mulan.evaluation.measure
Class LabelBasedBipartitionMeasureBase

java.lang.Object
  mulan.evaluation.measure.MeasureBase
      mulan.evaluation.measure.BipartitionMeasureBase
          mulan.evaluation.measure.LabelBasedBipartitionMeasureBase

All Implemented Interfaces:

Serializable, Measure

Direct Known Subclasses:

LabelBasedFMeasure, LabelBasedPrecision, LabelBasedRecall, LabelBasedSpecificity

public abstract class LabelBasedBipartitionMeasureBase
extends BipartitionMeasureBase

Base class for label-based bipartition measures

Version:

2012.05.29

Author:

Grigorios Tsoumakas

See Also:

Serialized Form

Field Summary

protected double[]	falseNegatives the number of false negative for each label
protected double[]	falsePositives the number of false positives for each label
protected int	numOfLabels the number of labels
protected double[]	trueNegatives the number of true negatives for each label
protected double[]	truePositives the number of true positives for each label

Constructor Summary

LabelBasedBipartitionMeasureBase(int aNumOfLabels)
Creates a new instance of this class

Method Summary

void	reset() Resets the cumulated measure value, so the process of computation can be started from beginning (e.g. for a new series of outputs from learning task).
void	updateBipartition(boolean[] bipartition, boolean[] truth) Updates the measure based on an example

Methods inherited from class mulan.evaluation.measure.BipartitionMeasureBase

updateInternal

Methods inherited from class mulan.evaluation.measure.MeasureBase

makeCopy, toString, update

Methods inherited from class java.lang.Object

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

Methods inherited from interface mulan.evaluation.measure.Measure

getIdealValue, getName, getValue

Field Detail

numOfLabels

protected int numOfLabels

the number of labels

falseNegatives

protected double[] falseNegatives

the number of false negative for each label

truePositives

protected double[] truePositives

the number of true positives for each label

falsePositives

protected double[] falsePositives

the number of false positives for each label

trueNegatives

protected double[] trueNegatives

the number of true negatives for each label

Constructor Detail

LabelBasedBipartitionMeasureBase

public LabelBasedBipartitionMeasureBase(int aNumOfLabels)

Creates a new instance of this class

Parameters:

aNumOfLabels - the number of labels

Method Detail

updateBipartition

public void updateBipartition(boolean[] bipartition,
                              boolean[] truth)

Description copied from class: BipartitionMeasureBase

Updates the measure based on an example

Specified by:

updateBipartition in class BipartitionMeasureBase

Parameters:

bipartition - the predicted bipartition

truth - the ground truth

reset

public void reset()

Description copied from interface: Measure

Resets the cumulated measure value, so the process of computation can be started from beginning (e.g. for a new series of outputs from learning task).