chime 0.1.0

data/lib/chime/version.rb

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

data/lib/chime.rb

@@ -0,0 +1,175 @@
+require_relative "./chime/version"
+require_relative './chime/emotions/emotion_bank.rb'
+require_relative './chime/emotions/term_polarities.rb'
+require_relative './chime/emotions/stopwords.rb'
+require 'lingua/stemmer'
+
+module Chime
+
+  # this method returns the best-fit emotion for the status message
+  def self.emotion(message)
+    # get the emotion for which the emotion score value is highest
+    Chime.get_emotion_score(message, EmotionBank.get_term_emotions, build_term_frequencies(message))
+  end
+
+  # this method returns the polarity value for the status message
+  # (normalized by the number of 'polar' words that the status
+  # message contains)
+  def self.polarity(message)
+    # get the polarity for which the polarity score value is highest
+    Chime.get_polarity_score(message, TermPolarities.get_term_polarities, Chime.build_term_frequencies(message))
+  end
+
+
+  private
+
+  	# this method reads the text of the status message
+  	# inputed by the user, removes common english words,
+  	# strips punctuation and capitalized letters, isolates
+  	# the stem of the word, and ultimately produces a hash
+  	# where the keys are the stems of the remaining words,
+  	# and the values are their respective frequencies within
+  	# the status message
+  	def self.build_term_frequencies(message, term_frequencies = {})
+  		# clean the text of the status message
+      happy_emoticon = happy_emoticon(message)
+      sad_emoticon = sad_emoticon(message)
+  		words = words_from_message_text(message)
+  		#filter for english stopwords
+  		stopwords = Stopwords.stopwords
+  		words = words - stopwords
+  		#get word stems
+  		word_stems = Chime.get_word_stems words
+  		#create term_frequencies
+  		#return term frequency hash
+    	create_term_frequencies(word_stems, term_frequencies)
+    end
+
+  	# this method takes an array of words an returns an array of word stems
+  	def self.get_word_stems(words, output=[])
+  		stemmer = Lingua::Stemmer.new(:language => "en")
+  		words.each do |word|
+  			output << stemmer.stem(word)
+  		end
+  		output
+  	end
+
+  	# this method takes an emotion-words hash and a hash containing word
+  	# frequencies for the status message, calculates a numerical score
+  	# for each possble emotion, and returns the emotion with the highest
+  	# "score"
+  	def self.get_emotion_score(message, emotions, term_frequencies, emotion_score = {})
+  		term_frequencies.each do |key,value|
+  			set_emotions(emotions, emotion_score, key, value)
+  		end
+  		# return an emotion_score_hash to be processed by emotion
+      # get clue from any emoticons present
+      check_emoticon_for_emotion(emotion_score, message)
+  	end
+
+  	# this method gives the status method a normalized polarity
+  	# value based on the words it contains
+  	def self.get_polarity_score (message, polarity_hash, term_frequencies, polarity_scores = [])
+  		term_frequencies.each do |key, value|
+        set_polarities(key, value, polarity_hash, polarity_scores)
+  		end
+
+  		# return an polarity_score_hash to be processed by polarity method
+  		# return an emotion_score_hash to be processed by emotion
+      # get clue from any emoticons present
+      check_emoticon_for_polarity(polarity_scores, message)
+  	end
+
+    def self.happy_emoticon(message)
+      (message.include?(":)") || message.include?(":-)") || message.include?(":]") || message.include?(":-]"))
+    end
+
+    def self.sad_emoticon(message)
+      (message.include?(":(") || message.include?(":-(") || message.include?(":[") || message.include?(":-["))
+    end
+
+    def self.words_from_message_text(message)
+      message.gsub!(/[^a-z ]/i, '')
+      message.downcase!
+      message.gsub!(/((([A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)((?:\/[\+~%\/.\w-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?)/, '')
+      message.gsub!(/(?=\w*h)(?=\w*t)(?=\w*t)(?=\w*p)\w*/, '')
+      message.gsub!(/\s\s+/,' ')
+      message.split(" ")
+    end
+
+    def self.set_emotions(emotions, emotion_score, term, frequency)
+      emotions.keys.each do |k|
+        store_emotions(emotions, emotion_score, k, term, frequency)
+      end
+    end
+
+    def self.set_polarities(term, frequency, polarity_hash, polarity_scores)
+      polarity_hash.keys.each do |k|
+        store_polarities(term, k, polarity_hash, polarity_scores)
+      end
+    end
+
+    def self.store_emotions(emotions, emotion_score, emotion, term, frequency)
+      if emotions[emotion].include?(term)
+        emotion_score[emotion] ||= 0
+        emotion_score[emotion] += frequency
+      end
+    end
+
+    def self.store_polarities(term, word, polarity_hash, polarity_scores)
+      if term == word
+        polarity_scores << (polarity_hash[word].to_f)
+      end
+    end
+
+    def self.check_emoticon_for_emotion(emotion_score, message)
+      if (happy_emoticon(message) && sad_emoticon(message))
+         "ambiguous"
+      elsif happy_emoticon(message)
+         "joy"
+      elsif sad_emoticon(message)
+         "sadness"
+      else
+        return_emotion_score(emotion_score)
+      end
+    end
+
+    def self.return_emotion_score(emotion_score)
+      ## 0 if unable to detect emotion
+      if emotion_score == {}
+        "ambiguous"
+      else
+        emotion_score.max_by{|k, v| v}[0]
+      end
+    end
+
+    def self.check_emoticon_for_polarity(polarity_scores, message)
+      if (happy_emoticon(message) && sad_emoticon(message))
+        score = 5
+      elsif happy_emoticon(message)
+        score = 8
+      elsif sad_emoticon(message)
+        score = 2
+      else
+        return_polarity_scores(polarity_scores)
+      end
+    end
+
+    def self.return_polarity_scores(polarity_scores)
+      if polarity_scores == []
+        # polarity unreadable; return a neutral score of 5
+        5
+      else
+        polarity_scores.inject(0.0){ |sum, el| sum + el}/polarity_scores.length
+      end
+    end
+
+    def self.create_term_frequencies(word_stems, term_frequencies)
+      word_stems.each do |stem|
+        term_frequencies[stem] = word_stems.count(stem)
+      end
+      term_frequencies
+    end
+
+
+end

