omnicat-bayes 0.2.0 → 0.2.1

data/README.md

@@ -57,6 +57,12 @@ Train category with a document.
 
     bayes.train('positive', 'great if you are in a slap happy mood .')
     bayes.train('negative', 'bad tracking issue')
+    
+### Untrain
+Untrain category with a document.
+
+    bayes.untrain('positive', 'great if you are in a slap happy mood .')
+    bayes.untrain('negative', 'bad tracking issue')
 
 ### Train batch
 Train category with multiple documents.
@@ -71,6 +77,20 @@ Train category with multiple documents.
       'interesting , but not compelling . ',
       'seems clever but not especially compelling'
     ])
+    
+### Untrain batch
+Untrain category with multiple documents.
+
+    bayes.untrain_batch('positive', [
+      'a feel-good picture in the best sense of the term...',
+      'it is a feel-good movie about which you can actually feel good.',
+      'love and money both of them are good choises'
+    ])
+    bayes.untrain_batch('negative', [
+      'simplistic , silly and tedious .',
+      'interesting , but not compelling . ',
+      'seems clever but not especially compelling'
+    ])
 
 ### Classify
 Classify a document.

data/Rakefile

@@ -9,7 +9,7 @@ task :default => [ :test ]
 desc "Run all unit tests"
 Rake::TestTask.new do |t|
   t.libs << 'lib'
-  t.test_files = FileList['lib/test/unit/*_test.rb']
+  t.test_files = FileList['test/unit/*_test.rb']
   t.verbose = true
 end
 

data/lib/omnicat/bayes/version.rb

@@ -1,5 +1,5 @@
 module Omnicat
   module Bayes
-    VERSION = '0.2.0'
+    VERSION = '0.2.1'
   end
 end

data/lib/omnicat/classifiers/bayes.rb

@@ -1,3 +1,4 @@
+require 'digest'
 require 'omnicat/classifiers/strategy'
 
 module OmniCat
@@ -54,7 +55,13 @@ module OmniCat
         if category_exists?(category_name)
           increment_doc_counts(category_name)
           update_priors
-          doc = OmniCat::Doc.new(content: doc_content)
+          doc_key = Digest::MD5.hexdigest(doc_content)
+          if doc = @categories[category_name].docs[doc_key]
+            doc.increment_count
+          else
+            doc = OmniCat::Doc.new(content: doc_content)
+          end
+          @categories[category_name].docs[doc_key] = doc
           doc.tokens.each do |token, count|
             increment_token_counts(category_name, token, count)
             @categories[category_name].tokens[token] = @categories[category_name].tokens[token].to_i + count
@@ -65,6 +72,42 @@ module OmniCat
         end
       end
 
+      # Untrain the desired category with a document
+      #
+      # ==== Parameters
+      #
+      # * +category_name+ - Name of the category from added categories list
+      # * +doc_content+ - Document text
+      #
+      # ==== Examples
+      #
+      #   # Untrain the desired category
+      #   bayes.untrain("positive", "clear documentation")
+      #   bayes.untrain("positive", "good, very well")
+      #   bayes.untrain("negative", "bad dog")
+      #   bayes.untrain("neutral", "how is the management gui")
+      def untrain(category_name, doc_content)
+        if category_exists?(category_name)
+          doc_key = Digest::MD5.hexdigest(doc_content)
+          if doc = @categories[category_name].docs[doc_key]
+            @categories[category_name].docs[doc_key].decrement_count
+          else
+            raise StandardError,
+                  "Document is not found in #{category_name} documents!"
+          end
+          doc.tokens.each do |token, count|
+            decrement_token_counts(category_name, token, count)
+            @categories[category_name].tokens[token] = @categories[category_name].tokens[token].to_i - count
+          end
+          @categories[category_name].docs.delete(doc_key) if @categories[category_name].docs[doc_key].count == 0
+          decrement_doc_counts(category_name)
+          update_priors
+        else
+          raise StandardError,
+                "Category with name '#{category_name}' does not exist!"
+        end
+      end
+
       # Classify the given document
       #
       # ==== Parameters
@@ -110,14 +153,33 @@ module OmniCat
 
         # nodoc
         def increment_token_counts(category_name, token, count)
-          increment_uniq_token_count(token)
+          modify_token_counts(category_name, token, count)
+        end
+
+        # nodoc
+        def decrement_token_counts(category_name, token, count)
+          modify_token_counts(category_name, token, -1 * count)
+        end
+
+        # nodoc
+        def modify_token_counts(category_name, token, count)
+          modify_uniq_token_count(token, count < 0 ? -1 : 1)
           @token_count += count
           @categories[category_name].token_count += count
         end
 
