edu.udo.cs.yale.operator.features
Class FeatureOperator

java.lang.Object
  edu.udo.cs.yale.operator.Operator
      edu.udo.cs.yale.operator.OperatorChain
          edu.udo.cs.yale.operator.features.FeatureOperator

All Implemented Interfaces:

ConfigurationListener

Direct Known Subclasses:

AbstractGeneticAlgorithm, BruteForceSelection, FeatureSelectionOperator, FeatureWeighting, WeightGuidedSelectionOperator

public abstract class FeatureOperator
extends OperatorChain

This class is the superclass of all feature selection and generation operators. It provides an easy to use plug-in interface for operators that modify populations. Subclasses just have to supply lists of PopulationOperators by overriding getPreEvalutaionPopulationOperators() and getPostEvalutaionPopulationOperators() during a loop which will terminate if solutionGoodEnough() returns true.

Version:

$Id: FeatureOperator.java,v 2.72 2006/10/01 12:09:24 ingomierswa Exp $

Author:

Simon Fischer, Ingo Mierswa

Field Summary

private boolean	checkForMaximalFitness
private int	evaluationCounter
private static java.lang.Class[]	INPUT_CLASSES
private double	maximalFitness The optimization stops if this maximal fitness was reached.
private static java.lang.Class[]	OUTPUT_CLASSES
private Population	population
private RandomGenerator	random
private int	totalEvaluations
private WeightApplier	weightApplier

Constructor Summary

FeatureOperator(OperatorDescription description)

Method Summary

IOObject[]	apply() Applies the feature operator: collects the pre- and postevaluation operators create an initial population evaluate the initial population loop as long as solution is not good enough apply all pre evaluation operators evaluate the population update the population's best individual apply all post evaluation operators return all generation's best individual
(package private) void	applyOpList(java.util.List opList, Population population) Applies all PopulationOperators in opList to the population.
abstract Population	createInitialPopulation(ExampleSet es) Create an initial population.
protected PerformanceVector	evaluate(Individual individual) Evaluates the given individual.
protected void	evaluate(Population population) Evaluates all individuals in the population by applying the inner operators.
protected boolean	getCheckForMaximum() Returns if the operator should check if the maximum was reached for the main criterion.
InnerOperatorCondition	getInnerOperatorCondition() Must return a condition of the IO behaviour of all desired inner operators.
java.lang.Class[]	getInputClasses() Returns the classes that are needed as input.
int	getMaxNumberOfInnerOperators() Returns the highest possible value for the maximum number of innner operators.
int	getMinNumberOfInnerOperators() Returns 0 for the minimum number of innner operators.
int	getNumberOfSteps() Returns the number of steps performed by this chain.
java.lang.Class[]	getOutputClasses() Returns the classes that are guaranteed to be returned by apply() as additional output.
java.util.List<ParameterType>	getParameterTypes() Returns a list of ParameterTypes describing the parameters of this operator.
abstract java.util.List<PopulationOperator>	getPostEvaluationPopulationOperators(ExampleSet input) Must return a list of PopulationOperators.
abstract java.util.List<PopulationOperator>	getPreEvaluationPopulationOperators(ExampleSet input) Must return a list of PopulationOperators.
protected RandomGenerator	getRandom()
private boolean	isMaximumReached() This method checks if the maximum was reached for the main criterion.
protected void	setCheckForMaximum(boolean checkForMaximalFitness) Sets if the operator should check if the maximum was reached for the main criterion.
abstract boolean	solutionGoodEnough(Population pop) Has to return true if the main loop can be stopped because a solution is concidered to be good enough according to some criterion.

Methods inherited from class edu.udo.cs.yale.operator.OperatorChain

addAddListener, addOperator, addOperator, checkDeprecations, checkIO, checkNumberOfInnerOperators, checkProperties, clearErrorList, clearStepCounter, cloneOperator, countStep, createExperimentTree, delete, experimentFinished, experimentStarts, getAllInnerOperators, getCurrentStep, getIndexOfOperator, getInnerOperatorForName, getInnerOperatorsXML, getNumberOfAllOperators, getNumberOfChildrensSteps, getNumberOfOperators, getOperator, getOperatorFromAll, getOperators, isEnabled, performAdditionalChecks, removeAddListener, removeOperator, setEnabled, setExperiment, shouldReturnInnerOutput

Methods inherited from class edu.udo.cs.yale.operator.Operator

addError, addValue, addWarning, apply, createExperimentTree, createFromXML, createMarkedExperimentTree, getAddOnlyAdditionalOutput, getApplyCount, getDeliveredOutputClasses, getDeprecationInfo, getDesiredInputClasses, getErrorList, getExperiment, getInput, getInput, getInput, getInputDescription, getIOContainerForInApplyLoopBreakpoint, getName, getOperatorClassName, getOperatorDescription, getParameter, getParameterAsBoolean, getParameterAsColor, getParameterAsDouble, getParameterAsFile, getParameterAsInt, getParameterAsString, getParameterList, getParameters, getParameterType, getParent, getStartTime, getStatus, getUserDescription, getValue, getValues, getXML, hasBreakpoint, hasBreakpoint, hasInput, inApplyLoop, isParameterSet, logMessage, register, remove, rename, resume, setBreakpoint, setInput, setListParameter, setOperatorParameters, setParameter, setParameters, setParent, setUserDescription, toString, writeXML

Methods inherited from class java.lang.Object

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

Field Detail

OUTPUT_CLASSES

private static final java.lang.Class[] OUTPUT_CLASSES

INPUT_CLASSES

private static final java.lang.Class[] INPUT_CLASSES

population

private Population population

weightApplier

private WeightApplier weightApplier

maximalFitness

private double maximalFitness

The optimization stops if this maximal fitness was reached.

checkForMaximalFitness

private boolean checkForMaximalFitness

evaluationCounter

private int evaluationCounter

totalEvaluations

private int totalEvaluations

random

private RandomGenerator random

Constructor Detail

FeatureOperator

public FeatureOperator(OperatorDescription description)

Method Detail

createInitialPopulation

public abstract Population createInitialPopulation(ExampleSet es)
                                            throws OperatorException

Create an initial population. The example set will be cloned before the method is invoked. This method is invoked after the pre- and postevaluation population operators were collected.

