AI-Genetic-Pro
view release on metacpan or search on metacpan
Normal distribution, where $av is average (default: size of
population /2) and $$sd is standard deviation (default: size of
population).
-selection => [ 'RouletteDistribution', 'beta', $aa, $bb ]
Beta distribution. The density of the beta is:
X^($aa - 1) * (1 - X)^($bb - 1) / B($aa , $bb) for 0 < X < 1.
$aa and $bb are set by default to number of parents.
Argument restrictions: Both $aa and $bb must not be less than
1.0E-37.
-selection => [ 'RouletteDistribution', 'binomial' ]
Binomial distribution. No additional parameters are needed.
-selection => [ 'RouletteDistribution', 'chi_square', $df ]
Chi-square distribution with $df degrees of freedom. $df by
default is set to size of population.
-selection => [ 'RouletteDistribution', 'exponential', $av ]
Exponential distribution, where $av is average . $av by default
is set to size of population.
-selection => [ 'RouletteDistribution', 'poisson', $mu ]
Poisson distribution, where $mu is mean. $mu by default is set
to size of population.
Distribution
Chromosomes/individuals are selected with specified distribution.
See below.
-selection => [ 'Distribution', 'uniform' ]
Standard uniform distribution. No additional parameters are
Normal distribution, where $av is average (default: size of
population /2) and $$sd is standard deviation (default: size of
population).
-selection => [ 'Distribution', 'beta', $aa, $bb ]
Beta distribution. The density of the beta is:
X^($aa - 1) * (1 - X)^($bb - 1) / B($aa , $bb) for 0 < X < 1.
$aa and $bb are set by default to number of parents.
Argument restrictions: Both $aa and $bb must not be less than
1.0E-37.
-selection => [ 'Distribution', 'binomial' ]
Binomial distribution. No additional parameters are needed.
-selection => [ 'Distribution', 'chi_square', $df ]
Chi-square distribution with $df degrees of freedom. $df by
default is set to size of population.
-selection => [ 'Distribution', 'exponential', $av ]
Exponential distribution, where $av is average . $av by default
is set to size of population.
-selection => [ 'Distribution', 'poisson', $mu ]
Poisson distribution, where $mu is mean. $mu by default is set
to size of population.
-strategy
This defines the astrategy of crossover operation. It expects an
array reference listed below:
-strategy => [ $type, @params ]
where type is one of:
Normal distribution, where $av is average (default: number of
parents/2) and $sd is standard deviation (default: number of
parents).
-strategy => [ 'Distribution', 'beta', $aa, $bb ]
Beta distribution. The density of the beta is:
X^($aa - 1) * (1 - X)^($bb - 1) / B($aa , $bb) for 0 < X < 1.
$aa and $bb are set by default to the number of parents.
Argument restrictions: Both $aa and $bb must not be less than
1.0E-37.
-strategy => [ 'Distribution', 'binomial' ]
Binomial distribution. No additional parameters are needed.
-strategy => [ 'Distribution', 'chi_square', $df ]
Chi-squared distribution with $df degrees of freedom. $df by
default is set to the number of parents.
-strategy => [ 'Distribution', 'exponential', $av ]
Exponential distribution, where $av is average . $av by default
is set to the number of parents.
-strategy => [ 'Distribution', 'poisson', $mu ]
Poisson distribution, where $mu is mean. $mu by default is set
to the number of parents.
PMX
PMX method defined by Goldberg and Lingle in 1985. Parameters:
none.
OX
OX method defined by Davis (?) in 1985. Parameters: none.
In example:
my $type = $ga->type();
$ga->type()
Alias for indType.
$ga->crossProb()
This method is used to query and set the crossover rate.
$ga->crossover()
Alias for crossProb.
$ga->mutProb()
This method is used to query and set the mutation rate.
$ga->mutation()
Alias for mutProb.
$ga->parents($parents)
Set/get number of parents in a crossover.
$ga->init($args)
$ga->load($file)
Load a state of the genetic algorithm from the specified file.
$ga->as_array($chromosome)
In list context return an array representing the specified
chromosome. In scalar context return an reference to an array
representing the specified chromosome. If variable_length is turned
on and is set to level 2, an array can have some undef values. To get
only not undef values use as_array_def_only instead of as_array.
