omnicat 0.1.1 → 0.1.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 5d04e29b0e2e16e019592553041b62eb9b759d3d
+  data.tar.gz: 1a4614e75aef06179e7c9589a73bf9c0b3552d20
+SHA512:
+  metadata.gz: d30317305905b877570cc2626665b74b56d3d4278422398ed05bb836d2316b2cb3fe4faee1cb0e26e1068121151fb0ba49b1eac61b79541fd2e44c23c6d19c03
+  data.tar.gz: bc998d7a815212af3881fb81bfa18bda74d1f68df1a273f9c17fdbf76340579de26953a384eb30edbdfac51409ddb7279e6195bac1e86d51f6e11bde48e5029e

data/CHANGELOG.txt

@@ -1,3 +1,6 @@
+0.1.2
+# fix the bayes algorithm (so important changes!)
+
 0.1.1
 # fix Regexp error for ruby version < 2.0.0
 

data/README.md

@@ -57,9 +57,9 @@ Train category with multiple documents.
 Classify a document.
 
     result = bayes.classify('I feel so good and happy')
-    => #<OmniCat::Result:0x007fe59b97b548 @category={:name=>"negative", :percentage=>99}, @scores={"positive"=>1.749909854122994e-07, "negative"=>0.014084507042253521}, @total_score=0.014084682033238934>
+    => #<OmniCat::Result:0x007fd20296aad8 @category={:name=>"positive", :percentage=>73}, @scores={"positive"=>5.4253472222222225e-09, "negative"=>1.9600796074572086e-09}, @total_score=7.385426829679431e-09>
     result.to_hash
-    => {:category=>{:name=>"negative", :percentage=>99}, :scores=>{"positive"=>1.749909854122994e-07, "negative"=>0.014084507042253521}, :total_score=>0.014084682033238934}
+    => {:category=>{:name=>"positive", :percentage=>73}, :scores=>{"positive"=>5.4253472222222225e-09, "negative"=>1.9600796074572086e-09}, :total_score=>7.385426829679431e-09}
 
 ### Classify batch
 Classify multiple documents at a time.
@@ -70,19 +70,22 @@ Classify multiple documents at a time.
         'a good piece of work'
       ]
     )
-    => [#<OmniCat::Result:0x007fe59b949d90 @category={:name=>"negative", :percentage=>75}, @scores={"positive"=>7.962089836259623e-06, "negative"=>2.5145916163515512e-05}, @total_score=3.3108005999775135e-05>, #<OmniCat::Result:0x007fe59c9d7d10 @category={:name=>"positive", :percentage=>100}, @scores={"positive"=>0.0005434126313247192, "negative"=>0}, @total_score=0.0005434126313247192>]
+    => [#<OmniCat::Result:0x007fd2029341b8 @category={:name=>"negative", :percentage=>78}, @scores={"positive"=>2.5521869888765736e-14, "negative"=>9.074442627116706e-14}, @total_score=1.162662961599328e-13>, #<OmniCat::Result:0x007fd20292e7e0 @category={:name=>"positive", :percentage=>80}, @scores={"positive"=>2.411265432098765e-07, "negative"=>5.880238822371627e-08}, @total_score=2.999289314335928e-07>]
 
 ### Convert to hash
 Convert full Bayes object to hash.
 
     # For storing, restoring modal data
     bayes_hash = bayes.to_hash
+    => {:categories=>{"positive"=>{:doc_count=>4, :tokens=>{"great"=>1, "if"=>1, "you"=>2, "are"=>2, "in"=>2, "slap"=>1, "happy"=>1, "mood"=>1, "feel-good"=>2, "picture"=>1, "the"=>2, "best"=>1, "sense"=>1, "of"=>2, "term"=>1, "it"=>1, "is"=>1, "movie"=>1, "about"=>1, "which"=>1, "can"=>1, "actually"=>1, "feel"=>1, "good"=>2, "love"=>1, "and"=>1, "money"=>1, "both"=>1, "them"=>1, "choises"=>1}, :token_count=>37}, "negative"=>{:doc_count=>4, :tokens=>{"bad"=>1, "tracking"=>1, "issue"=>1, "simplistic"=>1, "silly"=>1, "and"=>1, "tedious"=>1, "interesting"=>1, "but"=>2, "not"=>2, "compelling"=>2, "seems"=>1, "clever"=>1, "especially"=>1}, :token_count=>17}}, :category_count=>2, :doc_count=>8, :k_value=>1.0, :token_count=>54, :uniq_token_count=>43}
 
