blob: 104c780a1122d1de1f51fc3c0ce3488f5db68487 [file] [log] [blame]
<!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>Cross-Validation | Ignite Documentation</title>
<link rel="canonical" href="/docs/latest/machine-learning/model-selection/cross-validation" />
<link rel="stylesheet" href="/assets/css/styles.css?1600377059">
<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?1600377059"></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/latest/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/latest/quick-start/java"
class=''
>Java</a>
</li>
<li>
<a href="/docs/latest/quick-start/dotnet"
class=''
>.NET/C#</a>
</li>
<li>
<a href="/docs/latest/quick-start/cpp"
class=''
>C++</a>
</li>
<li>
<a href="/docs/latest/quick-start/python"
class=''
>Python</a>
</li>
<li>
<a href="/docs/latest/quick-start/nodejs"
class=''
>Node.JS</a>
</li>
<li>
<a href="/docs/latest/quick-start/sql"
class=''
>SQL</a>
</li>
<li>
<a href="/docs/latest/quick-start/php"
class=''
>PHP</a>
</li>
<li>
<a href="/docs/latest/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/latest/installation/installing-using-zip"
class=''
>Installing Using ZIP Archive</a>
</li>
<li>
<a href="/docs/latest/installation/installing-using-docker"
class=''
>Installing Using Docker</a>
</li>
<li>
<a href="/docs/latest/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/latest//installation/kubernetes/amazon-eks-deployment" class=''>Amazon EKS</a></li>
<li><a href="/docs/latest//installation/kubernetes/azure-deployment" class=''>Azure Kubernetes Service</a></li>
<li><a href="/docs/latest//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/latest/setup"
class=''
>Setting Up Ignite for Java</a>
</li>
<li>
<a href="/docs/latest/setup-dotnet"
class=''
>Setting Up Ignite for .NET/C#</a>
</li>
</nav>
</li>
<li>
<a href="/docs/latest/understanding-configuration" class='' >Understanding Configuration</a>
</li>
<li>
<a href="/docs/latest/logging" class='' >Configuring Logging</a>
</li>
<li>
<a href="/docs/latest/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/latest/clustering/clustering"
class=''
>Overview</a>
</li>
<li>
<a href="/docs/latest/clustering/tcp-ip-discovery"
class=''
>TCP/IP Discovery</a>
</li>
<li>
<a href="/docs/latest/clustering/zookeeper-discovery"
class=''
>ZooKeeper Discovery</a>
</li>
<li>
<a href="/docs/latest/clustering/discovery-in-the-cloud"
class=''
>Discovery in the Cloud</a>
</li>
<li>
<a href="/docs/latest/clustering/network-configuration"
class=''
>Network Configuration</a>
</li>
<li>
<a href="/docs/latest/clustering/connect-client-nodes"
class=''
>Connecting Client Nodes</a>
</li>
<li>
<a href="/docs/latest/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/latest/data-modeling/data-modeling"
class=''
>Introduction</a>
</li>
<li>
<a href="/docs/latest/data-modeling/data-partitioning"
class=''
>Data Partitioning</a>
</li>
<li>
<a href="/docs/latest/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/latest/memory-architecture"
class=''
>Memory Architecture</a>
</li>
<li>
<a href="/docs/latest/memory-configuration/data-regions"
class=''
>Configuring Data Regions</a>
</li>
<li>
<a href="/docs/latest/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/latest/configuring-caches/configuration-overview"
class=''
>Cache Configuration</a>
</li>
<li>
<a href="/docs/latest/configuring-caches/configuring-backups"
class=''
>Configuring Partition Backups</a>
</li>
<li>
<a href="/docs/latest/configuring-caches/atomicity-modes"
class=''
>Atomicity Modes</a>
</li>
<li>
<a href="/docs/latest/configuring-caches/expiry-policies"
class=''
>Expiry Policy</a>
</li>
<li>
<a href="/docs/latest/configuring-caches/on-heap-caching"
class=''
>On-Heap Caching</a>
</li>
<li>
<a href="/docs/latest/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/latest/persistence/native-persistence"
class=''
>Ignite Persistence</a>
</li>
<li>
<a href="/docs/latest/persistence/external-storage"
class=''
>External Storage</a>
</li>
<li>
<a href="/docs/latest/persistence/swap"
class=''
>Swapping</a>
</li>
<li>
<a href="/docs/latest/persistence/custom-cache-store"
class=''
