| <!DOCTYPE html> |
| |
| |
| |
| <html lang="en"> |
| <head> |
| <!-- Global site tag (gtag.js) - Google Analytics --> |
| <script async src="https://www.googletagmanager.com/gtag/js?id=UA-61232409-1"></script> |
| <script> |
| window.dataLayer = window.dataLayer || []; |
| function gtag(){dataLayer.push(arguments);} |
| gtag('js', new Date()); |
| |
| gtag('config', 'UA-61232409-1'); |
| </script> |
| |
| |
| |
| <meta charset="UTF-8"> |
| <meta name="ignite-version" content="2.9.0" /> |
| <title>Preprocessing | Ignite Documentation</title> |
| |
| <link rel="canonical" href="/docs/2.9.0/machine-learning/preprocessing" /> |
| |
| |
| <link rel="stylesheet" href="/assets/css/styles.css?1600286558"> |
| <link rel="stylesheet" href="/assets/css/asciidoc-pygments.css"> |
| <link rel="shortcut icon" href="/favicon.ico"> |
| <meta name='viewport' content='width=device-width, height=device-height, initial-scale=1.0, minimum-scale=1.0'> |
| |
| <script type="text/javascript" src="/assets/js/anchor.min.js?1600286558"></script> |
| |
| <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/docsearch.js@2/dist/cdn/docsearch.min.css" /> |
| |
| |
| </head> |
| <body> |
| <header> |
| <!--#include virtual="/includes/promotion_banner.html" --> |
| <div class="container"> |
| <button type='button' class='menu' title='Docs menu'> |
| <img src="/assets/images/menu-icon.svg"/> |
| </button> |
| <div class='home'> |
| <a href="/" class='home' title='Apache Ignite home'> |
| <img src="/assets/images/apache_ignite_logo.svg" alt="Apache Ignite logo" width="103" > |
| </a> |
| </div> |
| |
| <nav> |
| |
| </nav> |
| |
| <select id="version-selector"> |
| <option value="2.9.0">2.9.0</option> |
| </select> |
| |
| <a href="https://github.com/apache/ignite" title='GitHub' class='github' target="_blank"> |
| <img src="/assets/images/github-gray.svg" alt="GitHub logo"> |
| </a> |
| |
| <form class='search'> |
| <button class="search-close" type='button'><img src='/assets/images/cancel.svg'></button> |
| <input type="search" placeholder="Search…" id="search-input"> |
| </form> |
| <button type='button' class='search-toggle'><img src='/assets/images/search.svg'></button> |
| <button type='button' class='top-nav-toggle'>⋮</button> |
| |
| |
| |
| </div> |
| </header> |
| |
| |
| <link rel="stylesheet" href="/assets/css/docs.css"> |
| <section class='page-docs'> |
| |
| |
| |
| |
| <nav class='left-nav' data-swiftype-index='false'> |
| |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/preface" class='' >Preface</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Quick Start Guides<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/quick-start/java" |
| |
| class='' |
| >Java</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/quick-start/dotnet" |
| |
| class='' |
| >.NET/C#</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/quick-start/cpp" |
| |
| class='' |
| >C++</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/quick-start/python" |
| |
| class='' |
| >Python</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/quick-start/nodejs" |
| |
| class='' |
| >Node.JS</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/quick-start/sql" |
| |
| class='' |
| >SQL</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/quick-start/php" |
| |
| class='' |
| >PHP</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/quick-start/restapi" |
| |
| class='' |
| >REST API</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="/installation" class='group-toggle collapsed '>Installation<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/installation/installing-using-zip" |
| |
| class='' |
| >Installing Using ZIP Archive</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/installation/installing-using-docker" |
| |
| class='' |
| >Installing Using Docker</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/installation/deb-rpm" |
| |
| class='' |
| >Installing DEB or RPM package</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Kubernetes<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//installation/kubernetes/amazon-eks-deployment" class=''>Amazon EKS</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//installation/kubernetes/azure-deployment" class=''>Azure Kubernetes Service</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//installation/kubernetes/gke-deployment" class=''>Google Kubernetes Engine</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Setting Up<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/setup" |
| |
| class='' |
| >Setting Up Ignite for Java</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/setup-dotnet" |
| |
| class='' |
| >Setting Up Ignite for .NET/C#</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/understanding-configuration" class='' >Understanding Configuration</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/logging" class='' >Configuring Logging</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/starting-nodes" class='' >Starting and Stopping Nodes</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Clustering<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/clustering/clustering" |
| |
| class='' |
| >Overview</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/clustering/tcp-ip-discovery" |
| |
| class='' |
| >TCP/IP Discovery</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/clustering/zookeeper-discovery" |
| |
| class='' |
| >ZooKeeper Discovery</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/clustering/discovery-in-the-cloud" |
| |
| class='' |
| >Discovery in the Cloud</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/clustering/network-configuration" |
| |
| class='' |
| >Network Configuration</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/clustering/connect-client-nodes" |
| |
| class='' |
| >Connecting Client Nodes</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/clustering/running-client-nodes-behind-nat" |
| |
| class='' |
| >Running Client Nodes Behind NAT</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Data Modeling<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/data-modeling/data-modeling" |
| |
| class='' |
| >Introduction</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/data-modeling/data-partitioning" |
| |
| class='' |
