NAME

Lingua::JA::Categorize - Naive Bayes Classifier for Japanese document.

SYNOPSIS

use Lingua::JA::Categorize;

# generate
my $categorizer = Lingua::JA::Categorize->new;
$categorizer->generate($category_conf);
$categorizer->save('save_file');

# categorize
my $categorizer = Lingua::JA::Categorize->new;
$categorizer->load('save_file');
my $result = $categorizer->categorize($text);
print Dumper $result->score;

DESCRIPTION

Lingua::JA::Categorize is a Naive Bayes classifier for Japanese document.

THIS MODULE IS IN ITS ALPHA QUALITY.

METHODS

new

The constructor method.

categorize($text)

This method accepts $text, and returns Lingua::JA::Categorize::Result object.

train

Training method of bayesian filter.

generate(config => \%configuration_data)

This generate primary data set from the category configuration.

load('filename')

Load the saved file (that is Storable).

save('filemname')

Save the data to filename (that is Storable).

tokenizer

Accessor method to Lingua::JA::Categorize::Tokenizer.

categorizer

Accessor method to Lingua::JA::Categorize::Categorizer.

generator

Accessor method to Lingua::JA::Categorize::Generator.

AUTHOR

takeshi miki <miki@cpan.org>

LICENSE

This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself.

SEE ALSO