>Implementing Custom Cache Store</a>
</li>
<li>
<a href="/docs/latest/persistence/snapshots"
class=''
>Cluster Snapshots</a>
</li>
<li>
<a href="/docs/latest/persistence/disk-compression"
class=''
>Disk Compression</a>
</li>
<li>
<a href="/docs/latest/persistence/persistence-tuning"
class=''
>Tuning Persistence</a>
</li>
</nav>
</li>
<li>
<a href="/docs/latest/baseline-topology" class='' >Baseline Topology</a>
</li>
<li>
<a href="/docs/latest/cluster-states" class='' >Cluster States</a>
</li>
<li>
<a href="/docs/latest/data-rebalancing" class='' >Data Rebalancing</a>
</li>
<li>
<a href="/docs/latest/partition-loss-policy" class='' >Partition Loss Policy</a>
</li>
<li>
<a href="/docs/latest/deploying-user-code" class='' >Deploying User Code</a>
</li>
<li>
<a href="/docs/latest/peer-class-loading" class='' >Peer Class Loading</a>
</li>
<li>
<a href="/docs/latest/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/latest/key-value-api/basic-cache-operations"
class=''
>Basic Cache Operations</a>
</li>
<li>
<a href="/docs/latest/key-value-api/binary-objects"
class=''
>Working with Binary Objects</a>
</li>
<li>
<a href="/docs/latest/key-value-api/using-scan-queries"
class=''
>Using Scan Queries</a>
</li>
<li>
<a href="/docs/latest/read-repair"
class=''
>Read Repair</a>
</li>
</nav>
</li>
<li>
<a href="/docs/latest/key-value-api/continuous-queries" class='' >Using Continuous Queries</a>
</li>
<li>
<a href="/docs/latest/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/latest/SQL/sql-introduction"
class=''
>Introduction</a>
</li>
<li>
<a href="/docs/latest/SQL/schemas"
class=''
>Understanding Schemas</a>
</li>
<li>
<a href="/docs/latest/SQL/indexes"
class=''
>Defining Indexes</a>
</li>
<li>
<a href="/docs/latest/SQL/sql-api"
class=''
>Using SQL API</a>
</li>
<li>
<a href="/docs/latest/SQL/distributed-joins"
class=''
>Distributed Joins</a>
</li>
<li>
<a href="/docs/latest/SQL/sql-transactions"
class=''
>SQL Transactions</a>
</li>
<li>
<a href="/docs/latest/SQL/custom-sql-func"
class=''
>Custom SQL Functions</a>
</li>
<li>
<a href="/docs/latest/SQL/JDBC/jdbc-driver"
class=''
>JDBC Driver</a>
</li>
<li>
<a href="/docs/latest/SQL/JDBC/jdbc-client-driver"
class=''
>JDBC Client Driver</a>
</li>
<li>
<a href="/docs/latest/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/latest/distributed-computing/distributed-computing"
class=''
>Distributed Computing API</a>
</li>
<li>
<a href="/docs/latest/distributed-computing/cluster-groups"
class=''
>Cluster Groups</a>
</li>
<li>
<a href="/docs/latest/distributed-computing/executor-service"
class=''
>Executor Service</a>
</li>
<li>
<a href="/docs/latest/distributed-computing/map-reduce"
class=''
>MapReduce API</a>
</li>
<li>
<a href="/docs/latest/distributed-computing/load-balancing"
class=''
>Load Balancing</a>
</li>
<li>
<a href="/docs/latest/distributed-computing/fault-tolerance"
class=''
>Fault Tolerance</a>
</li>
<li>
<a href="/docs/latest/distributed-computing/job-scheduling"
class=''
>Job Scheduling</a>
</li>
</nav>
</li>
<li>
<a href="/docs/latest/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/latest/events/listening-to-events"
class=''
>Enabling and Listenting to Events</a>
</li>
<li>
<a href="/docs/latest/events/events"
class=''
>Events</a>
</li>
</nav>
</li>
<li>
<a href="/docs/latest/near-cache" class='' >Near Caches</a>
</li>
<li>
<a href="/docs/latest/platform-cache" class='' >.NET Platform Cache</a>
</li>
<li>
<a href="/docs/latest/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/latest/data-structures/queue-and-set"
class=''
>Queue and Set</a>
</li>
<li>
<a href="/docs/latest/data-structures/atomic-types"
class=''
>Atomic Types</a>
</li>
<li>
<a href="/docs/latest/data-structures/countdownlatch"
class=''
>CountDownLatch</a>
</li>
<li>
<a href="/docs/latest/data-structures/atomic-sequence"
class=''
>Atomic Sequence</a>
</li>
<li>
<a href="/docs/latest/data-structures/semaphore"
class=''
>Semaphore</a>
</li>
</nav>
</li>
<li>
<button type='button' data-guide-url="" class='group-toggle collapsed '>Machine Learning<img class="state-indicator" src="/assets/images/left-nav-arrow.svg"></button>
