithms/map-reduce/clustering/latent-dirichlet-allocation.html @@ -1,312 +1,169 @@ - - <!DOCTYPE html> -<html lang="en"> +<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"> - <title>(Deprecated) Latent Dirichlet Allocation</title> - - <meta name="author" content="Apache Mahout"> - - <!-- Enable responsive viewport --> - <meta name="viewport" content="width=device-width, initial-scale=1.0"> - - <!-- Bootstrap styles --> - <link href="/assets/themes/mahout3/css/bootstrap.min.css" rel="stylesheet"> - <!-- Optional theme --> - <link href="/assets/themes/mahout3/css/bootstrap-theme.min.css" rel="stylesheet"> - <!-- Sticky Footer --> - <link href="/assets/themes/mahout3/css/bs-sticky-footer.css" rel="stylesheet"> - - <!-- Custom styles --> - <link href="/assets/themes/mahout3/css/style.css" rel="stylesheet" type="text/css" media="all"> - - <!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries --> - <!-- WARNING: Respond.js doesn't work if you view the page via file:// --> - <!--[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]--> - - <!-- Fav and touch icons --> - <!-- Update these with your own images - <link rel="shortcut icon" href="images/favicon.ico"> - <link rel="apple-touch-icon" href="images/apple-touch-icon.png"> - <link rel="apple-touch-icon" sizes="72x72" href="images/apple-touch-icon-72x72.png"> - <link rel="apple-touch-icon" sizes="114x114" href="images/apple-touch-icon-114x114.png"> - --> - - <!-- atom & rss feed --> - <link href="/atom.xml" type="application/atom+xml" rel="alternate" title="Sitewide ATOM Feed"> - <link href="/rss.xml" type="application/rss+xml" rel="alternate" title="Sitewide RSS Feed"> - <script type="text/x-mathjax-config"> - MathJax.Hub.Config({ - tex2jax: { - skipTags: ['script', 'noscript', 'style', 'textarea', 'pre'] - } - }); - MathJax.Hub.Queue(function() { - var all = MathJax.Hub.getAllJax(), i; - for(i = 0; i < all.length; i += 1) { - all[i].SourceElement().parentNode.className += ' has-jax'; - } - }); - </script> - <script type="text/javascript"> - var mathjax = document.createElement('script'); - mathjax.type = 'text/javascript'; - mathjax.async = true; - - mathjax.src = ('https:' == document.location.protocol) ? - 'https://c328740.ssl.cf1.rackcdn.com/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML' : - 'http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML'; - - var s = document.getElementsByTagName('script')[0]; - s.parentNode.insertBefore(mathjax, s); - </script> -</head> - -<nav class="navbar navbar-default navbar-fixed-top"> - <div class="container-fluid"> - <!-- Brand and toggle get grouped for better mobile display --> - <div class="navbar-header"> - <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#bs-example-navbar-collapse-1" aria-expanded="false"> - <span class="sr-only">Toggle navigation</span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - <span class="icon-bar"></span> - </button> - <a class="navbar-brand" href="/"> - <img src="/assets/img/Mahout-logo-82x100.png" height="30" alt="I'm mahout"> - </a> - </div> - + <title> + (Deprecated) Latent Dirichlet Allocation + </title> + <meta name="description" content="Distributed Linear Algebra"> -<!-- Collect the nav links, forms, and other content for toggling --> -<div class="collapse navbar-collapse" id="main-navbar"> - <ul class="nav navbar-nav"> - - <!-- Quick Start --> - <li id="quickstart"> - <a href="/index.html" >Mahout Overview</a> - </li> - - <li id="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Key Concepts<span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><a href="/index.html">Mahout Overview</a></li> - <li><span><b> Scala DSL</b><span></li> - <li><a href="/mahout-samsara/in-core-reference.html">In-core Reference</a></li> - <li><a href="/mahout-samsara/out-of-core-reference.html">Out-of-core Reference</a></li> - <li><a href="/mahout-samsara/faq.html">Samsara FAQ</a></li> - <li role="separator" class="divider"></li> - <li><span> <b>Bindings</b><span></li> - <li><a href="/distributed/spark-bindings/">Spark Bindings</a></li> - <li><a href="/distributed/flink-bindings.html">Flink Bindings</a></li> - <li><a href="/distributed/flink-bindings.html">H20 Bindings</a></li> - <!