http://git-wip-us.apache.org/repos/asf/predictionio-site/blob/765e178c/archived/install-vagrant/index.html
----------------------------------------------------------------------
diff --git a/archived/install-vagrant/index.html 
b/archived/install-vagrant/index.html
new file mode 100644
index 0000000..ce838d2
--- /dev/null
+++ b/archived/install-vagrant/index.html
@@ -0,0 +1,49 @@
+<!DOCTYPE html><html><head><title>Installing PredictionIO with Vagrant 
(VirtualBox)</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="Installing PredictionIO with Vagrant 
(VirtualBox)"/><link rel="canonical" 
href="https://predictionio.apache.org/archived/install-vagrant/"/><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-eccfc6cb.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.apache.org/";><img alt="Apache 
PredictionIO" id="logo" 
src="/images/logos/logo-ee2b9bb3.png"/></a><span>®</span></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/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>Installing PredictionIO with Vagrant (VirtualBox)</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 i
 d="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® 
Documentation</span></a><ul><li class="level-2"><a class="final" 
href="/"><span>Welcome to Apache PredictionIO®</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</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" hre
 f="#"><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="/community/projects/#sdks"><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="/batchpredict/"><span>Batch P
 redictions</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><li class="level-2"><a class="final" 
href="/deploy/plugin/"><span>Engine Server Plugin</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="/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><li class="level-2"><a class="final" 
href="/datacollection/plugin/"><span>Event Server Plugin<
 /span></a></li></ul></li><li class="level-1"><a class="expandible" 
href="#"><span>Choosing an Algorithm</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>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><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>PredictionIO® Official 
Templates</span></a><ul><li class="level-2"><a class="final" 
href="/templates/"><span>Intro</span></a></li><li class="level-2"><a 
class="expandible" href="#"><span>Recommendation</span></a><ul><li 
class="level-3"><a class="final" 
href="/templates/recommendation/quickstart/"><span>Quick 
Start</span></a></li><li class="level-3"><a class="final" href="/templates/reco
 mmendation/dase/"><span>DASE</span></a></li><li class="level-3"><a 
class="final" href="/templates/recommendation/evaluation/"><span>Evaluation 
Explained</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/how-to/"><span>How-To</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/recommendation/reading-custom-events/"><span>Read Custom 
Events</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/customize-data-prep/"><span>Customize Data 
Preparator</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/customize-serving/"><span>Customize 
Serving</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/training-with-implicit-preference/"><span>Train 
with Implicit Preference</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/blacklist-items/"><span>Filter Recommended 
Items by Blacklist in Query</span></a></li><li class="l
 evel-3"><a class="final" 
href="/templates/recommendation/batch-evaluator/"><span>Batch Persistable 
Evaluator</span></a></li></ul></li><li class="level-2"><a class="expandible" 
href="#"><span>E-Commerce Recommendation</span></a><ul><li class="level-3"><a 
class="final" href="/templates/ecommercerecommendation/quickstart/"><span>Quick 
Start</span></a></li><li class="level-3"><a class="final" 
href="/templates/ecommercerecommendation/dase/"><span>DASE</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/ecommercerecommendation/how-to/"><span>How-To</span></a></li><li
 class="level-3"><a class="final" 
