omnicat-bayes 0.2.0

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in omnicat-bayes.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Mustafa Turan
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,122 @@
+# OmniCat Bayes
+
+[![Build Status](https://travis-ci.org/mustafaturan/omnicat-bayes.png)](https://travis-ci.org/mustafaturan/omnicat-bayes) [![Code Climate](https://codeclimate.com/github/mustafaturan/omnicat-bayes.png)](https://codeclimate.com/github/mustafaturan/omnicat-bayes)
+
+A Naive Bayes text classification implementation as an OmniCat classifier strategy.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'omnicat-bayes'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install omnicat-bayes
+
+## Usage
+
+See rdoc for detailed usage.
+
+### Configurations
+
+Optional configuration sample:
+
+    OmniCat.configure do |config|
+      config.exclude_tokens = ['something', 'anything'] # exclude token list
+      config.token_patterns = {
+        # exclude token Regex patterns
+        minus: [/[\s\t\n\r]+/, /(@[\w\d]+)/],
+        # include token Regex patterns
+        plus: [/[\p{L}\-0-9]{2,}/, /[\!\?]/, /[\:\)\(\;\-\|]{2,3}/]
+      }
+    end
+
+### Bayes classifier
+Create a classifier object with Bayes strategy.
+
+    # If you need to change strategy on runtime, you should prefer this inialization
+    bayes = OmniCat::Classifier.new(OmniCat::Classifiers::Bayes.new)
+or 
+
+    # If you only need to use only Bayes classification, then you can use
+    bayes = OmniCat::Classifiers::Bayes.new
+
+### Create categories
+Create a classification category.
+
+    bayes.add_category('positive')
+    bayes.add_category('negative')
+
+### Train
+Train category with a document.
+
+    bayes.train('positive', 'great if you are in a slap happy mood .')
+    bayes.train('negative', 'bad tracking issue')
+
+### Train batch
+Train category with multiple documents.
+
+    bayes.train_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.train_batch('negative', [
+      'simplistic , silly and tedious .',
+      'interesting , but not compelling . ',
+      'seems clever but not especially compelling'
+    ])
+
+### Classify
+Classify a document.
+
+    result = bayes.classify('I feel so good and happy')
+    => #<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=>"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.
+
+    results = bayes.classify_batch(
+      [
+        'the movie is silly so not compelling enough',
+        'a good piece of work'
+      ]
+    )
+    => [#<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
+* Implement all OmniCat(http://github.com/mustafaturan/omnicat) classifier strategy abstract methods
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request
+
+## Copyright
+Copyright © 2013 Mustafa Turan. See LICENSE for details.
+

data/Rakefile

@@ -0,0 +1,20 @@
+require "bundler/gem_tasks"
+require 'rake'
+require 'rake/testtask'
+
+desc "Default Task"
+task :default => [ :test ]
+
+# Run the unit tests
+desc "Run all unit tests"
+Rake::TestTask.new do |t|
+  t.libs << 'lib'
+  t.test_files = FileList['lib/test/unit/*_test.rb']
+  t.verbose = true
+end
+
+# Make a console for testing purposes
+desc "Generate a test console"
+task :console do
+   verbose( false ) { sh "irb -I lib/ -r 'omnicat/bayes'" }
+end

data/lib/omnicat/bayes/version.rb

@@ -0,0 +1,5 @@
+module Omnicat
+  module Bayes
+    VERSION = '0.2.0'
+  end
+end

data/lib/omnicat/bayes.rb

@@ -0,0 +1,3 @@
+require 'omnicat/bayes/version'
+require File.dirname(__FILE__) + '/classifiers/bayes'
+require File.dirname(__FILE__) + '/classifiers/bayes_internals/category'