--<li role="separator" class="divider"></li> - <li><span> <b>Native Solvers</b><span></li> - <li><a href="/native-solvers/viennacl.html">ViennaCL</a></li> - <li><a href="/native-solvers/viennacl-omp.html">ViennaCL-OMP</a></li> - <li><a href="/native-solvers/cuda.html">CUDA</a></li>--> - </ul> - </li> - - <li id="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Tutorials<span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><span> <b>Reccomenders</b><span></li> - <li><a href="/tutorials/cco-lastfm">CCO Example with Last.FM Data</a></li> - <li><a href="/tutorials/intro-cooccurrence-spark">Introduction to Cooccurrence in Spark</a></li> - <li role="separator" class="divider"></li> - <li><span> <b>Mahout Samsara</b><span></li> - <li><a href="/tutorials/samsara/play-with-shell.html">Playing with Samsara in Spark Shell</a></li> - <li><a href="/tutorials/samsara/playing-with-samsara-flink-batch.html">Playing with Samsara in Flink Batch</a></li> - <li><a href="/tutorials/samsara/classify-a-doc-from-the-shell.html">Text Classification (Shell)</a></li> - <li><a href="/tutorials/samsara/spark-naive-bayes.html">Spark Naive Bayes</a></li> - <li role="separator" class="divider"></li> - <li><span> <b>Misc</b><span></li> - <li><a href="/tutorials/misc/mahout-in-zeppelin">Mahout in Apache Zeppelin</a></li> - <li><a href="/tutorials/misc/contributing-algos">How To Contribute a New Algorithm</a></li> - <li><a href="/tutorials/misc/how-to-build-an-app.html">How To Build An App</a></li> - <li role="separator" class="divider"></li> - <li><span> <b>Deprecated</b><span></li> - <li><a href="/tutorials/map-reduce">MapReduce</a></li> - </ul> - </li> - - - <!-- Algorithms (Samsara / MR) --> - <li id="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Algorithms<span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><a href="/algorithms/linear-algebra">Distributed Linear Algebra</a></li> - <li><a href="/algorithms/preprocessors">Preprocessors</a></li> - <li><a href="/algorithms/regression">Regression</a></li> - <li><a href="/algorithms/reccomenders">Reccomenders</a></li> - <li role="separator" class="divider"></li> - <li><a href="/algorithms/map-reduce">MapReduce <i>(deprecated)</i></a></li> - </ul> - <!--<li><a href="/algorithms/reccomenders/recommender-overview.html">Reccomender Overview</a></li> Do we still need? seems like short version of next post--> - <!-- - <li><a href="/algorithms/reccomenders/intro-cooccurrence-spark.html">Intro to Coocurrence With Spark</a></li> - <li role="separator" class="divider"></li> - <li><span> <a href="/algorithms/map-reduce"><b>MapReduce</b> (deprecated)</a><span></li> + <link rel="stylesheet" href="/assets/css/main.css"> + <!-- Font Awesome --> + <link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.7.0/css/font-awesome.min.css" rel="stylesheet" integrity="sha384-wvfXpqpZZVQGK6TAh5PVlGOfQNHSoD2xbE+QkPxCAFlNEevoEH3Sl0sibVcOQVnN" crossorigin="anonymous"> - --> - </li> + <!-- Google Fonts --> + <link href="https://fonts.googleapis.com/css?family=Maven+Pro:400,500" rel="stylesheet"> + <link href="https://fonts.googleapis.com/css?family=Muli:400,400i,700,700i" rel="stylesheet"> - <!-- Scala Docs --> - <li id="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">API Docs<span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><a href="/0.13.0/api/index.html">0.13.0</a></li> - </ul> - </li> - - - </ul> - <form class="navbar-form navbar-left"> - <div class="form-group"> - <input type="text" class="form-control" placeholder="Search"> - </div> - <button type="submit" class="btn btn-default">Submit</button> - </form> - <ul class="nav navbar-nav navbar-right"> - <li><a href="http://github.com/apache/mahout">Github</a></li> - - <!