org.apache.ignite.ml.selection.cv

Class CrossValidation<M extends IgniteModel<Vector,Double>,K,V>

java.lang.Object

org.apache.ignite.ml.selection.cv.AbstractCrossValidation<M,K,V>

org.apache.ignite.ml.selection.cv.CrossValidation<M,K,V>

Type Parameters:

M - Type of model.

K - Type of a key in upstream data.

V - Type of a value in upstream data.

All Implemented Interfaces:

Serializable

public class CrossValidation<M extends IgniteModel<Vector,Double>,K,V>
extends AbstractCrossValidation<M,K,V>

Cross validation score calculator. Cross validation is an approach that allows to avoid overfitting that is made the following way: the training set is split into k smaller sets. The following procedure is followed for each of the k “folds”:

• A model is trained using k-1 of the folds as training data;
• the resulting model is validated on the remaining part of the data (i.e., it is used as a test set to compute a performance measure such as accuracy).

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.ignite.ml.selection.cv.AbstractCrossValidation

AbstractCrossValidation.TaskResult

Field Summary

Fields inherited from class org.apache.ignite.ml.selection.cv.AbstractCrossValidation

amountOfFolds, envBuilder, environment, filter, isRunningOnPipeline, mapper, metric, paramGrid, parts, pipeline, preprocessor, trainer

Constructor Summary

Constructors

Constructor and Description
CrossValidation()

Method Summary

Modifier and Type	Method and Description
double[]	scoreByFolds() Calculates score by folds.
CrossValidation<M,K,V>	withIgnite(Ignite ignite)
CrossValidation<M,K,V>	withUpstreamCache(IgniteCache<K,V> upstreamCache)

Methods inherited from class org.apache.ignite.ml.selection.cv.AbstractCrossValidation

isRunningOnPipeline, score, scorePipeline, tuneHyperParameters, withAmountOfFolds, withEnvironmentBuilder, withFilter, withMapper, withMetric, withParamGrid, withPipeline, withPreprocessor, withTrainer

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CrossValidation

public CrossValidation()

Method Detail

scoreByFolds

public double[] scoreByFolds()

Calculates score by folds.

Specified by:

scoreByFolds in class AbstractCrossValidation<M extends IgniteModel<Vector,Double>,K,V>

withIgnite

public CrossValidation<M,K,V> withIgnite(Ignite ignite)

Parameters:

ignite - Ignite.

withUpstreamCache

public CrossValidation<M,K,V> withUpstreamCache(IgniteCache<K,V> upstreamCache)

Parameters:

upstreamCache - Upstream cache.