href="/templates/ecommercerecommendation/train-with-rate-event/"><span>Train 
with Rate Event</span></a></li><li class="level-3"><a class="final" 
href="/templates/ecommercerecommendation/adjust-score/"><span>Adjust 
Score</span></a></li></ul></li><li class="level-2"><a class="expandible" 
href="#"><span>Similar Product</span></a><ul><li class="level-3"><a 
class="final" href="/tem
 plates/similarproduct/quickstart/"><span>Quick Start</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/similarproduct/dase/"><span>DASE</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/similarproduct/how-to/"><span>How-To</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/similarproduct/multi-events-multi-algos/"><span>Multiple 
Events and Multiple Algorithms</span></a></li><li class="level-3"><a 
class="final" 
href="/templates/similarproduct/return-item-properties/"><span>Returns Item 
Properties</span></a></li><li class="level-3"><a class="final" 
href="/templates/similarproduct/train-with-rate-event/"><span>Train with Rate 
Event</span></a></li><li class="level-3"><a class="final" 
href="/templates/similarproduct/rid-user-set-event/"><span>Get Rid of Events 
for Users</span></a></li><li class="level-3"><a class="final" 
href="/templates/similarproduct/recommended-user/"><span>Recommend 
Users</span></a></li></ul></li><li class="leve
 l-2"><a class="expandible" href="#"><span>Classification</span></a><ul><li 
class="level-3"><a class="final" 
href="/templates/classification/quickstart/"><span>Quick 
Start</span></a></li><li class="level-3"><a class="final" 
href="/templates/classification/dase/"><span>DASE</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/classification/how-to/"><span>How-To</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/classification/add-algorithm/"><span>Use Alternative 
Algorithm</span></a></li><li class="level-3"><a class="final" 
href="/templates/classification/reading-custom-properties/"><span>Read Custom 
Properties</span></a></li></ul></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="/community/projects/#demos"><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>Comm
 unity 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="/cli/"><span>Command-line Interface</span></a></li><li class="level-2"><a 
class="final" href="/resources/release/"><span>Release 
Cadence</span></a></li><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><li 
class="level-1"><a class="expandible" href="#"><span>Apache Software Foundation
 </span></a><ul><li class="level-2"><a class="final" 
href="https://www.apache.org/";><span>Apache Homepage</span></a></li><li 
class="level-2"><a class="final" 
href="https://www.apache.org/licenses/";><span>License</span></a></li><li 
class="level-2"><a class="final" 
href="https://www.apache.org/foundation/sponsorship.html";><span>Sponsorship</span></a></li><li
 class="level-2"><a class="final" 
href="https://www.apache.org/foundation/thanks.html";><span>Thanks</span></a></li><li
 class="level-2"><a class="final" 
href="https://www.apache.org/security/";><span>Security</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>Installing PredictionIO with Vagrant 
(VirtualBox)</h1></div></div><div id="table-of-content-wrapper"><h5>On this 
page</h5><aside id="table-of-contents"><ul> <li> <a 
href="#install-virtualbox">Install VirtualBox</a> </li> <li> <a 
href="#install-vagrant">Install Vagrant</a> </li> <li> <a
  href="#bring-up-predictoinio-vm-with-vagrant">Bring up PredictoinIO VM with 
Vagrant</a> </li> <li> <a href="#using-the-predictionio-vm">Using the 
PredictionIO VM</a> </li> </ul> </aside><hr/><a id="edit-page-link" 
href="https://github.com/apache/predictionio/tree/livedoc/docs/manual/source/archived/install-vagrant.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>Installing 
PredictionIO with Vagrant (VirtualBox)</h1></div></div><div class="content"> 
<div class="alert-message warning"><p>Running PredictionIO with Vagrant is 
intended for the purposes of simple tests in an isolated environment. Due to 
resource limitation and overhead of virtual machine (VM), it runs much more 
