view release on metacpan or  search on metacpan

lib/AI/Classifier/Text/FileLearner.pm  view on Meta::CPAN

    my ( $self, $doc ) = @_;
    my $f = $doc->{features};
    given ($self->term_weighting) {
        when ('n') {
            my $max_tf = max values %$f;
            $_ = 0.5 + 0.5 * $_ / $max_tf for values %$f;
        }
        when ('b') {
            $_ = $_ ? 1 : 0 for values %$f;
        }
        when (undef){
        }
        default {
            croak 'Unknown weighting type: '.$self->term_weighting;
        }
    }
}

# this doesn't quite fit the current model (it requires the entire collection
# of documents to be in memory at once), but it may be useful to someone, someday
# so let's just leave it here