$ga->as_array_def_only($chromosome)
In list context return an array representing the specified
chromosome. In scalar context return an reference to an array
representing the specified chromosome. If variable_length is turned
off, this function is just an alias for as_array. If variable_length
is turned on and is set to level 2, this function will return only
not undef values from chromosome. See example below:
# -variable_length => 2, -type => 'bitvector'
my @chromosome = $ga->as_array($chromosome)
# @chromosome looks something like that
# ( undef, undef, undef, 1, 0, 1, 1, 1, 0 )
@chromosome = $ga->as_array_def_only($chromosome)
# @chromosome looks something like that
# 1___0___1___1___1___0
# or
# -type => 'listvector'
$string = $ga->as_string($chromosome);
# $string looks something like that
# element0___element1___element2___element3...
Attention! If variable_length is turned on and is set to level 2, it
is possible to get undef values on the left side of the vector. In
the returned string undef values will be replaced with spaces. If you
don't want to see any spaces, use as_string_def_only instead of
as_string.
$ga->as_string_def_only($chromosome)
Return a string representation of specified chromosome. If
variable_length is turned off, this function is just alias for
as_string. If variable_length is turned on and is set to level 2,
this function will return a string without undef values. See example
below:
# -variable_length => 2, -type => 'bitvector'
my $string = $ga->as_string($chromosome);
# $string looks something like that
# ___ ___ ___1___1___0
$string = $ga->as_string_def_only($chromosome);
Examples.
More tests.
More warnings about incorrect parameters.
REPORTING BUGS
When reporting bugs/problems please include as much information as
possible. It may be difficult for me to reproduce the problem as almost
every setup is different.
A small script which yields the problem will probably be of help.
THANKS
Mario Roy for suggestions about efficiency.
Miles Gould for suggestions and some fixes (even in this documentation!
:-).
lib/AI/Genetic/Pro.pm view on Meta::CPAN
croak(q/Type of chromosomes cannot be "combination" if "variable length" feature is active!/)
if $self->type eq q/combination/ and $self->variable_length;
croak(q/You must specify a crossover strategy with -strategy!/)
unless defined ($self->strategy);
croak(q/Type of chromosomes cannot be "combination" if strategy is not one of: OX, PMX!/)
if $self->type eq q/combination/ and ($self->strategy->[0] ne q/OX/ and $self->strategy->[0] ne q/PMX/);
croak(q/Strategy cannot be "/,$self->strategy->[0],q/" if "variable length" feature is active!/ )
if ($self->strategy->[0] eq 'PMX' or $self->strategy->[0] eq 'OX') and $self->variable_length;
#-------------------------------------------------------------------
$self->_set_strict if $self->strict;
#-------------------------------------------------------------------
return $self unless $self->mce;
#-------------------------------------------------------------------
delete $self->{ mce };
'AI::Genetic::Pro::MCE'->use or die q[Cannot raise multicore support: ] . $@;
return AI::Genetic::Pro::MCE->new( $self, \%args );
}
#=======================================================================
sub _Cache { $_Cache; }
#=======================================================================
# INIT #################################################################
#=======================================================================
sub _set_strict {
my ($self) = @_;
# fitness
my $fitness = $self->fitness();
my $replacement = sub {
my @tmp = @{$_[1]};
my $ret = $fitness->(@_);
my @cmp = @{$_[1]};
die qq/Chromosome was modified in a fitness function from "@tmp" to "@{$_[1]}"!\n/ unless compare(\@tmp, \@cmp);
return $ret;
lib/AI/Genetic/Pro.pm view on Meta::CPAN
#-------------------------------------------------------------------
$self->generation(0);
$self->_init( $data );
$self->_fitness( { } );
$self->_fix_range( [ ] );
$self->_history( [ [ ], [ ], [ ] ] );
$self->_init_cache if $self->cache;
#-------------------------------------------------------------------
if($self->type eq q/listvector/){
croak(q/You have to pass array reference if "type" is set to "listvector"/) unless ref $data eq 'ARRAY';