-- Apache --> - <li class="dropdown"> - <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Apache <span class="caret"></span></a> - <ul class="dropdown-menu"> - <li><a href="http://www.apache.org/foundation/how-it-works.html">Apache Software Foundation</a></li> - <li><a href="http://www.apache.org/licenses/">Apache License</a></li> - <li><a href="http://www.apache.org/foundation/sponsorship.html">Sponsorship</a></li> - <li><a href="http://www.apache.org/foundation/thanks.html">Thanks</a></li> - </ul> - </li> + <link rel="canonical" href="http://mahout.apache.org//docs/latest/algorithms/map-reduce/clustering/latent-dirichlet-allocation.html"> + <link rel="alternate" type="application/rss+xml" title="Apache Mahout" href="/%20/feed.xml"> - </ul> -</div><!-- /.navbar-collapse --> - </div><!-- /.container-fluid --> -</nav> +</head> + <body> -<div id="wrap"> - <body class=""> + <nav class="navbar navbar-expand-lg navbar-light bg-light navbar-mahout"> + + <div class="container"> + + <a class="navbar-brand" href="/"> + <img src="/assets/mahout-logo-blue.svg" alt=""> + </a> + + <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbarSupportedContent" aria-controls="navbarSupportedContent" aria-expanded="false" aria-label="Toggle navigation"> + <span class="navbar-toggler-icon"></span> + </button> + + <div class="collapse navbar-collapse" id="navbarSupportedContent"> + + <div class="navbar-nav ml-auto"> + + <!-- Quick Start --> + <li class="nav-item"> + <a class="nav-link" href="//docs/latest/" >Mahout Overview</a> + </li> + + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Key Concepts</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <a class="dropdown-item" href="/docs/latest/index.html">Mahout Overview</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Scala DSL</h6> + <a class="dropdown-item" href="/docs/latest/mahout-samsara/in-core-reference.html">In-core Reference</a> + <a class="dropdown-item" href="/docs/latest/mahout-samsara/out-of-core-reference.html">Out-of-core Reference</a> + <a class="dropdown-item" href="/docs/latest/mahout-samsara/faq.html">Samsara FAQ</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Distributed Engine Bindings</h6> + <a class="dropdown-item" href="/docs/latest/distributed/spark-bindings/">Spark Bindings</a> + <a class="dropdown-item" href="/docs/latest/distributed/flink-bindings.html">Flink Bindings</a> + <a class="dropdown-item" href="/docs/latest/distributed/flink-bindings.html">H20 Bindings</a> + <!--<div class="dropdown-divider"></div> + <h6 class="dropdown-header">Native Solvers</h6> + <a class="dropdown-item" href="/docs/latest/native-solvers/viennacl.html">ViennaCL</a></li> + <a class="dropdown-item" href="/docs/latest/native-solvers/viennacl-omp.html">ViennaCL-OMP</a></li> + <a class="dropdown-item" href="/docs/latest/native-solvers/cuda.html">CUDA</a></li>--> + </div> + </li> + + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Tutorial</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Reccomenders</h6> + <a class="dropdown-item" href="/docs/latest/tutorials/cco-lastfm">CCO Example with Last.FM Data</a> + <a class="dropdown-item" href="/docs/latest/tutorials/intro-cooccurrence-spark">Introduction to Cooccurrence in Spark</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Mahout Samsara</h6> + <a class="dropdown-item" href="/docs/latest/tutorials/samsara/play-with-shell.html">Playing with Samsara in Spark Shell</a> + <a class="dropdown-item" href="/docs/latest/tutorials/samsara/playing-with-samsara-flink-batch.html">Playing with Samsara in Flink Batch</a> + <a class="dropdown-item" href="/docs/latest/tutorials/samsara/classify-a-doc-from-the-shell.html">Text Classification (Shell)</a> + <a class="dropdown-item" href="/docs/latest/tutorials/samsara/spark-naive-bayes.html">Spark Naive Bayes</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Misc</h6> + <a class="dropdown-item" href="/docs/latest/tutorials/misc/mahout-in-zeppelin">Mahout in Apache Zeppelin</a> + <a class="dropdown-item" href="/docs/latest/tutorials/misc/contributing-algos">How To Contribute a New Algorithm</a> + <a class="dropdown-item" href="/docs/latest/tutorials/misc/how-to-build-an-app.html">How To Build An App</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Deprecated</h6> + <a class="dropdown-item" href="/docs/latest/tutorials/map-reduce">MapReduce</a> + </div> + </li> + + + <!