org.apache.ignite.ml.selection.scoring.evaluator.context

Class BinaryClassificationEvaluationContext<L extends Serializable>

java.lang.Object

org.apache.ignite.ml.selection.scoring.evaluator.context.BinaryClassificationEvaluationContext<L>

All Implemented Interfaces:

Serializable, EvaluationContext<L,BinaryClassificationEvaluationContext<L>>

public class BinaryClassificationEvaluationContext<L extends Serializable>
extends Object
implements EvaluationContext<L,BinaryClassificationEvaluationContext<L>>

This context tries to define positive and negative labels for estimation of binary classifier.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
BinaryClassificationEvaluationContext() Creates an instance of BinaryClassificationEvaluationContext.
BinaryClassificationEvaluationContext(L firstClsLbl, L secondClsLbl) Creates an instance of BinaryClassificationEvaluationContext.

Method Summary

Modifier and Type	Method and Description
void	aggregate(LabeledVector<L> vector) Aggregates statistic from vector of sample.
L	getFirstClsLbl() Returns first class label.
L	getSecondClsLbl() Returns second class label.
BinaryClassificationEvaluationContext<L>	mergeWith(BinaryClassificationEvaluationContext<L> other) Merges statistics of this and other context.

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.ignite.ml.selection.scoring.evaluator.context.EvaluationContext

empty, needToCompute

Constructor Detail

BinaryClassificationEvaluationContext

public BinaryClassificationEvaluationContext()

Creates an instance of BinaryClassificationEvaluationContext.

BinaryClassificationEvaluationContext

public BinaryClassificationEvaluationContext(L firstClsLbl,
                                             L secondClsLbl)

Creates an instance of BinaryClassificationEvaluationContext.

Parameters:

firstClsLbl - First class lbl.

secondClsLbl - Second class lbl.

Method Detail

aggregate

public void aggregate(LabeledVector<L> vector)

Aggregates statistic from vector of sample.

Specified by:

aggregate in interface EvaluationContext<L extends Serializable,BinaryClassificationEvaluationContext<L extends Serializable>>

Parameters:

vector - Vector.

mergeWith

public BinaryClassificationEvaluationContext<L> mergeWith(BinaryClassificationEvaluationContext<L> other)

Merges statistics of this and other context.

Specified by:

mergeWith in interface EvaluationContext<L extends Serializable,BinaryClassificationEvaluationContext<L extends Serializable>>

Parameters:

other - Other context.

Returns:

New merged context.

getFirstClsLbl

public L getFirstClsLbl()

Returns first class label.

Returns:

First class label.

getSecondClsLbl

public L getSecondClsLbl()

Returns second class label.

Returns:

Second class label.