http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/d622bec7/system/deploy-cloudformation/index.html ---------------------------------------------------------------------- diff --git a/system/deploy-cloudformation/index.html b/system/deploy-cloudformation/index.html new file mode 100644 index 0000000..f0273a5 --- /dev/null +++ b/system/deploy-cloudformation/index.html @@ -0,0 +1,8 @@ +<!DOCTYPE html><html><head><title>Deploying with AWS CloudFormation</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="Deploying with AWS CloudFormation"/><link rel="canonical" href="https://predictionio.incubator.apache.org/system/deploy-cloudformation/"/><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-3a3867f7.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 col-xs-11"><div class="hidden-md hidden-lg" id="mobile-page-heading-wrapper"><p>PredictionIO Docs</p><h4>Deploying with AWS CloudFormation</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"><di v 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 Comm and-line Interface</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></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/"><spa n>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 Dashb oard</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/recommendation/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="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>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="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 you r 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-we bhook/"><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/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></ul></nav></div><div class="col-md-9 col-sm-12"><di v class="content-header hidden-md hidden-lg"><div id="page-title"><h1>Deploying with AWS CloudFormation</h1></div></div><div id="table-of-content-wrapper"><h5>On this page</h5><aside id="table-of-contents"><ul> <li> <a href="#overview">Overview</a> </li> <li> <a href="#step-by-step">Step-by-Step</a> </li> <li> <a href="#using-the-cluster">Using the Cluster</a> </li> <li> <a href="#scaling-the-cluster">Scaling the Cluster</a> </li> <li> <a href="#support-and-pricing">Support and Pricing</a> </li> </ul> </aside><hr/><a id="edit-page-link" href="https://github.com/apache/incubator-predictionio/tree/livedoc/docs/manual/source/system/deploy-cloudformation.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>Deploying with AWS CloudFormation</h1></div></div><div class="content"> <h2 id='overview' class='header-anchors'>Overview</h2><p>You can scale PredictionIO on AWS with <a href=" http://aws.amazon.com/cloudformation/";>CloudFormation</a>. Here we have defined a PredictionIO CloudFormation stack that you can deploy a functional, fully distributed PredictionIO cluster in minutes.</p><h3 id='instances' class='header-anchors'>Instances</h3><p>The PredictionIO CloudFormation stack creates two types of instance: <strong>compute and storage</strong>. By default, the stack will launch <strong>1 compute Instance and 3 Storage instances</strong>.</p><p>The compute instance <em>(ComputeInstance)</em> acts as Spark master. You can launch extra compute instances <em>(ComputeInstanceExtra)</em> by updating the stack. The storage instances <em>(StorageInstance)</em> form the core of the HDFS, ZooKeeper quorum, and HBase storage. Extra storage instances <em>(StorageInstanceExtra)</em> can be added to the cluster by updating the stack. They cannot be removed once they are spinned up.</p><p>PredictionIO Event Server will be launched on all storage instances.</p><h3 id='network ing' class='header-anchors'>Networking</h3><p>The stack will automatically create a VPC and a subnet with an Internet gateway. All cluster instances will be launched inside this subnet using a single security group that enables all TCP communications among all instances within the same group. All compute instances (including those that are launched after stack creation) will receive public IPs. All core storage instances will receive public Elastic IPs.</p><h2 id='step-by-step' class='header-anchors'>Step-by-Step</h2><p>First, you need to have an active Amazon Web Services account with permissions to use the following services:</p> <ul> <li>Auto Scaling</li> <li>CloudFormation</li> <li>EC2</li> <li>VPC</li> </ul> <h3 id='subscribe-to-predictionio-cluster' class='header-anchors'>Subscribe to PredictionIO Cluster</h3><p>Before you can start using PredictionIO CloudFormation template, you will need to subscribe to PredictionIO Cluster AMI through AWS Marketplace. To subscribe, go to th is <a href="https://aws.amazon.com/marketplace/pp/B00S74CY0A";>link</a>. Click the yellow "Continue" button on the next screen.