http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/c811983d/system/index.html ---------------------------------------------------------------------- diff --git a/system/index.html b/system/index.html new file mode 100644 index 0000000..7a0453f --- /dev/null +++ b/system/index.html @@ -0,0 +1,6 @@ +<!DOCTYPE html><html><head><title>System Architecture and Dependencies</title><meta charset="utf-8"/><meta content="IE=edge,chrome=1" http-equiv="X-UA-Compatible"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><meta class="swiftype" name="title" data-type="string" content="System Architecture and Dependencies"/><link rel="canonical" href="https://docs.prediction.io/system/"/><link href="/images/favicon/normal-b330020a.png" rel="shortcut icon"/><link href="/images/favicon/apple-c0febcf2.png" rel="apple-touch-icon"/><link href="//fonts.googleapis.com/css?family=Open+Sans:300italic,400italic,600italic,700italic,800italic,400,300,600,700,800" rel="stylesheet"/><link href="//maxcdn.bootstrapcdn.com/font-awesome/4.2.0/css/font-awesome.min.css" rel="stylesheet"/><link href="/stylesheets/application-a2a2f408.css" rel="stylesheet" type="text/css"/><script src="//cdnjs.cloudflare.com/ajax/libs/html5shiv/3.7.2/html5shiv.min.js"></script><script src="//cdn.mathjax.org/m athjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script><script src="//use.typekit.net/pqo0itb.js"></script><script>try{Typekit.load({ async: true });}catch(e){}</script></head><body><div id="global"><header><div class="container" id="header-wrapper"><div class="row"><div class="col-sm-12"><div id="logo-wrapper"><span id="drawer-toggle"></span><a href="#"></a><a href="http://predictionio.incubator.apache.org/";><img alt="PredictionIO" id="logo" src="/images/logos/logo-ee2b9bb3.png"/></a></div><div id="menu-wrapper"><div id="pill-wrapper"><a class="pill left" href="/gallery/template-gallery">TEMPLATES</a> <a class="pill right" href="//github.com/apache/incubator-predictionio/">OPEN SOURCE</a></div></div><img class="mobile-search-bar-toggler hidden-md hidden-lg" src="/images/icons/search-glass-704bd4ff.png"/></div></div></div></header><div id="search-bar-row-wrapper"><div class="container-fluid" id="search-bar-row"><div class="row"><div class="col-md-9 col-sm-11 col-xs-11"><div class="hidden-md hidden-lg" id="mobile-page-heading-wrapper"><p>PredictionIO Docs</p><h4>Architecture Overview</h4></div><h4 class="hidden-sm hidden-xs">PredictionIO Docs</h4></div><div class="col-md-3 col-sm-1 col-xs-1 hidden-md hidden-lg"><img id="left-menu-indicator" src="/images/icons/down-arrow-dfe9f7fe.png"/></div><div class="col-md-3 col-sm-12 col-xs-12 swiftype-wrapper"><div class="swiftype"><form class="search-form"><img class="search-box-toggler hidden-xs hidden-sm" src="/images/icons/search-glass-704bd4ff.png"/><div class="search-box"><img src="/images/icons/search-glass-704bd4ff.png"/><input type="text" id="st-search-input" class="st-search-input" placeholder="Search Doc..."/></div><img class="swiftype-row-hider hidden-md hidden-lg" src="/images/icons/drawer-toggle-active-fcbef12a.png"/></form></div></div><div class="mobile-left-menu-toggler hidden-md hidden-lg"></div></div></div></div><div id="page" class="container-fluid"><div class="row"><div id="left-menu-wrapper" c lass="col-md-3"><nav id="nav-main"><ul><li class="level-1"><a class="expandible" href="/"><span>Apache PredictionIO (incubating) Documentation</span></a><ul><li class="level-2"><a class="final" href="/"><span>Welcome to Apache PredictionIO (incubating)</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Getting Started</span></a><ul><li class="level-2"><a class="final" href="/start/"><span>A Quick Intro</span></a></li><li class="level-2"><a class="final" href="/install/"><span>Installing Apache PredictionIO (incubating)</span></a></li><li class="level-2"><a class="final" href="/start/download/"><span>Downloading an Engine Template</span></a></li><li class="level-2"><a class="final" href="/start/deploy/"><span>Deploying Your First Engine</span></a></li><li class="level-2"><a class="final" href="/start/customize/"><span>Customizing the Engine</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Integrating with Your App</span> </a><ul><li class="level-2"><a class="final" href="/appintegration/"><span>App Integration Overview</span></a></li><li class="level-2"><a class="expandible" href="/sdk/"><span>List of SDKs</span></a><ul><li class="level-3"><a class="final" href="/sdk/java/"><span>Java & Android SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/php/"><span>PHP SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/python/"><span>Python SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/ruby/"><span>Ruby SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/community/"><span>Community Powered SDKs</span></a></li></ul></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Deploying an Engine</span></a><ul><li class="level-2"><a class="final" href="/deploy/"><span>Deploying as a Web Service</span></a></li><li class="level-2"><a class="final" href="/cli/#engine-commands"><span>Engine Command-line Interface</span></a></li><li class ="level-2"><a class="final" href="/deploy/monitoring/"><span>Monitoring Engine</span></a></li><li class="level-2"><a class="final" href="/deploy/engineparams/"><span>Setting Engine Parameters</span></a></li><li class="level-2"><a class="final" href="/deploy/enginevariants/"><span>Deploying Multiple Engine Variants</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Customizing an Engine</span></a><ul><li class="level-2"><a class="final" href="/customize/"><span>Learning DASE</span></a></li><li class="level-2"><a class="final" href="/customize/dase/"><span>Implement DASE</span></a></li><li class="level-2"><a class="final" href="/customize/troubleshooting/"><span>Troubleshooting Engine Development</span></a></li><li class="level-2"><a class="final" href="/api/current/#package"><span>Engine Scala APIs</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Collecting and Analyzing Data</span></a><ul><li class="level-2"><a class="f inal" href="/datacollection/"><span>Event Server Overview</span></a></li><li class="level-2"><a class="final" href="/cli/#event-server-commands"><span>Event Server Command-line Interface</span></a></li><li class="level-2"><a class="final" href="/datacollection/eventapi/"><span>Collecting Data with REST/SDKs</span></a></li><li class="level-2"><a class="final" href="/datacollection/eventmodel/"><span>Events Modeling</span></a></li><li class="level-2"><a class="final" href="/datacollection/webhooks/"><span>Unifying Multichannel Data with Webhooks</span></a></li><li class="level-2"><a class="final" href="/datacollection/channel/"><span>Channel</span></a></li><li class="level-2"><a class="final" href="/datacollection/batchimport/"><span>Importing Data in Batch</span></a></li><li class="level-2"><a class="final" href="/datacollection/analytics/"><span>Using Analytics Tools</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Choosing an Algorithm(s)</span></a> <ul><li class="level-2"><a class="final" href="/algorithm/"><span>Built-in Algorithm Libraries</span></a></li><li class="level-2"><a class="final" href="/algorithm/switch/"><span>Switching to Another Algorithm</span></a></li><li class="level-2"><a class="final" href="/algorithm/multiple/"><span>Combining Multiple Algorithms</span></a></li><li class="level-2"><a class="final" href="/algorithm/custom/"><span>Adding Your Own Algorithms</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>ML Tuning and Evaluation</span></a><ul><li class="level-2"><a class="final" href="/evaluation/"><span>Overview</span></a></li><li class="level-2"><a class="final" href="/evaluation/paramtuning/"><span>Hyperparameter Tuning</span></a></li><li class="level-2"><a class="final" href="/evaluation/evaluationdashboard/"><span>Evaluation Dashboard</span></a></li><li class="level-2"><a class="final" href="/evaluation/metricchoose/"><span>Choosing Evaluation Metrics</span></a></li><l i class="level-2"><a class="final" href="/evaluation/metricbuild/"><span>Building Evaluation Metrics</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>System Architecture</span></a><ul><li class="level-2"><a class="final active" href="/system/"><span>Architecture Overview</span></a></li><li class="level-2"><a class="final" href="/system/anotherdatastore/"><span>Using Another Data Store</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Engine Template Gallery</span></a><ul><li class="level-2"><a class="final" href="/gallery/template-gallery/"><span>Browse</span></a></li><li class="level-2"><a class="final" href="/community/submit-template/"><span>Submit your Engine as a Template</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Demo Tutorials</span></a><ul><li class="level-2"><a class="final" href="/demo/tapster/"><span>Comics Recommendation Demo</span></a></li><li class="level-2"><a class ="final" href="/demo/community/"><span>Community Contributed Demo</span></a></li><li class="level-2"><a class="final" href="/demo/textclassification/"><span>Text Classification Engine Tutorial</span></a></li></ul></li><li class="level-1"><a class="expandible" href="/community/"><span>Getting Involved</span></a><ul><li class="level-2"><a class="final" href="/community/contribute-code/"><span>Contribute Code</span></a></li><li class="level-2"><a class="final" href="/community/contribute-documentation/"><span>Contribute Documentation</span></a></li><li class="level-2"><a class="final" href="/community/contribute-sdk/"><span>Contribute a SDK</span></a></li><li class="level-2"><a class="final" href="/community/contribute-webhook/"><span>Contribute a Webhook</span></a></li><li class="level-2"><a class="final" href="/community/projects/"><span>Community Projects</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Getting Help</span></a><ul><li class="level-2"> <a class="final" href="/resources/faq/"><span>FAQs</span></a></li><li class="level-2"><a class="final" href="/support/"><span>Support</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Resources</span></a><ul><li class="level-2"><a class="final" href="/resources/intellij/"><span>Developing Engines with