slowly or may encounter memory issue. We recommend using Linux or Mac machine 
for serious usage.</p></div><h2 id='install-virtualbox' 
class='header-anchors'>Install VirtualBox</h2><p>If you don&#39;t hav
 e VirtualBox installed, please follow the instructions in the <a 
href="https://www.virtualbox.org/wiki/Downloads";>VirtualBox site</a> to 
download and install it. After installation is done, you don&#39;t need to 
setup anything in Virtual Box. Vagrant will do it for you later.</p><h2 
id='install-vagrant' class='header-anchors'>Install Vagrant</h2><p>If you 
don&#39;t have Vagrant installed, please follow the instructions in the the <a 
href="https://www.vagrantup.com/downloads.html";>Vagrant site</a> to download 
and install it.</p><h2 id='bring-up-predictoinio-vm-with-vagrant' 
class='header-anchors'>Bring up PredictoinIO VM with Vagrant</h2><p>Get the 
latest vagrant setup from github and make sure in master branch:</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>git clone 
https://github.com/PredictionIO/PredictionIO-Vagrant.git
+<span class="gp">$ </span><span class="nb">cd </span>PredictionIO-Vagrant/
+<span class="gp">$ </span>git checkout master
+</pre></td></tr></tbody></table> </div> <p>Inside the directory 
<code>PredictionIO-Vagrant/</code>, you will find a file named 
<code>Vagrantfile</code> which is the configuration file used by Vagrant to 
setup the VM. You may modify this file if you want to change the VM 
configuration.</p><p>For example, if you want to change the memory of the VM, 
you can locate the following line in the <code>Vagrantfile</code> and change 
the value passed to the <code>memory</code> parameter (default is 
2048MB):</p><div class="highlight shell"><table style="border-spacing: 
0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre 
class="lineno">1</pre></td><td class="code"><pre>  v.customize <span 
class="o">[</span><span class="s2">"modifyvm"</span>, :id, <span 
class="s2">"--cpuexecutioncap"</span>, <span class="s2">"90"</span>, <span 
class="s2">"--memory"</span>, <span class="s2">"2048"</span><span 
class="o">]</span>
+</pre></td></tr></tbody></table> </div> <p>In the directory 
<code>PredictionIO-Vagrant/</code>, bring up PredictionIO VM by 
running:</p><div class="highlight shell"><table style="border-spacing: 
0"><tbody><tr><td class="gutter gl" style="text-align: right"><pre 
class="lineno">1</pre></td><td class="code"><pre><span class="gp">$ 
</span>vagrant up
+</pre></td></tr></tbody></table> </div> <div class="alert-message 
info"><p>When you run <code>vagrant up</code> for the first time, it will 
download the base box ubuntu/trusty64 if you don&#39;t have it. Then it will 
also install all necessary libraries and setup PredictionIO in the virtual 
machine.</p></div><p>When it finishes successfully, you should see something 
like the following:</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</pre></td><td class="code"><pre><span class="gp">==&gt; </span>default: 
Installation <span class="k">done</span>!
+<span class="gp">==&gt; </span>default: 
--------------------------------------------------------------------------------
+<span class="gp">==&gt; </span>default: Installation of PredictionIO 0.13.0 
<span class="nb">complete</span>!
+<span class="gp">==&gt; </span>default: IMPORTANT: You still have to start 
PredictionIO and dependencies manually:
+<span class="gp">==&gt; </span>default: Run: <span 
class="s1">'pio-start-all'</span>
+<span class="gp">==&gt; </span>default: Check the status with: <span 
class="s1">'pio status'</span>
+<span class="gp">==&gt; </span>default: Use: <span class="s1">'pio 
[train|deploy|...]'</span> commands
+<span class="gp">==&gt; </span>default: Please report any problems to: 
[email protected]
+<span class="gp">==&gt; </span>default: Documentation at: 
http://predictionio.apache.org
+<span class="gp">==&gt; </span>default: 
--------------------------------------------------------------------------------
+<span class="gp">==&gt; </span>default: Finish PredictionIO installation.