$self->_translations( $self->_check_data_ref($data) );
}elsif($self->type eq q/bitvector/){
croak(q/You have to pass integer if "type" is set to "bitvector"/) if $data !~ /^\d+$/o;
$self->_translations( [ [ 0, 1 ] ] );
$self->_translations->[$_] = $self->_translations->[0] for 1..$data-1;
}elsif($self->type eq q/combination/){
croak(q/You have to pass array reference if "type" is set to "combination"/) unless ref $data eq 'ARRAY';
$self->_translations( [ clone($data) ] );
$self->_translations->[$_] = $self->_translations->[0] for 1..$#$data;
}elsif($self->type eq q/rangevector/){
croak(q/You have to pass array reference if "type" is set to "rangevector"/) unless ref $data eq 'ARRAY';
$self->_translations( $self->_find_fix_range( $self->_check_data_ref($data) ));
}else{
croak(q/You have to specify first "type" of vector!/);
}
my $size = 0;
if($self->type ne q/rangevector/){ for(@{$self->_translations}){ $size = $#$_ if $#$_ > $size; } }
# else{ for(@{$self->_translations}){ $size = $_->[1] if $_->[1] > $size; } }
else{ for(@{$self->_translations}){ $size = $_->[2] if $_->[2] > $size; } } # Provisional patch for rangevector values truncated to signed 8-bit quantities. Thx to Tod Hagan
lib/AI/Genetic/Pro.pm view on Meta::CPAN
#=======================================================================
sub chart {
GD->require or croak(q/You need "/.GD.q/" module to draw chart of evolution!/);
my ($self, %params) = (shift, @_);
my $graph = GD()->new(($params{-width} || 640), ($params{-height} || 480));
my $data = $self->getHistory;
if(defined $params{-font}){
$graph->set_title_font ($params{-font}, 12);
$graph->set_x_label_font($params{-font}, 10);
$graph->set_y_label_font($params{-font}, 10);
$graph->set_legend_font ($params{-font}, 8);
}
$graph->set_legend(
$params{legend1} || q/Max value/,
$params{legend2} || q/Mean value/,
$params{legend3} || q/Min value/,
);
$graph->set(
x_label_skip => int(($data->[0]->[-1]*4)/100),
x_labels_vertical => 1,
x_label_position => .5,
y_label_position => .5,
y_long_ticks => 1, # poziome linie
x_ticks => 1, # poziome linie
l_margin => 10,
b_margin => 10,
r_margin => 10,
lib/AI/Genetic/Pro.pm view on Meta::CPAN
Normal distribution, where C<$av> is average (default: size of population /2) and $C<$sd> is standard deviation (default: size of population).
=item C<-selection =E<gt> [ 'RouletteDistribution', 'beta', $aa, $bb ]>
I<Beta> distribution. The density of the beta is:
X^($aa - 1) * (1 - X)^($bb - 1) / B($aa , $bb) for 0 < X < 1.
C<$aa> and C<$bb> are set by default to number of parents.
B<Argument restrictions:> Both $aa and $bb must not be less than 1.0E-37.
=item C<-selection =E<gt> [ 'RouletteDistribution', 'binomial' ]>
Binomial distribution. No additional parameters are needed.
=item C<-selection =E<gt> [ 'RouletteDistribution', 'chi_square', $df ]>
Chi-square distribution with C<$df> degrees of freedom. C<$df> by default is set to size of population.
=item C<-selection =E<gt> [ 'RouletteDistribution', 'exponential', $av ]>
Exponential distribution, where C<$av> is average . C<$av> by default is set to size of population.
=item C<-selection =E<gt> [ 'RouletteDistribution', 'poisson', $mu ]>
Poisson distribution, where C<$mu> is mean. C<$mu> by default is set to size of population.
=back
=item B<Distribution>
Chromosomes/individuals are selected with specified distribution. See below.
=over 12
=item C<-selection =E<gt> [ 'Distribution', 'uniform' ]>
lib/AI/Genetic/Pro.pm view on Meta::CPAN
=item C<-selection =E<gt> [ 'Distribution', 'normal', $av, $sd ]>
Normal distribution, where C<$av> is average (default: size of population /2) and $C<$sd> is standard deviation (default: size of population).
=item C<-selection =E<gt> [ 'Distribution', 'beta', $aa, $bb ]>
I<Beta> distribution. The density of the beta is:
X^($aa - 1) * (1 - X)^($bb - 1) / B($aa , $bb) for 0 < X < 1.
C<$aa> and C<$bb> are set by default to number of parents.
B<Argument restrictions:> Both $aa and $bb must not be less than 1.0E-37.
=item C<-selection =E<gt> [ 'Distribution', 'binomial' ]>
Binomial distribution. No additional parameters are needed.
=item C<-selection =E<gt> [ 'Distribution', 'chi_square', $df ]>
Chi-square distribution with C<$df> degrees of freedom. C<$df> by default is set to size of population.