IntelliJ IDEA</span></a></li><li class="level-2"><a class="final" href="/resources/upgrade/"><span>Upgrade Instructions</span></a></li><li class="level-2"><a class="final" href="/resources/glossary/"><span>Glossary</span></a></li></ul></li></ul></nav></div><div class="col-md-9 col-sm-12"><div class="content-header hidden-md hidden-lg"><div id="breadcrumbs" class="hidden-sm hidden xs"><ul><li><a href="#">System Architecture</a><span class="spacer">></span></li><li><span class="last">Architecture Overview</span></li></ul></div><div id="page-title"><h1>System Architecture and Dependencies</h1></div></div><div id="table-of-content-wrapper"><a id="edit-pag e-link" href="https://github.com/apache/incubator-predictionio/tree/livedoc/docs/manual/source/system/index.html.md";><img src="/images/icons/edit-pencil-d6c1bb3d.png"/>Edit this page</a></div><div class="content-header hidden-sm hidden-xs"><div id="breadcrumbs" class="hidden-sm hidden xs"><ul><li><a href="#">System Architecture</a><span class="spacer">></span></li><li><span class="last">Architecture Overview</span></li></ul></div><div id="page-title"><h1>System Architecture and Dependencies</h1></div></div><div class="content"><p>During the <a href="/install">installation</a>, you have installed the latest stable versions of the following software:</p> <ul> <li>Apache Hadoop up to 2.7.2 (required only if YARN and HDFS are needed)</li> <li>Apache HBase up to 1.2.4</li> <li>Apache Spark up to 1.6.3 for Hadoop 2.6 (not Spark 2.x version)</li> <li>Elasticsearch up to 1.7.5 (not the Elasticsearch 2.x version)</li> </ul> <p>This section explains general rules-of-thumb for how they are used in PredictionIO. The actual implementation of the Template will define how much of this applies. PredictionIO is flexible about much of this configuration but its Templates generally fit the Lambda model for integrating real-time serving with background periodic model updates. </p><p><img alt="PredictionIO Systems" src="/images/pio-architecture-a1e2a38c.svg"/></p><p><strong>HBase</strong>: Event Server uses Apache HBase (or JDBC DB for small data) as the data store. It stores imported events. If you are not using the PredictionIO Event Server, you do not need to install HBase.</p><p><strong>Apache Spark</strong>: Spark is a large-scale data processing engine that powers the data preparation and input to the algorithm, training, and sometimes the serving processing. PredictionIO allows for different engines to be used in training but many algorithms come from Spark's MLlib. </p><p><strong>HDFS</strong>: is a distributed filesystem from Hadoop. It allows storage to be shared among clustered machines. It is used to stage data for batch import into PIO, for export of Event Server datasets, and for storage of some models (see your template for details).</p><p>The output of training has two parts: a model and its meta-data. The model is then stored in HDFS, a local file system, or Elasticsearch. See the details of your algorithm.</p><p><strong>Elasticsearch</strong>: stores metadata such as model versions, engine versions, access key and app id mappings, evaluation results, etc. For some templates it may store the model.</p></div></div></div></div><footer><div class="container"><div class="seperator"></div><div class="row"><div class="col-md-6 col-xs-6 footer-link-column"><div class="footer-link-column-row"><h4>Community</h4><ul><li><a href="//docs.prediction.io/install/" target="blank">Download</a></li><li><a href="//docs.prediction.io/" target="blank">Docs</a></li><li><a href="//github.com/apache/incubator-predictionio" target="blank">GitHub</a></li><li>< a href="mailto:user-subscr...@predictionio.incubator.apache.org"; target="blank">Subscribe to User Mailing List</a></li><li><a href="//stackoverflow.com/questions/tagged/predictionio" target="blank">Stackoverflow</a></li></ul></div></div><div class="col-md-6 col-xs-6 footer-link-column"><div class="footer-link-column-row"><h4>Contribute</h4><ul><li><a href="//predictionio.incubator.apache.org/community/contribute-code/" target="blank">Contribute</a></li><li><a href="//github.com/apache/incubator-predictionio" target="blank">Source Code</a></li><li><a href="//issues.apache.org/jira/browse/PIO" target="blank">Bug Tracker</a></li><li><a href="mailto:dev-subscr...@predictionio.incubator.apache.org"; target="blank">Subscribe to Development Mailing List</a></li></ul></div></div></div></div><div id="footer-bottom"><div class="container"><div class="row"><div class="col-md-12"><div id="footer-logo-wrapper"><img alt="PredictionIO" src="/images/logos/logo-white-d1e9c6e6.png"/></div><div id="soc ial-icons-wrapper"><a class="github-button" href="https://github.com/apache/incubator-predictionio"; data-style="mega" data-count-href="/apache/incubator-predictionio/stargazers" data-count-api="/repos/apache/incubator-predictionio#stargazers_count" data-count-aria-label="# stargazers on GitHub" aria-label="Star apache/incubator-predictionio on GitHub">Star</a> <a class="github-button" href="https://github.com/apache/incubator-predictionio/fork"; data-icon="octicon-git-branch" data-style="mega" data-count-href="/apache/incubator-predictionio/network" data-count-api="/repos/apache/incubator-predictionio#forks_count" data-count-aria-label="# forks on GitHub" aria-label="Fork apache/incubator-predictionio on GitHub">Fork</a> <script id="github-bjs" async="" defer="" src="https://buttons.github.io/buttons.js";></script><a href="//www.facebook.com/predictionio" target="blank"><img alt="PredictionIO on Twitter" src="/images/icons/twitter-ea9dc152.png"/></a> <a href="//twitter.com/predictioni o" target="blank"><img alt="PredictionIO on Facebook" src="/images/icons/facebook-5c57939c.png"/></a> </div></div></div></div></div></footer></div><script>(function(w,d,t,u,n,s,e){w['SwiftypeObject']=n;w[n]=w[n]||function(){ +(w[n].q=w[n].q||[]).push(arguments);};s=d.createElement(t); +e=d.getElementsByTagName(t)[0];s.async=1;s.src=u;e.parentNode.insertBefore(s,e); +})(window,document,'script','//s.swiftypecdn.com/install/v1/st.js','_st'); + +_st('install','HaUfpXXV87xoB_zzCQ45');</script><script src="/javascripts/application-f819cf19.js"></script></body></html> \ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/c811983d/system/index.html.gz ---------------------------------------------------------------------- diff --git a/system/index.html.gz b/system/index.html.gz new file mode 100644 index 0000000..95e4395 Binary files /dev/null and b/system/index.html.gz differ http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/c811983d/templates/classification/add-algorithm/index.html ---------------------------------------------------------------------- diff --git a/templates/classification/add-algorithm/index.html b/templates/classification/add-algorithm/index.html new file mode 100644 index 0000000..a760e54 --- /dev/null +++ b/templates/classification/add-algorithm/index.html @@ -0,0 +1,147 @@ +<!DOCTYPE html><html><head><title>Using Alternative Algorithm</title><meta charset="utf-8"/><meta content="IE=edge,chrome=1" http-equiv="X-UA-Compatible"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><meta class="swiftype" name="title" data-type="string" content="Using Alternative Algorithm"/><link rel="canonical" href="https://docs.prediction.io/templates/classification/add-algorithm/"/><link href="/images/favicon/normal-b330020a.png" rel="shortcut icon"/><link href="/images/favicon/apple-c0febcf2.png" rel="apple-touch-icon"/><link href="//fonts.googleapis.com/css?family=Open+Sans:300italic,400italic,600italic,700italic,800italic,400,300,600,700,800" rel="stylesheet"/><link href="//maxcdn.bootstrapcdn.com/font-awesome/4.2.0/css/font-awesome.min.css" rel="stylesheet"/><link href="/stylesheets/application-a2a2f408.css" rel="stylesheet" type="text/css"/><script src="//cdnjs.cloudflare.com/ajax/libs/html5shiv/3.7.2/html5shiv.min.js"></script><script src="//cdn .mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script><script src="//use.typekit.net/pqo0itb.js"></script><script>try{Typekit.load({ async: true });}catch(e){}</script></head><body><div id="global"><header><div class="container" id="header-wrapper"><div class="row"><div class="col-sm-12"><div id="logo-wrapper"><span id="drawer-toggle"></span><a href="#"></a><a href="http://predictionio.incubator.apache.org/";><img alt="PredictionIO" id="logo" src="/images/logos/logo-ee2b9bb3.png"/></a></div><div id="menu-wrapper"><div id="pill-wrapper"><a class="pill left" href="/gallery/template-gallery">TEMPLATES</a> <a class="pill right" href="//github.com/apache/incubator-predictionio/">OPEN SOURCE</a></div></div><img class="mobile-search-bar-toggler hidden-md hidden-lg" src="/images/icons/search-glass-704bd4ff.png"/></div></div></div></header><div id="search-bar-row-wrapper"><div class="container-fluid" id="search-bar-row"><div class="row"><div class="col-md-9 col-sm-11 c ol-xs-11"><div class="hidden-md hidden-lg" id="mobile-page-heading-wrapper"><p>PredictionIO Docs</p><h4>Using Alternative Algorithm</h4></div><h4 class="hidden-sm hidden-xs">PredictionIO Docs</h4></div><div class="col-md-3 col-sm-1 col-xs-1 hidden-md hidden-lg"><img id="left-menu-indicator" src="/images/icons/down-arrow-dfe9f7fe.png"/></div><div class="col-md-3 col-sm-12 col-xs-12 swiftype-wrapper"><div class="swiftype"><form class="search-form"><img class="search-box-toggler hidden-xs hidden-sm" src="/images/icons/search-glass-704bd4ff.png"/><div class="search-box"><img src="/images/icons/search-glass-704bd4ff.png"/><input type="text" id="st-search-input" class="st-search-input" placeholder="Search Doc..."