-- Algorithms (Samsara / MR) --> + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Algorithms</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <a class="dropdown-item" href="/docs/latest/algorithms/linear-algebra">Distributed Linear Algebra</a> + <a class="dropdown-item" href="/docs/latest/algorithms/preprocessors">Preprocessors</a> + <a class="dropdown-item" href="/docs/latest/algorithms/regression">Regression</a> + <a class="dropdown-item" href="/docs/latest/algorithms/reccomenders">Reccomenders</a> + <div class="dropdown-divider"></div> + <h6 class="dropdown-header">Deprecated</h6> + <a class="dropdown-item" href="/docs/latest/algorithms/map-reduce">MapReduce <i>(deprecated)</i></a> + </div> + <!--<a class="dropdown-item" href="/docs/latest/algorithms/reccomenders/recommender-overview.html">Reccomender Overview</a></li> Do we still need? seems like short version of next post--> + <!-- + <a class="dropdown-item" href="/docs/latest/algorithms/reccomenders/intro-cooccurrence-spark.html">Intro to Coocurrence With Spark</a></li> + <li role="separator" class="divider"></li> + <li><span> <a href="/docs/latest/algorithms/map-reduce"><b>MapReduce</b> (deprecated)</a><span></li> + + + --> + </li> + + <!-- Scala /docs --> + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">API /docs</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <a class="dropdown-item" href="/docs/latest/0.13.0/api/index.html">0.13.0</a> + </div> + </li> + + <!-- Apache --> + <li class="nav-item dropdown"> + <a class="nav-link dropdown-toggle" href="" id="navbarDropdownMenuLink" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Apache</a> + <div class="dropdown-menu" aria-labelledby="navbarDropdownMenuLink"> + <a class="dropdown-item" href="http://www.apache.org/foundation/how-it-works.html">Apache Software Foundation</a> + <a class="dropdown-item" href="http://www.apache.org/licenses/">Apache License</a> + <a class="dropdown-item" href="http://www.apache.org/foundation/sponsorship.html">Sponsorship</a> + <a class="dropdown-item" href="http://www.apache.org/foundation/thanks.html">Thanks</a> + </div> + </li> - <div class="container"> - + </ul> + + <!--<form class="navbar-form navbar-left">--> + <!--<div class="form-group">--> + <!--<input type="text" class="form-control" placeholder="Search">--> + <!--</div>--> + <!--<button type="submit" class="btn btn-default">Submit</button>--> + <!--</form>--> + <!--<ul class="nav navbar-nav navbar-right">--> + <!--<a class="dropdown-item" href="http://github.com/apache/mahout">Github</a></li>--> -<div class="row"> - <div class="col-md-3"> - <div id="AlgoMenu"> - <span><b>Mahout-Samsara Algorithms</b></span> - <div class="list-group panel"> - <a href="#linalg" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Linear Algebra</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="linalg"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/linear-algebra/d-qr.html">Distributed QR Decomposition</a></li> - <li> <a href="/algorithms/linear-algebra/d-spca.html">Distributed Stochastic Principal Component Analysis</a></li> - <li> <a href="/algorithms/linear-algebra/d-ssvd.html">Distributed Stochastic Singular Value Decomposition</a></li> - </ul> - </div> - <a href="#clustering" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Clustering</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="clustering"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/clustering">Clustering Algorithms</a></li> - <li> <a href="/algorithms/clustering/distance-metrics.html">Distance Metrics</a></li> - <li> <a href="/algorithms/clustering/canopy">Canopy Clustering</a></li> - </ul> - </div> - <a href="#preprocessors" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Preprocessors</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="preprocessors"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/preprocessors/AsFactor.html">AsFactor (a.k.a. One-Hot-Encoding)</a></li> - <li> <a href="/algorithms/preprocessors/StandardScaler.html">StandardScaler</a></li> - <li> <a