data/lib/omnicat/classifiers/bayes.rb

@@ -0,0 +1,153 @@
+require 'omnicat/classifiers/strategy'
+
+module OmniCat
+  module Classifiers
+    class Bayes < ::OmniCat::Classifiers::Strategy
+      attr_accessor :k_value # Integer - Helper value for skipping some Bayes algorithm errors
+
+      def initialize(bayes_hash = {})
+        super(bayes_hash)
+        if bayes_hash.has_key?(:categories)
+          bayes_hash[:categories].each do |name, category|
+            @categories[name] = ::OmniCat::Classifiers::BayesInternals::Category.new(category)
+          end
+        end
+        @k_value = bayes_hash[:k_value] || 1.0
+      end
+
+      # Allows adding new classification category
+      #
+      # ==== Parameters
+      #
+      # * +category_name+ - Name for category
+      #
+      # ==== Examples
+      #
+      #   # Create a classification category
+      #   bayes = Bayes.new
+      #   bayes.add_category("positive")
+      def add_category(category_name)
+        if category_exists?(category_name)
+          raise StandardError,
+                "Category with name '#{category_name}' is already exists!"
+        else
+          increment_category_count
+          @categories[category_name] = ::OmniCat::Classifiers::BayesInternals::Category.new
+        end
+      end
+
+      # Train the desired category with a document
+      #
+      # ==== Parameters
+      #
+      # * +category_name+ - Name of the category from added categories list
+      # * +doc_content+ - Document text
+      #
+      # ==== Examples
+      #
+      #   # Train the desired category
+      #   bayes.train("positive", "clear documentation")
+      #   bayes.train("positive", "good, very well")
+      #   bayes.train("negative", "bad dog")
+      #   bayes.train("neutral", "how is the management gui")
+      def train(category_name, doc_content)
+        if category_exists?(category_name)
+          increment_doc_counts(category_name)
+          update_priors
+          doc = OmniCat::Doc.new(content: doc_content)
+          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
+          end
+        else
+          raise StandardError,
+                "Category with name '#{category_name}' does not exist!"
+        end
+      end
+
+      # Classify the given document
+      #
+      # ==== Parameters
+      #
+      # * +doc_content+ - The document for classification
+      #
+      # ==== Returns
+      #
+      # * +result+ - OmniCat::Result object
+      #
+      # ==== Examples
+      #
+      #   # Classify a document
+      #   bayes.classify("good documentation")
+      #   =>
+      def classify(doc_content)
+        return unless classifiable?
+        score = -1000000
+        result = ::OmniCat::Result.new
+        @categories.each do |category_name, category|
+          result.scores[category_name] = doc_probability(category, doc_content)
+          if result.scores[category_name] > score
+            result.category[:name] = category_name
+            score = result.scores[category_name]
+          end
+          result.total_score += result.scores[category_name]
+        end
+        result.total_score = 1 if result.total_score == 0
+        result.category[:percentage] = (
+          result.scores[result.category[:name]] * 100.0 /
+          result.total_score
+        ).floor
+        result
+      end
+
+      private
+        # nodoc
+        def update_priors
+          @categories.each do |_, category|
+            category.prior = category.doc_count / doc_count.to_f
+          end
+        end
+
+        # nodoc
+        def increment_token_counts(category_name, token, count)
+          increment_uniq_token_count(token)
+          @token_count += count
+          @categories[category_name].token_count += count
+        end
+
+        # nodoc
+        def increment_uniq_token_count(token)
+          uniq_token_addition = 1
+          categories.each do |_, category|
+             if category.tokens.has_key?(token)
+               uniq_token_addition = 0
+               break
+             end
+          end
+          @uniq_token_count += uniq_token_addition
+        end
+
+        # nodoc
+        def doc_probability(category, doc_content)
+          score = k_value
+          doc = OmniCat::Doc.new(content: doc_content)
+          doc.tokens.each do |token, count|
+            score *= token_probability(category, token, count)
+          end
+          category.prior * score
+        end
+
+        # nodoc
+        def token_probability(category, token, count)
+          if category.tokens[token].to_i == 0
+            k_value / token_count
+          else
+            count * (
+              (category.tokens[token].to_i + k_value) /
+              (category.token_count + uniq_token_count)
+            )
+          end
+        end
+    end
+  end
+end

data/lib/omnicat/classifiers/bayes_internals/category.rb

@@ -0,0 +1,14 @@
+module OmniCat
+  module Classifiers
+    module BayesInternals
+      class Category < ::OmniCat::Classifiers::StrategyInternals::Category
+        attr_accessor :prior
+
+        def initialize(category_hash = {})
+          super(category_hash)
+          @prior = category_hash[:prior].to_f
+        end
+      end
+    end
+  end
+end

data/lib/test/test_helper.rb

@@ -0,0 +1,2 @@
+require 'test/unit'
+require File.expand_path(File.join(File.dirname(__FILE__), '..', 'omnicat', 'bayes'))

data/lib/test/unit/bayes_test.rb

@@ -0,0 +1 @@
+require File.dirname(__FILE__) + '/classifiers/bayes_test'

