view release on metacpan or  search on metacpan

lib/Algorithm/NaiveBayes.pm  view on Meta::CPAN

  }
  return $package;
}

sub save_state {
  my ($self, $path) = @_;
  Storable::nstore($self, $path);
}

sub restore_state {
  my ($pkg, $path) = @_;
  my $self = Storable::retrieve($path)
    or die "Can't restore state from $path: $!";
  $self->_load_model_class;
  return $self;
}

sub add_instance {
  my ($self, %params) = @_;
  for ('attributes', 'label') {
    die "Missing required '$_' parameter" unless exists $params{$_};
  }
  for ($params{label}) {
    $_ = [$_] unless ref;
    @{$self->{labels}}{@$_} = ();
  }
  
  $self->{instances}++;
  $self->do_add_instance($params{attributes}, $params{label}, $self->{training_data});
}

sub labels { keys %{ $_[0]->{labels} } }
sub instances  { $_[0]->{instances} }
sub training_data { $_[0]->{training_data} }

sub train {
  my $self = shift;
  $self->{model} = $self->do_train($self->{training_data});
  $self->do_purge if $self->purge;
}

sub do_purge {
  my $self = shift;
  delete $self->{training_data};
}

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

sub predict {
  my ($self, %params) = @_;
  my $newattrs = $params{attributes} or die "Missing 'attributes' parameter for predict()";
  return $self->do_predict($self->{model}, $newattrs);
}

1;
__END__
# Below is stub documentation for your module. You better edit it!

=head1 NAME

Algorithm::NaiveBayes - Bayesian prediction of categories

=head1 SYNOPSIS

  use Algorithm::NaiveBayes;
  my $nb = Algorithm::NaiveBayes->new;

  $nb->add_instance
    (attributes => {foo => 1, bar => 1, baz => 3},
     label => 'sports');
  
  $nb->add_instance
    (attributes => {foo => 2, blurp => 1},
     label => ['sports', 'finance']);

  ... repeat for several more instances, then:
  $nb->train;
  
  # Find results for unseen instances
  my $result = $nb->predict
    (attributes => {bar => 3, blurp => 2});


=head1 DESCRIPTION

This module implements the classic "Naive Bayes" machine learning
algorithm.  It is a well-studied probabilistic algorithm often used in
automatic text categorization.  Compared to other algorithms (kNN,
SVM, Decision Trees), it's pretty fast and reasonably competitive in
the quality of its results.

A paper by Fabrizio Sebastiani provides a really good introduction to
text categorization:
L<http://faure.iei.pi.cnr.it/~fabrizio/Publications/ACMCS02.pdf>

=head1 METHODS

=over 4

=item new()

Creates a new C<Algorithm::NaiveBayes> object and returns it.  The
following parameters are accepted:

=over 4

=item purge

If set to a true value, the C<do_purge()> method will be invoked during
C<train()>.  The default is true.  Set this to a false value if you'd
like to be able to add additional instances after training and then
call C<train()> again.

=back

=item add_instance( attributes =E<gt> HASH, label =E<gt> STRING|ARRAY )