# NAME Lingua::JA::DocumentFrequency::AozoraBunko - Return the document frequency in Aozora Bunko # SYNOPSIS use Lingua::JA::DocumentFrequency::AozoraBunko; use utf8; aozora_df('���'); # => 5180 aozora_df('������'); # => 160 aozora_df('���������������'); # => 3 aozora_df('���������������'); # => 149 aozora_df('������������'); # => 0 Lingua::JA::DocumentFrequency::AozoraBunko::df('������������'); # => 2 Lingua::JA::DocumentFrequency::AozoraBunko::df('������'); # => 23 my $N = Lingua::JA::DocumentFrequency::AozoraBunko::number_of_documents(); # => 11176 idf('������������'); # => 8.62837672037685 idf('������'); # => 6.18602968500765 sub idf { log( $N / aozora_df(shift) ) } # DESCRIPTION Lingua::JA::DocumentFrequency::AozoraBunko returns the document frequency in Aozora Bunko. # METHODS ## df($word) Returns the document frequency of $word. ## aozora\_df($word) Same as df method, but this method is exported by default. ## number\_of\_documents Returns the number of the documents in Aozora Bunko. # LICENSE Copyright (C) pawa. This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself. # AUTHOR pawa <pawapawa@cpan.org>