view release on metacpan or  search on metacpan

lib/Algorithm/BoostedDecisionTree.pm  view on Meta::CPAN

package Algorithm::BoostedDecisionTree;

#--------------------------------------------------------------------------------------
# Copyright (c) 2017 Avinash Kak. All rights reserved.  This program is free
# software.  You may modify and/or distribute it under the same terms as Perl itself.
# This copyright notice must remain attached to the file.
#
# Algorithm::BoostedDecisionTree is a Perl module for boosted decision-tree based
# classification of multidimensional data.
# -------------------------------------------------------------------------------------

#use lib 'blib/lib', 'blib/arch';

#use 5.10.0;
use strict;
use warnings;
use Carp;
use Algorithm::DecisionTree 3.43;
use List::Util qw(reduce min max);

our $VERSION = '3.43';

@Algorithm::BoostedDecisionTree::ISA = ('Algorithm::DecisionTree');

############################################   Constructor  ##############################################
sub new { 
    my ($class, %args) = @_;
    my @params = keys %args;
    croak "\nYou have used a wrong name for a keyword argument --- perhaps a misspelling\n" 
                           if check_for_illegal_params(@params) == 0;
    my %dtargs = %args;
    delete $dtargs{how_many_stages};
    my $instance = Algorithm::DecisionTree->new(%dtargs);
    bless $instance, $class;
    $instance->{_how_many_stages}              =  $args{how_many_stages} || undef;
    $instance->{_stagedebug}                   =  $args{stagedebug} || 0;
    $instance->{_training_samples}             =  {map {$_ => []} 0..$args{how_many_stages}};
    $instance->{_all_trees}                    =  {map {$_ => Algorithm::DecisionTree->new(%dtargs)} 0..$args{how_many_stages}};
    $instance->{_root_nodes}                   =  {map {$_ => undef} 0..$args{how_many_stages}};
    $instance->{_sample_selection_probs}       =  {map {$_ => {}} 0..$args{how_many_stages}};
    $instance->{_trust_factors}                =  {map {$_ => undef} 0..$args{how_many_stages}};
    $instance->{_misclassified_samples}        =  {map {$_ => []} 0..$args{how_many_stages}};
    $instance->{_classifications}              =  undef;
    $instance->{_trust_weighted_decision_classes}  =  undef;
    bless $instance, $class;
}

##############################################  Methods  #################################################
sub get_training_data_for_base_tree {
    my $self = shift;
    die("Aborted. get_training_data_csv() is only for CSV files") unless $self->{_training_datafile} =~ /\.csv$/;
    my %class_names = ();
    my %all_record_ids_with_class_labels;
    my $firstline;
    my %data_hash;
    $|++;
    open FILEIN, $self->{_training_datafile};
    my $record_index = 0;
    my $firsetline;
    while (<FILEIN>) {
        next if /^[ ]*\r?\n?$/;
        $_ =~ s/\r?\n?$//;
        my $record =  $self->{_csv_cleanup_needed} ? cleanup_csv($_) : $_;
        if ($record_index == 0) {
            $firstline = $record;
            $record_index++;