tf-idf-similarity 0.1.0 → 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: bcd5811852a4ec0e65c55ac09854024c1256483b
+  data.tar.gz: 9978891aa4e76e8badec85da898b575ed91098cc
+SHA512:
+  metadata.gz: 3219126f9ea91f3d2bfb8db0954d6637f090d4c75bf5f7c57c8208b0a812c1d8e2fd488d438cedd5e188a6a169ff7b9bf1470e82146085bc2bdf7298de1572fb
+  data.tar.gz: d523d3e77ab1cfd31ddc4e6b7f429726b4d6b3520377e3504d8b0c2bc7a51b11dcaa55991ed19ff497ae75e993ce49aef34dcef619f066e7a7c6ac9e7ee1aa35

data/.travis.yml

@@ -23,10 +23,6 @@ before_install:
   # Installing ATLAS will install BLAS.
   - if [ $MATRIX_LIBRARY = 'nmatrix' ]; then sudo apt-get install -qq libatlas-dev libatlas-base-dev libatlas3gf-base; fi
   - if [ $MATRIX_LIBRARY = 'nmatrix' ]; then export CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/usr/include/atlas; fi
-  - if [ $MATRIX_LIBRARY = 'nmatrix' ]; then git clone git://github.com/SciRuby/nmatrix.git; fi
-  - if [ $MATRIX_LIBRARY = 'nmatrix' ]; then cd nmatrix && ORIGINAL_BUNDLE_GEMFILE=$BUNDLE_GEMFILE; fi
-  - if [ $MATRIX_LIBRARY = 'nmatrix' ]; then BUNDLE_GEMFILE=`pwd`/Gemfile && bundle && bundle exec rake install; fi
-  - if [ $MATRIX_LIBRARY = 'nmatrix' ]; then cd .. && BUNDLE_GEMFILE=$ORIGINAL_BUNDLE_GEMFILE; fi
 # Travis sometimes runs without Bundler.
 install: bundle
 script: bundle exec rake --trace

data/Gemfile

@@ -2,7 +2,7 @@ source "http://rubygems.org"
 
 gem 'gsl', '~> 1.15.3'     if ENV['MATRIX_LIBRARY'] == 'gsl'
 gem 'narray', '~> 0.6.0.0' if ENV['MATRIX_LIBRARY'] == 'narray'
-gem 'nmatrix', :git => 'git://github.com/SciRuby/nmatrix.git' if ENV['MATRIX_LIBRARY'] == 'nmatrix' && RUBY_VERSION >= '1.9'
+gem 'nmatrix', '~> 0.0.9'  if ENV['MATRIX_LIBRARY'] == 'nmatrix' && RUBY_VERSION >= '1.9'
 
 # Specify your gem's dependencies in the gemspec
 gemspec

data/README.md

@@ -5,8 +5,7 @@
 [![Coverage Status](https://coveralls.io/repos/opennorth/tf-idf-similarity/badge.png?branch=master)](https://coveralls.io/r/opennorth/tf-idf-similarity)
 [![Code Climate](https://codeclimate.com/github/opennorth/tf-idf-similarity.png)](https://codeclimate.com/github/opennorth/tf-idf-similarity)
 
-Calculates the similarity between texts using a [bag-of-words](http://en.wikipedia.org/wiki/Bag_of_words_model) [Vector Space Model](http://en.wikipedia.org/wiki/Vector_space_model) with [Term Frequency-Inverse Document Frequency (tf*idf)](http://en.wikipedia.org/wiki/
-) weights. If your use case demands performance, use [Lucene](http://lucene.apache.org/core/) or similar (see below).
+Calculates the similarity between texts using a [bag-of-words](http://en.wikipedia.org/wiki/Bag_of_words_model) [Vector Space Model](http://en.wikipedia.org/wiki/Vector_space_model) with [Term Frequency-Inverse Document Frequency (tf*idf)](http://en.wikipedia.org/wiki/Tf*idf) weights. If your use case demands performance, use [Lucene](http://lucene.apache.org/core/) (see below).
 
 ## Usage
 
@@ -20,34 +19,24 @@ Create a set of documents:
     corpus << TfIdfSimilarity::Document.new("Pellentesque sed ipsum dui...")
     corpus << TfIdfSimilarity::Document.new("Nam scelerisque dui sed leo...")
 