+</pre></td></tr></tbody></table> </div> <p>That&#39;s it! Now you have a 
PredictionIO VM running!</p><p>Please see the following notes regarding how to 
use PredictionIO VM with vagrant.</p><h2 id='using-the-predictionio-vm' 
class='header-anchors'>Using the PredictionIO VM</h2><h3 id='login-to-the-vm' 
class='header-anchors'>Login to the VM</h3><p>You could ssh to the VM by 
running the following from your host machine in the same directory where you 
run <code>vagrant up</code> (i.e. PredictionIO-Vagrant/)</p><div 
class="highlight shell"><table style="border-spacing: 0"><tbody><tr><td 
class="gutter gl" style="text-align: right"><pre class="lineno">1</pre></td><td 
class="code"><pre><span class="gp">$ </span>vagrant ssh
+</pre></td></tr></tbody></table> </div> <p>Then your console prompt becomes 
something like the following, which means you have logged into the VM:</p><div 
class="highlight shell"><table style="border-spacing: 0"><tbody><tr><td 
class="gutter gl" style="text-align: right"><pre class="lineno">1</pre></td><td 
class="code"><pre>vagrant@vagrant-ubuntu-trusty-64:~<span class="err">$</span>
+</pre></td></tr></tbody></table> </div> <p>One you&#39;ve logged into the VM, 
you can proceed to <a href="/start/download">Choosing an Engine Template</a> or 
continue the QuickStart of the Engine template you have chosen.</p><h3 
id='shutdown-and-bring-up-predictionio-vm-again' 
class='header-anchors'>Shutdown and bring up PredictionIO VM again</h3><p>When 
you are not using PredictionIO VM, you should shut down VM properly, by running 
the following <strong>in the host machine</strong> (not inside VM):</p><div 
class="highlight shell"><table style="border-spacing: 0"><tbody><tr><td 
class="gutter gl" style="text-align: right"><pre class="lineno">1</pre></td><td 
class="code"><pre><span class="gp">$ </span>vagrant halt
+</pre></td></tr></tbody></table> </div> <div class="alert-message 
warning"><p>If you didn&#39;t shut down VM properly or you ran <code>vagrant 
suspend</code>, the VM may go to suspend state. HBase may not be running 
properly next time when you run <code>vagrant up.</code> In this case, you can 
always run <code>vagrant halt</code> to do a clean shutdown first before run 
<code>vagrant up</code> again.</p></div><p>Then you can run <code>vagrant 
up</code> again later to bring up the PredicitonIO VM again.</p><div 
class="highlight shell"><table style="border-spacing: 0"><tbody><tr><td 
class="gutter gl" style="text-align: right"><pre class="lineno">1</pre></td><td 
class="code"><pre><span class="gp">$ </span>vagrant up
+</pre></td></tr></tbody></table> </div> <p>When it&#39;s ready, you should see 
the following:</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</pre></td><td class="code"><pre><span class="gp">==&gt; </span>default: 
--------------------------------------------------------------------------------
+<span class="gp">==&gt; </span>default: PredictionIO VM is up!
+<span class="gp">==&gt; </span>default: You could run <span class="s1">'pio 
status'</span> inside VM <span class="o">(</span><span class="s1">'vagrant 
ssh'</span> to VM first<span class="o">)</span> to confirm <span class="k">if 
</span>PredictionIO is ready.
+<span class="gp">==&gt; </span>default: IMPORTANT: You still have to start the 
eventserver manually <span class="o">(</span>inside VM<span class="o">)</span>:
+<span class="gp">==&gt; </span>default: Run: <span class="s1">'pio 
eventserver'</span>
+<span class="gp">==&gt; </span>default: 
--------------------------------------------------------------------------------
+</pre></td></tr></tbody></table> </div> </div></div></div></div><footer><div 
class="container"><div class="seperator"></div><div class="row"><div 
class="col-md-6 footer-link-column"><div 
class="footer-link-column-row"><h4>Community</h4><ul><li><a 
href="//predictionio.apache.org/install/" 
target="blank">Download</a></li><li><a href="//predictionio.apache.org/" 
target="blank">Docs</a></li><li><a href="//github.com/apache/predictionio" 
target="blank">GitHub</a></li><li><a 
href="mailto:[email protected]"; 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 
footer-link-column"><div 
class="footer-link-column-row"><h4>Contribute</h4><ul><li><a 
href="//predictionio.apache.org/community/contribute-code/" 
target="blank">Contribute</a></li><li><a 
href="//github.com/apache/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:[email protected]"; target="blank">Subscribe to 
Development Mailing List</a></li></ul></div></div></div><div class="row"><div 