/></div><img class="swiftype-row-hider hidden-md hidden-lg" src="/images/icons/drawer-toggle-active-fcbef12a.png"/></form></div></div><div class="mobile-left-menu-toggler hidden-md hidden-lg"></div></div></div></div><div id="page" class="container-fluid"><div class="row"><div id=" left-menu-wrapper" class="col-md-3"><nav id="nav-main"><ul><li class="level-1"><a class="expandible" href="/"><span>Apache PredictionIO (incubating) Documentation</span></a><ul><li class="level-2"><a class="final" href="/"><span>Welcome to Apache PredictionIO (incubating)</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Getting Started</span></a><ul><li class="level-2"><a class="final" href="/start/"><span>A Quick Intro</span></a></li><li class="level-2"><a class="final" href="/install/"><span>Installing Apache PredictionIO (incubating)</span></a></li><li class="level-2"><a class="final" href="/start/download/"><span>Downloading an Engine Template</span></a></li><li class="level-2"><a class="final" href="/start/deploy/"><span>Deploying Your First Engine</span></a></li><li class="level-2"><a class="final" href="/start/customize/"><span>Customizing the Engine</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Integrating with Your App</span></a><ul><li class="level-2"><a class="final" href="/appintegration/"><span>App Integration Overview</span></a></li><li class="level-2"><a class="expandible" href="/sdk/"><span>List of SDKs</span></a><ul><li class="level-3"><a class="final" href="/sdk/java/"><span>Java & Android SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/php/"><span>PHP SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/python/"><span>Python SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/ruby/"><span>Ruby SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/community/"><span>Community Powered SDKs</span></a></li></ul></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Deploying an Engine</span></a><ul><li class="level-2"><a class="final" href="/deploy/"><span>Deploying as a Web Service</span></a></li><li class="level-2"><a class="final" href="/cli/#engine-commands"><span>Engine Command-line Interface</spa n></a></li><li class="level-2"><a class="final" href="/deploy/monitoring/"><span>Monitoring Engine</span></a></li><li class="level-2"><a class="final" href="/deploy/engineparams/"><span>Setting Engine Parameters</span></a></li><li class="level-2"><a class="final" href="/deploy/enginevariants/"><span>Deploying Multiple Engine Variants</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Customizing an Engine</span></a><ul><li class="level-2"><a class="final" href="/customize/"><span>Learning DASE</span></a></li><li class="level-2"><a class="final" href="/customize/dase/"><span>Implement DASE</span></a></li><li class="level-2"><a class="final" href="/customize/troubleshooting/"><span>Troubleshooting Engine Development</span></a></li><li class="level-2"><a class="final" href="/api/current/#package"><span>Engine Scala APIs</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Collecting and Analyzing Data</span></a><ul><li class=" level-2"><a class="final" href="/datacollection/"><span>Event Server Overview</span></a></li><li class="level-2"><a class="final" href="/cli/#event-server-commands"><span>Event Server Command-line Interface</span></a></li><li class="level-2"><a class="final" href="/datacollection/eventapi/"><span>Collecting Data with REST/SDKs</span></a></li><li class="level-2"><a class="final" href="/datacollection/eventmodel/"><span>Events Modeling</span></a></li><li class="level-2"><a class="final" href="/datacollection/webhooks/"><span>Unifying Multichannel Data with Webhooks</span></a></li><li class="level-2"><a class="final" href="/datacollection/channel/"><span>Channel</span></a></li><li class="level-2"><a class="final" href="/datacollection/batchimport/"><span>Importing Data in Batch</span></a></li><li class="level-2"><a class="final" href="/datacollection/analytics/"><span>Using Analytics Tools</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Choosing an Alg orithm(s)</span></a><ul><li class="level-2"><a class="final" href="/algorithm/"><span>Built-in Algorithm Libraries</span></a></li><li class="level-2"><a class="final" href="/algorithm/switch/"><span>Switching to Another Algorithm</span></a></li><li class="level-2"><a class="final" href="/algorithm/multiple/"><span>Combining Multiple Algorithms</span></a></li><li class="level-2"><a class="final" href="/algorithm/custom/"><span>Adding Your Own Algorithms</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>ML Tuning and Evaluation</span></a><ul><li class="level-2"><a class="final" href="/evaluation/"><span>Overview</span></a></li><li class="level-2"><a class="final" href="/evaluation/paramtuning/"><span>Hyperparameter Tuning</span></a></li><li class="level-2"><a class="final" href="/evaluation/evaluationdashboard/"><span>Evaluation Dashboard</span></a></li><li class="level-2"><a class="final" href="/evaluation/metricchoose/"><span>Choosing Evaluation Metri cs</span></a></li><li class="level-2"><a class="final" href="/evaluation/metricbuild/"><span>Building Evaluation Metrics</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>System Architecture</span></a><ul><li class="level-2"><a class="final" href="/system/"><span>Architecture Overview</span></a></li><li class="level-2"><a class="final" href="/system/anotherdatastore/"><span>Using Another Data Store</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Engine Template Gallery</span></a><ul><li class="level-2"><a class="final" href="/gallery/template-gallery/"><span>Browse</span></a></li><li class="level-2"><a class="final" href="/community/submit-template/"><span>Submit your Engine as a Template</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Demo Tutorials</span></a><ul><li class="level-2"><a class="final" href="/demo/tapster/"><span>Comics Recommendation Demo</span></a></li><li class="leve l-2"><a class="final" href="/demo/community/"><span>Community Contributed Demo</span></a></li><li class="level-2"><a class="final" href="/demo/textclassification/"><span>Text Classification Engine Tutorial</span></a></li></ul></li><li class="level-1"><a class="expandible" href="/community/"><span>Getting Involved</span></a><ul><li class="level-2"><a class="final" href="/community/contribute-code/"><span>Contribute Code</span></a></li><li class="level-2"><a class="final" href="/community/contribute-documentation/"><span>Contribute Documentation</span></a></li><li class="level-2"><a class="final" href="/community/contribute-sdk/"><span>Contribute a SDK</span></a></li><li class="level-2"><a class="final" href="/community/contribute-webhook/"><span>Contribute a Webhook</span></a></li><li class="level-2"><a class="final" href="/community/projects/"><span>Community Projects</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Getting Help</span></a><ul><li cla ss="level-2"><a class="final" href="/resources/faq/"><span>FAQs</span></a></li><li class="level-2"><a class="final" href="/support/"><span>Support</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Resources</span></a><ul><li class="level-2"><a class="final" href="/resources/intellij/"><span>Developing Engines with IntelliJ IDEA</span></a></li><li class="level-2"><a class="final" href="/resources/upgrade/"><span>Upgrade Instructions</span></a></li><li class="level-2"><a class="final" href="/resources/glossary/"><span>Glossary</span></a></li></ul></li></ul></nav></div><div class="col-md-9 col-sm-12"><div class="content-header hidden-md hidden-lg"><div id="page-title"><h1>Using Alternative Algorithm</h1></div></div><div id="table-of-content-wrapper"><h5>On this page</h5><aside id="table-of-contents"><ul> <li> <a href="#create-a-new-file-randomforestalgorithm-scala">Create a new file RandomForestAlgorithm.scala</a> </li> <li> <a href="#define-the-algorith m-class-and-parameters">Define the algorithm class and parameters</a> </li> <li> <a href="#update-engine-scala">Update Engine.scala</a> </li> <li> <a href="#update-engine-json">Update engine.json</a> </li> </ul> </aside><hr/><a id="edit-page-link" href="https://github.com/apache/incubator-predictionio/tree/livedoc/docs/manual/source/templates/classification/add-algorithm.html.md";><img src="/images/icons/edit-pencil-d6c1bb3d.png"/>Edit this page</a></div><div class="content-header hidden-sm hidden-xs"><div id="page-title"><h1>Using Alternative Algorithm</h1></div></div><div class="content"><p>The classification template uses the Naive Bayes algorithm by default. You can easily add and use other MLlib classification algorithms. The following will demonstrate how to add the <a href="https://spark.apache.org/docs/latest/mllib-ensembles.html";>MLlib Random Forests algorithm</a> into the engine.</p><h2 id='create-a-new-file-randomforestalgorithm.scala' class='header-anchors'>Create a new f ile RandomForestAlgorithm.scala</h2><p>Locate <code>src/main/scala/NaiveBayesAlgorithm.scala</code> under your engine directory, which should be /MyClassification if you are following the <a href="/templates/classification/quickstart/">Classification QuickStart</a>. Copy <code>NaiveBayesAlgorithm.scala</code> and create a new file <code>RandomForestAlgorithm.scala</code>. You will modify this file and follow the instructions below to define a new RandomForestAlgorithm class.</p><h2 id='define-the-algorithm-class-and-parameters' class='header-anchors'>Define the algorithm class and parameters</h2><p>In 'RandomForestAlgorithm.scala', import the MLlib Random Forests algorithm by changing the following lines:</p><p>Original</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2</pre></td><td class="code"><pre><span class="k">import</span> <span class="nn">org.apache.spark.mllib.classification.NaiveBayes</span> +<span class="k">import</span> <span class="nn">org.apache.spark.mllib.classification.NaiveBayesModel</span> +</pre></td></tr></tbody></table> </div> <p>Change to:</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2</pre></td><td class="code"><pre><span class="k">import</span> <span class="nn">org.apache.spark.mllib.tree.RandomForest</span> <span class="c1">// CHANGED +</span><span class="k">import</span> <span class="nn">org.apache.spark.mllib.tree.model.RandomForestModel</span> <span class="c1">// CHANGED +</span></pre></td></tr></tbody></table> </div> <p>These are the necessary classes in order to use the MLLib's Random Forest algorithm.