en.wikipedia.org/wiki/Tf–idf

gem sources -a http://gemcutter.org
sudo gem install tf_idf

require 'rubygems'
require 'tf_idf'

data = [%w{a a a a a a a a b b}, %w{a a}]

a = TfIdf.new(data)

# To find the term frequencies
a.tf
  #=> [{'b' => 0.2, 'a' => etc...}, {'a' => 1}]

# To find the inverse document frequency
a.idf
  #=> {'b' => 0.301... etc...}

# And to find the tf-idf
a.tf_idf
  #=> [{'b' => 0.0602, 'a' => etc...}, {etc...}]

Copyright © 2009 Red Davis. See LICENSE for details.