class="col-md-12 footer-link-column"><p>Apache PredictionIO, PredictionIO, 
Apache, the Apache feather logo, and the Apache PredictionIO project logo are 
either registered trademarks or trademarks of The Apache Software Foundation in 
the United States and other countries.</p><p>All other marks mentioned may be 
trademarks or registered trademarks of their respective 
owners.</p></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"/><span>®</span></div><div 
id="social-icons-wrapper"><a class="github-button" 
href="https://github.com/apache/predictionio"; data-icon="octicon-star" 
data-show-count="true" aria-labe
 l="Star apache/predictionio on GitHub">Star</a> <a class="github-button" 
href="https://github.com/apache/predictionio/fork"; 
data-icon="octicon-repo-forked" data-show-count="true" aria-label="Fork 
apache/predictionio on GitHub">Fork</a> <script id="github-bjs" async="" 
defer="" src="https://buttons.github.io/buttons.js";></script><a 
href="https://twitter.com/predictionio"; target="blank"><img alt="PredictionIO 
on Twitter" src="/images/icons/twitter-ea9dc152.png"/></a> <a 
href="https://www.facebook.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-d943a254.js"></script></body></html>
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/predictionio-site/blob/765e178c/archived/supervisedlearning/index.html
----------------------------------------------------------------------
diff --git a/archived/supervisedlearning/index.html 
b/archived/supervisedlearning/index.html
new file mode 100644
index 0000000..8e3752d
--- /dev/null
+++ b/archived/supervisedlearning/index.html
@@ -0,0 +1,6 @@
+<!DOCTYPE html><html><head><title>Machine Learning With 
PredictionIO</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="Machine Learning With 
PredictionIO"/><link rel="canonical" 
href="https://predictionio.apache.org/archived/supervisedlearning/"/><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-eccfc6cb.css" 
rel="stylesheet" type="text/css"/><script 
src="//cdnjs.cloudflare.com/ajax/libs/html5shiv/3.7.2/html5shiv.min.js"></script><script
 sr
 
c="//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.apache.org/";><img alt="Apache 
PredictionIO" id="logo" 
src="/images/logos/logo-ee2b9bb3.png"/></a><span>®</span></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/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 c
 ol-sm-11 col-xs-11"><div class="hidden-md hidden-lg" 
id="mobile-page-heading-wrapper"><p>PredictionIO Docs</p><h4>Machine Learning 
With PredictionIO</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 
clas
 s="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® Documentation</span></a><ul><li 
class="level-2"><a class="final" href="/"><span>Welcome to Apache 
PredictionIO®</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</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</spa
 n></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="/community/projects/#sdks"><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="/batchpredict/"><span>Batch Predictions</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><li class="level-2"><a class="final" 
href="/deploy/plugin/"><span>Engine Server Plugin</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="expandi
 ble" 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="/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><li class="level-2"><a class="final" 
href="/datacollection/plugin/"><span>Event Server 
Plugin</span></a></li></ul></li><li class="level-
 1"><a class="expandible" href="#"><span>Choosing an 
Algorithm</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>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="/evaluati
 on/metricchoose/"><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>PredictionIO® Official Templates</span></a><ul><li 
class="level-2"><a class="final" 
href="/templates/"><span>Intro</span></a></li><li class="level-2"><a 
class="expandible" href="#"><span>Recommendation</span></a><ul><li 
class="level-3"><a class="final" 
href="/templates/recommendation/quickstart/"><span>Quick 
Start</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/dase/"><span>DASE</span></a></l
 i><li class="level-3"><a class="final" 
href="/templates/recommendation/evaluation/"><span>Evaluation 
Explained</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/how-to/"><span>How-To</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/recommendation/reading-custom-events/"><span>Read Custom 