</p><p>Modify the <code>AlgorithmParams</code> class for the Random Forest algorithm:</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9</pre></td><td class="code"><pre><span class="c1">// CHANGED +</span><span class="k">case</span> <span class="k">class</span> <span class="nc">RandomForestAlgorithmParams</span><span class="o">(</span> + <span class="n">numClasses</span><span class="k">:</span> <span class="kt">Int</span><span class="o">,</span> + <span class="n">numTrees</span><span class="k">:</span> <span class="kt">Int</span><span class="o">,</span> + <span class="n">featureSubsetStrategy</span><span class="k">:</span> <span class="kt">String</span><span class="o">,</span> + <span class="n">impurity</span><span class="k">:</span> <span class="kt">String</span><span class="o">,</span> + <span class="n">maxDepth</span><span class="k">:</span> <span class="kt">Int</span><span class="o">,</span> + <span class="n">maxBins</span><span class="k">:</span> <span class="kt">Int</span> +<span class="o">)</span> <span class="k">extends</span> <span class="nc">Params</span> +</pre></td></tr></tbody></table> </div> <p>This class defines the parameters of the Random Forest algorithm (which later you can specify the value in engine.json). Please refer to <a href="https://spark.apache.org/docs/latest/mllib-ensembles.html";>MLlib documentation</a> for the description and usage of these parameters.</p><p>Modify the <code>NaiveBayesAlgorithm</code> class to <code>RandomForestAlgorithm</code>. The changes are:</p> <ul> <li>The new <code>RandomForestAlgorithmParams</code> class is used as parameter.</li> <li><code>RandomForestModel</code> is used in type parameter. This is the model returned by the Random Forest algorithm.</li> <li>the <code>train()</code> function is modified and it returns the <code>RandomForestModel</code> instead of <code>NaiveBayesModel</code>.</li> <li>the <code>predict()</code> function takes the <code>RandomForestModel</code> as input.</li> </ul> <div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl " style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33</pre></td><td class="code"><pre><span class="c1">// extends P2LAlgorithm because the MLlib's RandomForestModel doesn't +// contain RDD. +</span><span class="k">class</span> <span class="nc">RandomForestAlgorithm</span><span class="o">(</span><span class="k">val</span> <span class="n">ap</span><span class="k">:</span> <span class="kt">RandomForestAlgorithmParams</span><span class="o">)</span> <span class="c1">// CHANGED +</span> <span class="k">extends</span> <span class="n">P2LAlgorithm</span><span class="o">[</span><span class="kt">PreparedData</span>, <span class="kt">RandomForestModel</span>, <span class="kt">//</span> <span class="kt">CHANGED</span> + <span class="kt">Query</span>, <span class="kt">PredictedResult</span><span class="o">]</span> <span class="o">{</span> + + <span class="c1">// CHANGED +</span> <span class="k">def</span> <span class="n">train</span><span class="o">(</span><span class="n">sc</span><span class="k">:</span> <span class="kt">SparkContext</span><span class="o">,</span> <span class="n">data</span><span class="k">:</span> <span class="kt">PreparedData</span><span class="o">)</span><span class="k">:</span> <span class="kt">RandomForestModel</span> <span class="o">=</span> <span class="o">{</span> + <span class="c1">// CHANGED +</span> <span class="c1">// Empty categoricalFeaturesInfo indicates all features are continuous. +</span> <span class="k">val</span> <span class="n">categoricalFeaturesInfo</span> <span class="k">=</span> <span class="nc">Map</span><span class="o">[</span><span class="kt">Int</span>, <span class="kt">Int</span><span class="o">]()</span> + <span class="nc">RandomForest</span><span class="o">.</span><span class="n">trainClassifier</span><span class="o">(</span> + <span class="n">data</span><span class="o">.</span><span class="n">labeledPoints</span><span class="o">,</span> + <span class="n">ap</span><span class="o">.</span><span class="n">numClasses</span><span class="o">,</span> + <span class="n">categoricalFeaturesInfo</span><span class="o">,</span> + <span class="n">ap</span><span class="o">.</span><span class="n">numTrees</span><span class="o">,</span> + <span class="n">ap</span><span class="o">.</span><span class="n">featureSubsetStrategy</span><span class="o">,</span> + <span class="n">ap</span><span class="o">.</span><span class="n">impurity</span><span class="o">,</span> + <span class="n">ap</span><span class="o">.</span><span class="n">maxDepth</span><span class="o">,</span> + <span class="n">ap</span><span class="o">.</span><span class="n">maxBins</span><span class="o">)</span> + <span class="o">}</span> + + <span class="k">def</span> <span class="n">predict</span><span class="o">(</span> + <span class="n">model</span><span class="k">:</span> <span class="kt">RandomForestModel</span><span class="o">,</span> <span class="c1">// CHANGED +</span> <span class="n">query</span><span class="k">:</span> <span class="kt">Query</span><span class="o">)</span><span class="k">:</span> <span class="kt">PredictedResult</span> <span class="o">=</span> <span class="o">{</span> + + <span class="k">val</span> <span class="n">label</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="o">(</span><span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span> + <span class="n">query</span><span class="o">.</span><span class="n">attr0</span><span class="o">,</span> <span class="n">query</span><span class="o">.</span><span class="n">attr1</span><span class="o">,</span> <span class="n">query</span><span class="o">.</span><span class="n">attr2</span> + <span class="o">))</span> + <span class="k">new</span> <span class="nc">PredictedResult</span><span class="o">(</span><span class="n">label</span><span class="o">)</span> + <span class="o">}</span> + +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <p>Note that the MLlib Random Forest algorithm takes the same training data as the Navie Bayes algorithm (ie, RDD[LabeledPoint]) so you don't need to modify the <code>DataSource</code>, <code>TrainigData</code> and <code>PreparedData</code> classes. If the new algorithm to be added requires different types of training data, then you need to modify these classes accordingly to accomodate your new algorithm.</p><h2 id='update-engine.scala' class='header-anchors'>Update Engine.scala</h2><p>Modify the EngineFactory to add the new algorithm class <code>RandomForestAlgorithm</code> you just defined and give it a name <code>"randomforest"</code>. The name will be used in <code>engine.json</code> to specify which algorithm to use.</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9 +10</pre></td><td class="code"><pre><span class="k">object</span> <span class="nc">ClassificationEngine</span> <span class="k">extends</span> <span class="nc">IEngineFactory</span> <span class="o">{</span> + <span class="k">def</span> <span class="n">apply</span><span class="o">()</span> <span class="k">=</span> <span class="o">{</span> + <span class="k">new</span> <span class="nc">Engine</span><span class="o">(</span> + <span class="n">classOf</span><span class="o">[</span><span class="kt">DataSource</span><span class="o">],</span> + <span class="n">classOf</span><span class="o">[</span><span class="kt">Preparator</span><span class="o">],</span> + <span class="nc">Map</span><span class="o">(</span><span class="s">"naive"</span> <span class="o">-></span> <span class="n">classOf</span><span class="o">[</span><span class="kt">NaiveBayesAlgorithm</span><span class="o">],</span> + <span class="s">"randomforest"</span> <span class="o">-></span> <span class="n">classOf</span><span class="o">[</span><span class="kt">RandomForestAlgorithm</span><span class="o">]),</span> <span class="c1">// ADDED +</span> <span class="n">classOf</span><span class="o">[</span><span class="kt">Serving</span><span class="o">])</span> + <span class="o">}</span> +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <p>This engine factory now returns an engine with two algorithms and they are named as <code>"naive"</code> and <code>"randomforest"</code> respectively.</p><h2 id='update-engine.json' class='header-anchors'>Update engine.json</h2><p>In order to use the new algorithm, you need to modify <code>engine.json</code> to specify the name of the algorithm and the parameters.</p><p>Update the engine.json to use <strong>randomforest</strong>:</p><div class="highlight json"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15</pre></td><td class="code"><pre><span class="err">...</span><span class="w"> +</span><span class="s2">"algorithms"</span><span class="err">:</span><span class="w"> </span><span class="p">[</span><span class="w"> + </span><span class="p">{</span><span class="w"> + </span><span class="s2">"name"</span><span class="p">:</span><span class="w"> </span><span class="s2">"randomforest"</span><span class="p">,</span><span class="w"> + </span><span class="s2">"params"</span><span class="p">:</span><span class="w"> </span><span class="p">{</span><span class="w"> + </span><span class="s2">"numClasses"</span><span class="p">:</span><span class="w"> </span><span class="mi">3</span><span class="p">,</span><span class="w"> + </span><span class="s2">"numTrees"</span><span class="p">:</span><span class="w"> </span><span class="mi">5</span><span class="p">,</span><span class="w"> + </span><span class="s2">"featureSubsetStrategy"</span><span class="p">:</span><span class="w"> </span><span class="s2">"auto"</span><span class="p">,</span><span class="w"> + </span><span class="s2">"impurity"</span><span class="p">:</span><span class="w"> </span><span class="s2">"gini"</span><span class="p">,</span><span class="w"> + </span><span class="s2">"maxDepth"</span><span class="p">:</span><span class="w"> </span><span class="mi">4</span><span class="p">,</span><span class="w"> + </span><span class="s2">"maxBins"</span><span class="p">:</span><span class="w"> </span><span class="mi">100</span><span class="w"> + </span><span class="p">}</span><span class="w"> + </span><span class="p">}</span><span class="w"> +</span><span class="p">]</span><span class="w"> +</span><span class="err">...</span><span class="w"> +</span></pre></td></tr></tbody></table> </div> <p>The engine now uses <strong>MLlib Random Forests algorithm</strong> instead of the default Naive Bayes algorithm. You are ready to build, train and deploy the engine as described in <a href="/templates/classification/quickstart/">quickstart</a>.