ruigi 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d2ffce2571016ff1adbbfa916134e90968bca826
+  data.tar.gz: 200149a6cd2f74c1dd178698cfa624adfe11eb12
+SHA512:
+  metadata.gz: af93a13deeef93ff520de19052b15dc42a80658d90ceeb4b9be94b31390d0d2a7a257a91bf25705f99a70bd8d36b9d7f8ba3190539c63bb27f95e1781e1a2a3c
+  data.tar.gz: db45474afcaf7e6a1ec626d2df65f25d56646d43523454e73611fa39eb78ab6dd14022de9bb35ea80bc50a48c4805412a268ba9226558670f058002ed3b59d5e

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+/vendor/bundle

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.3.1
+before_install: gem install bundler -v 1.12.5

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,49 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, and in the interest of
+fostering an open and welcoming community, we pledge to respect all people who
+contribute through reporting issues, posting feature requests, updating
+documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free
+experience for everyone, regardless of level of experience, gender, gender
+identity and expression, sexual orientation, disability, personal appearance,
+body size, race, ethnicity, age, religion, or nationality.
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery
+* Personal attacks
+* Trolling or insulting/derogatory comments
+* Public or private harassment
+* Publishing other's private information, such as physical or electronic
+  addresses, without explicit permission
+* Other unethical or unprofessional conduct
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+By adopting this Code of Conduct, project maintainers commit themselves to
+fairly and consistently applying these principles to every aspect of managing
+this project. Project maintainers who do not follow or enforce the Code of
+Conduct may be permanently removed from the project team.
+
+This code of conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting a project maintainer at k12naoki@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. Maintainers are
+obligated to maintain confidentiality with regard to the reporter of an
+incident.
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 1.3.0, available at
+[http://contributor-covenant.org/version/1/3/0/][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/3/0/

data/Gemfile

@@ -0,0 +1,7 @@
+source 'https://rubygems.org'
+
+gem 'stackprof'
+gem 'pry'
+gem 'pry-byebug'
+# Specify your gem's dependencies in ruigi.gemspec
+gemspec

data/README.md

@@ -0,0 +1,49 @@
+# Ruigi
+[![wercker status](https://app.wercker.com/status/67c3adba6bb11fcb230401bd76d4911d/s/master "wercker status")](https://app.wercker.com/project/byKey/67c3adba6bb11fcb230401bd76d4911d)
+
+## Ruigi = Ruby + Luigi
+It is said that the name of Luigi came from __similarity__( it's called "ruigi" in Japanese) to Mario.
+And Ruigi is __similarity__ calculation library, which is implemented by Ruby.
+
+### algorithms
+Now, only support TF-IDF and cosine similarity.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ruigi'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install ruigi
+
+## Usage
+1. array of words -> Ruigi::Document
+```ruby
+words = ["word1", "word2", ... , "wordN"]
+document1 = Ruigi::Document.new(words)
+```
+
+2. Make a Model from documents of array
+```ruby
+corpus = [document1, document2, ... , documentN] # each element's type is Ruigi::Document.
+model = Ruigi::Model.new(corpus)
+```
+3. You can get feature vector for each document and calculate similarity between document.
+```ruby
+model.feature_vector_of(0) # => return feature vector of 0th document
+```
+etc...
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/naoki-k/ruigi.  
+This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/lib/ruigi.rb

@@ -0,0 +1,7 @@
+require 'ruigi/constraints'
+require 'ruigi/document'
+require 'ruigi/error'
+require 'ruigi/model'
+require 'ruigi/version'
+require 'ruigi/word'
+require 'nmatrix'

data/lib/ruigi/constraints.rb

@@ -0,0 +1,12 @@
+module Ruigi
+  ENABLED_PARTS_OF_SPEECH = %w(
+    名詞
+    形容詞
+    動詞
+  ).map(&:freeze).freeze
+
+  EXCEPT_REGEXP = %r(
+    \\A\\p{hiragana}る\\z
+    \d+
+  ).freeze
+end

data/lib/ruigi/document.rb

@@ -0,0 +1,33 @@
+module Ruigi
+  class Document
+    extend Forwardable
+
+    attr_accessor :model, :words
+
+    def_delegator :model, :wordlist, :all_words
+
+    def initialize(words)
+      raise TypeError unless words.is_a?(Array)
+      raise TypeError unless words.all? { |e| e.is_a?(String) }
+
+      self.words = Hash.new
+      words.group_by { |e| e }.each do |k, v|
+        word = Ruigi::Word.new(k, v.length)
+        word.document = self
+        self.words[k] = word
+      end
+    end
+
+    def feature_vector
+      @feature_vector ||=
+        begin
+          vector = all_words.map { |word| words.keys.include?(word) ? words[word].tfidf : 0.0 }
+          norm = Math.sqrt(vector.inject(0) { |sum, e| sum + e ** 2 })
+          vector.map do |e|
+            quot = e / norm
+            quot.nan? ? 0.0 : quot
+          end
+        end
+    end
+  end
+end

