keel.Algorithms.Fuzzy_Rule_Learning.Hybrid.PDFCS

Class PDFC

java.lang.Object

keel.Algorithms.SVM.SMO.SMO

keel.Algorithms.Fuzzy_Rule_Learning.Hybrid.PDFCS.PDFC

All Implemented Interfaces:

TechnicalInformationHandler, WeightedInstancesHandler

public class PDFC
extends SMO

This class implements the Positive Definite Fuzzy Classifier from Chen and Wang's paper: Ref: Y. Chen, J.Z. Wang, Support Vector Learning for Fuzzy Rule-Based Classification Systems. IEEE Transactions on Fuzzy Systems 11(6) 716-728.

Since:

JDK 1.5

Version:

0.1

Author:

Written by Julián Luengo Martín 10/12/2008

Nested Class Summary

Nested classes/interfaces inherited from class keel.Algorithms.SVM.SMO.SMO

SMO.BinarySMO

Field Summary

Fields

Modifier and Type	Field and Description
protected SMO.BinarySMO[]	m_classifiers The binary classifier(s)
protected double	m_d The 'd' value for the Positive-Definite Reference Functions
protected FuzzyRuleSet[]	m_ruleSet The fuzzy rule sets

Fields inherited from class keel.Algorithms.SVM.SMO.SMO

FILTER_NONE, FILTER_NORMALIZE, FILTER_STANDARDIZE, input_test_name, input_train_name, input_validation_name, m_C, m_checksTurnedOff, m_classAttribute, m_classIndex, m_Del, m_eps, m_filterType, m_fitLogisticModels, m_kernel, m_KernelIsLinear, m_nominalToBinary, m_NumClasses, m_numFolds, m_randomSeed, m_seed, m_tol, mean, method_output, output_test_name, output_train_name, probabilities, std_dev, TAGS_FILTER

Constructor Summary

Constructors

Constructor and Description
PDFC() Default constructor
PDFC(java.lang.String fileParam) Creates a new instance of PDFC

Method Summary

Modifier and Type	Method and Description
void	buildClassifier(Instances insts) Method for building the classifier.
double[]	distributionForInstance(Instance inst) Estimates class probabilities for given instance.
protected void	printRuleBase() This method prints the actual Rule Base stored in m_ruleSet to a file
void	runModel() Run the model once the parameters have been set by the method config_read()

Methods inherited from class keel.Algorithms.SVM.SMO.SMO

attributeNames, bias, buildLogisticModelsTipText, checksTurnedOffTipText, classAttributeNames, computeStats, cTipText, epsilonTipText, filterTypeTipText, getBuildLogisticModels, getC, getChecksTurnedOff, getEpsilon, getFilterType, getKernel, getNumFolds, getRandomSeed, getTechnicalInformation, getToleranceParameter, globalInfo, InstancesKEEL2Weka, kernelTipText, normalize, numClassAttributeValues, numFoldsTipText, obtainVotes, pairwiseCoupling, printSVs, randomSeedTipText, runModel, setBuildLogisticModels, setC, setChecksTurnedOff, setEpsilon, setFilterType, setKernel, setNumFolds, setRandomSeed, setToleranceParameter, sparseIndices, sparseWeights, standardize, toleranceParameterTipText, turnChecksOff, turnChecksOn, writeOutput

Methods inherited from class java.lang.Object

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

Field Detail

m_classifiers

protected SMO.BinarySMO[] m_classifiers

The binary classifier(s)

m_ruleSet

protected FuzzyRuleSet[] m_ruleSet

The fuzzy rule sets

m_d

protected double m_d

The 'd' value for the Positive-Definite Reference Functions

Constructor Detail

PDFC

public PDFC(java.lang.String fileParam)

Creates a new instance of PDFC

Parameters:

fileParam - The path to the configuration file with all the parameters in KEEL format

PDFC

public PDFC()

Default constructor

Method Detail

buildClassifier

public void buildClassifier(Instances insts)
                     throws java.lang.Exception

Method for building the classifier. Implements a one-against-all wrapper for multi-class problems.

Overrides:

buildClassifier in class SMO

Parameters:

insts - the set of training instances

Throws:

java.lang.Exception - if the classifier can't be built successfully

distributionForInstance

public double[] distributionForInstance(Instance inst)
                                 throws java.lang.Exception

Estimates class probabilities for given instance.

Overrides:

distributionForInstance in class SMO

Parameters:

inst - the instance to compute the probabilities for

Returns:

class probabilities for given instance.

Throws:

java.lang.Exception - in case of an error

runModel

public void runModel()

Run the model once the parameters have been set by the method config_read()

Overrides:

runModel in class SMO

printRuleBase

protected void printRuleBase()

This method prints the actual Rule Base stored in m_ruleSet to a file