view release on metacpan or  search on metacpan

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

			'class_counts'    => {},
			'token_counts'    => {},
			'class_totals'    => {},
			'tokens'          => {},
			'total_docs'      => 0,
			'lc_tokens'       => defined( $args{'lc_tokens'} )      ? $args{'lc_tokens'}      : 1,
			'token_splitter'  => defined( $args{'token_splitter'} ) ? $args{'token_splitter'} : '\s+',
			'stop_regex'      => $args{'stop_regex'},
		},
	};
	bless $self, $pkg;

	return $self;
} ## end sub new

=head2 tokenize

Tokenizes the specified string. This is used internally by train,
untrain, and classify, but may also be called directly to see how a
string will be broken up.