org.apache.ignite.ml.multiclass

Class OneVsRestTrainer<M extends IgniteModel<Vector,Double>>

java.lang.Object

org.apache.ignite.ml.trainers.DatasetTrainer<M,Double>

org.apache.ignite.ml.trainers.SingleLabelDatasetTrainer<MultiClassModel<M>>

org.apache.ignite.ml.multiclass.OneVsRestTrainer<M>

public class OneVsRestTrainer<M extends IgniteModel<Vector,Double>>
extends SingleLabelDatasetTrainer<MultiClassModel<M>>

This is a common heuristic trainer for multi-class labeled models. NOTE: The current implementation suffers from unbalanced training over the dataset due to unweighted approach during the process of reassign labels from all range of labels to 0,1.

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.ignite.ml.trainers.DatasetTrainer

DatasetTrainer.EmptyDatasetException

Field Summary

Fields inherited from class org.apache.ignite.ml.trainers.DatasetTrainer

envBuilder, environment

Constructor Summary

Constructors

Constructor and Description
OneVsRestTrainer(SingleLabelDatasetTrainer<M> classifier)

Method Summary

Modifier and Type	Method and Description
<K,V> MultiClassModel<M>	fitWithInitializedDeployingContext(DatasetBuilder<K,V> datasetBuilder, Preprocessor<K,V> extractor) Trains model based on the specified data.
boolean	isUpdateable(MultiClassModel<M> mdl)
protected <K,V> MultiClassModel<M>	updateModel(MultiClassModel<M> newMdl, DatasetBuilder<K,V> datasetBuilder, Preprocessor<K,V> extractor) Trains new model taken previous one as a first approximation.

Methods inherited from class org.apache.ignite.ml.trainers.DatasetTrainer

fit, fit, fit, fit, fit, fit, getLastTrainedModelOrThrowEmptyDatasetException, identityTrainer, learningEnvironment, update, update, update, update, update, withConvertedLabels, withEnvironmentBuilder

Methods inherited from class java.lang.Object

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

Constructor Detail

OneVsRestTrainer

public OneVsRestTrainer(SingleLabelDatasetTrainer<M> classifier)

Method Detail

fitWithInitializedDeployingContext

public <K,V> MultiClassModel<M> fitWithInitializedDeployingContext(DatasetBuilder<K,V> datasetBuilder,
                                                                   Preprocessor<K,V> extractor)

Trains model based on the specified data.

Specified by:

fitWithInitializedDeployingContext in class DatasetTrainer<MultiClassModel<M extends IgniteModel<Vector,Double>>,Double>

Type Parameters:

K - Type of a key in upstream data.

V - Type of a value in upstream data.

Parameters:

datasetBuilder - Dataset builder.

extractor - Extractor of UpstreamEntry into LabeledVector.

Returns:

Model.

updateModel

protected <K,V> MultiClassModel<M> updateModel(MultiClassModel<M> newMdl,
                                               DatasetBuilder<K,V> datasetBuilder,
                                               Preprocessor<K,V> extractor)

Trains new model taken previous one as a first approximation.

Specified by:

updateModel in class DatasetTrainer<MultiClassModel<M extends IgniteModel<Vector,Double>>,Double>

Type Parameters:

K - Type of a key in upstream data.

V - Type of a value in upstream data.

Parameters:

newMdl - Learned model.

datasetBuilder - Dataset builder.

extractor - Extractor of UpstreamEntry into LabeledVector.

Returns:

Updated model.

isUpdateable

public boolean isUpdateable(MultiClassModel<M> mdl)

Specified by:

isUpdateable in class DatasetTrainer<MultiClassModel<M extends IgniteModel<Vector,Double>>,Double>

Parameters:

mdl - Model.

Returns:

True if current critical for training parameters correspond to parameters from last training.