keel.Algorithms.ImbalancedClassification.ImbalancedAlgorithms.GP_COACH_H

Class GP_COACH_H

java.lang.Object

keel.Algorithms.ImbalancedClassification.ImbalancedAlgorithms.GP_COACH_H.GP_COACH_H

public class GP_COACH_H
extends java.lang.Object

Title: GP-COACH

Description: It contains the implementation of the GP-COACH algorithm

Company: KEEL

Version:

1.0

Author:

Written by Victoria Lopez (University of Granada) 11/01/2011

Field Summary

Fields

Modifier and Type	Field and Description
static int	CF Configuration flag (CF)
static int	MAXIMUM Configuration flag (MAXIMUM)
static int	MINIMUM Configuration flag (MINIMUM)
static int	NO_RW Configuration flag (NO_RW)
static int	NORMALIZED_SUM Configuration flag (NORMALIZED_SUM)
static int	PCF_II Configuration flag (PCF_II)
static int	PCF_IV Configuration flag (PCF_IV)
static int	PROBABILISTIC_SUM Configuration flag (PROBABILISTIC_SUM)
static int	PRODUCT Configuration flag (PRODUCT)
static int	WINNING_RULE Configuration flag (WINNING_RULE)

Constructor Summary

Constructors

Constructor and Description
GP_COACH_H() Default constructor
GP_COACH_H(parseParameters parameters) It reads the data from the input files (training, validation and test) and parse all the parameters from the parameters array.

Method Summary

Modifier and Type	Method and Description
void	execute() It launches the algorithm
protected int	FRM_NS(java.util.ArrayList<Rule> pop, double[] example, boolean[] missing, java.util.ArrayList<java.lang.Integer> classifying_rules) Normalized Sum FRM (also known as Additive Combination)
protected int	FRM_WR(java.util.ArrayList<Rule> pop, double[] example, boolean[] missing, java.util.ArrayList<java.lang.Integer> classifying_rules) Winning Rule FRM
void	writeDataBase(java.lang.String filename) It writes the Data Base into an output file

Methods inherited from class java.lang.Object

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

Field Detail

CF

public static final int CF

Configuration flag (CF)

See Also:

Constant Field Values

PCF_IV

public static final int PCF_IV

Configuration flag (PCF_IV)

See Also:

Constant Field Values

PCF_II

public static final int PCF_II

Configuration flag (PCF_II)

See Also:

Constant Field Values

NO_RW

public static final int NO_RW

Configuration flag (NO_RW)

See Also:

Constant Field Values

MINIMUM

public static final int MINIMUM

Configuration flag (MINIMUM)

See Also:

Constant Field Values

PRODUCT

public static final int PRODUCT

Configuration flag (PRODUCT)

See Also:

Constant Field Values

MAXIMUM

public static final int MAXIMUM

Configuration flag (MAXIMUM)

See Also:

Constant Field Values

PROBABILISTIC_SUM

public static final int PROBABILISTIC_SUM

Configuration flag (PROBABILISTIC_SUM)

See Also:

Constant Field Values

WINNING_RULE

public static final int WINNING_RULE

Configuration flag (WINNING_RULE)

See Also:

Constant Field Values

NORMALIZED_SUM

public static final int NORMALIZED_SUM

Configuration flag (NORMALIZED_SUM)

See Also:

Constant Field Values

Constructor Detail

GP_COACH_H

public GP_COACH_H()

Default constructor

GP_COACH_H

public GP_COACH_H(parseParameters parameters)

It reads the data from the input files (training, validation and test) and parse all the parameters from the parameters array.

Parameters:

parameters - parseParameters It contains the input files, output files and parameters

Method Detail

execute

public void execute()

It launches the algorithm

FRM_WR

protected int FRM_WR(java.util.ArrayList<Rule> pop,
                     double[] example,
                     boolean[] missing,
                     java.util.ArrayList<java.lang.Integer> classifying_rules)

Winning Rule FRM

Parameters:

pop - Current rule base that contains the rules that compose the whole population

example - double[] the input example

missing - boolean[] containing the missing values of the input example

classifying_rules - ArrayList containing the rules that are used to classify a specific example

Returns:

int the class label for the rule with highest membership degree to the example

FRM_NS

protected int FRM_NS(java.util.ArrayList<Rule> pop,
                     double[] example,
                     boolean[] missing,
                     java.util.ArrayList<java.lang.Integer> classifying_rules)

Normalized Sum FRM (also known as Additive Combination)

Parameters:

pop - Current rule base that contains the rules that compose the whole population

example - double[] the input example

missing - boolean[] containing the missing values of the input example

classifying_rules - ArrayList containing the rules that are used to classify a specific example

Returns:

int the class label for the set of rules with the highest sum of membership degree per class

writeDataBase

public void writeDataBase(java.lang.String filename)

It writes the Data Base into an output file

Parameters:

filename - String the name of the output file