view release on metacpan or  search on metacpan

lib/AI/Categorizer/Learner/SVM.pm  view on Meta::CPAN

package AI::Categorizer::Learner::SVM;
$VERSION = '0.01';

use strict;
use AI::Categorizer::Learner::Boolean;
use base qw(AI::Categorizer::Learner::Boolean);
use Algorithm::SVM;
use Algorithm::SVM::DataSet;
use Params::Validate qw(:types);
use File::Spec;

__PACKAGE__->valid_params
  (
   svm_kernel => {type => SCALAR, default => 'linear'},
  );

sub create_model {
  my $self = shift;
  my $f = $self->knowledge_set->features->as_hash;
  my $rmap = [ keys %$f ];
  $self->{model}{feature_map} = { map { $rmap->[$_], $_ } 0..$#$rmap };
  $self->{model}{feature_map_reverse} = $rmap;
  $self->SUPER::create_model(@_);
}

sub _doc_2_dataset {
  my ($self, $doc, $label, $fm) = @_;

  my $ds = new Algorithm::SVM::DataSet(Label => $label);
  my $f = $doc->features->as_hash;
  while (my ($k, $v) = each %$f) {
    next unless exists $fm->{$k};
    $ds->attribute( $fm->{$k}, $v );
  }
  return $ds;
}

sub create_boolean_model {
  my ($self, $positives, $negatives, $cat) = @_;
  my $svm = new Algorithm::SVM(Kernel => $self->{svm_kernel});
  
  my (@pos, @neg);
  foreach my $doc (@$positives) {
    push @pos, $self->_doc_2_dataset($doc, 1, $self->{model}{feature_map});
  }
  foreach my $doc (@$negatives) {
    push @neg, $self->_doc_2_dataset($doc, 0, $self->{model}{feature_map});
  }

  $svm->train(@pos, @neg);
  return $svm;
}

sub get_scores {
  my ($self, $doc) = @_;
  local $self->{current_doc} = $self->_doc_2_dataset($doc, -1, $self->{model}{feature_map});
  return $self->SUPER::get_scores($doc);
}

sub get_boolean_score {
  my ($self, $doc, $svm) = @_;
  return $svm->predict($self->{current_doc});
}

sub save_state {
  my ($self, $path) = @_;
  {
    local $self->{model}{learners};
    local $self->{knowledge_set};
    $self->SUPER::save_state($path);
  }
  return unless $self->{model};
  
  my $svm_dir = File::Spec->catdir($path, 'svms');