</p><div class="highlight shell"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3</pre></td><td class="code"><pre><span class="gp">$ </span>pio build +<span class="gp">$ </span>pio train +<span class="gp">$ </span>pio deploy +</pre></td></tr></tbody></table> </div> <div class="alert-message info"><p>To switch back using Naive Bayes algorithm, simply modify engine.json.</p></div></div></div></div></div><footer><div class="container"><div class="seperator"></div><div class="row"><div class="col-md-6 col-xs-6 footer-link-column"><div class="footer-link-column-row"><h4>Community</h4><ul><li><a href="//docs.prediction.io/install/" target="blank">Download</a></li><li><a href="//docs.prediction.io/" target="blank">Docs</a></li><li><a href="//github.com/apache/incubator-predictionio" target="blank">GitHub</a></li><li><a href="mailto:user-subscr...@predictionio.incubator.apache.org"; target="blank">Subscribe to User Mailing List</a></li><li><a href="//stackoverflow.com/questions/tagged/predictionio" target="blank">Stackoverflow</a></li></ul></div></div><div class="col-md-6 col-xs-6 footer-link-column"><div class="footer-link-column-row"><h4>Contribute</h4><ul><li><a href="//predictionio.incubator.apache.org/commun ity/contribute-code/" target="blank">Contribute</a></li><li><a href="//github.com/apache/incubator-predictionio" target="blank">Source Code</a></li><li><a href="//issues.apache.org/jira/browse/PIO" target="blank">Bug Tracker</a></li><li><a href="mailto:dev-subscr...@predictionio.incubator.apache.org"; target="blank">Subscribe to Development Mailing List</a></li></ul></div></div></div></div><div id="footer-bottom"><div class="container"><div class="row"><div class="col-md-12"><div id="footer-logo-wrapper"><img alt="PredictionIO" src="/images/logos/logo-white-d1e9c6e6.png"/></div><div id="social-icons-wrapper"><a class="github-button" href="https://github.com/apache/incubator-predictionio"; data-style="mega" data-count-href="/apache/incubator-predictionio/stargazers" data-count-api="/repos/apache/incubator-predictionio#stargazers_count" data-count-aria-label="# stargazers on GitHub" aria-label="Star apache/incubator-predictionio on GitHub">Star</a> <a class="github-button" href="https:/ /github.com/apache/incubator-predictionio/fork" data-icon="octicon-git-branch" data-style="mega" data-count-href="/apache/incubator-predictionio/network" data-count-api="/repos/apache/incubator-predictionio#forks_count" data-count-aria-label="# forks on GitHub" aria-label="Fork apache/incubator-predictionio on GitHub">Fork</a> <script id="github-bjs" async="" defer="" src="https://buttons.github.io/buttons.js";></script><a href="//www.facebook.com/predictionio" target="blank"><img alt="PredictionIO on Twitter" src="/images/icons/twitter-ea9dc152.png"/></a> <a href="//twitter.com/predictionio" target="blank"><img alt="PredictionIO on Facebook" src="/images/icons/facebook-5c57939c.png"/></a> </div></div></div></div></div></footer></div><script>(function(w,d,t,u,n,s,e){w['SwiftypeObject']=n;w[n]=w[n]||function(){ +(w[n].q=w[n].q||[]).push(arguments);};s=d.createElement(t); +e=d.getElementsByTagName(t)[0];s.async=1;s.src=u;e.parentNode.insertBefore(s,e); +})(window,document,'script','//s.swiftypecdn.com/install/v1/st.js','_st'); + +_st('install','HaUfpXXV87xoB_zzCQ45');</script><script src="/javascripts/application-f819cf19.js"></script></body></html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/c811983d/templates/classification/add-algorithm/index.html.gz ---------------------------------------------------------------------- diff --git a/templates/classification/add-algorithm/index.html.gz b/templates/classification/add-algorithm/index.html.gz new file mode 100644 index 0000000..fa24336 Binary files /dev/null and b/templates/classification/add-algorithm/index.html.gz differ http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/c811983d/templates/classification/dase/index.html ---------------------------------------------------------------------- diff --git a/templates/classification/dase/index.html b/templates/classification/dase/index.html new file mode 100644 index 0000000..f90f23b --- /dev/null +++ b/templates/classification/dase/index.html @@ -0,0 +1,218 @@ +<!DOCTYPE html><html><head><title>DASE Components Explained (Classification)</title><meta charset="utf-8"/><meta content="IE=edge,chrome=1" http-equiv="X-UA-Compatible"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><meta class="swiftype" name="title" data-type="string" content="DASE Components Explained (Classification)"/><link rel="canonical" href="https://docs.prediction.io/templates/classification/dase/"/><link href="/images/favicon/normal-b330020a.png" rel="shortcut icon"/><link href="/images/favicon/apple-c0febcf2.png" rel="apple-touch-icon"/><link href="//fonts.googleapis.com/css?family=Open+Sans:300italic,400italic,600italic,700italic,800italic,400,300,600,700,800" rel="stylesheet"/><link href="//maxcdn.bootstrapcdn.com/font-awesome/4.2.0/css/font-awesome.min.css" rel="stylesheet"/><link href="/stylesheets/application-a2a2f408.css" rel="stylesheet" type="text/css"/><script src="//cdnjs.cloudflare.com/ajax/libs/html5shiv/3.7.2/html5shiv.min.js"></scri pt><script src="//cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script><script src="//use.typekit.net/pqo0itb.js"></script><script>try{Typekit.load({ async: true });}catch(e){}</script></head><body><div id="global"><header><div class="container" id="header-wrapper"><div class="row"><div class="col-sm-12"><div id="logo-wrapper"><span id="drawer-toggle"></span><a href="#"></a><a href="http://predictionio.incubator.apache.org/";><img alt="PredictionIO" id="logo" src="/images/logos/logo-ee2b9bb3.png"/></a></div><div id="menu-wrapper"><div id="pill-wrapper"><a class="pill left" href="/gallery/template-gallery">TEMPLATES</a> <a class="pill right" href="//github.com/apache/incubator-predictionio/">OPEN SOURCE</a></div></div><img class="mobile-search-bar-toggler hidden-md hidden-lg" src="/images/icons/search-glass-704bd4ff.png"/></div></div></div></header><div id="search-bar-row-wrapper"><div class="container-fluid" id="search-bar-row"><div class="row"><div class= "col-md-9 col-sm-11 col-xs-11"><div class="hidden-md hidden-lg" id="mobile-page-heading-wrapper"><p>PredictionIO Docs</p><h4>DASE Components Explained (Classification)</h4></div><h4 class="hidden-sm hidden-xs">PredictionIO Docs</h4></div><div class="col-md-3 col-sm-1 col-xs-1 hidden-md hidden-lg"><img id="left-menu-indicator" src="/images/icons/down-arrow-dfe9f7fe.png"/></div><div class="col-md-3 col-sm-12 col-xs-12 swiftype-wrapper"><div class="swiftype"><form class="search-form"><img class="search-box-toggler hidden-xs hidden-sm" src="/images/icons/search-glass-704bd4ff.png"/><div class="search-box"><img src="/images/icons/search-glass-704bd4ff.png"/><input type="text" id="st-search-input" class="st-search-input" placeholder="Search Doc..."/></div><img class="swiftype-row-hider hidden-md hidden-lg" src="/images/icons/drawer-toggle-active-fcbef12a.png"/></form></div></div><div class="mobile-left-menu-toggler hidden-md hidden-lg"></div></div></div></div><div id="page" class="contain er-fluid"><div class="row"><div id="left-menu-wrapper" class="col-md-3"><nav id="nav-main"><ul><li class="level-1"><a class="expandible" href="/"><span>Apache PredictionIO (incubating) Documentation</span></a><ul><li class="level-2"><a class="final" href="/"><span>Welcome to Apache PredictionIO (incubating)</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Getting Started</span></a><ul><li class="level-2"><a class="final" href="/start/"><span>A Quick Intro</span></a></li><li class="level-2"><a class="final" href="/install/"><span>Installing Apache PredictionIO (incubating)</span></a></li><li class="level-2"><a class="final" href="/start/download/"><span>Downloading an Engine Template</span></a></li><li class="level-2"><a class="final" href="/start/deploy/"><span>Deploying Your First Engine</span></a></li><li class="level-2"><a class="final" href="/start/customize/"><span>Customizing the Engine</span></a></li></ul></li><li class="level-1"><a class="exp andible" href="#"><span>Integrating with Your App</span></a><ul><li class="level-2"><a class="final" href="/appintegration/"><span>App Integration Overview</span></a></li><li class="level-2"><a class="expandible" href="/sdk/"><span>List of SDKs</span></a><ul><li class="level-3"><a class="final" href="/sdk/java/"><span>Java & Android SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/php/"><span>PHP SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/python/"><span>Python SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/ruby/"><span>Ruby SDK</span></a></li><li class="level-3"><a class="final" href="/sdk/community/"><span>Community Powered SDKs</span></a></li></ul></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Deploying an Engine</span></a><ul><li class="level-2"><a class="final" href="/deploy/"><span>Deploying as a Web Service</span></a></li><li class="level-2"><a class="final" href="/cli/#engine-commands"><spa n>Engine Command-line Interface</span></a></li><li class="level-2"><a class="final" href="/deploy/monitoring/"><span>Monitoring Engine</span></a></li><li class="level-2"><a class="final" href="/deploy/engineparams/"><span>Setting Engine Parameters</span></a></li><li class="level-2"><a class="final" href="/deploy/enginevariants/"><span>Deploying Multiple Engine Variants</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Customizing an Engine</span></a><ul><li class="level-2"><a class="final" href="/customize/"><span>Learning DASE</span></a></li><li class="level-2"><a class="final" href="/customize/dase/"><span>Implement DASE</span></a></li><li class="level-2"><a class="final" href="/customize/troubleshooting/"><span>Troubleshooting Engine Development</span></a></li><li class="level-2"><a class="final" href="/api/current/#package"><span>Engine Scala APIs</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Collecting and Anal yzing Data</span></a><ul><li class="level-2"><a class="final" href="/datacollection/"><span>Event Server Overview</span></a></li><li class="level-2"><a class="final" href="/cli/#event-server-commands"><span>Event Server Command-line