</p><p><img alt="AWS Marketplace Subscription Page" src="/images/cloudformation/awsmp-1-609eb919.png"/></p><p>In the next screen, click the "Manual Launch" tab, then select your preferred pricing model. Pick your desired version, then click "Accept Terms".</p><p><img alt="AWS Marketplace Term Page" src="/images/cloudformation/awsmp-2-7dd613ba.png"/></p><p>Once your subscription is in place, you may proceed to the next section.</p><h3 id='start-using-cloudformation' class='header-anchors'>Start Using CloudFormation</h3><p>From your main AWS console, locate CloudFormation and click on it.</p><p><img alt="CloudFormation on AWS Console" src="/images/cloudformation/cf-01-13c7f924.png"/></p><p>This will bring you to the CloudFormation console below.</p><p><img alt="CloudFormation Console" src="/images/cloudformation/cf-02-61cd8e67.png" /></p><h3 id='select-the-predictionio-cloudformation-stack-template' class='header-anchors'>Select the PredictionIO CloudFormation Stack Template</h3><p>From the CloudFormation console, click on the <strong>Create New Stack</strong> blue button as shown above. This will bring up the <strong>Select Template</strong> screen. Name your stack as you like. Within the <em>Template</em> section, choose <strong>Specify an Amazon S3 template URL</strong>, and put <a href="https://s3.amazonaws.com/cloudformation.prediction.io/0.12.0-incubating/pio.json";>https://s3.amazonaws.com/cloudformation.prediction.io/0.12.0-incubating/pio.json</a> as the value.</p><p><img alt="CloudFormation Stack Template Selection" src="/images/cloudformation/cf-03-d017fa2d.png"/></p><p>Click <strong>Next</strong> when you are done.</p><h3 id='specify-stack-parameters' class='header-anchors'>Specify Stack Parameters</h3><p>The next screen shows the stack parameters. You must enter your AWS SSH key pair. For the other parameters, you can change them to meet your needs or simply use the default values.</p><p><img alt="Stack Parameters" src="/images/cloudformation/cf-04-6b545f50.png"/></p> <table><thead> <tr> <th>Parameter</th> <th>Description</th> </tr> </thead><tbody> <tr> <td>AWS-KeyPair</td> <td>The AWS SSH key pair name that can be used to access all instances in the cluster.</td> </tr> <tr> <td>AvailabilityZone</td> <td>Specify the availability zone that the PredictionIO cluster will be launched in. All instances of the cluster will be launched into the same zone for optimal network performance between one another.</td> </tr> <tr> <td>ComputeInstanceType</td> <td>The EC2 instance type of all compute instances. Memory-optimized EC2 instances are recommended.</td> </tr> <tr> <td>ComputeInstanceExtra</td> <td>Number of extra compute instances besides the core compute instance. This can be increased and decreased.</td> </tr> <tr> <td>StorageInstanceExtra</td> <td>Number of extra storage instances besides core storage instances. <strong>Never decrease this value or you will risk data corruption.</strong></td> </tr> <tr> <td>StorageInstanceExtraSize</td> <td>Size in GB of each extra storage instance. This can be changed when you add an extra storage instance.</td> </tr> <tr> <td>StorageInstanceExtraVolumeType</td> <td>The EBS volume type of each extra storage instance. Valid values are <em>standard</em> and <em>gp2</em>. This can be changed when you add an extra storage instance.</td> </tr> <tr> <td>StorageInstanceType</td> <td>The EC2 instance type of all storage instances. General purpose EC2 instances are recommended.</td> </tr> <tr> <td>StorageInstanceSize</td> <td>Size in GB of each core storage instance. This cannot be changed once the cluster is launched.</td> </tr> <tr> <td>StorageInstanceVolumeType</td> <td>The EBS volume type of each core storage instance. Valid values are <em>standard</em> and <em>gp2</em>. This cannot be changed once the cluster is launched.</td> </tr> </tbody></table> <p>Click <strong>Next</strong> when you are done. You will arrive at the <strong>Options</strong> screen. You can skip this step if you do not have other options to specify.</p><p>At the <strong>Review</strong> screen, click <strong>Create</strong> to finish.</p><h2 id='using-the-cluster' class='header-anchors'>Using the Cluster</h2><p>You should see the following when the cluster is being created after the previous step.</p><p><img alt="Stack Creation" src="/images/cloudformation/cf-05-92ee63c2.png"/></p><p>Once the stack creation has finished, you can click on <strong>Events</strong> and select <strong>Outputs</strong> to arrive to the following screen.</p><p><img alt="Completed Stack" src="/images/cloudformation/cf-06-b36528fa.png"/></p><p>Take note of <strong>PIOComputeMasterPublicIp</strong> and <strong>PIOStorageMasterPublicIp</strong>. We will now access the cluster and make sure everything is in place.