 ### Load from hash
 Load full Bayes object from hash.
 
     another_bayes_obj = OmniCat::Classifiers::Bayes.new(bayes_hash)
+    => #<OmniCat::Classifiers::Bayes:0x007fd20308cff0 @categories={"positive"=>#<OmniCat::Classifiers::BayesInternals::Category:0x007fd20308cf78 @doc_count=4, @tokens={"great"=>1, "if"=>1, "you"=>2, "are"=>2, "in"=>2, "slap"=>1, "happy"=>1, "mood"=>1, "feel-good"=>2, "picture"=>1, "the"=>2, "best"=>1, "sense"=>1, "of"=>2, "term"=>1, "it"=>1, "is"=>1, "movie"=>1, "about"=>1, "which"=>1, "can"=>1, "actually"=>1, "feel"=>1, "good"=>2, "love"=>1, "and"=>1, "money"=>1, "both"=>1, "them"=>1, "choises"=>1}, @token_count=37>, "negative"=>#<OmniCat::Classifiers::BayesInternals::Category:0x007fd20308cf00 @doc_count=4, @tokens={"bad"=>1, "tracking"=>1, "issue"=>1, "simplistic"=>1, "silly"=>1, "and"=>1, "tedious"=>1, "interesting"=>1, "but"=>2, "not"=>2, "compelling"=>2, "seems"=>1, "clever"=>1, "especially"=>1}, @token_count=17>}, @category_count=2, @doc_count=8, @k_value=1.0, @token_count=54, @uniq_token_count=43>
     another_bayes_obj.classify('best senses')
+    => #<OmniCat::Result:0x007fd203075008 @category={:name=>"positive", :percentage=>57}, @scores={"positive"=>0.0002314814814814815, "negative"=>0.00017146776406035664}, @total_score=0.00040294924554183816>
 
 ## Todo
 * Add more text classification modules such as Support Vector Machine (SVM).

data/lib/omnicat/classifiers/bayes.rb

@@ -2,7 +2,7 @@ module OmniCat
   module Classifiers
     class Bayes < ::OmniCat::Classifiers::Base
 
-      attr_accessor :categories, :category_count, :doc_count, :token_count
+      attr_accessor :categories, :category_count, :doc_count, :token_count, :uniq_token_count
       attr_accessor :k_value # helper val for skipping some Bayes theorem errors
 
       def initialize(bayes_hash = {})
@@ -16,6 +16,7 @@ module OmniCat
         self.doc_count = bayes_hash[:doc_count].to_i
         self.k_value = bayes_hash[:k_value] || 1.0
         self.token_count = bayes_hash[:token_count].to_i
+        self.uniq_token_count = bayes_hash[:uniq_token_count].to_i
       end
 
       # Allows adding new classification category
@@ -53,18 +54,26 @@ module OmniCat
       #   bayes.train("positive", "good, very well")
       #   bayes.train("negative", "bad dog")
       #   bayes.train("neutral", "how is the management gui")
-      def train(category, doc)
-        if category_exists?(category)
+      def train(category_name, doc)
+        if category_exists?(category_name)
           self.doc_count += 1
-          categories[category].doc_count += 1
+          categories[category_name].doc_count += 1
           doc.tokenize_with_counts.each do |token, count|
+            uniq_token_addition = 0
+            categories.each do |name, category|
+               if category.tokens.has_key?(token)
+                 uniq_token_addition = 1
+                 break
+               end 
+            end
+            self.uniq_token_count += 1 if uniq_token_addition == 0
             self.token_count += count
-            self.categories[category].tokens[token] = self.categories[category].tokens[token].to_i + count
-            self.categories[category].token_count += count
+            self.categories[category_name].tokens[token] = self.categories[category_name].tokens[token].to_i + count
+            self.categories[category_name].token_count += count
           end
         else
           raise StandardError,
-                "Category with name '#{category}' does not exist!"
+                "Category with name '#{category_name}' does not exist!"
         end
       end
 
@@ -94,14 +103,18 @@ module OmniCat
           prior = category.doc_count / doc_count.to_f
           result.scores[name] = k_value
           doc.tokenize_with_counts.each do |token, count|
-            result.scores[name] *= (
-              (category.tokens[token].to_i + k_value) /
-              (category.token_count + token_count)
-            ) if category.tokens.has_key?(token)
+            if category.tokens[token].to_i == 0
+              result.scores[name] *= k_value / token_count
+            else
+              result.scores[name] *= (
+                count * (
+                  (category.tokens[token].to_i + k_value) /
+                  (category.token_count + uniq_token_count)
+                )
+              )
+            end
           end
-          result.scores[name] = (
-            result.scores[name].to_f == 1.0 ? 0 : (prior * result.scores[name])
-          )
+          result.scores[name] = prior * result.scores[name]
           if result.scores[name] > score
             result.category[:name] = name;
             score = result.scores[name];

data/lib/omnicat/version.rb

@@ -1,3 +1,3 @@
 module OmniCat
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

metadata

@@ -1,20 +1,18 @@
 --- !ruby/object:Gem::Specification
 name: omnicat
 version: !ruby/object:Gem::Version
-  version: 0.1.1
-  prerelease: 
+  version: 0.1.2
 platform: ruby
 authors:
 - Mustafa Turan
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-16 00:00:00.000000000 Z
+date: 2013-06-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -22,7 +20,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -30,17 +27,15 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 description: A generalized framework for text classifications.
@@ -77,26 +72,25 @@ files:
 homepage: https://github.com/mustafaturan/omnicat
 licenses:
 - MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: A generalized framework for text classifications.
 test_files: []