iterator
Class PCGA

java.lang.Object
  iterator.AbstractIterator
      iterator.AbstractOptimizer<T>
          iterator.AbstractInitialSampleBasedOptimizer<T>
              iterator.AbstractPopulationOptimizer<T>
                  iterator.BasicRealEncodedGA<BoundConstrainedProblem>
                      iterator.PCGA

All Implemented Interfaces:

DataListener, InitialSamplesSettable, Iterable, LoggableIterator, RepeatableLoggableIterator

public class PCGA
extends BasicRealEncodedGA<BoundConstrainedProblem>

Prof Ilan Kroo's 'Politically Correct' GA: all population members are assured to have a mate. Not particularly politically incorrect to do otherwise, but still. This is a real-encoded GA with a single point crossover.

Author:

dgorur

Field Summary

Fields inherited from class iterator.BasicRealEncodedGA

comparator, extrapolationFactor, interpolationFactor, xMutation

Fields inherited from class iterator.AbstractPopulationOptimizer

currentBestG, lastBestG, nextBlock

Fields inherited from class iterator.AbstractInitialSampleBasedOptimizer

uniform

Fields inherited from class iterator.AbstractOptimizer

doubleFormat, funEvalCount, logWriter

Fields inherited from class iterator.AbstractIterator

diagnosticString, iter

Constructor Summary

PCGA()

Method Summary

protected cern.colt.matrix.DoubleMatrix2D	computeNextPoints() Computes the next set of candidate solutions.
void	init() Initialization routine
static void	main(java.lang.String[] args) Runs some test problem.
void	singleIteration() This method is overriden here for this special implementation of PCGA, where generated offspring are immediately added to the eligible mating pool.

Methods inherited from class iterator.BasicRealEncodedGA

getExtrapolationFactor, getInterpolationFactor, getMutationBox, getMutationFraction, getMutationProbability, getPopulation, initializePopulation, makeChildren, setExtrapolationFactor, setInterpolationFactor, setMutationBox, setMutationFraction, setMutationProbability

Methods inherited from class iterator.AbstractPopulationOptimizer

evaluatePoints, getPopulationSize, setInitialSamples, setInitialSamples, setInitialSamples, setPopulationSize

Methods inherited from class iterator.AbstractInitialSampleBasedOptimizer

getRandomSeed, makeInitialSamples, setRandomSeed

Methods inherited from class iterator.AbstractOptimizer

clear, dataAdded, dataAdded, dataRemoved, dataRemoved, getDataHandler, getFunEvalCount, getLogFileName, getMaxFunEval, getProblem, isTerminated, iterate, setDataHandler, setFunEvalCount, setLogFileName, setMaxFunEval, setProblem, updateDiagnostics, writeInitialRunLog

Methods inherited from class iterator.AbstractIterator

isVerbose, printDiagnostics, setVerbose

Methods inherited from class java.lang.Object

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

Methods inherited from interface iterator.LoggableIterator

getLogFileName, setLogFileName

Methods inherited from interface iterator.Iterable

isTerminated, iterate

Constructor Detail

PCGA

public PCGA()

Method Detail

main

public static void main(java.lang.String[] args)

Runs some test problem. Make changes to this routine if desired, but better to use the spring framework.

Parameters:

args - None used.

init

public void init()

Description copied from interface: Iterable

Initialization routine

Specified by:

init in interface Iterable

Overrides:

init in class BasicRealEncodedGA<BoundConstrainedProblem>

singleIteration

public void singleIteration()

This method is overriden here for this special implementation of PCGA, where generated offspring are immediately added to the eligible mating pool. This means that one iteration actually consists of multiple 'sub-generations', in an embarrassingly incestuous scheme.

Specified by:

singleIteration in interface Iterable

Overrides:

singleIteration in class AbstractPopulationOptimizer<BoundConstrainedProblem>

computeNextPoints

protected cern.colt.matrix.DoubleMatrix2D computeNextPoints()

Description copied from class: AbstractPopulationOptimizer

Computes the next set of candidate solutions.

Specified by:

computeNextPoints in class AbstractPopulationOptimizer<BoundConstrainedProblem>

Returns:

a DoubleMatrix2D containing design points row-wise.