=item C<-selection =E<gt> [ 'Distribution', 'exponential', $av ]>
Exponential distribution, where C<$av> is average . C<$av> by default is set to size of population.
=item C<-selection =E<gt> [ 'Distribution', 'poisson', $mu ]>
Poisson distribution, where C<$mu> is mean. C<$mu> by default is set to size of population.
=back
=back
=item -strategy
This defines the astrategy of crossover operation. It expects an array
reference listed below:
lib/AI/Genetic/Pro.pm view on Meta::CPAN
=item C<-strategy =E<gt> [ 'Distribution', 'normal', $av, $sd ]>
Normal distribution, where C<$av> is average (default: number of parents/2) and C<$sd> is standard deviation (default: number of parents).
=item C<-strategy =E<gt> [ 'Distribution', 'beta', $aa, $bb ]>
I<Beta> distribution. The density of the beta is:
X^($aa - 1) * (1 - X)^($bb - 1) / B($aa , $bb) for 0 < X < 1.
C<$aa> and C<$bb> are set by default to the number of parents.
B<Argument restrictions:> Both $aa and $bb must not be less than 1.0E-37.
=item C<-strategy =E<gt> [ 'Distribution', 'binomial' ]>
Binomial distribution. No additional parameters are needed.
=item C<-strategy =E<gt> [ 'Distribution', 'chi_square', $df ]>
Chi-squared distribution with C<$df> degrees of freedom. C<$df> by default is set to the number of parents.
=item C<-strategy =E<gt> [ 'Distribution', 'exponential', $av ]>
Exponential distribution, where C<$av> is average . C<$av> by default is set to the number of parents.
=item C<-strategy =E<gt> [ 'Distribution', 'poisson', $mu ]>
Poisson distribution, where C<$mu> is mean. C<$mu> by default is set to the number of parents.
=back
=item PMX
PMX method defined by Goldberg and Lingle in 1985. Parameters: I<none>.
=item OX
OX method defined by Davis (?) in 1985. Parameters: I<none>.
lib/AI/Genetic/Pro.pm view on Meta::CPAN
In example:
my $type = $ga->type();
=item I<$ga>-E<gt>B<type>()
Alias for C<indType>.
=item I<$ga>-E<gt>B<crossProb>()
This method is used to query and set the crossover rate.
=item I<$ga>-E<gt>B<crossover>()
Alias for C<crossProb>.
=item I<$ga>-E<gt>B<mutProb>()
This method is used to query and set the mutation rate.
=item I<$ga>-E<gt>B<mutation>()
Alias for C<mutProb>.
=item I<$ga>-E<gt>B<parents>($parents)
Set/get number of parents in a crossover.
=item I<$ga>-E<gt>B<init>($args)
lib/AI/Genetic/Pro.pm view on Meta::CPAN
Save the current state of the genetic algorithm to the specified file.
=item I<$ga>-E<gt>B<load>($file)
Load a state of the genetic algorithm from the specified file.
=item I<$ga>-E<gt>B<as_array>($chromosome)
In list context return an array representing the specified chromosome.
In scalar context return an reference to an array representing the specified
chromosome. If I<variable_length> is turned on and is set to level 2, an array
can have some C<undef> values. To get only C<not undef> values use
C<as_array_def_only> instead of C<as_array>.
=item I<$ga>-E<gt>B<as_array_def_only>($chromosome)
In list context return an array representing the specified chromosome.
In scalar context return an reference to an array representing the specified
chromosome. If I<variable_length> is turned off, this function is just an
alias for C<as_array>. If I<variable_length> is turned on and is set to
level 2, this function will return only C<not undef> values from chromosome.
See example below:
# -variable_length => 2, -type => 'bitvector'
my @chromosome = $ga->as_array($chromosome)
# @chromosome looks something like that
# ( undef, undef, undef, 1, 0, 1, 1, 1, 0 )
@chromosome = $ga->as_array_def_only($chromosome)
lib/AI/Genetic/Pro.pm view on Meta::CPAN
# 1___0___1___1___1___0
# or
# -type => 'listvector'
$string = $ga->as_string($chromosome);
# $string looks something like that
# element0___element1___element2___element3...
Attention! If I<variable_length> is turned on and is set to level 2, it is
possible to get C<undef> values on the left side of the vector. In the returned
string C<undef> values will be replaced with B<spaces>. If you don't want
to see any I<spaces>, use C<as_string_def_only> instead of C<as_string>.