| >Data Partitioning</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/data-modeling/affinity-collocation" |
| |
| class='' |
| >Affinity Colocation</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Configuring Memory<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/memory-architecture" |
| |
| class='' |
| >Memory Architecture</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/memory-configuration/data-regions" |
| |
| class='' |
| >Configuring Data Regions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/memory-configuration/eviction-policies" |
| |
| class='' |
| >Eviction Policies</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Configuring Caches<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/configuring-caches/configuration-overview" |
| |
| class='' |
| >Cache Configuration</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/configuring-caches/configuring-backups" |
| |
| class='' |
| >Configuring Partition Backups</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/configuring-caches/atomicity-modes" |
| |
| class='' |
| >Atomicity Modes</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/configuring-caches/expiry-policies" |
| |
| class='' |
| >Expiry Policy</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/configuring-caches/on-heap-caching" |
| |
| class='' |
| >On-Heap Caching</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/configuring-caches/cache-groups" |
| |
| class='' |
| >Cache Groups</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Persistence<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/persistence/native-persistence" |
| |
| class='' |
| >Ignite Persistence</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/persistence/external-storage" |
| |
| class='' |
| >External Storage</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/persistence/swap" |
| |
| class='' |
| >Swapping</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/persistence/custom-cache-store" |
| |
| class='' |
| >Implementing Custom Cache Store</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/persistence/disk-compression" |
| |
| class='' |
| >Disk Compression</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/persistence/persistence-tuning" |
| |
| class='' |
| >Tuning Persistence</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/baseline-topology" class='' >Baseline Topology</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/cluster-states" class='' >Cluster States</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/data-rebalancing" class='' >Data Rebalancing</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/partition-loss-policy" class='' >Partition Loss Policy</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/deploying-user-code" class='' >Deploying User Code</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/peer-class-loading" class='' >Peer Class Loading</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/data-streaming" class='' >Data Streaming</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Using Key-Value Cache API<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/key-value-api/basic-cache-operations" |
| |
| class='' |
| >Basic Cache Operations</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/key-value-api/binary-objects" |
| |
| class='' |
| >Working with Binary Objects</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/key-value-api/using-scan-queries" |
| |
| class='' |
| >Using Scan Queries</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/read-repair" |
| |
| class='' |
| >Read Repair</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/key-value-api/continuous-queries" class='' >Using Continuous Queries</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/key-value-api/transactions" class='' >Performing Transactions</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Working with SQL<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/sql-introduction" |
| |
| class='' |
| >Introduction</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/schemas" |
| |
| class='' |
| >Understanding Schemas</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/indexes" |
| |
| class='' |
| >Defining Indexes</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/sql-api" |
| |
| class='' |
| >Using SQL API</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/distributed-joins" |
| |
| class='' |
| >Distributed Joins</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/sql-transactions" |
| |
| class='' |
| >SQL Transactions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/custom-sql-func" |
| |
| class='' |
| >Custom SQL Functions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/JDBC/jdbc-driver" |
| |
| class='' |
| >JDBC Driver</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/JDBC/jdbc-client-driver" |
| |
| class='' |
| >JDBC Client Driver</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/transactions/mvcc" |
| |
| class='' |
| >Multiversion Concurrency Control</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Distributed Computing<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/distributed-computing/distributed-computing" |
| |
| class='' |
| >Distributed Computing API</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/distributed-computing/cluster-groups" |
| |
| class='' |
| >Cluster Groups</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/distributed-computing/executor-service" |
| |
| class='' |
| >Executor Service</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/distributed-computing/map-reduce" |
| |
| class='' |
| >MapReduce API</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/distributed-computing/load-balancing" |
| |
| class='' |
| >Load Balancing</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/distributed-computing/fault-tolerance" |
| |
| class='' |
| >Fault Tolerance</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/distributed-computing/job-scheduling" |
| |
| class='' |
| >Job Scheduling</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/collocated-computations" class='' >Colocating Computations with Data</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Working with Events<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/events/listening-to-events" |
| |
| class='' |
| >Enabling and Listenting to Events</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/events/events" |