href="/algorithms/preprocessors/MeanCenter.html">MeanCenter</a></li> - </ul> - </div> - <a href="#regression" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Regression</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="regression"> - <ul class="nav sidebar-nav"> - <a href="#serial-correlation" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#regression"><b>• Serial Correlation</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="serial-correlation"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/regression/serial-correlation/cochrane-orcutt.html">Cochrane-Orcutt Procedure</a></li> - <li> <a href="/algorithms/regression/serial-correlation/dw-test.html">Durbin Watson Test</a></li> - </ul> - </div> - <li> <a href="/algorithms/regression/ols.html">Ordinary Least Squares (Closed Form)</a></li> - <li> <a href="/algorithms/regression/fittness-tests.html">Fitness Tests</a></li> - </ul> - </div> - <a href="#reccomenders" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Reccomenders</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="reccomenders"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/reccomenders">Reccomender Overview</a></li> - <li> <a href="/algorithms/reccomenders/cco.html">CCO</a></li> - <li> <a href="/algorithms/reccomenders/d-als.html">Distributed Alternating Least Squares</a></li> - </ul> - </div> - </div> - <span><b>Map Reduce Algorithms</b> (deprecated)</span> - <div class="list-group panel"> - <a href="#classification" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Classification</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="classification"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/map-reduce/classification/bayesian.html">Bayesian</a></li> - <li> <a href="/algorithms/map-reduce/classification/class-discovery.html">Class Discovery</a></li> - <li> <a href="/algorithms/map-reduce/classification/classifyingyourdata.html">Classifying Your Data</a></li> - <li> <a href="/algorithms/map-reduce/classification/collocations.html">Collocation</a></li> - <li> <a href="/algorithms/map-reduce/classification/gaussian-discriminative-analysis.html">Gaussian Discriminative Analysis</a></li> - <li> <a href="/algorithms/map-reduce/classification/hidden-markov-models.html">Hidden Markov Models</a></li> - <li> <a href="/algorithms/map-reduce/classification/independent-component-analysis.html">Independent Component Analysis</a></li> - <li> <a href="/algorithms/map-reduce/classification/locally-weighted-linear-regression.html">Locally Weighted Linear Regression</a></li> - <li> <a href="/algorithms/map-reduce/classification/logistic-regression.html">Logistic Regression</a></li> - <li> <a href="/algorithms/map-reduce/classification/mahout-collections.html">Mahout Collections</a></li> - <li> <a href="/algorithms/map-reduce/classification/mlp.html">Multilayer Perceptron</a></li> - <li> <a href="/algorithms/map-reduce/classification/naivebayes.html">Naive Bayes</a></li> - <li> <a href="/algorithms/map-reduce/classification/neural-network.html">Neural Networks</a></li> - <li> <a href="/algorithms/map-reduce/classification/partial-implementation.html">Partial Implementation</a></li> - <li> <a href="/algorithms/map-reduce/classification/random-forrests.html">Random Forrests</a></li> - <li> <a href="/algorithms/map-reduce/classification/restricted-boltzman-machines.html">Restricted Boltzman Machines</a></li> - <li> <a href="/algorithms/map-reduce/classification/support-vector-machines.html">Support Vector Machines</a></li> - </ul> - </div> - <a href="#mr-clustering" class="list-group-item list-group-item-success" data-toggle="collapse" data-parent="#AlgoMenu"><b>Clustering</b><i class="fa fa-caret-down"></i></a> - <div class="collapse" id="mr-clustering"> - <ul class="nav sidebar-nav"> - <li> <a href="/algorithms/map-reduce/clustering/canopy-clustering.html">Canopy Clustering</a></li> - <li> <a href="/algorithms/map-reduce/clustering/cluster-dumper.html">Cluster Dumper</a></li> - <li> <a href="/algorithms/map-reduce/clustering/expectation-maximization.html">Expectation Maximization</a></li> - <li> <a