poignant 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0f005ec458887532e94fc32a9f3c130039567cb5
+  data.tar.gz: 890379dc4360900fcdee8bec8d9dec2c1549fe0d
+SHA512:
+  metadata.gz: 2df2eff33931f6fefcbc18e183ddf346b2ae7bf9c7e0c5f5151023cd9e7cdda334427c033cb6fd34017fc4e3905683975dbf1d51b4c07006adf1a775ea7893e4
+  data.tar.gz: b11c5dcd3986163302bc51fc7c2989c82d9e6adff3e64ffc8945b9044be41755fff54a2a502d91c6eef066e68b342a16aa4dc4d3e1cf81f62be8438ea901d85e

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,13 @@
+Copyright (c) 2013 Aaron Massey
+
+Licensed under the Apache License, Version 2.0 (the 'License');
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+   http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an 'AS IS' BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

data/README.md

@@ -0,0 +1,33 @@
+# Poignant
+
+Poignant is a toolkit for natural language processing in Ruby.  It is named in
+honor of [why the lucky stiff][1].
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'poignant'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install poignant
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+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 new Pull Request
+
+
+[1]: http://en.wikipedia.org/wiki/Why_the_lucky_stiff

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/poignant/corpus.rb

@@ -0,0 +1,35 @@
+require "poignant/frequency_distribution"
+require "poignant/ngrams"
+require "poignant/word_operations"
+require "poignant/token_operations"
+
+module Poignant
+  class Corpus
+    include Poignant::FrequencyDistribution
+    include Poignant::NGrams
+    include Poignant::WordOperations
+    include Poignant::TokenOperations
+
+    attr_reader :collection
+    # this is kind of a hack; we want to remove this eventually
+    attr_reader :raw
+
+    def initialize(document_array)
+      @collection = document_array
+      prepare_raw
+    end
+
+    def add(document)
+      @collection << document
+      prepare_raw
+    end
+
+    def prepare_raw
+      @raw = ""
+      @collection.each do |c| 
+        @raw += c.raw
+      end
+    end
+
+  end
+end

data/lib/poignant/document.rb

@@ -0,0 +1,18 @@
+require "poignant/word_operations"
+require "poignant/frequency_distribution"
+require "poignant/token_operations"
+
+module Poignant
+  class Document
+    include Poignant::WordOperations
+    include Poignant::FrequencyDistribution
+    include Poignant::TokenOperations
+
+    attr_reader :raw
+
+    def initialize(string)
+      @raw = string
+    end
+  end
+end
+

data/lib/poignant/frequency_distribution.rb

@@ -0,0 +1,23 @@
+module Poignant
+  module FrequencyDistribution
+
+    def frequency_distribution(tokens=false)
+      fd = {}
+      if tokens
+        unique_tokens.each do |token|
+          fd[token] = raw.scan(token).count
+        end
+      else
+        unique_words.each do |word|
+          fd[word] = normalized.scan(word).count
+        end
+      end
+      fd
+    end
+
+    def lexical_diversity
+      word_count * 1.0 / unique_words.count
+    end
+
+  end
+end

data/lib/poignant/ngrams.rb

@@ -0,0 +1,19 @@
+module Poignant
+  module NGrams
+    def bigrams
+      ngrams(2)
+    end
+
+    def trigrams
+      ngrams(3)
+    end
+
+    def ngrams(num)
+      ngrams = []
+      for i in num-1..(words.length-1)
+        ngrams << words[i-(num-1)..i]
+      end
+      ngrams
+    end
+  end
+end

data/lib/poignant/simple_tokenizer.rb

@@ -0,0 +1,8 @@
+module Poignant
+  module SimpleTokenizer
+    def self.tokenize(string)
+      string.split
+    end
+  end
+end
+

data/lib/poignant/token_operations.rb

@@ -0,0 +1,17 @@
+module Poignant
+  module TokenOperations
+    def tokens
+      @raw.split
+    end
+
+    def unique_tokens
+      tokens.uniq
+    end
+
+    def token_count
+      tokens.count
+    end
+  end
+end
+
+

