view release on metacpan or  search on metacpan

lib/AI/Categorizer/Experiment.pm  view on Meta::CPAN

package AI::Categorizer::Experiment;

use strict;
use Class::Container;
use AI::Categorizer::Storable;
use Statistics::Contingency;

use base qw(Class::Container AI::Categorizer::Storable Statistics::Contingency);

use Params::Validate qw(:types);
__PACKAGE__->valid_params
  (
   categories => { type => ARRAYREF|HASHREF },
   sig_figs   => { type => SCALAR, default => 4 },
  );

sub new {
  my $package = shift;
  my $self = $package->Class::Container::new(@_);
  
  $self->{$_} = 0 foreach qw(a b c d);
  my $c = delete $self->{categories};
  $self->{categories} = { map {($_ => {a=>0, b=>0, c=>0, d=>0})} 
			  UNIVERSAL::isa($c, 'HASH') ? keys(%$c) : @$c
			};
  return $self;
}

sub add_hypothesis {
  my ($self, $h, $correct, $name) = @_;
  die "No hypothesis given to add_hypothesis()" unless $h;
  $name = $h->document_name unless defined $name;
  
  $self->add_result([$h->categories], $correct, $name);
}

sub stats_table {
  my $self = shift;
  $self->SUPER::stats_table($self->{sig_figs});
}

1;

__END__

=head1 NAME

AI::Categorizer::Experiment - Coordinate experimental results

=head1 SYNOPSIS

 use AI::Categorizer::Experiment;
 my $e = new AI::Categorizer::Experiment(categories => \%categories);
 my $l = AI::Categorizer::Learner->restore_state(...path...);
 
 while (my $d = ... get document ...) {
   my $h = $l->categorize($d); # A Hypothesis
   $e->add_hypothesis($h, [map $_->name, $d->categories]);
 }
 
 print "Micro F1: ", $e->micro_F1, "\n"; # Access a single statistic
 print $e->stats_table; # Show several stats in table form

=head1 DESCRIPTION

The C<AI::Categorizer::Experiment> class helps you organize the
results of categorization experiments.  As you get lots of
categorization results (Hypotheses) back from the Learner, you can
feed these results to the Experiment class, along with the correct
answers.  When all results have been collected, you can get a report
on accuracy, precision, recall, F1, and so on, with both
macro-averaging and micro-averaging over categories.

=head1 METHODS