org.apache.ignite.ml.svm

Class SVMLinearBinaryClassificationTrainer

java.lang.Object

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

org.apache.ignite.ml.trainers.SingleLabelDatasetTrainer<SVMLinearBinaryClassificationModel>

org.apache.ignite.ml.svm.SVMLinearBinaryClassificationTrainer

public class SVMLinearBinaryClassificationTrainer
extends SingleLabelDatasetTrainer<SVMLinearBinaryClassificationModel>

Base class for a soft-margin SVM linear classification trainer based on the communication-efficient distributed dual coordinate ascent algorithm (CoCoA) with hinge-loss function.

This trainer takes input as Labeled Dataset with 0 and 1 labels for two classes and makes binary classification.

The paper about this algorithm could be found here https://arxiv.org/abs/1409.1458.

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

environment

Constructor Summary

Constructors

Constructor and Description
SVMLinearBinaryClassificationTrainer()

Method Summary

Modifier and Type	Method and Description
protected boolean	checkState(SVMLinearBinaryClassificationModel mdl)
<K,V> SVMLinearBinaryClassificationModel	fit(DatasetBuilder<K,V> datasetBuilder, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,Double> lbExtractor) Trains model based on the specified data.
int	getAmountOfIterations() Get the amount of outer iterations of SCDA algorithm.
int	getAmountOfLocIterations() Get the amount of local iterations of SCDA algorithm.
double	getLambda() Get the regularization lambda.
long	getSeed() Get the seed number.
protected <K,V> SVMLinearBinaryClassificationModel	updateModel(SVMLinearBinaryClassificationModel mdl, DatasetBuilder<K,V> datasetBuilder, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,Double> lbExtractor) Gets state of model in arguments, update in according to new data and return new model.
SVMLinearBinaryClassificationTrainer	withAmountOfIterations(int amountOfIterations) Set up the amount of outer iterations of SCDA algorithm.
SVMLinearBinaryClassificationTrainer	withAmountOfLocIterations(int amountOfLocIterations) Set up the amount of local iterations of SCDA algorithm.
SVMLinearBinaryClassificationTrainer	withLambda(double lambda) Set up the regularization parameter.
SVMLinearBinaryClassificationTrainer	withSeed(long seed) Set up the seed.

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

fit, fit, fit, fit, getLastTrainedModelOrThrowEmptyDatasetException, setEnvironment, update, update, update, update, update

Methods inherited from class java.lang.Object

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

Constructor Detail

SVMLinearBinaryClassificationTrainer

public SVMLinearBinaryClassificationTrainer()

Method Detail

fit

public <K,V> SVMLinearBinaryClassificationModel fit(DatasetBuilder<K,V> datasetBuilder,
                                                    IgniteBiFunction<K,V,Vector> featureExtractor,
                                                    IgniteBiFunction<K,V,Double> lbExtractor)

Trains model based on the specified data.

Specified by:

fit in class DatasetTrainer<SVMLinearBinaryClassificationModel,Double>

Type Parameters:

K - Type of a key in upstream data.

V - Type of a value in upstream data.

Parameters:

datasetBuilder - Dataset builder.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

Returns:

Model.

updateModel

protected <K,V> SVMLinearBinaryClassificationModel updateModel(SVMLinearBinaryClassificationModel mdl,
                                                               DatasetBuilder<K,V> datasetBuilder,
                                                               IgniteBiFunction<K,V,Vector> featureExtractor,
                                                               IgniteBiFunction<K,V,Double> lbExtractor)

Gets state of model in arguments, update in according to new data and return new model.

Specified by:

updateModel in class DatasetTrainer<SVMLinearBinaryClassificationModel,Double>

Type Parameters:

K - Type of a key in upstream data.

V - Type of a value in upstream data.

Parameters:

mdl - Learned model.

datasetBuilder - Dataset builder.

featureExtractor - Feature extractor.

lbExtractor - Label extractor.

Returns:

Updated model.

checkState

protected boolean checkState(SVMLinearBinaryClassificationModel mdl)

Specified by:

checkState in class DatasetTrainer<SVMLinearBinaryClassificationModel,Double>

Parameters:

mdl - Model.

Returns:

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

withLambda

public SVMLinearBinaryClassificationTrainer withLambda(double lambda)

Set up the regularization parameter.

Parameters:

lambda - The regularization parameter. Should be more than 0.0.

Returns:

Trainer with new lambda parameter value.

getLambda

public double getLambda()

Get the regularization lambda.

Returns:

The property value.

getAmountOfIterations

public int getAmountOfIterations()

Get the amount of outer iterations of SCDA algorithm.

Returns:

The property value.

withAmountOfIterations

public SVMLinearBinaryClassificationTrainer withAmountOfIterations(int amountOfIterations)

Set up the amount of outer iterations of SCDA algorithm.

Parameters:

amountOfIterations - The parameter value.

Returns:

Trainer with new amountOfIterations parameter value.

getAmountOfLocIterations

public int getAmountOfLocIterations()

Get the amount of local iterations of SCDA algorithm.

Returns:

The property value.

withAmountOfLocIterations

public SVMLinearBinaryClassificationTrainer withAmountOfLocIterations(int amountOfLocIterations)

Set up the amount of local iterations of SCDA algorithm.

Parameters:

amountOfLocIterations - The parameter value.

Returns:

Trainer with new amountOfLocIterations parameter value.

getSeed

public long getSeed()

Get the seed number.

Returns:

The property value.

withSeed

public SVMLinearBinaryClassificationTrainer withSeed(long seed)

Set up the seed.

Parameters:

seed - The parameter value.

Returns:

Model with new seed parameter value.