keel.Algorithms.Preprocess.NoiseFilters.SaturationFilter

Class SaturationFilter

java.lang.Object

keel.Algorithms.Preprocess.NoiseFilters.SaturationFilter.SaturationFilter

public class SaturationFilter
extends java.lang.Object

This class implements the Gamberger's algorithm to remove class noise

Since:

JDK1.6

Version:

1.0

Author:

Written by Jose A. Saez Munoz, research group SCI2S (Soft Computing and Intelligent Information Systems). DECSAI (DEpartment of Computer Science and Artificial Intelligence), University of Granada - Spain. Date: 06/01/10

Constructor Summary

Constructors

Constructor and Description
SaturationFilter() Constructor of the class

Method Summary

Modifier and Type	Method and Description
void	createDatasets(java.lang.String trainIN, java.lang.String trainOUT, java.lang.String testIN, java.lang.String testOUT) It apllies the changes to remove the noise
java.util.Vector<java.lang.Integer>	minimalCov(int positiveClass, java.util.Vector<pnPair> U) It runs the algorithm
void	remove(int indexLit, java.util.Vector<pnPair> Uaux) It runs the algorithm
void	run() It runs the noise elimination algorithm for multiclass problems
boolean[]	saturationFilter(int positiveClass) Constructor of the class
double	sumOfWeights(int indexLit, java.util.Vector<pnPair> Uaux) Constructor of the class

Methods inherited from class java.lang.Object

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

Constructor Detail

SaturationFilter

public SaturationFilter()

Constructor of the class

Method Detail

run

public void run()

It runs the noise elimination algorithm for multiclass problems

saturationFilter

public boolean[] saturationFilter(int positiveClass)

Constructor of the class

Parameters:

positiveClass - positive class id.

Returns:

boolean vector which indicates for each instance if it is noisy or not.

minimalCov

public java.util.Vector<java.lang.Integer> minimalCov(int positiveClass,
                                                      java.util.Vector<pnPair> U)

It runs the algorithm

Parameters:

positiveClass -

U -

Returns:

remove

public void remove(int indexLit,
                   java.util.Vector<pnPair> Uaux)

It runs the algorithm

Parameters:

indexLit -

Uaux -

sumOfWeights

public double sumOfWeights(int indexLit,
                           java.util.Vector<pnPair> Uaux)

Constructor of the class

Parameters:

indexLit -

Uaux -

Returns:

createDatasets

public void createDatasets(java.lang.String trainIN,
                           java.lang.String trainOUT,
                           java.lang.String testIN,
                           java.lang.String testOUT)

It apllies the changes to remove the noise

Parameters:

trainIN -

trainOUT -

testIN -

testOUT -