| |
| class='' |
| >Events</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/near-cache" class='' >Near Caches</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/platform-cache" class='' >.NET Platform Cache</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/services/services" class='' >Services</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Distributed Data Structures<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/data-structures/queue-and-set" |
| |
| class='' |
| >Queue and Set</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/data-structures/atomic-types" |
| |
| class='' |
| >Atomic Types</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/data-structures/countdownlatch" |
| |
| class='' |
| >CountDownLatch</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/data-structures/atomic-sequence" |
| |
| class='' |
| >Atomic Sequence</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/data-structures/semaphore" |
| |
| class='' |
| >Semaphore</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle expanded '>Machine Learning<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group expanded'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/machine-learning/machine-learning" |
| |
| class='' |
| >Machine Learning</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/machine-learning/partition-based-dataset" |
| |
| class='' |
| >Partition Based Dataset</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/machine-learning/updating-trained-models" |
| |
| class='' |
| >Updating Trained Models</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Binary Classification<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/binary-classification/introduction" class=''>Introduction</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/binary-classification/linear-svm" class=''>Linear SVM (Support Vector Machine)</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/binary-classification/decision-trees" class=''>Decision Trees</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/binary-classification/multilayer-perceptron" class=''>Multilayer Perceptron</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/binary-classification/logistic-regression" class=''>Logistic Regression</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/binary-classification/knn-classification" class=''>k-NN Classification</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/binary-classification/ann" class=''>ANN (Approximate Nearest Neighbor)</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/binary-classification/naive-bayes" class=''>Naive Bayes</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Regression<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/regression/introduction" class=''>Introduction</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/regression/linear-regression" class=''>Linear Regression</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/regression/decision-trees-regression" class=''>Decision Trees Regression</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/regression/knn-regression" class=''>k-NN Regression</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Clustering<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/clustering/introduction" class=''>Introduction</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/clustering/k-means-clustering" class=''>K-Means Clustering</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/clustering/gaussian-mixture" class=''>Gaussian mixture (GMM)</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/machine-learning/preprocessing" |
| |
| class='active' |
| >Preprocessing</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Model Selection<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/model-selection/introduction" class=''>Introduction</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/model-selection/evaluator" class=''>Evaluator</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/model-selection/split-the-dataset-on-test-and-train-datasets" class=''>Split the dataset on test and train datasets</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/model-selection/hyper-parameter-tuning" class=''>Hyper-parameter tuning</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/model-selection/pipeline-api" class=''>Pipeline API</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/machine-learning/multiclass-classification" |
| |
| class='' |
| >Multiclass Classification</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Ensemble Methods<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/ensemble-methods/introduction" class=''></a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/ensemble-methods/stacking" class=''>Stacking</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/ensemble-methods/baggin" class=''>Bagging</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/ensemble-methods/random-forest" class=''>Random Forest</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/ensemble-methods/gradient-boosting" class=''>Gradient Boosting</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/machine-learning/recommendation-systems" |
| |
| class='' |
| >Recommendation Systems</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Importing Model<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/importing-model/introduction" class=''>Introduction</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/importing-model/model-import-from-gxboost" class=''>Import Model from XGBoost</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//machine-learning/importing-model/model-import-from-apache-spark" class=''>Import Model from Apache Spark</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Monitoring<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/monitoring-metrics/intro" |
| |
| class='' |
| >Introduction</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/monitoring-metrics/cluster-id" |
| |
| class='' |
