epitome 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 00f6a83c548383971f75d417ed9f5a65c1a88656
+  data.tar.gz: 405fce9771c575a89975d9729e02f8b52bb28580
+SHA512:
+  metadata.gz: 2a4053ac8b0c4faf4ebab5240e4ae88f5094e22fb3d3255d552a30f4301566d0219ecee97ddaac5fdff2c9afadcdbe50c039502c367db64dab4666003b58508e
+  data.tar.gz: 8f7e8a17eb7ac524f36e25c6caf73abce6ee4cef9d16e5ff3977fc6bb01ab79fdb6aa4ec52dd962f6332a65ad6828d60b9cdcd66917c89fb1aa0a43afe41bc61

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.travis.yml

@@ -0,0 +1,3 @@
+language: ruby
+rvm:
+  - 2.2.0

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2015 McFreely
+
+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 +1,67 @@
+# Epitome
+
+A small gem to make your text shorter. It's an implementation of the Lexrank algorithm. You can use it on a single text, but lexrank is designed to be used on a collection of texts. But it works the same anyway.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'epitome'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install hemingway
+
+## Usage
+
+Firstly, you need to create some documents.
+
+```ruby
+document_one = Epitome::Document.new("The cat likes catnip. He rolls and rolls")
+document_two = Epitome::Document.new("The cat plays in front of the dog. The dog is placid.")
+```
+
+Then, organize your documents in a corpus
+
+```ruby
+document_collection = [document_one, document_two]
+@corpus = Epitome::Corpus.new(document_collection)
+```
+
+Finally, output the summary
+```ruby
+@corpus.summary(length=3)
+```
+
+This returns a nice, short text.
+
+## Options
+### Summary options
+You can pass options to set the length of the expected summary, and set the similarity threshold
+```ruby
+@corpus.summary(5, 0.2)
+```
+The length is the number of sentences of the final output.
+
+The threshold is a value between 0.1 and 0.3, but 0.2 is considered to give the best results (and thus the default value).
+
+### Stopword option
+When creating the corpus, you can set the language of the stopword list to be used
+```ruby
+@corpus = Epitome::Corpus.new(document_collection, "fr")
+```
+The default value is english "en".
+You can find more about the stopword filter [here](https://github.com/brenes/stopwords-filter).
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/hemingway/fork )
+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 a new Pull Request

data/Rakefile

@@ -0,0 +1,9 @@
+require "bundler/gem_tasks"
+
+require "rake/testtask"
+
+Rake::TestTask.new do |t|
+  t.test_files = FileList['test/*_test.rb']
+end
+
+task default: :test

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "epitome"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/epitome.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'epitome/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "epitome"
+  spec.version       = Epitome::VERSION
+  spec.authors       = ["McFreely"]
+  spec.email         = ["paulmcfreely@gmail.com"]
+
+  spec.summary       = %q{Epitome makes your texts shorter.}
+  spec.description   = %q{An implementation of the Lexrank Algorithm, which summarize corpus of text documents.}
+  spec.homepage      = "https://github.com/McFreely/epitome"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.9"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "minitest"
+  spec.add_dependency "scalpel"
+  spec.add_dependency "stopwords-filter"
+end

data/lib/epitome.rb

@@ -0,0 +1,7 @@
+require "epitome/version"
+
+module Epitome
+end
+
+require "epitome/document"
+require "epitome/corpus"