<nav class='nav-group collapsed'>
<li>
<a href="/docs/latest/machine-learning/machine-learning"
class=''
>Machine Learning</a>
</li>
<li>
<a href="/docs/latest/machine-learning/partition-based-dataset"
class=''
>Partition Based Dataset</a>
</li>
<li>
<a href="/docs/latest/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/latest//machine-learning/binary-classification/introduction" class=''>Introduction</a></li>
<li><a href="/docs/latest//machine-learning/binary-classification/linear-svm" class=''>Linear SVM (Support Vector Machine)</a></li>
<li><a href="/docs/latest//machine-learning/binary-classification/decision-trees" class=''>Decision Trees</a></li>
<li><a href="/docs/latest//machine-learning/binary-classification/multilayer-perceptron" class=''>Multilayer Perceptron</a></li>
<li><a href="/docs/latest//machine-learning/binary-classification/logistic-regression" class=''>Logistic Regression</a></li>
<li><a href="/docs/latest//machine-learning/binary-classification/knn-classification" class=''>k-NN Classification</a></li>
<li><a href="/docs/latest//machine-learning/binary-classification/ann" class=''>ANN (Approximate Nearest Neighbor)</a></li>
<li><a href="/docs/latest//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/latest//machine-learning/regression/introduction" class=''>Introduction</a></li>
<li><a href="/docs/latest//machine-learning/regression/linear-regression" class=''>Linear Regression</a></li>
<li><a href="/docs/latest//machine-learning/regression/decision-trees-regression" class=''>Decision Trees Regression</a></li>
<li><a href="/docs/latest//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/latest//machine-learning/clustering/introduction" class=''>Introduction</a></li>
<li><a href="/docs/latest//machine-learning/clustering/k-means-clustering" class=''>K-Means Clustering</a></li>
<li><a href="/docs/latest//machine-learning/clustering/gaussian-mixture" class=''>Gaussian mixture (GMM)</a></li>
</nav>
</li>
<li>
<a href="/docs/latest/machine-learning/preprocessing"
class=''
>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/latest//machine-learning/model-selection/introduction" class=''>Introduction</a></li>
<li><a href="/docs/latest//machine-learning/model-selection/evaluator" class=''>Evaluator</a></li>
<li><a href="/docs/latest//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/latest//machine-learning/model-selection/hyper-parameter-tuning" class=''>Hyper-parameter tuning</a></li>
<li><a href="/docs/latest//machine-learning/model-selection/pipeline-api" class=''>Pipeline API</a></li>
</nav>
</li>
<li>
<a href="/docs/latest/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/latest//machine-learning/ensemble-methods/introduction" class=''></a></li>
<li><a href="/docs/latest//machine-learning/ensemble-methods/stacking" class=''>Stacking</a></li>
<li><a href="/docs/latest//machine-learning/ensemble-methods/baggin" class=''>Bagging</a></li>
<li><a href="/docs/latest//machine-learning/ensemble-methods/random-forest" class=''>Random Forest</a></li>
<li><a href="/docs/latest//machine-learning/ensemble-methods/gradient-boosting" class=''>Gradient Boosting</a></li>
</nav>
</li>
<li>
<a href="/docs/latest/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/latest//machine-learning/importing-model/introduction" class=''>Introduction</a></li>
<li><a href="/docs/latest//machine-learning/importing-model/model-import-from-gxboost" class=''>Import Model from XGBoost</a></li>
<li><a href="/docs/latest//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/latest/monitoring-metrics/intro"
class=''
>Introduction</a>
</li>
<li>
<a href="/docs/latest/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/latest//monitoring-metrics/configuring-metrics" class=''>Configuring Metrics</a></li>
<li><a href="/docs/latest//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/latest//monitoring-metrics/new-metrics-system" class=''>Introduction</a></li>
<li><a href="/docs/latest//monitoring-metrics/new-metrics" class=''>Metrics</a></li>
</nav>
</li>
<li>
<a href="/docs/latest/monitoring-metrics/system-views"
