ruby-tf-idf 0.0.2 → 0.0.3

data/README.md

@@ -1,6 +1,9 @@
-# Ruby::Tf::Idf
+# Ruby-Tf-Idf
 
-TODO: Write a gem description
+This gem calculates TF-IDF to find the most relevant words of each document in corpus
+
+TF-IDF is for Term Frequency - Inverse Document Frequency
+http://en.wikipedia.org/wiki/Tf%E2%80%93idf
 
 ## Installation
 
@@ -10,7 +13,7 @@ Add this line to your application's Gemfile:
 
 And then execute:
 
-    $ bundle
+    $ bundle install
 
 Or install it yourself as:
 
@@ -18,7 +21,25 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+    require 'rubygems'
+    require 'ruby-tf-idf'
+
+    corpus = 
+	[
+	'A big enough hammer can usually fix anything',
+	'A bird in the hand is a big mistake .',
+	'A bird in the hand is better than one overhead!',
+	'A career is a job that takes about 20 more hours a week.'
+	'A clean desk is a sign of a cluttered desk drawer.'
+	'A cynic smells flowers and looks for the casket.'
+	]
+	
+    limit = 2 #restrict to the top 2 relevant words per document
+    exclude_stop_words = false
+
+    @t = Tfidf.new(corpus,limit,exclude_stop_words)
+    puts @t.tf_idf
+
 
 ## Contributing
 

data/lib/ruby-tf-idf.rb

@@ -1,3 +1,6 @@
+#!/bin/env ruby
+# encoding: ISO-8859-1
+
 require "ruby-tf-idf/version"
 
 module RubyTfIdf
@@ -37,8 +40,7 @@ module RubyTfIdf
 
     STOP_WORDS_FR = [
 
-      '-elle','-il','10ème','1er','1ère','2ème','3ème','4ème','5ème','6ème','7ème','8ème',
-      '9ème','à','a','afin','ai','ainsi','ais','ait','alors','après','as','assez','au','aucun',
+      '-elle','-il','à','a','afin','ai','ainsi','ais','ait','alors','après','as','assez','au','aucun',
       'aucune','auprès','auquel','auquelles','auquels','auraient','aurais','aurait','aurez',
       'auriez','aurions','aurons','auront','aussi','aussitôt','autre','autres','aux',
       'avaient','avais','avait','avant','avec','avez','aviez','avoir','avons','ayant',

data/lib/ruby-tf-idf/version.rb

@@ -1,3 +1,3 @@
 module RubyTfIdf
-      VERSION = "0.0.2"
+      VERSION = "0.0.3"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ruby-tf-idf
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors: