Package unifeat.featureSelection.filter.unsupervised

Class RRFS

java.lang.Object

unifeat.featureSelection.FeatureSelection

unifeat.featureSelection.filter.FilterApproach

unifeat.featureSelection.filter.unsupervised.RRFS

public class RRFS
extends FilterApproach

This java class is used to implement the relevance-redundancy feature selection(RRFS) method. Also, it is the unsupervised version of the RRFS.

Author:

Sina Tabakhi

See Also:

• FilterApproach
• FeatureSelection

Field Summary

Fields

Modifier and Type	Field	Description
private final double	MAX_SIM_VALUE

Fields inherited from class unifeat.featureSelection.FeatureSelection

numClass, numFeatures, numSelectedFeature, selectedFeatureSubset, trainSet

Constructor Summary

Constructors

Constructor	Description
RRFS(int sizeSelectedFeatureSubset, double maxSimilarity)	Initializes the parameters
RRFS(Object... arguments)	Initializes the parameters

Method Summary

Modifier and Type	Method	Description
private double	computeMAD(int indexFeature, double mean)	Computes the mean absolute difference(MAD) values of the features
void	evaluateFeatures()	Starts the feature selection process by relevance-redundancy feature selection(RRFS) method

Methods inherited from class unifeat.featureSelection.filter.FilterApproach

newMethod

Methods inherited from class unifeat.featureSelection.FeatureSelection

getSelectedFeatureSubset, loadDataSet, loadDataSet, setNumSelectedFeature, validate

Methods inherited from class java.lang.Object

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

Field Details

MAX_SIM_VALUE

private final double MAX_SIM_VALUE

Constructor Details

RRFS

public RRFS(Object... arguments)

Initializes the parameters

Parameters:

arguments - array of parameters contains (sizeSelectedFeatureSubset, maxSimilarity) in which sizeSelectedFeatureSubset is the number of selected features, and maxSimilarity is maximum allowed similarity between two features

RRFS

public RRFS(int sizeSelectedFeatureSubset,
 double maxSimilarity)

Initializes the parameters

Parameters:

sizeSelectedFeatureSubset - the number of selected features

maxSimilarity - maximum allowed similarity between two features

Method Details

computeMAD

private double computeMAD(int indexFeature,
 double mean)

Computes the mean absolute difference(MAD) values of the features

Parameters:

indexFeature - index of the given feature

mean - the mean value of the given feature (indexFeature)

Returns:

the mean absolute difference

evaluateFeatures

public void evaluateFeatures()

Starts the feature selection process by relevance-redundancy feature selection(RRFS) method

Specified by:

evaluateFeatures in class FeatureSelection