| >Cluster ID and Tag</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Metrics<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//monitoring-metrics/configuring-metrics" class=''>Configuring Metrics</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//monitoring-metrics/metrics" class=''>JMX Metrics</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>New Metrics System<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//monitoring-metrics/new-metrics-system" class=''>Introduction</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//monitoring-metrics/new-metrics" class=''>Metrics</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/monitoring-metrics/system-views" |
| |
| class='' |
| >System Views</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/monitoring-metrics/tracing" |
| |
| class='' |
| >Tracing</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="/security" class='group-toggle collapsed '>Security<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/security/authentication" |
| |
| class='' |
| >Authentication</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/security/ssl-tls" |
| |
| class='' |
| >SSL/TLS</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Transparent Data Encryption<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//security/tde" class=''>Introduction</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//security/master-key-rotation" class=''>Master key rotation</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Thin Clients<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/thin-clients/getting-started-with-thin-clients" |
| |
| class='' |
| >Thin Clients Overview</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/thin-clients/java-thin-client" |
| |
| class='' |
| >Java Thin Client</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/thin-clients/dotnet-thin-client" |
| |
| class='' |
| >.NET Thin Client</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/thin-clients/cpp-thin-client" |
| |
| class='' |
| >C++ Thin Client</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/thin-clients/python-thin-client" |
| |
| class='' |
| >Python Thin Client</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/thin-clients/php-thin-client" |
| |
| class='' |
| >PHP Thin Client</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/thin-clients/nodejs-thin-client" |
| |
| class='' |
| >Node.js Thin Client</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| |
| |
| <button |
| type='button' |
| class='collapsed '>Binary Client Protocol<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class="sub_pages collapsed"> |
| |
| |
| |
| |
| <li><a href="/docs/2.9.0//binary-client-protocol/binary-client-protocol" class=''>Binary Client Protocol</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//binary-client-protocol/data-format" class=''>Data Format</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//binary-client-protocol/key-value-queries" class=''>Key-Value Queries</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//binary-client-protocol/sql-and-scan-queries" class=''>SQL and Scan Queries</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//binary-client-protocol/binary-type-metadata" class=''>Binary Types Metadata</a></li> |
| |
| |
| |
| <li><a href="/docs/2.9.0//binary-client-protocol/cache-configuration" class=''>Cache Configuration</a></li> |
| |
| </nav> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>ODBC Driver<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/ODBC/odbc-driver" |
| |
| class='' |
| >ODBC Driver</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/ODBC/connection-string-dsn" |
| |
| class='' |
| >Connection String and DSN</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/ODBC/querying-modifying-data" |
| |
| class='' |
| >Querying and Modifying Data</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/ODBC/specification" |
| |
| class='' |
| >Specification</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/ODBC/data-types" |
| |
| class='' |
| >Data Types</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/SQL/ODBC/error-codes" |
| |
| class='' |
| >Error Codes</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/restapi" class='' >REST API</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/control-script" class='' >Control Script</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/plugins" class='' >Plugins</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| <a href="/docs/2.9.0/sqlline" class='' >SQLLine</a> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="" class='group-toggle collapsed '>Ignite for Spark<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/ignite-for-spark/overview" |
| |
| class='' |
| >Overview</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/ignite-for-spark/ignitecontext-and-rdd" |
| |
| class='' |
| >IgniteContext and IgniteRDD</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/ignite-for-spark/ignite-dataframe" |
| |
| class='' |
| >Ignite DataFrame</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/ignite-for-spark/installation" |
| |
| class='' |
| >Installation</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/ignite-for-spark/spark-shell" |
| |
| class='' |
| >Test Ignite with Spark-shell</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/ignite-for-spark/troubleshooting" |
| |
| class='' |
| >Troubleshooting</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| <li> |
| |
| |
| |
| |
| |
| |
| <button type='button' data-guide-url="/sql-reference/sql-reference-overview" class='group-toggle collapsed '>SQL Reference<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button> |
| <nav class='nav-group collapsed'> |
| |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/sql-conformance" |
| |
| class='' |
| >SQL Conformance</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/ddl" |
| |
| class='' |
| >Data Definition Language (DDL)</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/dml" |
| |
| class='' |
| >Data Manipulation Language (DML)</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/transactions" |
| |
| class='' |
| >Transactions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/operational-commands" |
| |
| class='' |
| >Operational Commands</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/aggregate-functions" |
| |
| class='' |
| >Aggregate functions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/numeric-functions" |
| |
| class='' |
| >Numeric Functions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/string-functions" |
| |
| class='' |
| >String Functions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/date-time-functions" |
