NAME

AI::Genetic::Individual - Base class for AI::Genetic Individuals.

SYNOPSIS

See AI::Genetic.

DESCRIPTION

This package implements the base class for all AI::Genetic individuals. It provides basic methods required by AI::Genetic for correct evolution. Furthermore, it can be very easily used as a base class for additional types of individuals. AI::Genetic comes with three individual types that inherit from this class. These are IndBitVector, IndListVector, and IndRangeVector.

See "CREATING YOUR OWN INDIVIDUAL CLASS" for more details.

CLASS METHODS

The following methods are accessible publicly. They are not meant to be over-ridden:

$individual ->new(options)

AI::Genetic::IndBitVector ->new(options)

AI::Genetic::IndListVector ->new(options)

AI::Genetic::IndRangeVector->new(options)

This is the default constructor. It can be called as an instance method or as a class method. In both cases it returns a new individual of the proper type.

If called as an instance method, it expects one argument which defines the genes of the individual. All other attributes, like fitness function, class, etc, will be copied from the calling instance.

If called as a class method, then it calls newSpecific(). See below for details.

$individual->fitness(?anon_sub?)

This method is used to set/query the anonymous subroutine used to calculate the individual's fitness. If an argument is given, it expects a subroutine reference which will be set as the fitness subroutine. In either case, it'll return the fitness sub ref.

$individual->score()

This method returns the fitness score of the individual. If the score has never been calculated before, then the fitness function is executed and the score saved. Subsequent calls to score() will return the cached value.

$individual->resetScore()

This method resets the score of the individual such that a subsequent call to score() will result in the execution of the fitness sub.

The following methods are meant to be over-ridden by any class that inherits from AI::Genetic::Individual:

$individual->newRandom(options): This method returns an individual with random genes. It is called with the arguments supplied to AI::Genetic::init() as explained in "$ga->init(initArgs)" in AI::Genetic.
$individual->newSpecific(options): This method returns an individual with the given genetic makeup. The options depend on the type of individual:

o bitvector

One argument is expected which is an anonymous list of genes:

  AI::Genetic::IndBitVector->new([0, 1, 1, 0, 1, 0]);

o listvector

Two arguments are expected. The first is an anonymous list of genes, the second is an anonymous list of lists of possible gene values, similar to the argument of newRandom.

  AI::Genetic::IndListVector->new(
    [qw/red medium fat/],   # genes
    [  # possible values
     [qw/red blue green/],
     [qw/big medium small/],
     [qw/very_fat fat fit thin very_thin/],
    ]);

o rangevector

Two arguments are expected. The first is an anonymous list of genes, the second is an anonymous list of lists of possible gene values, similar to the argument of newRandom.

  AI::Genetic::IndListVector->new(
    [3, 14, 4],   # genes
    [   # possible values
     [1, 5],
     [0, 20],
     [4, 9],
    ]);

$individual->genes(): In list context, returns a list of genes. In scalar context returns an anonymous list of the genes.

Other useful non-generic methods:

$listVectorInd->lists(): This method returns an anonymous list of lists which describes the possible value of each gene for the given AI::Genetic::IndListVector individual. This is the same argument passed to newRandom().
$rangeVectorInd->ranges(): This method returns an anonymous list of lists which describes the possible range of each gene for the given AI::Genetic::IndRangeVector individual. This is the same argument passed to newRandom().

CREATING YOUR OWN INDIVIDUAL CLASS

Creating your own individual class is easy. All you have to do is inherit from AI::Genetic::Individual and override the newRandom(), newSpecific, and genes() methods to conform with the documentation above. Specifically, the arguments to i<newRandom> and newSpecific have to match what AI::Genetic::init() expects as arguments. You can also define any additional methods that you might require in your own custom-made strategies.

Note that in order for your own individual class to be useful, you have to define your own custom strategy that knows how to evolve such individuals. Conceptually, this should be very simple.

AUTHOR

Written by Ala Qumsieh aqumsieh@cpan.org.

COPYRIGHTS

POD ERRORS

Hey! The above document had some coding errors, which are explained below:

Around line 248:: =cut found outside a pod block. Skipping to next block.