Interface</span></a></li><li class="level-2"><a class="final" href="/datacollection/eventapi/"><span>Collecting Data with REST/SDKs</span></a></li><li class="level-2"><a class="final" href="/datacollection/eventmodel/"><span>Events Modeling</span></a></li><li class="level-2"><a class="final" href="/datacollection/webhooks/"><span>Unifying Multichannel Data with Webhooks</span></a></li><li class="level-2"><a class="final" href="/datacollection/channel/"><span>Channel</span></a></li><li class="level-2"><a class="final" href="/datacollection/batchimport/"><span>Importing Data in Batch</span></a></li><li class="level-2"><a class="final" href="/datacollection/analytics/"><span>Using Analytics Tools</span></a></li></ul></li><li class="level-1"><a class="expand ible" href="#"><span>Choosing an Algorithm(s)</span></a><ul><li class="level-2"><a class="final" href="/algorithm/"><span>Built-in Algorithm Libraries</span></a></li><li class="level-2"><a class="final" href="/algorithm/switch/"><span>Switching to Another Algorithm</span></a></li><li class="level-2"><a class="final" href="/algorithm/multiple/"><span>Combining Multiple Algorithms</span></a></li><li class="level-2"><a class="final" href="/algorithm/custom/"><span>Adding Your Own Algorithms</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>ML Tuning and Evaluation</span></a><ul><li class="level-2"><a class="final" href="/evaluation/"><span>Overview</span></a></li><li class="level-2"><a class="final" href="/evaluation/paramtuning/"><span>Hyperparameter Tuning</span></a></li><li class="level-2"><a class="final" href="/evaluation/evaluationdashboard/"><span>Evaluation Dashboard</span></a></li><li class="level-2"><a class="final" href="/evaluation/metricchoo se/"><span>Choosing Evaluation Metrics</span></a></li><li class="level-2"><a class="final" href="/evaluation/metricbuild/"><span>Building Evaluation Metrics</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>System Architecture</span></a><ul><li class="level-2"><a class="final" href="/system/"><span>Architecture Overview</span></a></li><li class="level-2"><a class="final" href="/system/anotherdatastore/"><span>Using Another Data Store</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Engine Template Gallery</span></a><ul><li class="level-2"><a class="final" href="/gallery/template-gallery/"><span>Browse</span></a></li><li class="level-2"><a class="final" href="/community/submit-template/"><span>Submit your Engine as a Template</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Demo Tutorials</span></a><ul><li class="level-2"><a class="final" href="/demo/tapster/"><span>Comics Recommendation Demo</span></a></li><li class="level-2"><a class="final" href="/demo/community/"><span>Community Contributed Demo</span></a></li><li class="level-2"><a class="final" href="/demo/textclassification/"><span>Text Classification Engine Tutorial</span></a></li></ul></li><li class="level-1"><a class="expandible" href="/community/"><span>Getting Involved</span></a><ul><li class="level-2"><a class="final" href="/community/contribute-code/"><span>Contribute Code</span></a></li><li class="level-2"><a class="final" href="/community/contribute-documentation/"><span>Contribute Documentation</span></a></li><li class="level-2"><a class="final" href="/community/contribute-sdk/"><span>Contribute a SDK</span></a></li><li class="level-2"><a class="final" href="/community/contribute-webhook/"><span>Contribute a Webhook</span></a></li><li class="level-2"><a class="final" href="/community/projects/"><span>Community Projects</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><spa n>Getting Help</span></a><ul><li class="level-2"><a class="final" href="/resources/faq/"><span>FAQs</span></a></li><li class="level-2"><a class="final" href="/support/"><span>Support</span></a></li></ul></li><li class="level-1"><a class="expandible" href="#"><span>Resources</span></a><ul><li class="level-2"><a class="final" href="/resources/intellij/"><span>Developing Engines with IntelliJ IDEA</span></a></li><li class="level-2"><a class="final" href="/resources/upgrade/"><span>Upgrade Instructions</span></a></li><li class="level-2"><a class="final" href="/resources/glossary/"><span>Glossary</span></a></li></ul></li></ul></nav></div><div class="col-md-9 col-sm-12"><div class="content-header hidden-md hidden-lg"><div id="page-title"><h1>DASE Components Explained (Classification)</h1></div></div><div id="table-of-content-wrapper"><h5>On this page</h5><aside id="table-of-contents"><ul> <li> <a href="#the-engine-design">The Engine Design</a> </li> <li> <a href="#data">Data</a> </li> <li > <a href="#algorithm">Algorithm</a> </li> <li> <a href="#serving">Serving</a> > </li> </ul> </aside><hr/><a id="edit-page-link" > href="https://github.com/apache/incubator-predictionio/tree/livedoc/docs/manual/source/templates/classification/dase.html.md.erb";><img > src="/images/icons/edit-pencil-d6c1bb3d.png"/>Edit this page</a></div><div > class="content-header hidden-sm hidden-xs"><div id="page-title"><h1>DASE > Components Explained (Classification)</h1></div></div><div > class="content"><p>PredictionIO's DASE architecture brings the > separation-of-concerns design principle to predictive engine development. > DASE stands for the following components of an engine:</p> <ul> > <li><strong>D</strong>ata - includes Data Source and Data Preparator</li> > <li><strong>A</strong>lgorithm(s)</li> <li><strong>S</strong>erving</li> > <li><strong>E</strong>valuator</li> </ul> <p><p>Let's look at the code > and see how you can customize the engine you built from the Classification > Engine Template.</p><div c lass="alert-message note"><p>Evaluator will not be covered in this tutorial. Please visit <a href="/evaluation/paramtuning/">evaluation explained</a> for using evaluation.</p></div></p><h2 id='the-engine-design' class='header-anchors'>The Engine Design</h2><p>As you can see from the Quick Start, <em>MyClassification</em> takes a JSON prediction query, e.g. <code>{ "attr0":4, "attr1":3, "attr2":8 }</code>, and return a JSON predicted result.</p><div class="alert-message warning"><p>for version < v0.3.1, it is array of features values: <code>{ "features": [4, 3, 8] }</code></p></div><p>In MyClassification/src/main/scala/<strong><em>Engine.scala</em></strong>, the <code>Query</code> case class defines the format of <strong>query</strong>, such as <code>{ "attr0":4, "attr1":3, "attr2":8 }</code>:</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: rig ht"><pre class="lineno">1 +2 +3 +4 +5 +6</pre></td><td class="code"><pre><span class="k">class</span> <span class="nc">Query</span><span class="o">(</span> + <span class="k">val</span> <span class="n">attr0</span> <span class="k">:</span> <span class="kt">Double</span><span class="o">,</span> + <span class="k">val</span> <span class="n">attr1</span> <span class="k">:</span> <span class="kt">Double</span><span class="o">,</span> + <span class="k">val</span> <span class="n">attr2</span> <span class="k">:</span> <span class="kt">Double</span> +<span class="o">)</span> <span class="k">extends</span> <span class="nc">Serializable</span> + +</pre></td></tr></tbody></table> </div> <p>The <code>PredictedResult</code> case class defines the format of <strong>predicted result</strong>, such as <code>{"label":2.0}</code>:</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3</pre></td><td class="code"><pre><span class="k">class</span> <span class="nc">PredictedResult</span><span class="o">(</span> + <span class="k">val</span> <span class="n">label</span><span class="k">:</span> <span class="kt">Double</span> +<span class="o">)</span> <span class="k">extends</span> <span class="nc">Serializable</span> +</pre></td></tr></tbody></table> </div> <p>Finally, <code>ClassificationEngine</code> is the Engine Factory that defines the components this engine will use: Data Source, Data Preparator, Algorithm(s) and Serving components.</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9</pre></td><td class="code"><pre><span class="k">object</span> <span class="nc">ClassificationEngine</span> <span class="k">extends</span> <span class="nc">IEngineFactory</span> <span class="o">{</span> + <span class="k">def</span> <span class="n">apply</span><span class="o">()</span> <span class="k">=</span> <span class="o">{</span> + <span class="k">new</span> <span class="nc">Engine</span><span class="o">(</span> + <span class="n">classOf</span><span class="o">[</span><span class="kt">DataSource</span><span class="o">],</span> + <span class="n">classOf</span><span class="o">[</span><span class="kt">Preparator</span><span class="o">],</span> + <span class="nc">Map</span><span class="o">(</span><span class="s">"naive"</span> <span class="o">-></span> <span class="n">classOf</span><span class="o">[</span><span class="kt">NaiveBayesAlgorithm</span><span class="o">]),</span> + <span class="n">classOf</span><span class="o">[</span><span class="kt">Serving</span><span class="o">])</span> + <span class="o">}</span> +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <h3 id='spark-mllib' class='header-anchors'>Spark MLlib</h3><p>Spark's MLlib NaiveBayes algorithm takes training data of RDD type, i.e. <code>RDD[LabeledPoint]</code> and train a model, which is a <code>NaiveBayesModel</code> object.</p><p>PredictionIO's MLlib Classification engine template, which <em>MyClassification</em> bases on, integrates this algorithm under the DASE architecture. We will take a closer look at the DASE code below.</p> <blockquote> <p><a href="https://spark.apache.org/docs/latest/mllib-naive-bayes.html";>Check this out</a> to learn more about MLlib's NaiveBayes algorithm.</p></blockquote> <h2 id='data' class='header-anchors'>Data</h2><p>In the DASE architecture, data is prepared by 2 components sequentially: <em>Data Source</em> and <em>Data Preparator</em>. <em>Data Source</em> and <em>Data Preparator</em> takes data from the data store and prepares <code>RDD[LabeledPoint]</code> for the NaiveBayes algorithm.< /p><h3 id='data-source' class='header-anchors'>Data Source</h3><p>In MyClassification/src/main/scala/<strong><em>DataSource.scala</em></strong>, the <code>readTraining</code> method of the class <code>DataSource</code> reads, and selects, data from datastore of EventServer and it returns <code>TrainingData</code>.