class=''
>System Views</a>
</li>
<li>
<a href="/docs/latest/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/latest/security/authentication"
class=''
>Authentication</a>
</li>
<li>
<a href="/docs/latest/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/latest//security/tde" class=''>Introduction</a></li>
<li><a href="/docs/latest//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/latest/thin-clients/getting-started-with-thin-clients"
class=''
>Thin Clients Overview</a>
</li>
<li>
<a href="/docs/latest/thin-clients/java-thin-client"
class=''
>Java Thin Client</a>
</li>
<li>
<a href="/docs/latest/thin-clients/dotnet-thin-client"
class=''
>.NET Thin Client</a>
</li>
<li>
<a href="/docs/latest/thin-clients/cpp-thin-client"
class=''
>C++ Thin Client</a>
</li>
<li>
<a href="/docs/latest/thin-clients/python-thin-client"
class=''
>Python Thin Client</a>
</li>
<li>
<a href="/docs/latest/thin-clients/php-thin-client"
class=''
>PHP Thin Client</a>
</li>
<li>
<a href="/docs/latest/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/latest//binary-client-protocol/binary-client-protocol" class=''>Binary Client Protocol</a></li>
<li><a href="/docs/latest//binary-client-protocol/data-format" class=''>Data Format</a></li>
<li><a href="/docs/latest//binary-client-protocol/key-value-queries" class=''>Key-Value Queries</a></li>
<li><a href="/docs/latest//binary-client-protocol/sql-and-scan-queries" class=''>SQL and Scan Queries</a></li>
<li><a href="/docs/latest//binary-client-protocol/binary-type-metadata" class=''>Binary Types Metadata</a></li>
<li><a href="/docs/latest//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/latest/SQL/ODBC/odbc-driver"
class=''
>ODBC Driver</a>
</li>
<li>
<a href="/docs/latest/SQL/ODBC/connection-string-dsn"
class=''
>Connection String and DSN</a>
</li>
<li>
<a href="/docs/latest/SQL/ODBC/querying-modifying-data"
class=''
>Querying and Modifying Data</a>
</li>
<li>
<a href="/docs/latest/SQL/ODBC/specification"
class=''
>Specification</a>
</li>
<li>
<a href="/docs/latest/SQL/ODBC/data-types"
class=''
>Data Types</a>
</li>
<li>
<a href="/docs/latest/SQL/ODBC/error-codes"
class=''
>Error Codes</a>
</li>
</nav>
</li>
<li>
<a href="/docs/latest/restapi" class='' >REST API</a>
</li>
<li>
<a href="/docs/latest/control-script" class='' >Control Script</a>
</li>
<li>
<a href="/docs/latest/plugins" class='' >Plugins</a>
</li>
<li>
<a href="/docs/latest/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/latest/ignite-for-spark/overview"
class=''
>Overview</a>
</li>
<li>
<a href="/docs/latest/ignite-for-spark/ignitecontext-and-rdd"
class=''
>IgniteContext and IgniteRDD</a>
</li>
<li>
<a href="/docs/latest/ignite-for-spark/ignite-dataframe"
class=''
>Ignite DataFrame</a>
</li>
<li>
<a href="/docs/latest/ignite-for-spark/installation"
class=''
>Installation</a>
</li>
<li>
<a href="/docs/latest/ignite-for-spark/spark-shell"
class=''
>Test Ignite with Spark-shell</a>
</li>
<li>
<a href="/docs/latest/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/latest/sql-reference/sql-conformance"
class=''
>SQL Conformance</a>
</li>
<li>
<a href="/docs/latest/sql-reference/ddl"
class=''
>Data Definition Language (DDL)</a>
</li>
<li>
<a href="/docs/latest/sql-reference/dml"
class=''
>Data Manipulation Language (DML)</a>
</li>
<li>
<a href="/docs/latest/sql-reference/transactions"
class=''
>Transactions</a>
</li>
<li>
<a href="/docs/latest/sql-reference/operational-commands"
class=''
>Operational Commands</a>
</li>
<li>
<a href="/docs/latest/sql-reference/aggregate-functions"
class=''
>Aggregate functions</a>
</li>
<li>
<a href="/docs/latest/sql-reference/numeric-functions"
class=''
>Numeric Functions</a>
</li>
<li>
<a href="/docs/latest/sql-reference/string-functions"
class=''
>String Functions</a>
</li>
<li>
<a href="/docs/latest/sql-reference/date-time-functions"
class=''
>Data and Time Functions</a>
</li>
<li>
<a href="/docs/latest/sql-reference/system-functions"
class=''
>System Functions</a>
</li>
<li>
<a href="/docs/latest/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/model-selection/cross-validation.adoc" target="_blank">Edit</a>
