sentimenticon 0.1.0

data/lib/sentimenticon.rb

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+
+# Public: 
+#
+# The sentiment module provides methods for returning word-level and
+# average word sentiment scores, currently for English only.
+#
+# The sentiment data is from the article Temporal Patterns of Happiness and Information in a Global Social Network: 
+# Hedonometrics and Twitter
+# Peter Sheridan Dodds, Kameron Decker Harris, Isabel M. Kloumann, Catherine A. Bliss, and Christopher M. Danforth
+#
+# Sentiments range from -1.0 to 1.0, where -1.0 is the most unfavorable, and 1.0 is the most favorable.
+# Words must be downcased; sentences must be downcased and tokenized.
+#
+# In addition, a Sentiment object can be inspected for the original values from the Hedonometrics paper.
+# 
+# Examples:
+#
+# >> require 'sentimenticon'
+# >> analyzer = Sentimenticon::Analyzer.new; true
+# => true
+# >> analyzer.word_sentiment("love")
+# => 0.855
+# >> analyzer.word_sentiment("terrorist")
+# => -0.925
+# >> analyzer.average_word_sentiment("I love my happy friend.".downcase.scan(/\w+/))
+# => 0.5730000000000001
+# >> analyzer.average_word_sentiment("I hate my terrorist enemy.".downcase.scan(/\w+/))
+# => -0.332
+# >> analyzer.average_word_sentiment("I fear our terrorist enemies.".downcase.scan(/\w+/))
+# => -0.34700000000000003
+# 
+module Sentimenticon
+end
+
+require_relative "sentimenticon/version"
+require_relative "sentimenticon/models/analyzer"
+require_relative "sentimenticon/models/sentiment"
+
+
+

data/lib/sentimenticon/models/analyzer.rb

@@ -0,0 +1,97 @@
+# frozen_string_literal: true
+
+module Sentimenticon
+
+# Public: A sentiment analyzer.
+class Analyzer
+
+    attr_accessor :language
+    attr_accessor :minimum_frequency
+    attr_reader   :sentiments
+
+    def initialize(language: 'en', minimum_frequency: 1.0e-08)
+        @language = language
+        @minimum_frequency = minimum_frequency
+        @sentiments = Hash.new
+        load_data
+    end
+
+    # Private: safely parse a float
+    def self.safe_float(str)
+        begin
+            Float(str)
+        rescue ArgumentError
+            nil
+        end
+    end
+
+    # Private: safely parse an int
+    def self.safe_int(str)
+        begin
+            Integer(str)
+        rescue ArgumentError
+            nil
+        end
+    end
+
+    # Private: normalize a Likert-scale of 1-9 to -1.0 to 1.0
+    def self.normalize(ave)
+        """normalize a Likert-scale of 1-9 to -1.0 to 1.0"""
+        raise ArgumentError("#{ave} not in range (1.0, 9.0)") if (ave > 9.0) or (ave < 1.0)
+        return (((ave - 1) / 8) * 2) - 1.0
+    end
+
+    # Private: Load data (happens on init)
+    def load_data
+        raise ArgumentError("Don't know how to load #{language}") unless language == 'en'
+        File.open(File.join(Analyzer::data_directory, 'en', 'journal.pone.0026752.s001.txt')) do |io|
+            io.each_line do |line|
+                parts = line.strip.split("\t")
+                next unless parts.size == 8
+                word, rank, average, std, twitter, google, nyt, lyrics = parts
+                r = Analyzer::safe_int(rank)
+                ave = Analyzer::safe_float(average)
+                s = Analyzer::safe_float(std)
+                next unless r && ave && s
+                norm = Analyzer::normalize(ave)
+                twitter = Analyzer::safe_int(twitter)
+                google = Analyzer::safe_int(google)
+                nyt = Analyzer::safe_int(nyt)
+                lyrics = Analyzer::safe_int(lyrics)
+                s = Sentiment.new(word: word, rank: r, normed_average: norm, average: ave, std: s, twitter:twitter, google:google, nyt:nyt, lyrics:lyrics)
+                @sentiments[word] = s
+            end
+        end
+        self
+    end
+
+    # Public: Is the file loaded?
+    def loaded?
+        @sentiments.size > 0
+    end
+
+    # Private: Find the data directory
+    def self.data_directory
+        File.join(__dir__, "../../../data")
+    end
+
+    # Public:
+    # return the normed sentiment of a word, returning default value if not found. word must be lowercased.
+    def word_sentiment(word, default=0.0)
+        s = @sentiments.dig(word)
+        s ? s.normed_average : default
+    end
+
+    # Public:
+    # return the average word sentiment of an iterable of words, using 0.0 for unknown words.
+    # returns 0.0 for empty lists.
+    def average_word_sentiment(words, default_sentiment=0.0)
+        return default_sentiment unless words.size > 0
+        words.map{|word| word_sentiment(word)}.sum / words.size
+    end
+
+    def sentiment_object(word)
+        @sentiments.dig(word)
+    end
+end
+end