data/lib/epitome/corpus.rb

@@ -0,0 +1,145 @@
+require 'matrix'
+require 'stopwords'
+
+module Epitome
+  class Corpus
+    attr_reader :original_corpus
+    def initialize(document_collection, lang="en")
+      # lang is the language used to initialize the stopword list
+      @lang = lang
+
+      # Massage the document_collection into a more workable form
+      @original_corpus = {}
+      document_collection.each { |document| @original_corpus[document.id] = document.text }
+      @clean_corpus = {}
+      @original_corpus.each do |key, value|
+        @clean_corpus[key] = clean value
+      end
+
+      # Dictionary of term-frequency for each word
+      # to avoid unnecessary computations
+      @word_tf_doc = {}
+
+      # Just the sentences
+      @sentences = @original_corpus.values.flatten
+
+      # The number of documents in the corpus
+      @n_docs = @original_corpus.keys.size
+      
+    end
+
+    def summary(summary_length, threshold=0.2)
+      s = @clean_corpus.values.flatten
+      # n is the number of sentences in the total corpus
+      n = @clean_corpus.values.flatten.size
+
+      # Vector of Similarity Degree for each sentence in the corpus
+      degree = Array.new(n) {0.00} 
+
+      # Square matrix of dimension n = number of sentences
+      cosine_matrix = Matrix.build(n) do |i, j|
+        if idf_modified_cosine(s[i], s[j]) > threshold
+          degree[i] += 1.0
+          1.0
+        else
+          0.0
+        end
+      end
+      
+      # Similarity Matrix
+      similarity_matrix = Matrix.build(n) do |i,j|
+        degree[i] == 0 ? 0.0 : ( cosine_matrix[i,j] / degree[i] )
+      end
+
+      # Random walk ala PageRank
+      # in the form of a power method
+      results = power_method similarity_matrix, n, 0.85
+
+      # Ugly sleight of hand to return a text based on results
+      # <Array>Results => <Hash>Results => <String>ResultsText
+      h = Hash[@sentences.zip(results)]
+      return h.sort_by {|k, v| v}.reverse.first(summary_length).to_h.keys
+    end
+
+    private
+    def clean(sentence_array)
+      # Clean the sentences a bit to avoid unnecessary operations
+      #
+      # Create stopword filter
+      filter = Stopwords::Snowball::Filter.new @lang 
+      sentence_array.map do |s| 
+        s = s.downcase
+        filter.filter(s.split).join(" ")
+      end
+    end
+
+    def n_docs_including_w(word)
+      # Count the number of documents in the corpus containing the word
+      # Look for the word in the dictionnary first, calculate if not present
+      @word_tf_doc.fetch(word) do |w|
+        count = 0
+        docs = []
+
+        # Concanate the each document sentences to make it easier to search
+        @clean_corpus.values.each { |sentences| docs << sentences.join(" ") }
+
+        # Here, we user an interpolated string instead of a regex to avoid
+        # weird corner cases
+        docs.each { |s| count += 1 if s.include? "#{word}" }
+
+        @word_tf_doc[w] = count
+        count
+      end
+    end
+
+    def idf(word)
+      # Number of documents in which word appears
+      # Inverse Frequency Smooth (as per wikipedia article)
+      Math.log( @n_docs / n_docs_including_w(word) )
+    end
+
+    def tf(sentence, word)
+      # Number of occurences of word in sentence
+      sentence.scan(word).count
+    end
+
+    def sentence_tfidf_sum(sentence)
+      # The Sum of tfidf values for each of the words in a sentence
+      sentence.split(" ")
+        .map { |word|  (tf(sentence, word)**2) * idf(word) }
+        .inject(:+)
+    end
+
+    def idf_modified_cosine(x, y)
+      # Compute the similarity between two sentences x, y
+      # using the modified cosine tfidf formula
+      numerator = (x + " " + y).split(" ")
+                    .map { |word| tf(x, word) * tf(y, word) * (idf(word)**2) }
+                    .inject(:+)
+
+      denominator = Math.sqrt(sentence_tfidf_sum(x)) * Math.sqrt(sentence_tfidf_sum(y))
+      numerator / denominator
+    end      
+
+    def power_method(matrix, n, e)
+      # Accept a stochastic, irreducible & aperiodic matrix M
+      # Accept a matrix size n, an error tolerance e
+      # Output Eigenvector p
+      
+      # init values
+      t = 0
+      p = Vector.elements(Array.new(n) { (1.0 / n) * 1} )
+      sigma = 1
+
+      until sigma < e
+        t += 1
+        prev_p = p.clone
+        p = matrix.transpose * prev_p
+        sigma = (p - prev_p).norm
+      end
+      
+      p.to_a
+    end
+  end
+end
+

data/lib/epitome/document.rb

@@ -0,0 +1,13 @@
+require "scalpel"
+require "securerandom"
+
+module Epitome
+  class Document
+    attr_reader :id
+    attr_reader :text
+    def initialize(text)
+      @id = SecureRandom.uuid
+      @text = Scalpel.cut text
+    end
+  end
+end

data/lib/epitome/version.rb

@@ -0,0 +1,3 @@
+module Epitome
+  VERSION = "0.2.0"
+end

metadata

@@ -0,0 +1,128 @@
+--- !ruby/object:Gem::Specification
+name: epitome
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- McFreely
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2015-04-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+- !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: minitest
+  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: scalpel
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: stopwords-filter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: An implementation of the Lexrank Algorithm, which summarize corpus of
+  text documents.
+email:
+- paulmcfreely@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- epitome.gemspec
+- lib/epitome.rb
+- lib/epitome/corpus.rb
+- lib/epitome/document.rb
+- lib/epitome/version.rb
+homepage: https://github.com/McFreely/epitome
+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: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Epitome makes your texts shorter.
+test_files: []