-Create a document-term matrix using [Term Frequency-Inverse Document Frequency function](http://en.wikipedia.org/wiki/) (default:
+Create a document-term matrix using [Term Frequency-Inverse Document Frequency function](http://en.wikipedia.org/wiki/):
 
-    model = TfIdfSimilarity::TfIdfModel(corpus, :function => :tf_idf)
+    model = TfIdfSimilarity::TfIdfModel.new(corpus)
 
 Create a document-term matrix using the [Okapi BM25 ranking function](http://en.wikipedia.org/wiki/Okapi_BM25):
 
-    model = TfIdfSimilarity::TfIdfModel(corpus, :function => :bm25)
+    model = TfIdfSimilarity::BM25Model.new(corpus)
 
 [Read the documentation at RubyDoc.info.](http://rubydoc.info/gems/tf-idf-similarity)
 
 ## Speed
 
-Instead of using the Ruby Standard Library's [Matrix](http://www.ruby-doc.org/stdlib-2.0/libdoc/matrix/rdoc/Matrix.html) class, you can use one of the `gsl`, `narray` or `nmatrix` gems for faster matrix operations, e.g.:
+Instead of using the Ruby Standard Library's [Matrix](http://www.ruby-doc.org/stdlib-2.0/libdoc/matrix/rdoc/Matrix.html) class, you can use one of the [GNU Scientific Library (GSL)](http://www.gnu.org/software/gsl/), [NArray](http://narray.rubyforge.org/) or [NMatrix](https://github.com/SciRuby/nmatrix) (0.0.9 or greater) gems for faster matrix operations. For example:
 
     require 'gsl'
-    model = TfIdfSimilarity::TfIdfModel(corpus, :library => :gsl)
+    model = TfIdfSimilarity::TfIdfModel.new(corpus, :library => :gsl)
 
-### [GNU Scientific Library (GSL)](http://www.gnu.org/software/gsl/)
-
-    gem install gsl
-
-### [NArray](http://narray.rubyforge.org/)
-
-    gem install narray
-
-### [NMatrix](https://github.com/SciRuby/nmatrix)
-
-The nmatrix gem gives access to [Automatically Tuned Linear Algebra Software (ATLAS)](http://math-atlas.sourceforge.net/), which you may know of through [Linear Algebra PACKage (LAPACK)](http://www.netlib.org/lapack/) or [Basic Linear Algebra Subprograms (BLAS)](http://www.netlib.org/blas/). Follow [these instructions](https://github.com/SciRuby/nmatrix#synopsis) to install the nmatrix gem. You may need [additional instructions for Mac OS X Lion](https://github.com/SciRuby/nmatrix/wiki/Installation).
+The NMatrix gem gives access to [Automatically Tuned Linear Algebra Software (ATLAS)](http://math-atlas.sourceforge.net/), which you may know of through [Linear Algebra PACKage (LAPACK)](http://www.netlib.org/lapack/) or [Basic Linear Algebra Subprograms (BLAS)](http://www.netlib.org/blas/). Follow [these instructions](https://github.com/SciRuby/nmatrix#synopsis) to install the NMatrix gem. You may need [additional instructions for Mac OS X Lion](https://github.com/SciRuby/nmatrix/wiki/Installation).
 
 ## Extras
 
@@ -68,22 +57,25 @@ At the time of writing, no other Ruby gem implemented the tf*idf formula used by
 
 ### Term frequencies
 
-The [vss](https://github.com/mkdynamic/vss) gem does not normalize the frequency of a term in a document; this occurs frequently in the academic literature, but only to demonstrate why normalization is important. The [tf_idf](https://github.com/reddavis/TF-IDF) and similarity gems normalize the frequency of a term in a document to the number of terms in that document, which never occurs in the literature. The [tf-idf](https://github.com/mchung/tf-idf) gem normalizes the frequency of a term in a document to the number of *unique* terms in that document, which never occurs in the literature.
+* The [vss](https://github.com/mkdynamic/vss) gem does not normalize the frequency of a term in a document; this occurs frequently in the academic literature, but only to demonstrate why normalization is important.
+* The [tf_idf](https://github.com/reddavis/TF-IDF) and similarity gems normalize the frequency of a term in a document to the number of terms in that document, which never occurs in the literature.
+* The [tf-idf](https://github.com/mchung/tf-idf) gem normalizes the frequency of a term in a document to the number of *unique* terms in that document, which never occurs in the literature.
 
 ### Document frequencies
 
-The vss gem does not normalize the inverse document frequency. The treat, tf_idf, tf-idf and similarity gems use variants of the typical inverse document frequency formula.
+* The vss gem does not normalize the inverse document frequency.
+* The treat, tf_idf, tf-idf and similarity gems use variants of the typical inverse document frequency formula.
 
 ### Normalization
 
-The treat, tf_idf, tf-idf, rsemantic and vss gems have no normalization component.
+* The treat, tf_idf, tf-idf, rsemantic and vss gems have no normalization component.
 
 ## Additional adapters
 
 Adapters for the following projects were also considered:
 
 * [Ruby-LAPACK](http://ruby.gfd-dennou.org/products/ruby-lapack/) is a very thin wrapper around LAPACK, which has an opaque Fortran-style naming scheme.
-* [Linalg](https://github.com/quix/linalg) and [RNum](http://rnum.rubyforge.org/) give access to LAPACK from Ruby, but are old and unavailable as gems.
+* [Linalg](https://github.com/quix/linalg) and [RNum](http://rnum.rubyforge.org/) give access to LAPACK from Ruby but are old and unavailable as gems.
 
