view release on metacpan or  search on metacpan

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

package AI::Categorizer::KnowledgeSet;

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

use Params::Validate qw(:types);
use AI::Categorizer::ObjectSet;
use AI::Categorizer::Document;
use AI::Categorizer::Category;
use AI::Categorizer::FeatureVector;
use AI::Categorizer::Util;
use Carp qw(croak);

__PACKAGE__->valid_params
  (
   categories => {
		  type => ARRAYREF,
		  default => [],
		  callbacks => { 'all are Category objects' => 
				 sub { ! grep !UNIVERSAL::isa($_, 'AI::Categorizer::Category'),
					 @{$_[0]} },
			       },
		 },
   documents  => {
		  type => ARRAYREF,
		  default => [],
		  callbacks => { 'all are Document objects' => 
				 sub { ! grep !UNIVERSAL::isa($_, 'AI::Categorizer::Document'),
					 @{$_[0]} },
			       },
		 },
   scan_first => {
		  type => BOOLEAN,
		  default => 1,
		 },
   feature_selector => {
			isa => 'AI::Categorizer::FeatureSelector',
		       },
   tfidf_weighting  => {
			type => SCALAR,
			optional => 1,
		       },
   term_weighting  => {
		       type => SCALAR,
		       default => 'x',
		      },
   collection_weighting => {
			    type => SCALAR,
			    default => 'x',
			   },
   normalize_weighting => {
			   type => SCALAR,
			   default => 'x',
			  },
   verbose => {
	       type => SCALAR,
	       default => 0,
	      },
  );

__PACKAGE__->contained_objects
  (
   document => { delayed => 1,
		 class => 'AI::Categorizer::Document' },
   category => { delayed => 1,
		 class => 'AI::Categorizer::Category' },
   collection => { delayed => 1,
		   class => 'AI::Categorizer::Collection::Files' },
   features => { delayed => 1,
		 class => 'AI::Categorizer::FeatureVector' },
   feature_selector => 'AI::Categorizer::FeatureSelector::DocFrequency',
  );

sub new {
  my ($pkg, %args) = @_;
  
  # Shortcuts
  if ($args{tfidf_weighting}) {
    @args{'term_weighting', 'collection_weighting', 'normalize_weighting'} = split '', $args{tfidf_weighting};
    delete $args{tfidf_weighting};
  }

  my $self = $pkg->SUPER::new(%args);

  # Convert to AI::Categorizer::ObjectSet sets
  $self->{categories} = new AI::Categorizer::ObjectSet( @{$self->{categories}} );
  $self->{documents}  = new AI::Categorizer::ObjectSet( @{$self->{documents}}  );