File Coverage

blib/lib/AI/Categorizer/Learner/Boolean.pm

Criterion	Covered	Total	%
statement	37	44	84.0
branch	4	10	40.0
condition	3	5	60.0
subroutine	8	9	88.8
pod	0	4	0.0
total	52	72	72.2

package AI::Categorizer::Learner::Boolean;

use strict;
use AI::Categorizer::Learner;
use base qw(AI::Categorizer::Learner);
use Params::Validate qw(:types);
use AI::Categorizer::Util qw(random_elements);

__PACKAGE__->valid_params
  (
   max_instances => {type => SCALAR, default => 0},
   threshold => {type => SCALAR, default => 0.5},
  );

sub create_model {
  my $self = shift;
  my $m = $self->{model} ||= {};
  my $mi = $self->{max_instances};

  foreach my $cat ($self->knowledge_set->categories) {
    my (@p, @n);
    foreach my $doc ($self->knowledge_set->documents) {
      if ($doc->is_in_category($cat)) {
	push @p, $doc;
      } else {
	push @n, $doc;
      }
    }
    if ($mi and @p + @n > $mi) {
      # Get rid of random instances from training set, preserving
      # current positive/negative ratio
      my $ratio = $mi / (@p + @n);
      @p = random_elements(\@p, @p * $ratio);
      @n = random_elements(\@n, @n * $ratio);

      warn "Limiting to ". @p ." positives and ". @n ." negatives\n" if $self->verbose;
    }

    warn "Creating model for ", $cat->name, "\n" if $self->verbose;
    $m->{learners}{ $cat->name } = $self->create_boolean_model(\@p, \@n, $cat);
  }
}

sub create_boolean_model;  # Abstract method

sub get_scores {
  my ($self, $doc) = @_;
  my $m = $self->{model};
  my %scores;
  foreach my $cat (keys %{$m->{learners}}) {
    $scores{$cat} = $self->get_boolean_score($doc, $m->{learners}{$cat});
  }
  return (\%scores, $self->{threshold});
}

sub get_boolean_score;  # Abstract method

sub threshold {
  my $self = shift;
  $self->{threshold} = shift if @_;
  return $self->{threshold};
}

sub categories {
  my $self = shift;
  return map AI::Categorizer::Category->by_name( name => $_ ), keys %{ $self->{model}{learners} };
}

1;
__END__