view release on metacpan or  search on metacpan

lib/AI/NaiveBayes.pm  view on Meta::CPAN

package AI::NaiveBayes;
$AI::NaiveBayes::VERSION = '0.04';
use strict;
use warnings;
use 5.010;
use AI::NaiveBayes::Classification;
use AI::NaiveBayes::Learner;
use Moose;
use MooseX::Storage;

use List::Util qw(max);

with Storage(format => 'Storable', io => 'File');

has model   => (is => 'ro', isa => 'HashRef[HashRef]', required => 1);

sub train {
    my $self = shift;
    my $learner = AI::NaiveBayes::Learner->new();
    for my $example ( @_ ){
        $learner->add_example( %$example );
    }
    return $learner->classifier;
}


sub classify {
    my ($self, $newattrs) = @_;
    $newattrs or die "Missing parameter for classify()";

    my $m = $self->model;

    # Note that we're using the log(prob) here.  That's why we add instead of multiply.

    my %scores = %{$m->{prior_probs}};
    my %features;
    while (my ($feature, $value) = each %$newattrs) {
        next unless exists $m->{attributes}{$feature};  # Ignore totally unseen features
        while (my ($label, $attributes) = each %{$m->{probs}}) {
            my $score = ($attributes->{$feature} || $m->{smoother}{$label})*$value;  # P($feature|$label)**$value
            $scores{$label} += $score;
            $features{$feature}{$label} = $score;
        }
    }

    rescale(\%scores);

    return AI::NaiveBayes::Classification->new( label_sums => \%scores, features => \%features );
}

sub rescale {
    my ($scores) = @_;

    # Scale everything back to a reasonable area in logspace (near zero), un-loggify, and normalize
    my $total = 0;
    my $max = max(values %$scores);
    foreach (values %$scores) {
        $_ = exp($_ - $max);
        $total += $_**2;
    }
    $total = sqrt($total);
    foreach (values %$scores) {
        $_ /= $total;
    }
}


__PACKAGE__->meta->make_immutable;

1;

=pod

=encoding UTF-8