| |
| class='' |
| >Data and Time Functions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/system-functions" |
| |
| class='' |
| >System Functions</a> |
| |
| </li> |
| |
| |
| |
| |
| |
| <li> |
| |
| <a href="/docs/2.9.0/sql-reference/data-types" |
| |
| class='' |
| >Data Types</a> |
| |
| </li> |
| |
| |
| |
| </nav> |
| |
| </li> |
| |
| </nav> |
| <div class="left-nav__overlay"></div> |
| |
| |
| <article data-swiftype-index='true'> |
| <a class='edit-link' href="https://github.com/apache/ignite/tree/IGNITE-7595/docs/_docs/machine-learning/preprocessing.adoc" target="_blank">Edit</a> |
| |
| <h1>Preprocessing</h1> |
| |
| <div id="preamble"> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>Preprocessing is required to transform raw data stored in an Ignite cache to the dataset of feature vectors suitable for further use in a machine learning pipeline.</p> |
| </div> |
| <div class="paragraph"> |
| <p>This section covers algorithms for working with features, roughly divided into the following groups:</p> |
| </div> |
| <div class="ulist"> |
| <ul> |
| <li> |
| <p>Extracting features from “raw” data</p> |
| </li> |
| <li> |
| <p>Scaling features</p> |
| </li> |
| <li> |
| <p>Converting features</p> |
| </li> |
| <li> |
| <p>Modifying features</p> |
| </li> |
| </ul> |
| </div> |
| <div class="admonitionblock note"> |
| <table> |
| <tr> |
| <td class="icon"> |
| <div class="title">Note</div> |
| </td> |
| <td class="content"> |
| Usually it starts from label and feature extraction via vectorizer usage and can be complicated with other preprocessing stages. |
| </td> |
| </tr> |
| </table> |
| </div> |
| </div> |
| </div> |
| <div class="sect1"> |
| <h2 id="normalization-preprocessor">Normalization preprocessor</h2> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>The normal flow is to extract features and labels from Ignite data via a vectorizer, transform the features and then normalize them.</p> |
| </div> |
| <div class="paragraph"> |
| <p>In addition to the ability to build any custom preprocessor, Apache Ignite provides a built-in normalization preprocessor. This preprocessor makes normalization on each vector using p-norm.</p> |
| </div> |
| <div class="paragraph"> |
| <p>For normalization, you need to create a NormalizationTrainer and fit a normalization preprocessor as follows:</p> |
| </div> |
| <div class="listingblock"> |
| <div class="content"> |
| <pre class="rouge highlight"><code data-lang="java"><span class="c1">// Train the preprocessor on the given data</span> |
| <span class="nc">Preprocessor</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">></span> <span class="n">preprocessor</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">NormalizationTrainer</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">>()</span> |
| <span class="o">.</span><span class="na">withP</span><span class="o">(</span><span class="mi">1</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">ignite</span><span class="o">,</span> <span class="n">data</span><span class="o">,</span> <span class="n">vectorizer</span><span class="o">);</span> |
| |
| <span class="c1">// Create linear regression trainer.</span> |
| <span class="nc">LinearRegressionLSQRTrainer</span> <span class="n">trainer</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">LinearRegressionLSQRTrainer</span><span class="o">();</span> |
| |
| <span class="c1">// Train model.</span> |
| <span class="nc">LinearRegressionModel</span> <span class="n">mdl</span> <span class="o">=</span> <span class="n">trainer</span><span class="o">.</span><span class="na">fit</span><span class="o">(</span> |
| <span class="n">ignite</span><span class="o">,</span> |
| <span class="n">upstreamCache</span><span class="o">,</span> |
| <span class="n">preprocessor</span> |
| <span class="o">);</span></code></pre> |
| </div> |
| </div> |
| </div> |
| </div> |
| <div class="sect1"> |
| <h2 id="examples">Examples</h2> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>To see how the Normalization Preprocessor can be used in practice, try this <a href="https://github.com/apache/ignite/blob/master/examples/src/main/java/org/apache/ignite/examples/ml/preprocessing/NormalizationExample.java">example</a> that is available on GitHub and delivered with every Apache Ignite distribution.</p> |
| </div> |
| </div> |
| </div> |
| <div class="sect1"> |
| <h2 id="binarization-preprocessor">Binarization preprocessor</h2> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>Binarization is the process of thresholding numerical features to binary (0/1) features. |
| Feature values greater than the threshold are binarized to 1.0; values equal to or less than the threshold are binarized to 0.0.</p> |
| </div> |
| <div class="paragraph"> |
| <p>It contains only one significant parameter, which is the threshold.</p> |
| </div> |
| <div class="listingblock"> |
| <div class="content"> |
| <pre class="rouge highlight"><code data-lang="java"><span class="c1">// Create binarization trainer.</span> |
| <span class="nc">BinarizationTrainer</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">></span> <span class="n">binarizationTrainer</span> |
| <span class="o">=</span> <span class="k">new</span> <span class="nc">BinarizationTrainer</span><span class="o"><>().</span><span class="na">withThreshold</span><span class="o">(</span><span class="mi">40</span><span class="o">);</span> |
| |
| <span class="c1">// Build the preprocessor.</span> |
| <span class="nc">Preprocessor</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">></span> <span class="n">preprocessor</span> <span class="o">=</span> <span class="n">binarizationTrainer</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">ignite</span><span class="o">,</span> <span class="n">data</span><span class="o">,</span> <span class="n">vectorizer</span><span class="o">);</span></code></pre> |
| </div> |
| </div> |
| <div class="paragraph"> |
| <p>To see how the Binarization Preprocessor can be used in practice, try this <a href="https://github.com/apache/ignite/blob/master/examples/src/main/java/org/apache/ignite/examples/ml/preprocessing/BinarizationExample.java">example</a>.</p> |
| </div> |
| </div> |
| </div> |
| <div class="sect1"> |
