view release on metacpan or  search on metacpan

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

}

sub reduce_features {
  # Takes a feature vector whose weights are "feature scores", and
  # chops to the highest n features.  n is specified by the
  # 'features_kept' parameter.  If it's zero, all features are kept.
  # If it's between 0 and 1, we multiply by the present number of
  # features.  If it's greater than 1, we treat it as the number of
  # features to use.

  my ($self, $f, %args) = @_;
  my $kept = defined $args{features_kept} ? $args{features_kept} : $self->{features_kept};
  return $f unless $kept;

  my $num_kept = ($kept < 1 ? 
		  $f->length * $kept :
		  $kept);

  print "Trimming features - # features = " . $f->length . "\n" if $self->verbose;
  
  # This is algorithmic overkill, but the sort seems fast enough.  Will revisit later.
  my $features = $f->as_hash;
  my @new_features = (sort {$features->{$b} <=> $features->{$a}} keys %$features)
                      [0 .. $num_kept-1];

  my $result = $f->intersection( \@new_features );
  print "Finished trimming features - # features = " . $result->length . "\n" if $self->verbose;
  return $result;
}

# Abstract methods
sub rank_features;
sub scan_features;

sub select_features {
  my ($self, %args) = @_;
  
  die "No knowledge_set parameter provided to select_features()"
    unless $args{knowledge_set};

  my $f = $self->rank_features( knowledge_set => $args{knowledge_set} );
  return $self->reduce_features( $f, features_kept => $args{features_kept} );
}


1;

__END__

=head1 NAME

AI::Categorizer::FeatureSelector - Abstract Feature Selection class

=head1 SYNOPSIS

 ...

=head1 DESCRIPTION

The KnowledgeSet class that provides an interface to a set of
documents, a set of categories, and a mapping between the two.  Many
parameters for controlling the processing of documents are managed by
the KnowledgeSet class.

=head1 METHODS

=over 4

=item new()

Creates a new KnowledgeSet and returns it.  Accepts the following
parameters:

=over 4

=item load

If a C<load> parameter is present, the C<load()> method will be
invoked immediately.  If the C<load> parameter is a string, it will be
passed as the C<path> parameter to C<load()>.  If the C<load>
parameter is a hash reference, it will represent all the parameters to
pass to C<load()>.

=item categories

An optional reference to an array of Category objects representing the
complete set of categories in a KnowledgeSet.  If used, the
C<documents> parameter should also be specified.

=item documents

An optional reference to an array of Document objects representing the
complete set of documents in a KnowledgeSet.  If used, the
C<categories> parameter should also be specified.

=item features_kept

A number indicating how many features (words) should be considered
when training the Learner or categorizing new documents.  May be
specified as a positive integer (e.g. 2000) indicating the absolute
number of features to be kept, or as a decimal between 0 and 1
(e.g. 0.2) indicating the fraction of the total number of features to
be kept, or as 0 to indicate that no feature selection should be done
and that the entire set of features should be used.  The default is
0.2.

=item feature_selection

A string indicating the type of feature selection that should be
performed.  Currently the only option is also the default option:
C<document_frequency>.

=item tfidf_weighting

Specifies how document word counts should be converted to vector
values.  Uses the three-character specification strings from Salton &
Buckley's paper "Term-weighting approaches in automatic text
retrieval".  The three characters indicate the three factors that will
be multiplied for each feature to find the final vector value for that
feature.  The default weighting is C<xxx>.