data/lib/sentimenticon/models/sentiment.rb

@@ -0,0 +1,41 @@
+module Sentimenticon
+
+    # Pubilc
+    # Sentiment object. See paper or data for details. The normed average in the normalized average.
+    class Sentiment
+
+    attr_accessor :word
+    attr_accessor :rank
+    attr_accessor :normed_average
+    attr_accessor :average
+    attr_accessor :std 
+    attr_accessor :twitter
+    attr_accessor :google
+    attr_accessor :nyt
+    attr_accessor :lyrics
+    
+
+    def initialize(
+        word:, 
+        rank:, 
+        normed_average:, 
+        average:, 
+        std:, 
+        twitter:, 
+        google:, 
+        nyt:, 
+        lyrics:
+        )
+        @word = word
+        @rank = rank
+        @normed_average = normed_average
+        @average = average
+        @std = std
+        @twitter = twitter
+        @google = google
+        @nyt = nyt
+        @lyrics = lyrics
+    end
+
+    end
+end

data/lib/sentimenticon/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Sentimenticon
+  VERSION = "0.1.0"
+end

data/sentimenticon.gemspec

@@ -0,0 +1,38 @@
+# frozen_string_literal: true
+
+require_relative "lib/sentimenticon"
+
+Gem::Specification.new do |spec|
+  spec.name          = "sentimenticon"
+  spec.version       = Sentimenticon::VERSION
+  spec.authors       = ["Will Fitzgerald"]
+  spec.email         = ["will.fitzgerald@pobox.com"]
+
+  spec.summary       = "Word level sentiment analyzer."
+  spec.description   = "Word level sentiment analyzer, currently English only"
+  spec.homepage      = "https://github.com/willf/sentimenticon_rb"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
+
+  # spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://github.com/willf/sentimenticon_rb"
+  spec.metadata["changelog_uri"] = "https://github.com/willf/sentimenticon_rb/CHANGELOG.md"
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{\A(?:test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib", "data"]
+
+  # Uncomment to register a new dependency of your gem
+  # spec.add_dependency "example-gem", "~> 1.0"
+
+  spec.add_development_dependency "rspec", "~> 3.2"
+
+  # For more information and examples about making a new gem, checkout our
+  # guide at: https://bundler.io/guides/creating_gem.html
+end

metadata

@@ -0,0 +1,74 @@
+--- !ruby/object:Gem::Specification
+name: sentimenticon
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Will Fitzgerald
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2021-04-05 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+description: Word level sentiment analyzer, currently English only
+email:
+- will.fitzgerald@pobox.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- CHANGELOG.md
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- data/en/journal.pone.0026752.s001.txt
+- lib/sentimenticon.rb
+- lib/sentimenticon/models/analyzer.rb
+- lib/sentimenticon/models/sentiment.rb
+- lib/sentimenticon/version.rb
+- sentimenticon.gemspec
+homepage: https://github.com/willf/sentimenticon_rb
+licenses: []
+metadata:
+  homepage_uri: https://github.com/willf/sentimenticon_rb
+  source_code_uri: https://github.com/willf/sentimenticon_rb
+  changelog_uri: https://github.com/willf/sentimenticon_rb/CHANGELOG.md
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+- data
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.4.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.3
+signing_key:
+specification_version: 4
+summary: Word level sentiment analyzer.
+test_files: []