| <h2 id="imputer-preprocessor">Imputer preprocessor</h2> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>The Imputer preprocessor completes missing values in a dataset, either using the mean or another statistic of the column in which the missing values are located. The missing values should be presented as Double.NaN. The input dataset column should be of Double. Currently, the Imputer preprocessor does not support categorical features and possibly creates incorrect values for columns containing categorical features.</p> |
| </div> |
| <div class="paragraph"> |
| <p>During the training phase, the Imputer Trainer collects statistics about the preprocessing dataset and in the preprocessing phase it changes the data according to the collected statistics.</p> |
| </div> |
| <div class="paragraph"> |
| <p>The Imputer Trainer contains only one parameter: <code>imputingStgy</code> that is presented as enum <strong>ImputingStrategy</strong> with two available values (NOTE: future releases may support more values):</p> |
| </div> |
| <div class="ulist"> |
| <ul> |
| <li> |
| <p>MEAN: The default strategy. If this strategy is chosen, then replace missing values using the mean for the numeric features along the axis.</p> |
| </li> |
| <li> |
| <p>MOST_FREQUENT: If this strategy is chosen, then replace missing values using the most frequent value along the axis.</p> |
| </li> |
| </ul> |
| </div> |
| <div class="listingblock"> |
| <div class="content"> |
| <pre class="rouge highlight"><code data-lang="java"><span class="c1">// Create imputer trainer.</span> |
| <span class="nc">ImputerTrainer</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">>()</span> <span class="n">imputerTrainer</span> <span class="o">=</span> |
| <span class="k">new</span> <span class="nc">ImputerTrainer</span><span class="o"><>().</span><span class="na">withImputingStrategy</span><span class="o">(</span><span class="nc">ImputingStrategy</span><span class="o">.</span><span class="na">MOST_FREQUENT</span><span class="o">);</span> |
| |
| <span class="c1">// Train imputer preprocessor.</span> |
| <span class="nc">Preprocessor</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">></span> <span class="n">preprocessor</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">ImputerTrainer</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">>()</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">ignite</span><span class="o">,</span> <span class="n">data</span><span class="o">,</span> <span class="n">vectorizer</span><span class="o">);</span></code></pre> |
| </div> |
| </div> |
| <div class="paragraph"> |
| <p>To see how the Imputer Preprocessor can be used in practice, try <a href="https://github.com/apache/ignite/blob/master/examples/src/main/java/org/apache/ignite/examples/ml/preprocessing/ImputingExample.java">this</a>.</p> |
| </div> |
| </div> |
| </div> |
| <div class="sect1"> |
| <h2 id="one-hot-encoder-preprocessor">One-Hot Encoder preprocessor</h2> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>One-hot encoding maps a categorical feature, represented as a label index (Double or String value), to a binary vector with at most a single one-value indicating the presence of a specific feature value from among the set of all feature values.</p> |
| </div> |
| <div class="paragraph"> |
| <p>This preprocessor can transform multiple columns in which indices are handled during the training process. These indexes could be defined via a <code>withEncodedFeature(featureIndex)</code> call.</p> |
| </div> |
| <div class="admonitionblock note"> |
| <table> |
| <tr> |
| <td class="icon"> |
| <div class="title">Note</div> |
| </td> |
| <td class="content"> |
| <div class="paragraph"> |
| <p>Each one-hot encoded binary vector adds its cells to the end of the current feature vector.</p> |
| </div> |
| <div class="ulist"> |
| <ul> |
| <li> |
| <p>This preprocessor always creates a separate column for NULL values.</p> |
| </li> |
| <li> |
| <p>The index value associated with NULL will be located in a binary vector according to the frequency of NULL values.</p> |
| </li> |
| </ul> |
| </div> |
| </td> |
| </tr> |
| </table> |
| </div> |
| <div class="paragraph"> |
| <p><code>StringEncoderPreprocessor</code> and <code>OneHotEncoderPreprocessor</code> use the same EncoderTraining to collect data about categorial features during the training phase. To preprocess the dataset with the One-Hot Encoder preprocessor, set the <code>encoderType</code> with the value <code>EncoderType.ONE_HOT_ENCODER</code> as shown in the code snippet below:</p> |
| </div> |
| <div class="listingblock"> |
| <div class="content"> |
| <pre class="rouge highlight"><code data-lang="java"><span class="nc">Preprocessor</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Object</span><span class="o">[]></span> <span class="n">encoderPreprocessor</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">EncoderTrainer</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Object</span><span class="o">[]>()</span> |
| <span class="o">.</span><span class="na">withEncoderType</span><span class="o">(</span><span class="nc">EncoderType</span><span class="o">.</span><span class="na">ONE_HOT_ENCODER</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">withEncodedFeature</span><span class="o">(</span><span class="mi">0</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">withEncodedFeature</span><span class="o">(</span><span class="mi">1</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">withEncodedFeature</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">ignite</span><span class="o">,</span> |
| <span class="n">dataCache</span><span class="o">,</span> |
| <span class="n">vectorizer</span> |
| <span class="o">);</span></code></pre> |
| </div> |
| </div> |
| </div> |
| </div> |
| <div class="sect1"> |
| <h2 id="string-encoder-preprocessor">String Encoder preprocessor</h2> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>The String Encoder encodes string values (categories) to double values in the range [0.0, amountOfCategories) where the most popular value will be presented as 0.0 and the least popular value presented with amountOfCategories-1 value.</p> |
| </div> |
| <div class="paragraph"> |
| <p>This preprocessor can transform multiple columns in which indices are handled during the training process. These indexes could be defined via a <code>withEncodedFeature(featureIndex)</code> call.</p> |