<h1>Cross-Validation</h1>
<div id="preamble">
<div class="sectionbody">
<div class="paragraph">
<p>Cross validation functionality in Apache Ignite is represented by the <code>CrossValidation</code> class. This is a calculator parameterized by the type of model, type of label and key-value types of data. After instantiation (constructor doesn’t accept any additional parameters) we can use a score method to perform cross validation.</p>
</div>
<div class="paragraph">
<p>Let’s imagine that we have a trainer, a training set and we want to make cross validation using accuracy as a metric and using 4 folds. Apache Ignite allows us to do this as shown in the following example:</p>
</div>
</div>
</div>
<div class="sect1">
<h2 id="cross-validation-without-pipeline-api-usage">Cross-Validation (without Pipeline API usage)</h2>
<div class="sectionbody">
<div class="listingblock">
<div class="content">
<pre class="rouge highlight"><code data-lang="java"><span class="c1">// Create classification trainer</span>
<span class="nc">DecisionTreeClassificationTrainer</span> <span class="n">trainer</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">DecisionTreeClassificationTrainer</span><span class="o">(</span><span class="mi">4</span><span class="o">,</span> <span class="mi">0</span><span class="o">);</span>
<span class="c1">// Create cross-validation instance</span>
<span class="nc">CrossValidation</span><span class="o">&lt;</span><span class="nc">DecisionTreeNode</span><span class="o">,</span> <span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">&gt;</span> <span class="n">scoreCalculator</span>
<span class="o">=</span> <span class="k">new</span> <span class="nc">CrossValidation</span><span class="o">&lt;&gt;();</span>
<span class="c1">// Set up the cross-validation process</span>
<span class="n">scoreCalculator</span>
<span class="o">.</span><span class="na">withIgnite</span><span class="o">(</span><span class="n">ignite</span><span class="o">)</span>
<span class="o">.</span><span class="na">withUpstreamCache</span><span class="o">(</span><span class="n">trainingSet</span><span class="o">)</span>
<span class="o">.</span><span class="na">withTrainer</span><span class="o">(</span><span class="n">trainer</span><span class="o">)</span>
<span class="o">.</span><span class="na">withMetric</span><span class="o">(</span><span class="nc">MetricName</span><span class="o">.</span><span class="na">ACCURACY</span><span class="o">)</span>
<span class="o">.</span><span class="na">withPreprocessor</span><span class="o">(</span><span class="n">vectorizer</span><span class="o">)</span>
<span class="o">.</span><span class="na">withAmountOfFolds</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span>
<span class="o">.</span><span class="na">isRunningOnPipeline</span><span class="o">(</span><span class="kc">false</span><span class="o">)</span>
<span class="c1">// Calculate accuracy for each fold</span>
<span class="kt">double</span><span class="o">[]</span> <span class="n">accuracyScores</span> <span class="o">=</span> <span class="n">scoreCalculator</span><span class="o">.</span><span class="na">scoreByFolds</span><span class="o">();</span></code></pre>
</div>
</div>
<div class="paragraph">
<p>In this example we specify trainer and metric as parameters, after that we pass common training arguments such as a link to the Ignite instance, cache, vectorizers, and finally specify the number of folds. This method returns an array containing chosen metrics for all possible splits of the training set.</p>
</div>
</div>
</div>
<div class="sect1">
<h2 id="cross-validation-with-pipeline-api-usage">Cross-Validation (with Pipeline API usage)</h2>
<div class="sectionbody">
<div class="paragraph">
<p>Define the pipeline and pass it as a parameter to Cross-Validation instance to run cross-validation on Pipeline.</p>
</div>
<div class="admonitionblock caution">
<table>
<tr>
<td class="icon">
<div class="title">Caution</div>
</td>
<td class="content">
The Pipeline API is experimental and could be changed in the next releases.
