org.apache.ignite.ml.knn.ann

Class ANNClassificationTrainer

java.lang.Object

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

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

org.apache.ignite.ml.knn.ann.ANNClassificationTrainer

public class ANNClassificationTrainer
extends SingleLabelDatasetTrainer<ANNClassificationModel>

ANN algorithm trainer to solve multi-class classification task. This trainer is based on ACD strategy and KMeans clustering algorithm to find centroids.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ANNClassificationTrainer.CentroidStat Service class used for statistics.

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
ANNClassificationTrainer()

Method Summary

Modifier and Type	Method and Description
protected boolean	checkState(ANNClassificationModel mdl)
<K,V> ANNClassificationModel	fit(DatasetBuilder<K,V> datasetBuilder, IgniteBiFunction<K,V,Vector> featureExtractor, IgniteBiFunction<K,V,Double> lbExtractor) Trains model based on the specified data.
DistanceMeasure	getDistance() Gets the distance.
double	getEpsilon() Gets the epsilon.
int	getK() Gets the amount of clusters.
int	getMaxIterations() Gets the max number of iterations before convergence.
long	getSeed() Gets the seed number.
protected <K,V> ANNClassificationModel	updateModel(ANNClassificationModel 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.
ANNClassificationTrainer	withDistance(DistanceMeasure distance) Set up the distance.
ANNClassificationTrainer	withEpsilon(double epsilon) Set up the epsilon.
ANNClassificationTrainer	withK(int k) Set up the amount of clusters.
ANNClassificationTrainer	withMaxIterations(int maxIterations) Set up the max number of iterations before convergence.
ANNClassificationTrainer	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

ANNClassificationTrainer

public ANNClassificationTrainer()

Method Detail

fit

public <K,V> ANNClassificationModel 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<ANNClassificationModel,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> ANNClassificationModel updateModel(ANNClassificationModel 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<ANNClassificationModel,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(ANNClassificationModel mdl)

Specified by:

checkState in class DatasetTrainer<ANNClassificationModel,Double>

Parameters:

mdl - Model.

Returns:

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

getK

public int getK()

Gets the amount of clusters.

Returns:

The parameter value.

withK

public ANNClassificationTrainer withK(int k)

Set up the amount of clusters.

Parameters:

k - The parameter value.

Returns:

Model with new amount of clusters parameter value.

getMaxIterations

public int getMaxIterations()

Gets the max number of iterations before convergence.

Returns:

The parameter value.

withMaxIterations

public ANNClassificationTrainer withMaxIterations(int maxIterations)

Set up the max number of iterations before convergence.

Parameters:

maxIterations - The parameter value.

Returns:

Model with new max number of iterations before convergence parameter value.

getEpsilon

public double getEpsilon()

Gets the epsilon.

Returns:

The parameter value.

withEpsilon

public ANNClassificationTrainer withEpsilon(double epsilon)

Set up the epsilon.

Parameters:

epsilon - The parameter value.

Returns:

Model with new epsilon parameter value.

getDistance

public DistanceMeasure getDistance()

Gets the distance.

Returns:

The parameter value.

withDistance

public ANNClassificationTrainer withDistance(DistanceMeasure distance)

Set up the distance.

Parameters:

distance - The parameter value.

Returns:

Model with new distance parameter value.

getSeed

public long getSeed()

Gets the seed number.

Returns:

The parameter value.

withSeed

public ANNClassificationTrainer withSeed(long seed)

Set up the seed.

Parameters:

seed - The parameter value.

Returns:

Model with new seed parameter value.