Package adams.opt.optimise.genetic.fitnessfunctions

Class AttributeSelection

java.lang.Object

adams.core.logging.LoggingObject

adams.core.logging.CustomLoggingLevelObject

adams.core.option.AbstractOptionHandler

adams.opt.optimise.AbstractFitnessFunction

adams.opt.optimise.genetic.fitnessfunctions.AbstractWEKAFitnessFunction

adams.opt.optimise.genetic.fitnessfunctions.AttributeSelection

All Implemented Interfaces:

Destroyable, GlobalInfoSupporter, LoggingLevelHandler, LoggingSupporter, OptionHandler, SizeOfHandler, FitnessFunction, Serializable

public class AttributeSelection
extends AbstractWEKAFitnessFunction

Perform attribute selection using WEKA classification.

Version:

$Revision$

Author:

dale

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class adams.opt.optimise.genetic.fitnessfunctions.AbstractWEKAFitnessFunction

AbstractWEKAFitnessFunction.Measure

Field Summary

Fields inherited from class adams.opt.optimise.genetic.fitnessfunctions.AbstractWEKAFitnessFunction

m_Classifier, m_ClassIndex, m_CrossValidationSeed, m_Dataset, m_Folds, m_init, m_Instances, m_Measure, m_OutputDirectory

Fields inherited from class adams.core.option.AbstractOptionHandler

m_OptionManager

Fields inherited from class adams.core.logging.LoggingObject

m_Logger, m_LoggingIsEnabled, m_LoggingLevel

Constructor Summary

Constructors

Constructor	Description
AttributeSelection()

Method Summary

Modifier and Type	Method	Description
double	evaluate(OptData opd)	Get fitness given vars.
OptData	getDataDef()
String	getRemoveAsString(int[] m_weights)	Generates a range string of attributes to keep (= one has to use the inverse matching sense with the Remove filter).
protected int[]	getWeights(OptData opd)
String	globalInfo()	Returns a string describing the object.
void	newBest(double val, OptData opd)	Callback for best measure so far

Methods inherited from class adams.opt.optimise.genetic.fitnessfunctions.AbstractWEKAFitnessFunction

classifierTipText, classIndexTipText, crossValidationSeedTipText, datasetTipText, defineOptions, foldsTipText, getClassifier, getClassIndex, getCrossValidationSeed, getDataset, getFolds, getInstances, getMeasure, getOutputDirectory, init, measureTipText, outputDirectoryTipText, setClassifier, setClassIndex, setCrossValidationSeed, setDataset, setFolds, setInstances, setMeasure, setOutputDirectory

Methods inherited from class adams.core.option.AbstractOptionHandler

cleanUpOptions, destroy, finishInit, getDefaultLoggingLevel, getOptionManager, initialize, loggingLevelTipText, newOptionManager, reset, setLoggingLevel, toCommandLine, toString

Methods inherited from class adams.core.logging.LoggingObject

configureLogger, getLogger, getLoggingLevel, initializeLogging, isLoggingEnabled, sizeOf

Methods inherited from class java.lang.Object

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

Methods inherited from interface adams.core.logging.LoggingLevelHandler

getLoggingLevel

Constructor Detail

AttributeSelection

public AttributeSelection()

Method Detail

globalInfo

public String globalInfo()

Description copied from class: AbstractOptionHandler

Returns a string describing the object.

Specified by:

globalInfo in interface GlobalInfoSupporter

Overrides:

globalInfo in class AbstractWEKAFitnessFunction

Returns:

a description suitable for displaying in the gui

getDataDef

public OptData getDataDef()

getWeights

protected int[] getWeights(OptData opd)

evaluate

public double evaluate(OptData opd)

Description copied from interface: FitnessFunction

Get fitness given vars. Higher the better.

Parameters:

opd - vars

Returns:

fitness

getRemoveAsString

public String getRemoveAsString(int[] m_weights)

Generates a range string of attributes to keep (= one has to use the inverse matching sense with the Remove filter).

Returns:

the range of attributes to keep

newBest

public void newBest(double val,
                    OptData opd)

Callback for best measure so far

Specified by:

newBest in interface FitnessFunction

Overrides:

newBest in class AbstractFitnessFunction

opd - data for new best