AI-Genetic

 view release on metacpan or  search on metacpan

Genetic.pm  view on Meta::CPAN

}

# sub init():
# This method initializes the population to completely
# random individuals. It deletes all current individuals!!!
# It also examines the type of individuals we want, and
# require()s the proper class. Throws an error if it can't.
# Must pass to it an anon list that will be passed to the
# newRandom method of the individual.

# In case of bitvector, $newArgs is length of bitvector.
# In case of rangevector, $newArgs is anon list of anon lists.
# each sub-anon list has two elements, min number and max number.
# In case of listvector, $newArgs is anon list of anon lists.
# Each sub-anon list contains possible values of gene.

sub init {
  my ($self, $newArgs) = @_;

  $self->{INIT} = 0;

Genetic.pm  view on Meta::CPAN

This method initializes the population with random individuals. It B<MUST>
be called before any call to I<evolve()> or I<inject()>. As a side effect,
any already existing individuals in the population are deleted. It expects
one argument, which depends on the type of individuals:

=over

=item o

For bitvectors, the argument is simply the length of the bitvector.

    $ga->init(10);

this initializes a population where each individual has 10 genes.

=item o

For listvectors, the argument is an anonymous list of lists. The
number of sub-lists is equal to the number of genes of each individual.
Each sub-list defines the possible string values that the corresponding gene

Genetic/IndBitVector.pm  view on Meta::CPAN

package AI::Genetic::IndBitVector;

use strict;
use base qw/AI::Genetic::Individual/;

1;

sub newRandom {
  my ($class, $length) = @_;

  my $self = bless {
		    GENES   => [],
		    SCORE   => 0,
		    FITFUNC => sub {},
		    CALCED  => 0,
		   } => $class;

  push @{$self->{GENES}} => rand > 0.5 ? 1 : 0
    for 1 .. $length;

  return $self;
}

sub newSpecific {
  my ($class, $genes) = @_;

  my $self = bless {
		    GENES   => $genes,
		    CALCED  => 0,

Genetic/OpCrossover.pm  view on Meta::CPAN

use strict;

1;

# sub vectorSinglePoint():
# Single point crossover.
# arguments are crossover prob, two
# anon lists of genes (parents).
# If crossover occurs, returns two anon lists
# of children genes. If no crossover, returns 0.
# both parents have to be of same length.

sub vectorSinglePoint {
  my ($prob, $mom, $dad) = @_;

  return 0 if rand > $prob;

  # get single index from 1 to $#{$dad}
  my $ind = 1 + int rand $#{$dad};

  my @c1 = (@$mom[0 .. $ind - 1],

Genetic/OpCrossover.pm  view on Meta::CPAN

  return (\@c1, \@c2);
}

# sub vectorTwoPoint():
# Two point crossover.
# arguments are crossover prob, two
# anon lists of genes (parents).
# If crossover occurs, returns two anon lists
# of children genes. If no crossover, returns 0.
# both parents have to be of same length.

sub vectorTwoPoint {
  my ($prob, $mom, $dad) = @_;

  return 0 if rand > $prob;

  # get first index from 1 to $#{$dad}-1
  my $ind1 = 1 + int rand($#{$dad} - 1);

  # get second index from $ind1 to $#{$dad}

Genetic/OpCrossover.pm  view on Meta::CPAN

  return (\@c1, \@c2);
}

# sub vectorUniform():
# Uniform crossover.
# arguments are crossover prob, two
# anon lists of genes (parents).
# If crossover occurs, returns two anon lists
# of children genes. If no crossover, returns 0.
# both parents have to be of same length.

sub vectorUniform {
  my ($prob, $mom, $dad) = @_;

  return 0 if rand > $prob;

  my (@c1, @c2);
  for my $i (0 .. $#{$dad}) {
    if (rand > 0.5) {
      push @c1 => $mom->[$i];

README  view on Meta::CPAN

        the population at each generation. See the section on "STRATEGIES"
        for more information.

    *$ga*->init(*initArgs*)
        This method initializes the population with random individuals. It
        MUST be called before any call to *evolve()* or *inject()*. As a
        side effect, any already existing individuals in the population are
        deleted. It expects one argument, which depends on the type of
        individuals:

        o   For bitvectors, the argument is simply the length of the
            bitvector.

                $ga->init(10);

            this initializes a population where each individual has 10
            genes.

        o   For listvectors, the argument is an anonymous list of lists. The
            number of sub-lists is equal to the number of genes of each
            individual. Each sub-list defines the possible string values