Events</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/customize-data-prep/"><span>Customize Data 
Preparator</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/customize-serving/"><span>Customize 
Serving</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/training-with-implicit-preference/"><span>Train 
with Implicit Preference</span></a></li><li class="level-3"><a class="final" 
href="/templates/recommendation/blacklist-items/"><span>Filter Recommended 
Items by Blacklist in Query</span></a></li><li class="level-3"><a class="final" 
href="/templates/
 recommendation/batch-evaluator/"><span>Batch Persistable 
Evaluator</span></a></li></ul></li><li class="level-2"><a class="expandible" 
href="#"><span>E-Commerce Recommendation</span></a><ul><li class="level-3"><a 
class="final" href="/templates/ecommercerecommendation/quickstart/"><span>Quick 
Start</span></a></li><li class="level-3"><a class="final" 
href="/templates/ecommercerecommendation/dase/"><span>DASE</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/ecommercerecommendation/how-to/"><span>How-To</span></a></li><li
 class="level-3"><a class="final" 
href="/templates/ecommercerecommendation/train-with-rate-event/"><span>Train 
with Rate Event</span></a></li><li class="level-3"><a class="final" 
href="/templates/ecommercerecommendation/adjust-score/"><span>Adjust 
Score</span></a></li></ul></li><li class="level-2"><a class="expandible" 
href="#"><span>Similar Product</span></a><ul><li class="level-3"><a 
class="final" href="/templates/similarproduct/quickstart/"><span>Q
 uick Start</span></a></li><li class="level-3"><a class="final" 
href="/templates/similarproduct/dase/"><span>DASE</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/similarproduct/how-to/"><span>How-To</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/similarproduct/multi-events-multi-algos/"><span>Multiple 
Events and Multiple Algorithms</span></a></li><li class="level-3"><a 
class="final" 
href="/templates/similarproduct/return-item-properties/"><span>Returns Item 
Properties</span></a></li><li class="level-3"><a class="final" 
href="/templates/similarproduct/train-with-rate-event/"><span>Train with Rate 
Event</span></a></li><li class="level-3"><a class="final" 
href="/templates/similarproduct/rid-user-set-event/"><span>Get Rid of Events 
for Users</span></a></li><li class="level-3"><a class="final" 
href="/templates/similarproduct/recommended-user/"><span>Recommend 
Users</span></a></li></ul></li><li class="level-2"><a class="expandible" 
href="#"><span>
 Classification</span></a><ul><li class="level-3"><a class="final" 
href="/templates/classification/quickstart/"><span>Quick 
Start</span></a></li><li class="level-3"><a class="final" 
href="/templates/classification/dase/"><span>DASE</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/classification/how-to/"><span>How-To</span></a></li><li 
class="level-3"><a class="final" 
href="/templates/classification/add-algorithm/"><span>Use Alternative 
Algorithm</span></a></li><li class="level-3"><a class="final" 
href="/templates/classification/reading-custom-properties/"><span>Read Custom 
Properties</span></a></li></ul></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="/community/projects/#demos"><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><l
 i 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="/cli/"><span>Command-line Interface</span></a></li><li class="level-2"><a 
class="final" href="/resources/release/"><span>Release 
Cadence</span></a></li><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><li 
class="level-1"><a class="expandible" href="#"><span>Apache Software 
Foundation</span></a><ul><li class="level-2"><a clas
 s="final" href="https://www.apache.org/";><span>Apache 
Homepage</span></a></li><li class="level-2"><a class="final" 
href="https://www.apache.org/licenses/";><span>License</span></a></li><li 
class="level-2"><a class="final" 
href="https://www.apache.org/foundation/sponsorship.html";><span>Sponsorship</span></a></li><li
 class="level-2"><a class="final" 
href="https://www.apache.org/foundation/thanks.html";><span>Thanks</span></a></li><li
 class="level-2"><a class="final" 
href="https://www.apache.org/security/";><span>Security</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>Machine Learning With 
PredictionIO</h1></div></div><div id="table-of-content-wrapper"><h5>On this 
page</h5><aside id="table-of-contents"><ul> <li> <a 
href="#introduction-to-supervised-learning">Introduction to Supervised 