data/test/helper.rb

@@ -0,0 +1,18 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'chime'
+
+class Test::Unit::TestCase
+end

data/test/test_chime.rb

@@ -0,0 +1,7 @@
+require 'helper'
+
+class TestChime < Test::Unit::TestCase
+  should "probably rename this file and start testing for real" do
+    flunk "hey buddy, you should probably rename this file and start testing for real"
+  end
+end

metadata

@@ -0,0 +1,134 @@
+--- !ruby/object:Gem::Specification
+name: chime
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- jonathanamccann
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-10-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  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: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.12'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.8.7
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.8.7
+- !ruby/object:Gem::Dependency
+  name: rcov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.9.11
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.9.11
+description: Text Analysis for Member Based Organizations
+email: jonathanamccann@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.md
+- README.rdoc
+files:
+- .document
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- README.rdoc
+- Rakefile
+- VERSION
+- chime.gemspec
+- lib/chime.rb
+- lib/chime/emotions/emotion_bank.rb
+- lib/chime/emotions/emotions.csv
+- lib/chime/emotions/stopwords.rb
+- lib/chime/emotions/subjectivity.csv
+- lib/chime/emotions/term_polarities.rb
+- lib/chime/version.rb
+- test/helper.rb
+- test/test_chime.rb
+homepage: http://github.com/jonathanamccann/chime
+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: 2.0.5
+signing_key: 
+specification_version: 4
+summary: Text Analysis for Member Based Organizations
+test_files: []