Throws:

OperatorException

getPreEvaluationPopulationOperators

public abstract java.util.List<PopulationOperator> getPreEvaluationPopulationOperators(ExampleSet input)
                                                                                throws OperatorException

Must return a list of PopulationOperators. All operators are applied to the population in their order within the list before the population is evaluated. Since this methode is invoked only once the list cannot by dynamically changed during runtime.

Throws:

OperatorException

getPostEvaluationPopulationOperators

public abstract java.util.List<PopulationOperator> getPostEvaluationPopulationOperators(ExampleSet input)
                                                                                 throws OperatorException

Must return a list of PopulationOperators. All operators are applied to the population in their order within the list after the population is evaluated. Since this methode is invoked only once the list cannot by dynamically changed during runtime.

Throws:

OperatorException

solutionGoodEnough

public abstract boolean solutionGoodEnough(Population pop)
                                    throws OperatorException

Has to return true if the main loop can be stopped because a solution is concidered to be good enough according to some criterion.

Throws:

OperatorException

getOutputClasses

public java.lang.Class[] getOutputClasses()

Description copied from class: Operator

Returns the classes that are guaranteed to be returned by apply() as additional output. Please note that input object which should not be consumed must also be defined by this method (e.g. for preprocessing operators). The default behavior for input consumation is defined by Operator.getInputDescription(Class) and can be changed by overwriting this method. Objects which are not consumed must not be defined as additional output in this method. May be null or an empy array (no additional output is produced).

Specified by:

getOutputClasses in class Operator

getInputClasses

public java.lang.Class[] getInputClasses()

Description copied from class: Operator

Returns the classes that are needed as input. May be null or an empty (no desired input). As default, all delivered input objects are consumed and must be also delivered as output in both Operator.getOutputClasses() and Operator.apply() if this is necessary. This default behavior can be changed by overriding Operator.getInputDescription(Class). Subclasses which implement this method should not make use of parameters since this method is invoked by getParameterTypes(). Therefore, parameters are not fully available at this point of time and this might lead to exceptions. Please use InputDescriptions instead.

Specified by:

getInputClasses in class Operator

getInnerOperatorCondition

public InnerOperatorCondition getInnerOperatorCondition()

Description copied from class: OperatorChain

Must return a condition of the IO behaviour of all desired inner operators. If there are no "special" conditions and the chain works similar to a simple operator chain this method should at least return a SimpleChainInnerOperatorCondition. More than one condition should be combined with help of the class CombinedInnerOperatorCondition.

Specified by:

getInnerOperatorCondition in class OperatorChain

getRandom

protected RandomGenerator getRandom()

apply

public IOObject[] apply()
                 throws OperatorException

Applies the feature operator:

1. collects the pre- and postevaluation operators
2. create an initial population
3. evaluate the initial population
4. loop as long as solution is not good enough
   1. apply all pre evaluation operators
   2. evaluate the population
   3. update the population's best individual
   4. apply all post evaluation operators
5. return all generation's best individual

Overrides:

apply in class OperatorChain

Returns:

the last inner operator's output or the input itself if the chain is empty.

Throws:

OperatorException

applyOpList

void applyOpList(java.util.List opList,
                 Population population)
           throws OperatorException

Applies all PopulationOperators in opList to the population.

Throws:

OperatorException

evaluate

protected void evaluate(Population population)
                 throws OperatorException

Evaluates all individuals in the population by applying the inner operators.

Throws:

OperatorException

evaluate

protected PerformanceVector evaluate(Individual individual)
                              throws OperatorException

Evaluates the given individual. The performance is set as user data of the individual and also returned by this method.

Throws:

OperatorException

isMaximumReached

private boolean isMaximumReached()

This method checks if the maximum was reached for the main criterion.

setCheckForMaximum

protected void setCheckForMaximum(boolean checkForMaximalFitness)

Sets if the operator should check if the maximum was reached for the main criterion. Subclasses may want to set this to false, e.g. for multiobjective optimization.

getCheckForMaximum

protected boolean getCheckForMaximum()

Returns if the operator should check if the maximum was reached for the main criterion. Subclasses may want to set this to false, e.g. for multiobjective optimization.

getMaxNumberOfInnerOperators

public int getMaxNumberOfInnerOperators()

Returns the highest possible value for the maximum number of innner operators.

Specified by:

getMaxNumberOfInnerOperators in class OperatorChain

getMinNumberOfInnerOperators

public int getMinNumberOfInnerOperators()

Returns 0 for the minimum number of innner operators.

Specified by:

getMinNumberOfInnerOperators in class OperatorChain

getNumberOfSteps

public int getNumberOfSteps()

Description copied from class: OperatorChain

Returns the number of steps performed by this chain.

Specified by:

getNumberOfSteps in class OperatorChain

getParameterTypes

public java.util.List<ParameterType> getParameterTypes()

Description copied from class: Operator

Returns a list of ParameterTypes describing the parameters of this operator. The default implementation returns an empty list if no input objects can be retained and special parameters for those input objects which can be prevented from being consumed.

Overrides:

getParameterTypes in class Operator