Learning</a> </li> <li> <a 
href="#predictionio-and-supervised-learning">PredictionIO and Supervised Learnin
 g</a> </li> </ul> </aside><hr/><a id="edit-page-link" 
href="https://github.com/apache/predictionio/tree/livedoc/docs/manual/source/archived/supervisedlearning.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>Machine 
Learning With PredictionIO</h1></div></div><div class="content"> <p>This guide 
is designed to give developers a brief introduction to fundamental concepts in 
machine learning, as well as an explanation of how these concept tie into 
PredictionIO&#39;s engine development platform. This particular guide will 
largely deal with giving some</p><h2 id='introduction-to-supervised-learning' 
class='header-anchors'>Introduction to Supervised Learning</h2><p>The first 
question we must ask is: what is machine learning? <strong>Machine 
learning</strong> is the field of study at the intersection of computer 
science, engineering, mathematics, and statistics which seeks to discover
  or infer patterns hidden within a set of observations, which we call our 
data. Some examples of problems that machine learning seeks to solve are:</p> 
<ul> <li>Predict whether a patient has breast cancer based on their mammogram 
results.</li> <li>Predict whether an e-mail is spam or not based on the 
e-mail&#39;s content.</li> <li>Predict today&#39;s temperature based on climate 
variables collected for the previous week.</li> </ul> <h3 
id='thinking-about-data' class='header-anchors'>Thinking About Data</h3><p>In 
the latter examples, we are trying to predict an outcome \(Y\), or 
<strong>response</strong>, based on some recorded or observed variables \(X\), 
or <strong>features</strong>. For example: in the third problem each 
observation is a patient, the response variable \(Y\) is equal to 1 if this 
patient has breast cancer and 0 otherwise, and \(X\) represents the mammogram 
results.</p><p>When we say we want to predict \(Y\) using \(X\), we are trying 
to answer the question: how doe
 s a response \(Y\) depend on a set of features \(X\) affect the response 
\(Y\)? To do this we need a set of observations, which we call our 
<strong>training data</strong>, consisting of observations for which we have 
observed both \(Y\) and \(X\), in order to make inference about this 
relationship.</p><h3 id='different-types-of-supervised-learning-problems' 
class='header-anchors'>Different Types of Supervised Learning 
Problems</h3><p>Note that in the first two examples, the outcome \(Y\) can only 
take on two values (1 : cancer/spam, 0: no cancer/ no spam). Whenever the 
outcome variable \(Y\) denotes a label associated to a particular group of 
observations (i.e. cancer group), the <strong>supervised learning</strong> 
problem is also called a <strong>classification</strong> problem. In the third 
example, however, \(Y\) can take on any numerical value since it denotes some 
temperature reading (i.e. 25.143, 25.14233, 32.0). These types of supervised 
learning problems are also called <st
 rong>regression</strong> problems.</p><h3 id='training-a-predictive-model' 
class='header-anchors'>Training a Predictive Model</h3><p>A predictive model 
should be thought of as a function \(f\) that takes as input a set of features, 
and outputs a predicted outcome (i.e. \(f(X) = Y\)). The phrase 
<strong>training a model</strong> simply refers to the process of using the 
training data to estimate such a function. </p><h2 
id='predictionio-and-supervised-learning' class='header-anchors'>PredictionIO 
and Supervised Learning</h2><p>Machine learning methods generally assume that 
our observation responses and features are numeric vectors. We will say that 
observations in this format are in <strong>standard form</strong>. However, 
when you are working with real-life data this will often not be the case. The 
data will often be formatted in a manner that is specific to the 
application&#39;s needs. As an example, let&#39;s suppose our application is <a 
href="http://stackoverflow.com";>StackOverF
 low</a>. The data we want to analyze are questions, and we want to predict 
based on a question&#39;s content whether or not it is related to 
Scala.</p><p><strong>Self-check:</strong> Is this a classification or 
regression problem?</p><h3 id='thinking-about-data-with-predictionio' 
class='header-anchors'>Thinking About Data With 
PredictionIO</h3><p>PredictionIO&#39;s predictive engine development platform 
allows you to easily incorporate observations that are not in standard form. 