</p><div class="alert-message warning"><p>Sometimes the stack is created successfully but not all cluster services would launch due to potential network glitches or system issues within a cluster instance. In this case, simply delete and create the stack again.</p></div><h3 id='verify-compute-instances' class='header-anchors'>Verify Compute Instances</h3><p>SSH to the master compute instance using the <strong>PIOComputeMasterPublicIp</strong>. In this example, let us assume the IP address be 54.175.145.84, and your private key file be <strong>yourkey.pem</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</pre></td><td class="code"><pre><span class="gp">$ </span>ssh -i yourkey.pem -A -L 8080:localhost:8080 [email protected] +</pre></td></tr></tbody></table> </div> <p>Once you are in, point your web browser to <a href="http://localhost:8080";>http://localhost:8080</a>. You should see something similar to the following.</p><p><img alt="Example Spark UI" src="/images/cloudformation/spark-019c2cf1.png"/></p><div class="alert-message note"><p>In the example above <strong>NumberOfComputeWorkers</strong> is <strong>2</strong>. This is because the example has 1 compute instance and 1 extra compute instance. If you do not have any extra compute instances, you will see only 1 worker on the above page.</p></div><h3 id='verify-storage-instances' class='header-anchors'>Verify Storage Instances</h3><p>SSH to the storage instance using the <strong>PIOStorageMasterPublicIp</strong>. In this example, let us assume the IP address be 54.175.1.36, and your private key file be <strong>yourkey.pem</strong>.</p><div class="highlight shell"><table style="border-spacing: 0"><tbody><tr><td class="gutter gl" style="text-align: rig ht"><pre class="lineno">1</pre></td><td class="code"><pre><span class="gp">$ </span>ssh -i yourkey.pem -A -L 50070:localhost:50070 -L 16010:localhost:16010 -L 16030:localhost:16030 [email protected] +</pre></td></tr></tbody></table> </div> <p>Once you are in, point your web browser to <a href="http://localhost:50070";>http://localhost:50070</a> and click on <strong>Datainstances</strong> at the top menu. You should see the following page.</p><p><img alt="Example HDFS UI" src="/images/cloudformation/hdfs-51f0231f.png"/></p><div class="alert-message warning"><p>All <strong>3 storage instances</strong> must be up for proper operation.</p></div><p>If all <strong>3 storage instances</strong> are working properly, you can then verify HBase by pointing your web browser to <a href="http://localhost:16010";>http://localhost:16010</a>. You should see something similar to the following.</p><p><img alt="Example HBase UI" src="/images/cloudformation/hbase-32538c47.png"/></p><p>If you do not specify any extra storage instances, you should see 2 region servers. There should also be 1 backup master.</p><h3 id='running-quick-start' class='header-anchors'>Running Quick Start</h3><p>You can now star t with the fully-distributed PredictionIO cluster. Let's start with the <a href="/templates/recommendation/quickstart/">recommendation quick start</a> with a few twists.</p> <ol> <li><p>Skip the installation steps and run <code>pio status</code>. You should see everything functional.</p></li> <li><p>Run through the section <strong>Create a Sample App</strong> as described. The installation directory of PredictionIO is <code>/opt/PredictionIO</code>.</p></li> <li><p>Run through the section <strong>Collecting Data</strong> as described, except that you will be connecting to the Event Server at the master core storage instance. Assuming the private IP of the master core storage instance is <code>10.0.0.123</code>, add <code>--url http://10.0.0.123:7070</code> to the <code>import_eventserver.py</code> command.</p></li> <li><p>Copy HBase configuration to the engine template directory. The full path of the configuration file is <code>/opt/hbase-0.98.9-hadoop2/conf/hbase-site.xml</code >. (This step will not be required in future releases.)</p></li> <li><p>Run >through the section <strong>Deploy the Engine as a Service</strong> up to the >subsection <strong>Training</strong>. Assuming the private DNS name of the >master compute instance is <code>ip-10-0-0-234.ec2.internal</code>, add ><code>-- --master spark://ip-10-0-0-234.ec2.internal:7077</code> after the ><code>pio train</code> command. This will send the training to the compute >cluster instead of the local machine. The Spark master URL must match exactly >the one shown on its web UI. Repeat the same steps for subsection ><strong>Deploying</strong>, which will create an Engine Server backed by the >compute cluster.</p></li> </ol> <h2 id='scaling-the-cluster' >class='header-anchors'>Scaling the Cluster</h2><p>As your data size and/or >audience grow, you can scale your cluster to handle more workload or decrease >turnaround time. In this section, we will provide some general guidelines >about when and how to scale your clus ter with CloudFormation.