=item I<$ga>-E<gt>B<as_string_def_only>($chromosome)
Return a string representation of specified chromosome. If I<variable_length>
is turned off, this function is just alias for C<as_string>. If I<variable_length>
is turned on and is set to level 2, this function will return a string without
C<undef> values. See example below:
# -variable_length => 2, -type => 'bitvector'
my $string = $ga->as_string($chromosome);
# $string looks something like that
# ___ ___ ___1___1___0
$string = $ga->as_string_def_only($chromosome);
# $string looks something like that
lib/AI/Genetic/Pro.pm view on Meta::CPAN
=item More tests.
=item More warnings about incorrect parameters.
=back
=head1 REPORTING BUGS
When reporting bugs/problems please include as much information as possible.
It may be difficult for me to reproduce the problem as almost every setup
is different.
A small script which yields the problem will probably be of help.
=head1 THANKS
Mario Roy for suggestions about efficiency.
Miles Gould for suggestions and some fixes (even in this documentation! :-).
lib/AI/Genetic/Pro/Selection/Distribution.pm view on Meta::CPAN
bless {
type => $type,
params => \@params,
}, $class;
}
#=======================================================================
sub run {
my ($self, $ga) = @_;
my ($fitness, $chromosomes) = ($ga->_fitness, $ga->chromosomes);
croak "You must set a number of parents to use the Distribution strategy"
unless defined($ga->parents);
my $parents = $ga->parents;
my @parents;
my $high = scalar @$chromosomes;
#-------------------------------------------------------------------
if($self->{type} eq q/uniform/){
push @parents,
pack 'I*', random_uniform_integer($parents, 0, $#$chromosomes)
for 0..$#$chromosomes;
}elsif($self->{type} eq q/normal/){
lib/AI/Genetic/Pro/Selection/Roulette.pm view on Meta::CPAN
# elders
for my $idx (0..$count){
push @elders, $idx for 1..int((($fitness->{$idx} + $const) / $total) * $count);
}
if((my $add = $count - scalar @elders) > 0){
my $idx = $elders[rand @elders];
push @elders, int rand($count) for 0..$add;
}
croak "You must set a crossover probability to use the Roulette strategy"
unless defined($ga->crossover);
croak "You must set a number of parents to use the Roulette strategy"
unless defined($ga->parents);
# parents
for(0..$count){
if(rand > $ga->crossover){
push @parents, pack 'I*', $elders[ rand @elders ]
}else{
my @group;
push @group, $elders[ rand @elders ] for 1..$ga->parents;
push @parents, pack 'I*', @group;
lib/AI/Genetic/Pro/Selection/RouletteBasic.pm view on Meta::CPAN
#use Data::Dumper; $Data::Dumper::Sortkeys = 1;
use List::MoreUtils qw(first_index);
use Carp 'croak';
#=======================================================================
sub new { bless \$_[0], $_[0]; }
#=======================================================================
sub run {
my ($self, $ga) = @_;
my ($fitness, $chromosomes) = ($ga->_fitness, $ga->chromosomes);
croak "You must set a number of parents to use the RouletteBasic strategy"
unless defined($ga->parents);
my $parents = $ga->parents;
my (@parents, @wheel);
my $const = min values %$fitness;
$const = $const < 0 ? abs($const) : 0;
my $total = 0;
#-------------------------------------------------------------------
foreach my $key (keys %$fitness){
$total += $fitness->{$key} + $const;
push @wheel, [ $key, $total ];
lib/AI/Genetic/Pro/Selection/RouletteDistribution.pm view on Meta::CPAN
my $idx = first_index { $_->[1] > $rand } @$wheel;
if($idx == 0){ $idx = 1 }
elsif($idx == -1 ) { $idx = scalar @$wheel; }
return $wheel->[$idx-1]->[0];
}
#=======================================================================
sub run {
my ($self, $ga) = @_;
my ($fitness, $chromosomes) = ($ga->_fitness, $ga->chromosomes);
croak "You must set a number of parents for the RouletteDistribution strategy"
unless defined($ga->parents);
my $parents = $ga->parents;
my $high = scalar @$chromosomes;
my (@parents, @wheel);
my $const = min values %$fitness;
$const = $const < 0 ? abs($const) : 0;
my $total = 0;
#-------------------------------------------------------------------
foreach my $key (keys %$fitness){
$total += $fitness->{$key} + $const;
( run in 1.862 second using v1.01-cache-2.11-cpan-49f99fa48dc )