| </div> |
| <div class="admonitionblock note"> |
| <table> |
| <tr> |
| <td class="icon"> |
| <div class="title">Note</div> |
| </td> |
| <td class="content"> |
| It doesn’t add a new column but changes data in-place. |
| </td> |
| </tr> |
| </table> |
| </div> |
| <div class="paragraph"> |
| <p><strong>Example</strong></p> |
| </div> |
| <div class="paragraph"> |
| <p>Assume that we have the following Dataset with features id and category:</p> |
| </div> |
| <table class="tableblock frame-all grid-all stripes-even stretch"> |
| <colgroup> |
| <col style="width: 50%;"> |
| <col style="width: 50%;"> |
| </colgroup> |
| <thead> |
| <tr> |
| <th class="tableblock halign-left valign-top">Id</th> |
| <th class="tableblock halign-left valign-top">Category</th> |
| </tr> |
| </thead> |
| <tbody> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">0</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">a</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">1</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">b</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">2</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">c</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">3</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">a</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">4</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">a</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">5</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">c</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <table class="tableblock frame-all grid-all stripes-even stretch"> |
| <colgroup> |
| <col style="width: 50%;"> |
| <col style="width: 50%;"> |
| </colgroup> |
| <thead> |
| <tr> |
| <th class="tableblock halign-left valign-top">Id</th> |
| <th class="tableblock halign-left valign-top">Category</th> |
| </tr> |
| </thead> |
| <tbody> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">0</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">0.0</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">1</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">2.0</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">2</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">1.0</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">3</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">0.0</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">4</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">0.0</p></td> |
| </tr> |
| <tr> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">5</p></td> |
| <td class="tableblock halign-left valign-top"><p class="tableblock">1.0</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <div class="paragraph"> |
| <p>“a” gets index 0 because it is the most frequent, followed by “c” with index 1 and “b” with index 2.</p> |
| </div> |
| <div class="admonitionblock note"> |
| <table> |
| <tr> |
| <td class="icon"> |
| <div class="title">Note</div> |
| </td> |
| <td class="content"> |
| <div class="paragraph"> |
| <p>There is only one strategy regarding how StringEncoder will handle unseen labels when you have to fit a StringEncoder on one dataset and then use it to transform another: put unseen labels in a special additional bucket, at the index equal to <code>amountOfCategories</code>.</p> |
| </div> |
| </td> |
| </tr> |
| </table> |
| </div> |
| <div class="paragraph"> |
| <p><code>StringEncoderPreprocessor</code> and <code>OneHotEncoderPreprocessor</code> use the same EncoderTraining to collect data about categorial features during the training phase. To preprocess the dataset with the <code>StringEncoderPreprocessor</code>, set the <code>encoderType</code> with the value <code>EncoderType.STRING_ENCODER</code> as shown below in the code snippet:</p> |
| </div> |
| <div class="listingblock"> |
| <div class="content"> |
| <pre class="rouge highlight"><code data-lang="java"><span class="nc">Preprocessor</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Object</span><span class="o">[]></span> <span class="n">encoderPreprocessor</span> |
| <span class="o">=</span> <span class="k">new</span> <span class="nc">EncoderTrainer</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Object</span><span class="o">[]>()</span> |
| <span class="o">.</span><span class="na">withEncoderType</span><span class="o">(</span><span class="nc">EncoderType</span><span class="o">.</span><span class="na">STRING_ENCODER</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">withEncodedFeature</span><span class="o">(</span><span class="mi">1</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">withEncodedFeature</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">ignite</span><span class="o">,</span> |
| <span class="n">dataCache</span><span class="o">,</span> |
| <span class="n">vectorizer</span> |
| <span class="o">);</span></code></pre> |
| </div> |
| </div> |
| <div class="paragraph"> |
| <p>To see how the String Encoder or OHE can be used in practice, try <a href="https://github.com/apache/ignite/tree/master/examples/src/main/java/org/apache/ignite/examples/ml/preprocessing/encoding">this</a> example.</p> |
| </div> |
| </div> |
| </div> |
| <div class="sect1"> |
| <h2 id="minmax-scaler-preprocessor">MinMax Scaler preprocessor</h2> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>The MinMax Scaler transforms the given dataset, rescaling each feature to a specific range.</p> |
| </div> |
| <div class="paragraph"> |
| <p>From a mathematical point of view, it is the following function which is applied to every element in the dataset:</p> |
| </div> |
| <div class="imageblock"> |
| <div class="content"> |
| <img src="/docs/2.9.0/images/preprocessing.png" alt="preprocessing"> |
| </div> |
| </div> |
| <div class="paragraph"> |
| <p>for all i, where i is a number of column, max_i is the value of the maximum element in this column, min_i is the value of the minimal element in this column.</p> |
| </div> |
| <div class="listingblock"> |
| <div class="content"> |
| <pre class="rouge highlight"><code data-lang="java"><span class="c1">// Create min-max scaler trainer.</span> |
| <span class="nc">MinMaxScalerTrainer</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">></span> <span class="n">trainer</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">MinMaxScalerTrainer</span><span class="o"><>();</span> |