href="/algorithms/map-reduce/clustering/fuzzy-k-means.html">Fuzzy K-Means</a></li> - <li> <a href="/algorithms/map-reduce/clustering/hierarchical-clustering.html">Hierarchical Clustering</a></li> - <li> <a href="/algorithms/map-reduce/clustering/k-means-clustering.html">K-Means Clustering</a></li> - <li> <a href="/algorithms/map-reduce/clustering/latent-dirichlet-allocation.html">Latent Dirichlet Allocation</a></li> - <li> <a href="/algorithms/map-reduce/clustering/llr---log-likelihood-ratio.html">Log Likelihood Ratio</a></li> - <li> <a href="/algorithms/map-reduce/clustering/spectral-clustering.html">Spectral Clustering</a></li> - <li> <a href="/algorithms/map-reduce/clustering/streaming-k-means.html">Streaming K-Means</a></li> - </ul> - </div> - </div> -</div> + <!--</ul>--> + </div><!-- /.navbar-collapse --> </div> +</nav> - <div class="col-md-8"> - <div class="page-header"> - <h1>(Deprecated) Latent Dirichlet Allocation </h1> - </div> - <p><a name="LatentDirichletAllocation-Overview"></a></p> + <div class="container mt-5 pb-4"> + + <div class="row"> + + <div class="col-lg-8"> + <p><a name="LatentDirichletAllocation-Overview"></a></p> <h1 id="overview">Overview</h1> <p>Latent Dirichlet Allocation (Blei et al, 2003) is a powerful learning @@ -377,7 +234,7 @@ vectors, itâs recommended that you follow the instructions in <a href="../basi <p>Invocation takes the form:</p> -<pre><code>bin/mahout cvb \ +<div class="highlighter-rouge"><pre class="highlight"><code>bin/mahout cvb \ -i <input path for document vectors> \ -dict <path to term-dictionary file(s) , glob expression supported> \ -o <output path for topic-term distributions> @@ -393,6 +250,7 @@ vectors, itâs recommended that you follow the instructions in <a href="../basi -tf <fraction of data to hold for testing> \ -block <number of iterations per perplexity check, ignored unless test_set_percentage>0> \ </code></pre> +</div> <p>Topic smoothing should generally be about 50/K, where K is the number of topics. The number of words in the vocabulary can be an upper bound, though @@ -404,7 +262,7 @@ recommended that you try several values.</p> <p>After running LDA you can obtain an output of the computed topics using the LDAPrintTopics utility:</p> -<pre><code>bin/mahout ldatopics \ +<div class="highlighter-rouge"><pre class="highlight"><code>bin/mahout ldatopics \ -i <input vectors directory> \ -d <input dictionary file> \ -w <optional number of words to print> \ @@ -412,6 +270,7 @@ LDAPrintTopics utility:</p> -h <print out help> \ -dt <optional dictionary type (text|sequencefile). Default is text> </code></pre> +</div> <p><a name="LatentDirichletAllocation-Example"></a></p> <h1 id="example">Example</h1> @@ -452,32 +311,25 @@ post-processing step.</p> <p><a href="-http://aclweb.org/anthology//D/D08/D08-1038.pdf">David Hall, Dan Jurafsky, and Christopher D. Manning. 2008. Studying the History of Ideas Using Topic Models </a></p> </div> -</div> - </div> - - -</div> -<div id="footer"> - <div class="container"> - <p>© 2017 Apache Mahout - with help from <a href="http://jekyllbootstrap.com" target="_blank" title="The Definitive Jekyll Blogging Framework">Jekyll Bootstrap</a> - and <a href="http://getbootstrap.com" target="_blank">Bootstrap</a> - </p> </div> -</div> - - +</div> + <footer class="footer bg-light"> + <div class="container text-center small"> + Copyright © 2014-2017 The Apache Software Foundation, Licensed under the Apache License, Version 2.0. + </div> +</footer> + <script src="/assets/vendor/jquery/jquery-slim.min.js"></script> + <script src="/assets/vendor/popper/popper.min.js"></script> + <script src="/assets/vendor/bootstrap/js/bootstrap.min.js"></script> + <script src="/assets/header.js"></script> + <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script> -<!-- Latest compiled and minified JavaScript, requires jQuery 1.x (2.x not supported in IE8) --> -<!-- Placed at the end of the document so the pages load faster --> -<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script> -<script src="/assets/themes/mahout3/js/bootstrap.min.js"></script> </body> -</html> +</html>
