de.jstacs.classifiers.performanceMeasures

Interface PerformanceMeasure

All Known Subinterfaces:

NumericalPerformanceMeasure

All Known Implementing Classes:

AbstractNumericalTwoClassPerformanceMeasure, AbstractPerformanceMeasure, AbstractTwoClassPerformanceMeasure, AucPR, AucROC, ClassificationRate, ConfusionMatrix, CorrelationCoefficient, FalsePositiveRateForFixedSensitivity, MaximumCorrelationCoefficient, MaximumFMeasure, MaximumNumericalTwoClassMeasure, PositivePredictiveValueForFixedSensitivity, PRCurve, ROCCurve, SensitivityForFixedSpecificity

public interface PerformanceMeasure

Interface of any performance measure used to evaluate an AbstractClassifier. It is recommended to use the method AbstractClassifier.evaluate(AbstractPerformanceMeasureParameterSet, boolean, de.jstacs.data.DataSet...) for evaluating the performance of any classifier.

Author:

Jan Grau, Jens Keilwagen

See Also:

AbstractClassifier, NumericalPerformanceMeasure

Method Summary

Modifier and Type	Method and Description
ResultSet	compute(double[][][] classSpecificScores) This method allows to compute the performance measure of given class specific scores.
ResultSet	compute(double[][][] classSpecificScores, double[][] weights) This method allows to compute the performance measure of given class specific scores.
ResultSet	compute(double[] sortedScoresClass0, double[] sortedScoresClass1) This method allows to compute the performance measure of given sorted score ratios.
ResultSet	compute(double[] sortedScoresClass0, double[] weightsClass0, double[] sortedScoresClass1, double[] weightsClass1) This method allows to compute the performance measure of given sorted score ratios.
int	getAllowedNumberOfClasses() This method returns the allowed number of classes.
String	getName() The method returns the name of the performance measure.

Method Detail

getName

String getName()

The method returns the name of the performance measure.

Returns:

the name of the performance measure

compute

ResultSet compute(double[] sortedScoresClass0,
                  double[] sortedScoresClass1)

This method allows to compute the performance measure of given sorted score ratios. This method can only be used for binary classifiers.

Parameters:

sortedScoresClass0 - the sorted score ratios of class 0

sortedScoresClass1 - the sorted score ratios of class 1

Returns:

a result set containing the results of the performance measure

See Also:

compute(double[], double[], double[], double[])

compute

ResultSet compute(double[][][] classSpecificScores)

This method allows to compute the performance measure of given class specific scores.

Parameters:

classSpecificScores - the scores; first dimension = data sets, second dimension = sequences of the data set, third dimension classes of the classifier

Returns:

a result set containing the results of the performance measure

See Also:

compute(double[][][], double[][])

compute

ResultSet compute(double[] sortedScoresClass0,
                  double[] weightsClass0,
                  double[] sortedScoresClass1,
                  double[] weightsClass1)

This method allows to compute the performance measure of given sorted score ratios. This method can only be used for binary classifiers.

Parameters:

sortedScoresClass0 - the sorted score ratios of class 0

weightsClass0 - the weights of the sequences of class 0 sorted along with the scores sortedScoresClass0

sortedScoresClass1 - the sorted score ratios of class 1

weightsClass1 - the weights of the sequences of class 1 sorted along with the scores sortedScoresClass1

Returns:

a result set containing the results of the performance measure

See Also:

ToolBox.sortAlongWith(double[], double[][])

compute

ResultSet compute(double[][][] classSpecificScores,
                  double[][] weights)

This method allows to compute the performance measure of given class specific scores.

Parameters:

classSpecificScores - the scores; first dimension = data sets, second dimension = sequences of the data set, third dimension classes of the classifier

weights - the weights for all sequence in all data sets

Returns:

a result set containing the results of the performance measure

getAllowedNumberOfClasses

int getAllowedNumberOfClasses()

This method returns the allowed number of classes. For many performance measures this number is fixed, e.g. for AUC-ROC the number is 2. If the number is not fixed the method returns 0, e.g. for the classification rate.

Returns:

the allowed number of classes

See Also:

AbstractClassifier.getNumberOfClasses()