</td>
</tr>
</table>
</div>
<div class="listingblock">
<div class="content">
<pre class="rouge highlight"><code data-lang="java"><span class="c1">// Create classification trainer</span>
<span class="nc">DecisionTreeClassificationTrainer</span> <span class="n">trainer</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">DecisionTreeClassificationTrainer</span><span class="o">(</span><span class="mi">4</span><span class="o">,</span> <span class="mi">0</span><span class="o">);</span>
<span class="nc">Pipeline</span><span class="o">&lt;</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">,</span> <span class="nc">Integer</span><span class="o">,</span> <span class="nc">Double</span><span class="o">&gt;</span> <span class="n">pipeline</span>
<span class="o">=</span> <span class="k">new</span> <span class="nc">Pipeline</span><span class="o">&lt;</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">,</span> <span class="nc">Integer</span><span class="o">,</span> <span class="nc">Double</span><span class="o">&gt;()</span>
<span class="o">.</span><span class="na">addVectorizer</span><span class="o">(</span><span class="n">vectorizer</span><span class="o">)</span>
<span class="o">.</span><span class="na">addPreprocessingTrainer</span><span class="o">(</span><span class="k">new</span> <span class="nc">ImputerTrainer</span><span class="o">&lt;</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">&gt;())</span>
<span class="o">.</span><span class="na">addPreprocessingTrainer</span><span class="o">(</span><span class="k">new</span> <span class="nc">MinMaxScalerTrainer</span><span class="o">&lt;</span><span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">&gt;())</span>
<span class="o">.</span><span class="na">addTrainer</span><span class="o">(</span><span class="n">trainer</span><span class="o">);</span>
<span class="c1">// Create cross-validation instance</span>
<span class="nc">CrossValidation</span><span class="o">&lt;</span><span class="nc">DecisionTreeNode</span><span class="o">,</span> <span class="nc">Integer</span><span class="o">,</span> <span class="nc">Vector</span><span class="o">&gt;</span> <span class="n">scoreCalculator</span>
<span class="o">=</span> <span class="k">new</span> <span class="nc">CrossValidation</span><span class="o">&lt;&gt;();</span>
<span class="c1">// Set up the cross-validation process</span>
<span class="n">scoreCalculator</span>
<span class="o">.</span><span class="na">withIgnite</span><span class="o">(</span><span class="n">ignite</span><span class="o">)</span>
<span class="o">.</span><span class="na">withUpstreamCache</span><span class="o">(</span><span class="n">trainingSet</span><span class="o">)</span>
<span class="o">.</span><span class="na">withPipeline</span><span class="o">(</span><span class="n">pipeline</span><span class="o">)</span>
<span class="o">.</span><span class="na">withMetric</span><span class="o">(</span><span class="nc">MetricName</span><span class="o">.</span><span class="na">ACCURACY</span><span class="o">)</span>
<span class="o">.</span><span class="na">withPreprocessor</span><span class="o">(</span><span class="n">vectorizer</span><span class="o">)</span>
<span class="o">.</span><span class="na">withAmountOfFolds</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span>
<span class="o">.</span><span class="na">isRunningOnPipeline</span><span class="o">(</span><span class="kc">false</span><span class="o">)</span>
<span class="c1">// Calculate accuracy for each fold</span>
<span class="kt">double</span><span class="o">[]</span> <span class="n">accuracyScores</span> <span class="o">=</span> <span class="n">scoreCalculator</span><span class="o">.</span><span class="na">scoreByFolds</span><span class="o">();</span></code></pre>
</div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="example">Example</h2>
<div class="sectionbody">
<div class="paragraph">
<p>To see how the Cross Validation can be used in practice, try <a href="https://github.com/apache/ignite/blob/master/examples/src/main/java/org/apache/ignite/examples/ml/selection/cv/CrossValidationExample.java">this example</a> and see step <a href="https://github.com/apache/ignite/blob/master/examples/src/main/java/org/apache/ignite/examples/ml/tutorial/Step_8_CV_with_Param_Grid_and_pipeline.java">8 of ML Tutorial</a> that are available on GitHub and delivered with every Apache Ignite distribution.</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="#cross-validation-without-pipeline-api-usage">Cross-Validation (without Pipeline API usage)</a></li>
<li><a href="#cross-validation-with-pipeline-api-usage">Cross-Validation (with Pipeline API usage)</a></li>
<li><a href="#example">Example</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?1600377059' async crossorigin></script>
<script type='module' src='/assets/js/versioning.js?1600377059' async crossorigin></script>
</body>
</html>