| |
| <span class="c1">// Build the preprocessor.</span> |
| <span class="nc">Preprocessor</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">></span> <span class="n">preprocessor</span> <span class="o">=</span> <span class="n">trainer</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">ignite</span><span class="o">,</span> <span class="n">data</span><span class="o">,</span> <span class="n">vectorizer</span><span class="o">);</span></code></pre> |
| </div> |
| </div> |
| <div class="paragraph"> |
| <p><code>MinMaxScalerTrainer</code> computes summary statistics on a data set and produces a <code>MinMaxScalerPreprocessor</code> |
| The preprocessor can then transform each feature individually such that it is in the given range.</p> |
| </div> |
| <div class="paragraph"> |
| <p>To see how the <code>MinMaxScalerPreprocessor</code> can be used in practice, try <a href="https://github.com/apache/ignite/blob/master/examples/src/main/java/org/apache/ignite/examples/ml/preprocessing/MinMaxScalerExample.java">this</a> tutorial example.</p> |
| </div> |
| </div> |
| </div> |
| <div class="sect1"> |
| <h2 id="maxabsscaler-preprocessor">MaxAbsScaler Preprocessor</h2> |
| <div class="sectionbody"> |
| <div class="paragraph"> |
| <p>The MaxAbsScaler transforms the given dataset, rescaling each feature to the range [-1, 1] by dividing through the maximum absolute value in each feature.</p> |
| </div> |
| <div class="paragraph"> |
| <p>NOTE:It does not shift or center the data, and thus does not destroy any sparsity.</p> |
| </div> |
| <div class="listingblock"> |
| <div class="content"> |
| <pre class="rouge highlight"><code data-lang="java"><span class="c1">// Create max-abs trainer.</span> |
| <span class="nc">MaxAbsScalerTrainer</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">></span> <span class="n">trainer</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">MaxAbsScalerTrainer</span><span class="o"><>();</span> |
| |
| <span class="c1">// Build the preprocessor.</span> |
| <span class="nc">Preprocessor</span><span class="o"><</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">></span> <span class="n">preprocessor</span> <span class="o">=</span> <span class="n">trainer</span> |
| <span class="o">.</span><span class="na">fit</span><span class="o">(</span><span class="n">ignite</span><span class="o">,</span> <span class="n">data</span><span class="o">,</span> <span class="n">vectorizer</span><span class="o">);</span></code></pre> |
| </div> |
| </div> |
| <div class="paragraph"> |
| <p>From a mathematical point of view it is the following function which is applied to every element in a dataset:</p> |
| </div> |
| <div class="imageblock"> |
| <div class="content"> |
| <img src="/docs/2.9.0/images/preprocessing2.png" alt="preprocessing2"> |
| </div> |
| </div> |
| <div class="paragraph"> |
| <p>for all i, where i is a number of column, maxabs_i is the value of the absolute maximum element in this column.</p> |
| </div> |
| <div class="paragraph"> |
| <p><code>MaxAbsScalerTrainer</code> computes summary statistics on a data set and produces a <code>MaxAbsScalerPreprocessor</code></p> |
| </div> |
| <div class="paragraph"> |
| <p>To see how the <code>MaxAbsScalerPreprocessor</code> can be used in practice, try <a href="https://github.com/apache/ignite/blob/master/examples/src/main/java/org/apache/ignite/examples/ml/preprocessing/MaxAbsScalerExample.java">this</a> tutorial example.</p> |
| </div> |
| </div> |
| </div> |
| <div class="copyright"> |
| © 2020 The Apache Software Foundation.<br/> |
| Apache, Apache Ignite, the Apache feather and the Apache Ignite logo are either registered trademarks or trademarks of The Apache Software Foundation. |
| |
| </div> |
| |
| </article> |
| <nav class="right-nav" data-swiftype-index='false'> |
| <ul class="sectlevel1"> |
| <li><a href="#normalization-preprocessor">Normalization preprocessor</a></li> |
| <li><a href="#examples">Examples</a></li> |
| <li><a href="#binarization-preprocessor">Binarization preprocessor</a></li> |
| <li><a href="#imputer-preprocessor">Imputer preprocessor</a></li> |
| <li><a href="#one-hot-encoder-preprocessor">One-Hot Encoder preprocessor</a></li> |
| <li><a href="#string-encoder-preprocessor">String Encoder preprocessor</a></li> |
| <li><a href="#minmax-scaler-preprocessor">MinMax Scaler preprocessor</a></li> |
| <li><a href="#maxabsscaler-preprocessor">MaxAbsScaler Preprocessor</a></li> |
| </ul> |
| |
| |
| <footer> |
| </footer> |
| |
| </nav> |
| |
| </section> |
| <script type='module' src='/assets/js/code-copy-to-clipboard.js' async crossorigin></script> |
| |
| <script> |
| // inits deep anchors -- needs to be done here because of https://www.bryanbraun.com/anchorjs/#dont-run-it-too-late |
| anchors.add('.page-docs h1, .page-docs h2, .page-docs h3:not(.discrete), .page-docs h4, .page-docs h5'); |
| anchors.options = { |
| placement: 'right', |
| visible: 'always' |
| }; |
| </script> |
| <!-- load google fonts async --> |
| <script type="text/javascript"> |
| WebFontConfig = { |
| google: { families: [ 'Open+Sans:300,400,600,700&display=swap' ] } |
| }; |
| (function() { |
| var wf = document.createElement('script'); |
| wf.src = 'https://ajax.googleapis.com/ajax/libs/webfont/1/webfont.js'; |
| wf.type = 'text/javascript'; |
| wf.async = 'true'; |
| var s = document.getElementsByTagName('script')[0]; |
| s.parentNode.insertBefore(wf, s); |
| })(); </script> |
| <script src="https://cdn.jsdelivr.net/npm/docsearch.js@2/dist/cdn/docsearch.min.js"></script> |
| <script> |
| docsearch({ |
| // Your apiKey and indexName will be given to you once |
| // we create your config |
| apiKey: '3eee686c0ebe39eff3baeb18c56fa5f8', |
| indexName: 'apache_ignite', |
| // Replace inputSelector with a CSS selector |
| // matching your search input |
| inputSelector: '#search-input', |
| // algoliaOptions: { 'facetFilters': ["version:$VERSION"] }, |
| |
| // Set debug to true to inspect the dropdown |
| debug: false, |
| }); |
| </script> |
| <script type='module' src='/assets/js/index.js?1600286558' async crossorigin></script> |
| <script type='module' src='/assets/js/versioning.js?1600286558' async crossorigin></script> |
| </body> |
| |
| </html> |