</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12 +13 +14 +15 +16 +17 +18 +19 +20 +21 +22 +23 +24 +25 +26 +27 +28 +29 +30 +31 +32 +33 +34 +35 +36 +37 +38</pre></td><td class="code"><pre><span class="k">case</span> <span class="k">class</span> <span class="nc">DataSourceParams</span><span class="o">(</span><span class="n">appName</span><span class="k">:</span> <span class="kt">String</span><span class="o">)</span> <span class="k">extends</span> <span class="nc">Params</span> + +<span class="k">class</span> <span class="nc">DataSource</span><span class="o">(</span><span class="k">val</span> <span class="n">dsp</span><span class="k">:</span> <span class="kt">DataSourceParams</span><span class="o">)</span> + <span class="k">extends</span> <span class="nc">PDataSource</span><span class="o">[</span><span class="kt">TrainingData</span>, <span class="kt">EmptyEvaluationInfo</span>, <span class="kt">Query</span>, <span class="kt">EmptyActualResult</span><span class="o">]</span> <span class="o">{</span> + + <span class="nd">@transient</span> <span class="k">lazy</span> <span class="k">val</span> <span class="n">logger</span> <span class="k">=</span> <span class="nc">Logger</span><span class="o">[</span><span class="kt">this.</span><span class="k">type</span><span class="o">]</span> + + <span class="k">override</span> + <span class="k">def</span> <span class="n">readTraining</span><span class="o">(</span><span class="n">sc</span><span class="k">:</span> <span class="kt">SparkContext</span><span class="o">)</span><span class="k">:</span> <span class="kt">TrainingData</span> <span class="o">=</span> <span class="o">{</span> + + <span class="k">val</span> <span class="n">labeledPoints</span><span class="k">:</span> <span class="kt">RDD</span><span class="o">[</span><span class="kt">LabeledPoint</span><span class="o">]</span> <span class="k">=</span> <span class="nc">PEventStore</span><span class="o">.</span><span class="n">aggregateProperties</span><span class="o">(</span> + <span class="n">appName</span> <span class="k">=</span> <span class="n">dsp</span><span class="o">.</span><span class="n">appName</span><span class="o">,</span> + <span class="n">entityType</span> <span class="k">=</span> <span class="s">"user"</span><span class="o">,</span> + <span class="c1">// only keep entities with these required properties defined +</span> <span class="n">required</span> <span class="k">=</span> <span class="nc">Some</span><span class="o">(</span><span class="nc">List</span><span class="o">(</span><span class="s">"plan"</span><span class="o">,</span> <span class="s">"attr0"</span><span class="o">,</span> <span class="s">"attr1"</span><span class="o">,</span> <span class="s">"attr2"</span><span class="o">)))(</span><span class="n">sc</span><span class="o">)</span> + <span class="c1">// aggregateProperties() returns RDD pair of +</span> <span class="c1">// entity ID and its aggregated properties +</span> <span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="k">case</span> <span class="o">(</span><span class="n">entityId</span><span class="o">,</span> <span class="n">properties</span><span class="o">)</span> <span class="k">=></span> + <span class="k">try</span> <span class="o">{</span> + <span class="nc">LabeledPoint</span><span class="o">(</span><span class="n">properties</span><span class="o">.</span><span class="n">get</span><span class="o">[</span><span class="kt">Double</span><span class="o">](</span><span class="s">"plan"</span><span class="o">),</span> + <span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span><span class="nc">Array</span><span class="o">(</span> + <span class="n">properties</span><span class="o">.</span><span class="n">get</span><span class="o">[</span><span class="kt">Double</span><span class="o">](</span><span class="s">"attr0"</span><span class="o">),</span> + <span class="n">properties</span><span class="o">.</span><span class="n">get</span><span class="o">[</span><span class="kt">Double</span><span class="o">](</span><span class="s">"attr1"</span><span class="o">),</span> + <span class="n">properties</span><span class="o">.</span><span class="n">get</span><span class="o">[</span><span class="kt">Double</span><span class="o">](</span><span class="s">"attr2"</span><span class="o">)</span> + <span class="o">))</span> + <span class="o">)</span> + <span class="o">}</span> <span class="k">catch</span> <span class="o">{</span> + <span class="k">case</span> <span class="n">e</span><span class="k">:</span> <span class="kt">Exception</span> <span class="o">=></span> <span class="o">{</span> + <span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="o">(</span><span class="n">s</span><span class="s">"Failed to get properties ${properties} of"</span> <span class="o">+</span> + <span class="n">s</span><span class="s">" ${entityId}. Exception: ${e}."</span><span class="o">)</span> + <span class="k">throw</span> <span class="n">e</span> + <span class="o">}</span> + <span class="o">}</span> + <span class="o">}.</span><span class="n">cache</span><span class="o">()</span> + + <span class="k">new</span> <span class="nc">TrainingData</span><span class="o">(</span><span class="n">labeledPoints</span><span class="o">)</span> + <span class="o">}</span> +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <p><code>PEventStore</code> is an object which provides function to access data that is collected through the <em>Event Server</em>, and <code>PEventStore.aggregateProperties</code> aggregates the event records of the 4 properties (attr0, attr1, attr2 and plan) for each user.</p><p>PredictionIO automatically loads the parameters of <em>datasource</em> specified in MyEngine/<strong><em>engine.json</em></strong>, including <em>appName</em>, to <code>dsp</code>.</p><p>In <strong><em>engine.json</em></strong>:</p><div class="highlight shell"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9</pre></td><td class="code"><pre><span class="o">{</span> + ... + <span class="s2">"datasource"</span>: <span class="o">{</span> + <span class="s2">"params"</span>: <span class="o">{</span> + <span class="s2">"appName"</span>: <span class="s2">"MyApp1"</span> + <span class="o">}</span> + <span class="o">}</span>, + ... +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <p>In this sample text data file, columns are delimited by comma (,). The first column are labels. The second column are features.</p><p>The class definition of <code>TrainingData</code> is:</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3</pre></td><td class="code"><pre><span class="k">class</span> <span class="nc">TrainingData</span><span class="o">(</span> + <span class="k">val</span> <span class="n">labeledPoints</span><span class="k">:</span> <span class="kt">RDD</span><span class="o">[</span><span class="kt">LabeledPoint</span><span class="o">]</span> +<span class="o">)</span> <span class="k">extends</span> <span class="nc">Serializable</span> +</pre></td></tr></tbody></table> </div> <p>and PredictionIO passes the returned <code>TrainingData</code> object to <em>Data Preparator</em>.</p><h3 id='data-preparator' class='header-anchors'>Data Preparator</h3><p>In MyClassification/src/main/scala/<strong><em>Preparator.scala</em></strong>, the <code>prepare</code> of class <code>Preparator</code> takes <code>TrainingData</code>. It then conducts any necessary feature selection and data processing tasks. At the end, it returns <code>PreparedData</code> which should contain the data <em>Algorithm</em> needs. For MLlib NaiveBayes, it is <code>RDD[LabeledPoint]</code>.</p><p>By default, <code>prepare</code> simply copies the unprocessed <code>TrainingData</code> data to <code>PreparedData</code>:</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11</pre></td><td class="code"><pre><span class="k">class</span> <span class="nc">PreparedData</span><span class="o">(</span> + <span class="k">val</span> <span class="n">labeledPoints</span><span class="k">:</span> <span class="kt">RDD</span><span class="o">[</span><span class="kt">LabeledPoint</span><span class="o">]</span> +<span class="o">)</span> <span class="k">extends</span> <span class="nc">Serializable</span> + +<span class="k">class</span> <span class="nc">Preparator</span> + <span class="k">extends</span> <span class="nc">PPreparator</span><span class="o">[</span><span class="kt">TrainingData</span>, <span class="kt">PreparedData</span><span class="o">]</span> <span class="o">{</span> + + <span class="k">def</span> <span class="n">prepare</span><span class="o">(</span><span class="n">sc</span><span class="k">:</span> <span class="kt">SparkContext</span><span class="o">,</span> <span class="n">trainingData</span><span class="k">:</span> <span class="kt">TrainingData</span><span class="o">)</span><span class="k">:</span> <span class="kt">PreparedData</span> <span class="o">=</span> <span class="o">{</span> + <span class="k">new</span> <span class="nc">PreparedData</span><span class="o">(</span><span class="n">trainingData</span><span class="o">.</span><span class="n">labeledPoints</span><span class="o">)</span> + <span class="o">}</span> +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <p>PredictionIO passes the returned <code>PreparedData</code> object to Algorithm's <code>train</code> function.</p><h2 id='algorithm' class='header-anchors'>Algorithm</h2><p>In MyClassification/src/main/scala/<strong><em>NaiveBayesAlgorithm.scala</em></strong>, the two methods of the algorithm class are <code>train</code> and <code>predict</code>. <code>train</code> is responsible for training a predictive model. PredictionIO will store this model and <code>predict</code> is responsible for using this model to make prediction.</p><h3 id='train(...)' class='header-anchors'>train(...)</h3><p><code>train</code> is called when you run <strong>pio train</strong>. This is where MLlib NaiveBayes algorithm, i.e. <code>NaiveBayes.train</code>, is used to train a predictive model.