data/lib/poignant/tokenizer_interface.rb

@@ -0,0 +1,11 @@
+module Poignant
+  module TokenizerInterface
+    def tokenize(string) 
+      raise NotImplementedError, "Implementing 'tokenize' is required for this class."
+    end
+
+    def span_tokenize(string) 
+      raise NotImplementedError, "Implementing 'span_tokenize' is required for this class."
+    end
+  end
+end

data/lib/poignant/version.rb

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

data/lib/poignant/word_operations.rb

@@ -0,0 +1,20 @@
+module Poignant
+  module WordOperations
+    def words
+      normalized.split
+    end
+
+    def unique_words
+      words.uniq
+    end
+
+    def word_count
+      words.count
+    end
+
+    def normalized
+      @raw.downcase.gsub(/[^a-z ]/, '')
+    end
+  end
+end
+

data/lib/poignant.rb

@@ -0,0 +1,8 @@
+require "poignant/version"
+require "poignant/corpus"
+require "poignant/document"
+require "poignant/simple_tokenizer"
+
+module Poignant
+  # Your code goes here...
+end

data/poignant.gemspec

@@ -0,0 +1,22 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'poignant/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "poignant"
+  gem.version       = Poignant::VERSION
+  gem.authors       = ["Aaron Massey"]
+  gem.email         = ["akmassey@sixlines.org"]
+  gem.description   = %q{Poignant is a toolkit for natural language processing in Ruby.}
+  gem.summary       = %q{Poignant is a toolkit for natural language processing in Ruby.  It is named in honor of why the lucky stiff.}
+  gem.homepage      = ""
+
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+
+  gem.add_development_dependency 'rspec'
+  gem.add_development_dependency 'rake'
+end

data/spec/corpus_spec.rb

@@ -0,0 +1,60 @@
+require 'poignant'
+
+module Poignant
+
+  describe Corpus do 
+    before(:each) do 
+      @small = "This is a small sentence."
+      @repeating = "This is a small sentence with repeated words.  Words are repeated in this small sentence."
+      @punctuation = "This is a small sentence. It includes? Punctuation!"
+
+      @document_small = Document.new(@small)
+      @document_repeating = Document.new(@repeating)
+    end
+
+    it "should be initialized with an array of documents" do 
+      document = Document.new(@small)
+      another = Document.new(@repeating)
+      lambda { Corpus.new([document, another]) }.should_not raise_error
+    end
+
+    it "should be able to add a document to the collection" do 
+      first = Document.new(@small)
+      corpus = Corpus.new([first])
+      lambda { corpus.add(Document.new(@repeating)) }.should_not raise_error
+    end
+
+    it "should be able to calculate a lexical diversity" do 
+      corpus = Corpus.new([@document_small])
+      corpus.lexical_diversity.should eq 1.0
+      another = Corpus.new([@document_repeating])
+      another.lexical_diversity.should eq (15.0 / 10) # this words repeated small sentence
+    end
+
+    # it "should be able to calculate a frequency distribution" do 
+      # corpus = Corpus.new(@repeating)
+      # corpus.frequency_distribution["repeated"].should eq 2
+      # corpus.frequency_distribution["small"].should eq 2
+      # corpus.frequency_distribution["this"].should eq 2
+      # corpus.frequency_distribution["are"].should eq 1
+    # end
+
+    # it "should be able to calculate a frequency distribution for tokens" do 
+      # corpus = Corpus.new(@repeating)
+      # corpus.frequency_distribution(tokens=true)["repeated"].should eq 2
+      # corpus.frequency_distribution(tokens=true)["words."].should eq 1
+    # end
+
+    # it "should be able to remove punctuation" do 
+      # Corpus.new(@punctuation).normalized.should eq "this is a small sentence it includes punctuation"
+    # end
+
+    # it "should be able to calculate ngrams" do 
+      # bigrams = Corpus.new(@small).ngrams(2)
+      # bigrams.should_not be_nil
+      # bigrams[0].should eq ["this", "is"]
+      # bigrams[1].should eq ["is", "a"]
+      # bigrams[2].should eq ["a", "small"]
+    # end
+  end
+end 