data/lib/ruigi/error.rb

@@ -0,0 +1,4 @@
+module Ruigi
+  class NoModelError < StandardError; end
+  class NoDocumentError < StandardError; end
+end

data/lib/ruigi/model.rb

@@ -0,0 +1,32 @@
+module Ruigi
+  class Model
+    attr_accessor :corpus
+
+    def initialize(corpus)
+      raise TypeError unless corpus.is_a?(Array)
+      raise TypeError unless corpus.all? { |e| e.is_a?(Ruigi::Document) }
+
+      self.corpus = corpus
+
+      corpus.each do |document|
+        document.model = self
+      end
+    end
+
+    def matrix
+      @matrix ||= corpus.map(&:feature_vector).to_nm
+    end
+
+    def feature_vector_of(index)
+      corpus[index].feature_vector.to_nm
+    end
+
+    def wordlist
+      @wordlist ||= corpus.map { |document| document.words.keys }.flatten.uniq.sort
+    end
+
+    def inner_product_matrix
+      matrix.dot(matrix.transpose)
+    end
+  end
+end

data/lib/ruigi/version.rb

@@ -0,0 +1,3 @@
+module Ruigi
+  VERSION = '0.1.0'.freeze
+end

data/lib/ruigi/word.rb

@@ -0,0 +1,41 @@
+module Ruigi
+  class Word
+    extend Forwardable
+
+    attr_accessor :document, :count, :name
+
+    def_delegator :document, :model, :involved_model
+
+    def initialize(name, count)
+      self.name = name
+      self.count = count
+    end
+
+    def tfidf
+      tf * idf
+    end
+
+    def tf
+      raise NoDocumentError unless document
+
+      document_length = document.words.inject(0) { |sum, (k, v)| sum + v.count }
+      count.to_f / document_length
+    end
+
+    def df
+      raise NoModelError unless involved_model
+
+      involved_model.corpus.count { |document| document.words[name] != nil }
+    end
+
+    def idf
+      df2idf(df)
+    end
+
+    private
+
+    def df2idf(df, base = 2.0, add = 0.0)
+      Math.log(involved_model.corpus.size.to_f / df, base) + add
+    end
+  end
+end

data/ruigi.gemspec

@@ -0,0 +1,33 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'ruigi/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "ruigi"
+  spec.version       = Ruigi::VERSION
+  spec.authors       = ["naoki-k"]
+  spec.email         = ["k12naoki@gmail.com"]
+
+  spec.summary       = %q{calculate similarity between documents}
+  spec.description   = %q{calculate similarity between documents}
+  spec.homepage      = "https://github.com/naoki-k/ruigi"
+
+  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # to allow pushing to a single host or delete this section to allow pushing to any host.
+  if spec.respond_to?(:metadata)
+    spec.metadata['allowed_push_host'] = "https://rubygems.org"
+  else
+    raise "RubyGems 2.0 or newer is required to protect against public gem pushes."
+  end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "nmatrix"
+  spec.add_development_dependency "natto", "~> 1.1"
+  spec.add_development_dependency "bundler", "~> 1.12"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

data/wercker.yml

@@ -0,0 +1,7 @@
+box: ruby
+build:
+    steps:
+        - bundle-install
+        - script:
+            name: rspec
+            code: bundle exec rspec

metadata

@@ -0,0 +1,130 @@
+--- !ruby/object:Gem::Specification
+name: ruigi
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- naoki-k
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-10-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nmatrix
+  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: natto
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.1'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: calculate similarity between documents
+email:
+- k12naoki@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- README.md
+- Rakefile
+- lib/ruigi.rb
+- lib/ruigi/constraints.rb
+- lib/ruigi/document.rb
+- lib/ruigi/error.rb
+- lib/ruigi/model.rb
+- lib/ruigi/version.rb
+- lib/ruigi/word.rb
+- ruigi.gemspec
+- wercker.yml
+homepage: https://github.com/naoki-k/ruigi
+licenses: []
+metadata:
+  allowed_push_host: https://rubygems.org
+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: 2.5.1
+signing_key: 
+specification_version: 4
+summary: calculate similarity between documents
+test_files: []