         # nodoc
         def increment_uniq_token_count(token)
-          uniq_token_addition = 1
+          modify_uniq_token_count(token, 1)
+        end
+
+        # nodoc
+        def decrement_uniq_token_count(token)
+          modify_uniq_token_count(token, -1)
+        end
+
+        # nodoc
+        def modify_uniq_token_count(token, uniq_token_addition)
           categories.each do |_, category|
              if category.tokens.has_key?(token)
                uniq_token_addition = 0

data/omnicat-bayes.gemspec

@@ -18,7 +18,7 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']
   
-  spec.add_dependency 'omnicat', '~> 0.2.0'
+  spec.add_dependency 'omnicat', '~> 0.2.1'
   spec.add_development_dependency 'bundler', '~> 1.3'
   spec.add_development_dependency 'rake'
 end

data/{lib/test → test}/test_helper.rb

@@ -1,2 +1,2 @@
 require 'test/unit'
-require File.expand_path(File.join(File.dirname(__FILE__), '..', 'omnicat', 'bayes'))
+require File.expand_path(File.join(File.dirname(__FILE__), '..', 'lib', 'omnicat', 'bayes'))

data/{lib/test → test}/unit/classifiers/bayes_test.rb

@@ -65,6 +65,56 @@ class TestBayes < Test::Unit::TestCase
     )
   end
 
+  def test_untrain_valid_category
+    @bayes.add_category 'neutral'
+    @bayes.train 'neutral', 'how are you?? : :| :) ;-) :('
+    @bayes.untrain 'neutral', 'how are you?? : :| :) ;-) :('
+    assert_equal(
+      0,
+      @bayes.categories['neutral'].doc_count
+    )
+    assert_equal(
+      0,
+      @bayes.categories['neutral'].docs.count
+    )
+    assert_equal(
+      0,
+      @bayes.categories['neutral'].token_count
+    )
+  end
+  
+  def test_untrain_with_doc_count_2
+    @bayes.add_category 'neutral'
+    @bayes.train 'neutral', 'how are you?? : :| :) ;-) :('
+    @bayes.train 'neutral', 'how are you?? : :| :) ;-) :('
+    @bayes.untrain 'neutral', 'how are you?? : :| :) ;-) :('
+    assert_equal(
+      1,
+      @bayes.categories['neutral'].doc_count
+    )
+    assert_equal(
+      {'how' => 1, 'you' => 1, '?' => 2, ':|' => 1, ':)' => 1, ';-)' => 1, ':(' => 1},
+      @bayes.categories['neutral'].tokens
+    )
+    assert_equal(
+      8,
+      @bayes.categories['neutral'].token_count
+    )
+  end
+
+  def test_untrain_invalid_category
+    assert_equal(false, @bayes.categories.has_key?('neutral'))
+    assert_raise(StandardError) {
+      @bayes.untrain 'neutral', 'how are you?? : :| :) ;-) :('
+    }
+  end
+
+  def test_untrain_with_missing_doc
+    @bayes.add_category 'neutral'
+    assert_raise(StandardError) {
+      @bayes.untrain 'neutral', 'how are you?? : :| :) ;-) :(' }
+  end
+
   def test_train_batch
     @bayes.add_category 'positive'
     @bayes.train_batch 'positive', ['good job ever', 'valid syntax',

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: omnicat-bayes
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-06 00:00:00.000000000 Z
+date: 2013-07-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: omnicat
@@ -18,7 +18,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.2.0
+        version: 0.2.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -26,7 +26,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.2.0
+        version: 0.2.1
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -75,10 +75,10 @@ files:
 - lib/omnicat/bayes/version.rb
 - lib/omnicat/classifiers/bayes.rb
 - lib/omnicat/classifiers/bayes_internals/category.rb
-- lib/test/test_helper.rb
-- lib/test/unit/bayes_test.rb
-- lib/test/unit/classifiers/bayes_test.rb
 - omnicat-bayes.gemspec
+- test/test_helper.rb
+- test/unit/bayes_test.rb
+- test/unit/classifiers/bayes_test.rb
 homepage: https://github.com/mustafaturan/omnicat-bayes
 licenses:
 - MIT
@@ -104,4 +104,7 @@ rubygems_version: 1.8.23
 signing_key: 
 specification_version: 3
 summary: Naive Bayes text classification implementation as an OmniCat classifier strategy.
-test_files: []
+test_files:
+- test/test_helper.rb
+- test/unit/bayes_test.rb
+- test/unit/classifiers/bayes_test.rb