</p><h3 id='scaling-compute-instances' class='header-anchors'>Scaling Compute Instances</h3><p>You can increase compute instances to reduce training time <em>($pio train)</em> and the time to query an engine server. You can also check the [Spark Master Web UI] to see if you need additional compute power.</p><p>Notice that for compute instances, you can increase or decrease the number of extra compute instances <em>(ComputeInstanceExtra)</em> as much as you like. The extra compute instances will join the master and become slave compute instances as Spark workers.</p><p>Let us begin by adding 2 extra compute instances. At the CloudFormation console, right click on the cluster stack and click on <strong>Update Stack</strong>.</p><p><img alt="Updating Stack to Add Extra Compute Instances" src="/images/cloudformation/compute-1-c572ea84.png"/></p><p>At the <strong>Select Template</strong> screen, make sure <strong>Use existing template</strong> is picked, then clic k <strong>Next</strong>.</p><p>At the <strong>Specify Parameters</strong> screen, increase the value of <strong>ComputeInstanceExtra</strong> to <strong>2</strong>, then click <strong>Next</strong>.</p><p><img alt="Adding 2 Extra Compute Instances" src="/images/cloudformation/compute-2-f7da8e72.png"/></p><p>At the <strong>Options</strong> screen, leave everything unchanged, and click <strong>Next</strong>.</p><p>At the <strong>Review</strong> screen, make sure <strong>ComputeInstanceExtra</strong> is now updated to <strong>2</strong>. Finish by clicking <strong>Update</strong>.</p><p><img alt="Review Changes of Adding Extra Compute Instances" src="/images/cloudformation/compute-3-ee5fc6a8.png"/></p><p>You will be brought back to the CloudFormation console. You should see the stack status changed to <strong>UPDATE_IN_PROGRESS</strong>.</p><p><img alt="Adding Extra Compute Instances In Progress" src="/images/cloudformation/compute-4-67fe0caa.png"/></p><p>Once the status become <strong >UPDATE_COMPLETED</strong>, you will have 2 extra compute instances. Notice >that during the update, your cluster is still functional and any existing >work will not be affected. If you are downscaling, existing work might be >affected during the update process.</p><h3 id='scaling-storage-instances' >class='header-anchors'>Scaling Storage Instances</h3><p>You can scale your >storage instances when you are about to run out of space. You can check your >storage usage at the [Hadoop NameNode web UI].</p><div class="alert-message >warning"><p>For storage instances, you can only increase the number of extra >storage instances <em>(StorageInstanceExtra)</em> within the bounds of AWS >EC2 limits. Decreasing the instances will risk data >corruption.</p></div><p>Let us begin by adding 2 extra storage instances. At >the CloudFormation console, right click on the cluster stack and click on ><strong>Update Stack</strong>.</p><p><img alt="Updating Stack to Add Extra >Storage Instances" src="/images/cloudform ation/compute-1-c572ea84.png"/></p><p>At the <strong>Select Template</strong> screen, make sure <strong>Use existing template</strong> is picked, then click <strong>Next</strong>.</p><p>At the <strong>Specify Parameters</strong> screen, increase the value of <strong>StorageInstanceExtra</strong> to <strong>2</strong>, and set the value of <strong>StorageInstanceExtraSize</strong> to <strong>100</strong>, then click <strong>Next</strong>. Notice that whenever you add an extra storage instance, you can change its size to a new value. The new size will not affect existing storage instances and your data will be safe.</p><p><img alt="Adding 2 Extra Storage Instances" src="/images/cloudformation/storage-1-ca3ae3a6.png"/></p><p>At the <strong>Options</strong> screen, leave everything unchanged, and click <strong>Next</strong>.</p><p>At the <strong>Review</strong> screen, make sure <strong>StorageInstanceExtra</strong> is now updated to <strong>2</strong>, and <strong>StorageInstanceExtraS ize</strong> is updated to <strong>100</strong>. Finish by clicking <strong>Update</strong>.</p><p><img alt="Review Changes of Adding Extra Storage Instances" src="/images/cloudformation/storage-2-9395c9f2.png"/></p><p>You will be brought back to the CloudFormation console. You should see the stack status changed to <strong>UPDATE_IN_PROGRESS</strong>.</p><p><img alt="Adding Extra Compute Instances In Progress" src="/images/cloudformation/compute-4-67fe0caa.png"/></p><p>Once the status become <strong>UPDATE_COMPLETED</strong>, you will have 2 extra storage instances. Notice that during the up-scaling update, your cluster is still functional and existing work will not be affected. They may be affected during downscale.