Continuing with our example, we can import the observations, or StackOverFlow 
questions, into <a href="/datacollection/">PredictionIO&#39;s Event Server</a> 
as events with the following properties:</p><p><code>properties = {question : 
String, topic : String}</code></p><p>The value <code>question</code> is the 
actual question stored as a <code>String</code>, and topic is also a string 
equal to either <code>&quot;Scala&quot;</code> or 
<code>&quot;Other&quot;</code>. Our outcome here is <code>topic</code>, and 
 <code>question</code> will provide a source for extracting features. That is, 
we will be using <code>question</code> to predict the outcome 
<code>topic</code>.</p><p>Once the observations are loaded as events into the 
Event Server, the engine&#39;s <a href="/customize/">Data Source</a> component 
is able to read them, which allows you to treat them as objects in a Scala 
project. The engine&#39;s Preparator component is in charge of converting these 
observations into standard form. To do this, we can first map the topic values 
as follows:</p><p><code>Map(&quot;Other&quot; -&gt; 0, &quot;Scala&quot; -&gt; 
1)</code>.</p><p>We can then vectorize the observation&#39;s associated 
question text to obtain a numeric feature vector for each of our observations. 
This text vectorization procedure is an example of a general concept in machine 
learning called <strong>feature extraction</strong>. After performing these 
transformations of our observations, they are now in standard form and can be us
 ed for training a large quantity of machine learning models.</p><h3 
id='training-the-model-with-predictionio' class='header-anchors'>Training the 
Model With PredictionIO</h3><p>The Algorithm engine component serves two 
purposes: outputting a predictive model \(f\) and using this to predict the 
outcome variable. Here \(f\) takes as input a vectorized question and outputs 
either 0 or 1. However, our <code>Query</code> input will be again a question, 
and our <code>PredictedResult</code> the topic associated to the predicted 
label (0 or 1):</p><p><code>Query = {question : String}</code> 
<code>PredictedResult = {topic : String}</code></p><p>With PredictionIO&#39;s 
engine development platform, you can easily automate the vectorization of the 
Query question, as well as mapping the predicted label to the appropriate topic 
output format.</p></div></div></div></div><footer><div class="container"><div 
class="seperator"></div><div class="row"><div class="col-md-6 
footer-link-column"><div class=
 "footer-link-column-row"><h4>Community</h4><ul><li><a 
href="//predictionio.apache.org/install/" 
target="blank">Download</a></li><li><a href="//predictionio.apache.org/" 
target="blank">Docs</a></li><li><a href="//github.com/apache/predictionio" 
target="blank">GitHub</a></li><li><a 
href="mailto:[email protected]"; 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 
footer-link-column"><div 
class="footer-link-column-row"><h4>Contribute</h4><ul><li><a 
href="//predictionio.apache.org/community/contribute-code/" 
target="blank">Contribute</a></li><li><a 
href="//github.com/apache/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:[email protected]"; target="blank">Subscribe to 
Development Mailing List</a></li></u
 l></div></div></div><div class="row"><div class="col-md-12 
footer-link-column"><p>Apache PredictionIO, PredictionIO, Apache, the Apache 
feather logo, and the Apache PredictionIO project logo are either registered 
trademarks or trademarks of The Apache Software Foundation in the United States 
and other countries.</p><p>All other marks mentioned may be trademarks or 
registered trademarks of their respective owners.</p></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"/><span>®</span></div><div 
id="social-icons-wrapper"><a class="github-button" 
href="https://github.com/apache/predictionio"; data-icon="octicon-star" 
data-show-count="true" aria-label="Star apache/predictionio on GitHub">Star</a> 
<a class="github-button" href="https://github.com/apache/predictionio/fork"; 
data-icon="octicon-repo-forked" data-show-count="true" aria-label="Fo
 rk apache/predictionio on GitHub">Fork</a> <script id="github-bjs" async="" 
defer="" src="https://buttons.github.io/buttons.js";></script><a 
href="https://twitter.com/predictionio"; target="blank"><img alt="PredictionIO 
on Twitter" src="/images/icons/twitter-ea9dc152.png"/></a> <a 
href="https://www.facebook.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-d943a254.js"></script></body></html>
\ No newline at end of file

Reply via email to