data/lib/test/unit/classifiers/bayes_test.rb

@@ -0,0 +1,142 @@
+# encoding: UTF-8
+require File.expand_path(File.join(File.dirname(__FILE__), '..', '..', 'test_helper'))
+
+class TestBayes < Test::Unit::TestCase
+  def setup
+    OmniCat.configure do |config|
+      config.exclude_tokens = ['are', 'at', 'by']
+      config.token_patterns = {
+        minus: [/[\s\t\n\r]+/, /(@[\w\d]+)/],
+        plus: [/[\p{L}\-0-9]{2,}/, /[\!\?]/, /[\:\)\(\;\-\|]{2,3}/]
+      }
+    end
+    @bayes = OmniCat::Classifiers::Bayes.new
+  end
+
+  def test_add_category
+    @bayes.add_category 'neutral'
+    assert_not_nil(@bayes.categories['neutral'])
+    assert_equal(
+      ['neutral'],
+      @bayes.categories.keys
+    )
+    assert_equal(
+      0,
+      @bayes.categories['neutral'].doc_count
+    )
+    assert_equal(
+      {},
+      @bayes.categories['neutral'].tokens
+    )
+    assert_equal(
+      0,
+      @bayes.categories['neutral'].token_count
+    )
+  end
+
+  def test_add_category_that_already_exists
+    @bayes.add_category 'neutral'
+    assert_raise(StandardError) { @bayes.add_category 'neutral' }
+  end
+
+  def test_add_categories
+    @bayes.add_categories ['neutral', 'positive', 'negative']
+    assert_not_nil(@bayes.categories['neutral'])
+    assert_equal(
+      ['neutral', 'positive', 'negative'],
+      @bayes.categories.keys
+    )
+  end
+
+  def test_train_valid_category
+    @bayes.add_category 'neutral'
+    @bayes.train '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_train_batch
+    @bayes.add_category 'positive'
+    @bayes.train_batch 'positive', ['good job ever', 'valid syntax',
+      'best moments of my life']
+    assert_equal(
+      3,
+      @bayes.categories['positive'].doc_count
+    )
+  end
+
+  def test_train_missing_category
+    assert_raise(StandardError) { @bayes.train 'neutral', 'how are you?' }
+  end
+
+  def test_classifiability_error
+    @bayes.add_category 'positive'
+    @bayes.add_category 'negative'
+    assert_raise(StandardError) { @bayes.classify 'good job' }
+    @bayes.train('positive', 'good job')
+    assert_raise(StandardError) { @bayes.classify 'good job' }
+  end
+
+  def test_classify
+    @bayes.add_category 'positive'
+    @bayes.add_category 'negative'
+    @bayes.train('positive', 'good job')
+    @bayes.train('negative', 'bad work')
+    assert_equal(
+      'positive',
+      @bayes.classify('very good position for this sentence').category[:name]
+    )
+    assert_equal(
+      'negative',
+      @bayes.classify('bad words').category[:name]
+    )
+  end
+
+  def test_classify_batch
+    @bayes.add_category 'positive'
+    @bayes.add_category 'negative'
+    @bayes.train_batch 'positive', ['good job ever', 'valid syntax',
+      'best moments of my life']
+    @bayes.train_batch('negative', ['bad work', 'awfull day', 'never liked it'])
+    results = @bayes.classify_batch(
+      ['good sytanx research', 'bad words']
+    )
+
+    assert_equal(2, results.count)
+
+    assert_equal(
+      'positive',
+      results[0].category[:name]
+    )
+    assert_equal(
+      'negative',
+      results[1].category[:name]
+    )
+  end
+
+  def test_initialize_with_hash
+    bayes1 = ::OmniCat::Classifiers::Bayes.new
+    bayes1.add_category 'positive'
+    bayes1.add_category 'negative'
+    bayes1.train('positive', 'good job')
+    bayes1.train('negative', 'bad work')
+    h1 = bayes1.to_hash
+
+    bayes2 = ::OmniCat::Classifiers::Bayes.new(h1)
+    assert_equal(h1, bayes2.to_hash)
+  end
+
+  def test_classify_with_insufficient_categories
+    assert_raise(StandardError) { @bayes.classify 'blank' }
+  end
+end

data/omnicat-bayes.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'omnicat/bayes/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'omnicat-bayes'
+  spec.version       = Omnicat::Bayes::VERSION
+  spec.authors       = ['Mustafa Turan']
+  spec.email         = ['mustafaturan.net@gmail.com']
+  spec.description   = %q{Naive Bayes classifier strategy for OmniCat}
+  spec.summary       = %q{Naive Bayes text classification implementation as an OmniCat classifier strategy.}
+  spec.homepage      = 'https://github.com/mustafaturan/omnicat-bayes'
+  spec.license       = 'MIT'
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ['lib']
+  
+  spec.add_dependency 'omnicat', '~> 0.2.0'
+  spec.add_development_dependency 'bundler', '~> 1.3'
+  spec.add_development_dependency 'rake'
+end

metadata

@@ -0,0 +1,107 @@
+--- !ruby/object:Gem::Specification
+name: omnicat-bayes
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+  prerelease: 
+platform: ruby
+authors:
+- Mustafa Turan
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-07-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: omnicat
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.2.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.2.0
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !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: Naive Bayes classifier strategy for OmniCat
+email:
+- mustafaturan.net@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/omnicat/bayes.rb
+- 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
+homepage: https://github.com/mustafaturan/omnicat-bayes
+licenses:
+- MIT
+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
+signing_key: 
+specification_version: 3
+summary: Naive Bayes text classification implementation as an OmniCat classifier strategy.
+test_files: []