</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3</pre></td><td class="code"><pre><span class="k">def</span> <span class="n">train</span><span class="o">(</span><span class="n">sc</span><span class="k">:</span> <span class="kt">SparkContext</span><span class="o">,</span> <span class="n">data</span><span class="k">:</span> <span class="kt">PreparedData</span><span class="o">)</span><span class="k">:</span> <span class="kt">NaiveBayesModel</span> <span class="o">=</span> <span class="o">{</span> + <span class="nc">NaiveBayes</span><span class="o">.</span><span class="n">train</span><span class="o">(</span><span class="n">data</span><span class="o">.</span><span class="n">labeledPoints</span><span class="o">,</span> <span class="n">ap</span><span class="o">.</span><span class="n">lambda</span><span class="o">)</span> +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <p>In addition to <code>RDD[LabeledPoint]</code> (i.e. <code>data.labeledPoints</code>), <code>NaiveBayes.train</code> takes 1 parameter: <em>lambda</em>.</p><p>The values of this parameter is specified in <em>algorithms</em> of MyClassification/<strong><em>engine.json</em></strong>:</p><div class="highlight shell"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9 +10 +11 +12</pre></td><td class="code"><pre><span class="o">{</span> + ... + <span class="s2">"algorithms"</span>: <span class="o">[</span> + <span class="o">{</span> + <span class="s2">"name"</span>: <span class="s2">"naive"</span>, + <span class="s2">"params"</span>: <span class="o">{</span> + <span class="s2">"lambda"</span>: 1.0 + <span class="o">}</span> + <span class="o">}</span> + <span class="o">]</span> + ... +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <p>PredictionIO will automatically loads these values into the constructor <code>ap</code>, which has a corresponding case class <code>AlgorithmParams</code>:</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3</pre></td><td class="code"><pre><span class="k">case</span> <span class="k">class</span> <span class="nc">AlgorithmParams</span><span class="o">(</span> + <span class="n">lambda</span><span class="k">:</span> <span class="kt">Double</span> +<span class="o">)</span> <span class="k">extends</span> <span class="nc">Params</span> +</pre></td></tr></tbody></table> </div> <p><code>NaiveBayes.train</code> then returns a <code>NaiveBayesModel</code> model. PredictionIO will automatically store the returned model.</p><h3 id='predict(...)' class='header-anchors'>predict(...)</h3><p>The <code>predict</code> method is called when you send a JSON query to <a href="http://localhost:8000/queries.json";>http://localhost:8000/queries.json</a>. PredictionIO converts the query, such as <code>{ "attr0":4, "attr1":3, "attr2":8 }</code> to the <code>Query</code> class you defined previously.</p><p>The predictive model <code>NaiveBayesModel</code> of MLlib NaiveBayes offers a function called <code>predict</code>. <code>predict</code> takes a dense vector of features. It predicts the label of the item represented by this feature vector.</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6</pre></td><td class="code"><pre> <span class="k">def</span> <span class="n">predict</span><span class="o">(</span><span class="n">model</span><span class="k">:</span> <span class="kt">NaiveBayesModel</span><span class="o">,</span> <span class="n">query</span><span class="k">:</span> <span class="kt">Query</span><span class="o">)</span><span class="k">:</span> <span class="kt">PredictedResult</span> <span class="o">=</span> <span class="o">{</span> + <span class="k">val</span> <span class="n">label</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="o">(</span><span class="nc">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="o">(</span> + <span class="n">query</span><span class="o">.</span><span class="n">attr0</span><span class="o">,</span> <span class="n">query</span><span class="o">.</span><span class="n">attr1</span><span class="o">,</span> <span class="n">query</span><span class="o">.</span><span class="n">attr2</span> + <span class="o">))</span> + <span class="k">new</span> <span class="nc">PredictedResult</span><span class="o">(</span><span class="n">label</span><span class="o">)</span> + <span class="o">}</span> +</pre></td></tr></tbody></table> </div> <blockquote> <p>You have defined the class <code>PredictedResult</code> earlier in this page.</p></blockquote> <p>PredictionIO passes the returned <code>PredictedResult</code> object to <em>Serving</em>.</p><h2 id='serving' class='header-anchors'>Serving</h2><p>The <code>serve</code> method of class <code>Serving</code> processes predicted result. It is also responsible for combining multiple predicted results into one if you have more than one predictive model. <em>Serving</em> then returns the final predicted result. PredictionIO will convert it to a JSON response automatically.</p><p>In MyClassification/src/main/scala/<strong><em>Serving.scala</em></strong>,</p><div class="highlight scala"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre class="lineno">1 +2 +3 +4 +5 +6 +7 +8 +9</pre></td><td class="code"><pre><span class="k">class</span> <span class="nc">Serving</span> + <span class="k">extends</span> <span class="nc">LServing</span><span class="o">[</span><span class="kt">Query</span>, <span class="kt">PredictedResult</span><span class="o">]</span> <span class="o">{</span> + + <span class="k">override</span> + <span class="k">def</span> <span class="n">serve</span><span class="o">(</span><span class="n">query</span><span class="k">:</span> <span class="kt">Query</span><span class="o">,</span> + <span class="n">predictedResults</span><span class="k">:</span> <span class="kt">Seq</span><span class="o">[</span><span class="kt">PredictedResult</span><span class="o">])</span><span class="k">:</span> <span class="kt">PredictedResult</span> <span class="o">=</span> <span class="o">{</span> + <span class="n">predictedResults</span><span class="o">.</span><span class="n">head</span> + <span class="o">}</span> +<span class="o">}</span> +</pre></td></tr></tbody></table> </div> <p>When you send a JSON query to <a href="http://localhost:8000/queries.json";>http://localhost:8000/queries.json</a>, <code>PredictedResult</code> from all models will be passed to <code>serve</code> as a sequence, i.e. <code>Seq[PredictedResult]</code>.</p> <blockquote> <p>An engine can train multiple models if you specify more than one Algorithm component in <code>object RecommendationEngine</code> inside <strong><em>Engine.scala</em></strong>. Since only one <code>NaiveBayesAlgorithm</code> is implemented by default, this <code>Seq</code> contains one element.</p></blockquote> <p>In this case, <code>serve</code> simply returns the predicted result of the first, and the only, algorithm, i.e. <code>predictedResults.head</code>.</p><p>Congratulations! You have just learned how to customize and build a production-ready engine. Have fun!</p></div></div></div></div><footer><div class="container"><div class="seperator"></div><div class="row"><div class="col-md-6 col-xs-6 footer-link-column"><div class="footer-link-column-row"><h4>Community</h4><ul><li><a href="//docs.prediction.io/install/" target="blank">Download</a></li><li><a href="//docs.prediction.io/" target="blank">Docs</a></li><li><a href="//github.com/apache/incubator-predictionio" target="blank">GitHub</a></li><li><a href="mailto:user-subscr...@predictionio.incubator.apache.org"; target="blank">Subscribe to User Mailing List</a></li><li><a href="//stackoverflow.com/questions/tagged/predictionio" target="blank">Stackoverflow</a></li></ul></div></div><div class="col-md-6 col-xs-6 footer-link-column"><div class="footer-link-column-row"><h4>Contribute</h4><ul><li><a href="//predictionio.incubator.apache.org/community/contribute-code/" target="blank">Contribute</a></li><li><a href="//github.com/apache/incubator-predictionio" target="blank">Source Code</a></li><li><a href="//issues.apache.org/jira/browse/PIO" target="blank">Bug Tracker</a></li><li><a href="mailto:dev-subs cr...@predictionio.incubator.apache.org" target="blank">Subscribe to Development Mailing List</a></li></ul></div></div></div></div><div id="footer-bottom"><div class="container"><div class="row"><div class="col-md-12"><div id="footer-logo-wrapper"><img alt="PredictionIO" src="/images/logos/logo-white-d1e9c6e6.png"/></div><div id="social-icons-wrapper"><a class="github-button" href="https://github.com/apache/incubator-predictionio"; data-style="mega" data-count-href="/apache/incubator-predictionio/stargazers" data-count-api="/repos/apache/incubator-predictionio#stargazers_count" data-count-aria-label="# stargazers on GitHub" aria-label="Star apache/incubator-predictionio on GitHub">Star</a> <a class="github-button" href="https://github.com/apache/incubator-predictionio/fork"; data-icon="octicon-git-branch" data-style="mega" data-count-href="/apache/incubator-predictionio/network" data-count-api="/repos/apache/incubator-predictionio#forks_count" data-count-aria-label="# forks on GitHub" aria-label="Fork apache/incubator-predictionio on GitHub">Fork</a> <script id="github-bjs" async="" defer="" src="https://buttons.github.io/buttons.js";></script><a href="//www.facebook.com/predictionio" target="blank"><img alt="PredictionIO on Twitter" src="/images/icons/twitter-ea9dc152.png"/></a> <a href="//twitter.com/predictionio" target="blank"><img alt="PredictionIO on Facebook" src="/images/icons/facebook-5c57939c.png"/></a> </div></div></div></div></div></footer></div><script>(function(w,d,t,u,n,s,e){w['SwiftypeObject']=n;w[n]=w[n]||function(){ +(w[n].q=w[n].q||[]).push(arguments);};s=d.createElement(t); +e=d.getElementsByTagName(t)[0];s.async=1;s.src=u;e.parentNode.insertBefore(s,e); +})(window,document,'script','//s.swiftypecdn.com/install/v1/st.js','_st'); + +_st('install','HaUfpXXV87xoB_zzCQ45');</script><script src="/javascripts/application-f819cf19.js"></script></body></html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/c811983d/templates/classification/dase/index.html.gz ---------------------------------------------------------------------- diff --git a/templates/classification/dase/index.html.gz b/templates/classification/dase/index.html.gz new file mode 100644 index 0000000..24d39cd Binary files /dev/null and b/templates/classification/dase/index.html.gz differ