</p><h2 id='support-and-pricing' class='header-anchors'>Support and Pricing</h2><p>PredictionIO Cluster comes with Enterprise Support. For pricing and support details, please contact <a href="mailto:[email protected]";>[email protected]</a>.</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.incubator.apache.org/install/" target="blank">Download</a></li><li><a href="//predictionio.incubator.apache.org/" target="blank">Docs</a></li><li><a href="//github.com/apache/incubator-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.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:[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"><a class="pull-right" href="http://incubator.apache.org/projects/predictionio.html";><img alt="Apache Incubator" src="/images/logos/apache_incubator-6954bd16.png"/></a><span>Apache PredictionIO is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.</ span></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="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-3058a372.js"></script></body></html> \ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/d622bec7/system/deploy-cloudformation/index.html.gz ---------------------------------------------------------------------- diff --git a/system/deploy-cloudformation/index.html.gz b/system/deploy-cloudformation/index.html.gz new file mode 100644 index 0000000..93a4ae3 Binary files /dev/null and b/system/deploy-cloudformation/index.html.gz differ http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/d622bec7/system/index.html ---------------------------------------------------------------------- diff --git a/system/index.html b/system/index.html new file mode 100644 index 0000000..306ea02 --- /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://predictionio.incubator.apache.org/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-3a3867f7.css" rel="stylesheet" type="text/css"/><script src="//cdnjs.cloudflare.com/ajax/libs/html5shiv/3.7.2/html5shiv.min.js"></script><script src="//cd n.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>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" 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</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></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</spa n></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 clas s="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 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>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="/templat es/recommendation/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 c lass="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" hre f="/templates/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 clas s="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 Templat e</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>Contrib ute 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/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></ul></nav></div><div class="col-md-9 col-sm-12"><div class="content-head er 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-page-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 followi ng 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 clas s="row"><div class="col-md-6 footer-link-column"><div class="footer-link-column-row"><h4>Community</h4><ul><li><a href="//predictionio.incubator.apache.org/install/" target="blank">Download</a></li><li><a href="//predictionio.incubator.apache.org/" target="blank">Docs</a></li><li><a href="//github.com/apache/incubator-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.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:[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"><a class="pull-right" >href="http://incubator.apache.org/projects/predictionio.html";><img >alt="Apache Incubator" >src="/images/logos/apache_incubator-6954bd16.png"/></a><span>Apache >PredictionIO is an effort undergoing incubation at The Apache Software >Foundation (ASF), sponsored by the Apache Incubator. Incubation is required >of all newly accepted projects until a further review indicates that the >infrastructure, communications, and decision making process have stabilized >in a manner consistent with other successful ASF projects. While incubation >status is not necessarily a reflection of the completeness or stability of >the code, it does indicate that the project has yet to be fully endorsed by >the ASF.</span></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="https://twit ter.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-3058a372.js"></script></body></html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/d622bec7/system/index.html.gz ---------------------------------------------------------------------- diff --git a/system/index.html.gz b/system/index.html.gz new file mode 100644 index 0000000..43cea01 Binary files /dev/null and b/system/index.html.gz differ