data/spec/document_spec.rb

@@ -0,0 +1,55 @@
+require 'poignant'
+
+module Poignant
+
+  describe Document do 
+    before(:each) do 
+      @small = "This is a small sentence."
+      @repeating = "This is a small sentence with repeated words.  Words are repeated in this small sentence."
+      @punctuation = "This is a small sentence. It includes? Punctuation!"
+    end
+
+    it "should be initialized with a string" do 
+      lambda { Document.new(@small) }.should_not raise_error
+    end
+
+    it "should be able to calculate a lexical diversity" do 
+      corpus = Document.new(@small)
+      corpus.lexical_diversity.should eq 1.0
+      another = Document.new(@repeating)
+      another.lexical_diversity.should eq (15.0 / 10) # this words repeated small sentence
+    end
+
+    it "should be able to calculate unique tokens" do
+      document = Document.new(@repeating)
+      document.unique_tokens.count.should eq 13
+    end
+
+    it "should be able to calculate a frequency distribution" do 
+      corpus = Document.new(@repeating)
+      corpus.frequency_distribution["repeated"].should eq 2
+      corpus.frequency_distribution["small"].should eq 2
+      corpus.frequency_distribution["this"].should eq 2
+      corpus.frequency_distribution["are"].should eq 1
+    end
+
+    it "should be able to calculate a frequency distribution for tokens" do 
+      corpus = Document.new(@repeating)
+      corpus.frequency_distribution(tokens=true)["repeated"].should eq 2
+      corpus.frequency_distribution(tokens=true)["words."].should eq 1
+    end
+
+    it "should be able to remove punctuation" do 
+      Document.new(@punctuation).normalized.should eq "this is a small sentence it includes punctuation"
+    end
+
+    # it "should be able to calculate ngrams" do 
+      # bigrams = Document.new(@small).ngrams(2)
+      # bigrams.should_not be_nil
+      # bigrams[0].should eq ["this", "is"]
+      # bigrams[1].should eq ["is", "a"]
+      # bigrams[2].should eq ["a", "small"]
+    # end
+  end
+end 
+

data/spec/tokenizers_spec.rb

@@ -0,0 +1,15 @@
+require 'poignant'
+
+module Poignant
+
+  describe SimpleTokenizer do 
+
+    it "should be able to tokenize based on spaces" do 
+      text = "This is a sentence."
+      result = ["This", "is", "a", "sentence."]
+      SimpleTokenizer.tokenize(text).should eq result
+    end
+
+  end
+
+end

metadata

@@ -0,0 +1,94 @@
+--- !ruby/object:Gem::Specification
+name: poignant
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Aaron Massey
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-04-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  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: 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'
+description: Poignant is a toolkit for natural language processing in Ruby.
+email:
+- akmassey@sixlines.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/poignant.rb
+- lib/poignant/corpus.rb
+- lib/poignant/document.rb
+- lib/poignant/frequency_distribution.rb
+- lib/poignant/ngrams.rb
+- lib/poignant/simple_tokenizer.rb
+- lib/poignant/token_operations.rb
+- lib/poignant/tokenizer_interface.rb
+- lib/poignant/version.rb
+- lib/poignant/word_operations.rb
+- poignant.gemspec
+- spec/corpus_spec.rb
+- spec/document_spec.rb
+- spec/tokenizers_spec.rb
+homepage: ''
+licenses: []
+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: Poignant is a toolkit for natural language processing in Ruby.  It is named
+  in honor of why the lucky stiff.
+test_files:
+- spec/corpus_spec.rb
+- spec/document_spec.rb
+- spec/tokenizers_spec.rb