sentiments 0.0.1

data/lib/sentiments/data/prefix.json

@@ -0,0 +1,6 @@
+[
+    "isn't",
+    "aren't",
+    "not",
+    "isn't"
+]

data/lib/sentiments/version.rb

@@ -0,0 +1,3 @@
+module Sentiments
+  VERSION = "0.0.1"
+end

data/lib/sentiments.rb

@@ -0,0 +1,109 @@
+require "sentiments/version"
+require 'json'
+module Sentiments
+  class Classifier
+    MIN_TOKEN_LENGTH = 1
+    MAX_TOKEN_LENGTH = 15
+    PRIOR_SCORE = 0.33
+    def initialize
+      # @neg_words    = load_json('neg')
+      # @pos_words    = load_json('pos')
+      # @neu_words    = load_json('neu')
+      @prefix_words = load_json('prefix')
+      @ignore_words = load_json('ignore')
+
+      @categories = ['pos', 'neg', 'neu']
+
+      @dictionary = {}
+      @doc_count = 0
+      @token_count = 0
+      @category_tok_count = {'pos' => 0, 'neg' => 0, 'neu' => 0}
+      @category_doc_count = {'pos' => 0, 'neg' => 0, 'neu' => 0}
+
+      @categories.each do |category|
+        if (!set_dictionary(category))
+          raise "Unable to Set Dictionaries"
+        end #if
+      end
+
+    end #initialize
+
+    def score(sentence)
+      scores = {}
+      @prefix_words.each do |pw|
+        # Search if that prefix is in the sentence
+        if sentence.index(pw)
+          # Remove the white space after the negative prefix
+          sentence.sub! pw+" ", pw
+        end
+      end
+      tokens = tokenize(sentence)
+      total_score = 0
+
+      @categories.each do |category|
+        scores[category] = 1
+        tokens.each do |token|
+          if (token.length > MIN_TOKEN_LENGTH && token.length < MAX_TOKEN_LENGTH && !(@ignore_words.include? token))
+
+            # If Token is not in our dictionary, don't do anything
+            if(@dictionary[token].nil?)
+              break
+            end #if
+
+            if (@dictionary[token][category].nil?)
+              count = 0
+            else
+              count = @dictionary[token][category]
+            end # elseif
+            scores[category] *= (count + 1)
+          end #if
+        end #tokens
+        scores[category] = PRIOR_SCORE * scores[category]
+      end #categories
+
+      @categories.each do |category|
+        total_score += scores[category]
+      end #categories
+
+      @categories.each do |category|
+        scores[category] = scores[category]/total_score
+      end #categories
+
+      return scores
+    end #score
+
+    private
+
+    def load_json(filename)
+      path = 'sentiments/data/'
+      path = File.dirname(__FILE__) + '/sentiments/data/'
+      return JSON.parse(IO.read(path +filename +'.json'))
+    end
+
+    def set_dictionary(category)
+      words = load_json(category)
+      words.each do |word|
+        @doc_count += 1
+        @category_doc_count[category] += 1
+
+        if (@dictionary[word].nil?)
+          @dictionary[word] = {}
+          @dictionary[word][category] = 1
+        end
+        @category_tok_count[category] += 1
+        @token_count += 1
+      end
+      return true
+    end #set_dictionary
+
+    def tokenize(sentence)
+      sentence = sentence.downcase
+      return sentence.split()
+    end #tokenize
+
+  end #class
+end #module
+
+def sentiments
+  return Sentiments::Classifier.new
+end

data/sentiments.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'sentiments/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "sentiments"
+  spec.version       = Sentiments::VERSION
+  spec.authors       = ["Pulkit Kathuria"]
+  spec.email         = ["kevincobain2000@gmail.com"]
+  spec.description   = %q{Sentiment Analysis with negation}
+  spec.summary       = %q{Simple and Faster Sentiment Classifier categorizes sentence into positive & negative}
+  spec.homepage      = "http://www8355ue.sakura.ne.jp/?action_classifiers_sentiment=true"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  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_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "json"
+end

data/test/sentiments.rb

@@ -0,0 +1,4 @@
+require 'sentiments'
+puts sentiments.score("nice movie")
+
+

metadata

@@ -0,0 +1,102 @@
+--- !ruby/object:Gem::Specification
+name: sentiments
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Pulkit Kathuria
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-12-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Sentiment Analysis with negation
+email:
+- kevincobain2000@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/sentiments.rb
+- lib/sentiments/data/ignore.json
+- lib/sentiments/data/neg.json
+- lib/sentiments/data/neu.json
+- lib/sentiments/data/pos.json
+- lib/sentiments/data/prefix.json
+- lib/sentiments/version.rb
+- sentiments.gemspec
+- test/sentiments.rb
+homepage: http://www8355ue.sakura.ne.jp/?action_classifiers_sentiment=true
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.3
+signing_key: 
+specification_version: 4
+summary: Simple and Faster Sentiment Classifier categorizes sentence into positive
+  & negative
+test_files:
+- test/sentiments.rb