 ## Reference
 

data/lib/tf-idf-similarity.rb

@@ -13,5 +13,6 @@ end
 require 'tf-idf-similarity/matrix_methods'
 require 'tf-idf-similarity/term_count_model'
 require 'tf-idf-similarity/tf_idf_model'
+require 'tf-idf-similarity/bm25_model'
 require 'tf-idf-similarity/document'
 require 'tf-idf-similarity/token'

data/lib/tf-idf-similarity/bm25_model.rb

@@ -0,0 +1,69 @@
+# A document-term matrix using the BM25 function.
+#
+# @see http://lucene.apache.org/core/4_0_0-BETA/core/org/apache/lucene/search/similarities/BM25Similarity.html
+# @see http://en.wikipedia.org/wiki/Okapi_BM25
+class TfIdfSimilarity::BM25Model
+  include TfIdfSimilarity::MatrixMethods
+
+  extend Forwardable
+  def_delegators :@model, :documents, :terms, :document_count
+
+  # @param [Array<TfIdfSimilarity::Document>] documents documents
+  # @param [Hash] opts optional arguments
+  # @option opts [Symbol] :library :gsl, :narray, :nmatrix or :matrix (default)
+  def initialize(documents, opts = {})
+    @model = TfIdfSimilarity::TermCountModel.new(documents, opts)
+    @library = (opts[:library] || :matrix).to_sym
+
+    array = Array.new(terms.size) do |i|
+      idf = inverse_document_frequency(terms[i])
+      Array.new(documents.size) do |j|
+        term_frequency(documents[j], terms[i]) * idf
+      end
+    end
+
+    @matrix = initialize_matrix(array)
+  end
+
+  # Return the term's inverse document frequency.
+  #
+  # @param [String] term a term
+  # @return [Float] the term's inverse document frequency
+  def inverse_document_frequency(term)
+    df = @model.document_count(term)
+    log((documents.size - df + 0.5) / (df + 0.5))
+  end
+  alias_method :idf, :inverse_document_frequency
+
+  # Returns the term's frequency in the document.
+  #
+  # @param [Document] document a document
+  # @param [String] term a term
+  # @return [Float] the term's frequency in the document
+  #
+  # @note Like Lucene, we use a b value of 0.75 and a k1 value of 1.2.
+  def term_frequency(document, term)
+    tf = document.term_count(term)
+    (tf * 2.2) / (tf + 0.3 + 0.9 * documents.size / @model.average_document_size)
+  end
+  alias_method :tf, :term_frequency
+
+  # Return the term frequency–inverse document frequency.
+  #
+  # @param [Document] document a document
+  # @param [String] term a term
+  # @return [Float] the term frequency–inverse document frequency
+  def term_frequency_inverse_document_frequency(document, term)
+    inverse_document_frequency(term) * term_frequency(document, term)
+  end
+  alias_method :tfidf, :term_frequency_inverse_document_frequency
+
+  # Returns a similarity matrix for the documents in the corpus.
+  #
+  # @return [GSL::Matrix,NMatrix,Matrix] a similarity matrix
+  # @note Columns are normalized to unit vectors, so we can calculate the cosine
+  #   similarity of all document vectors.
+  def similarity_matrix
+    multiply_self(normalize)
+  end
+end

data/lib/tf-idf-similarity/matrix_methods.rb

@@ -17,7 +17,7 @@ private
       norm[norm.where2[1]] = 1.0 # avoid division by zero
       NMatrix.refer(@matrix / norm) # must be NMatrix for matrix multiplication
     when :nmatrix # @see https://github.com/SciRuby/nmatrix/issues/38
-      normal = NMatrix.new(:dense, @matrix.shape, :float64)
+      normal = NMatrix.new(:dense, @matrix.shape, 0, :float64)
       (0...@matrix.shape[1]).each do |j|
         column = @matrix.column(j)
         norm = Math.sqrt(column.transpose.dot(column)[0, 0])
@@ -100,7 +100,7 @@ private
   def values
     case @library
     when :nmatrix
-      @matrix.each.to_a
+      @matrix.each.to_a # faster than NMatrix's `to_a` and `to_flat_a`
     else
       @matrix.to_a.flatten
     end
@@ -124,8 +124,8 @@ private
       GSL::Matrix[*array]
     when :narray
       NArray[*array]
-    when :nmatrix # @see https://github.com/SciRuby/nmatrix/issues/91
-      NMatrix.new(:dense, [array.size, array.empty? ? 0 : array[0].size], array.flatten)
+    when :nmatrix # @see https://github.com/SciRuby/nmatrix/issues/91#issuecomment-18870619
+      NMatrix.new(:dense, [array.size, array.empty? ? 0 : array[0].size], array.flatten, :float64)
     else
       Matrix[*array]
     end

data/lib/tf-idf-similarity/term_count_model.rb

@@ -1,8 +1,4 @@
 # A simple document-term matrix.
-#
-# @see http://lucene.apache.org/core/4_0_0-BETA/core/org/apache/lucene/search/similarities/TFIDFSimilarity.html
-# @see http://lucene.apache.org/core/4_0_0-BETA/core/org/apache/lucene/search/similarities/BM25Similarity.html
-# @see http://en.wikipedia.org/wiki/Okapi_BM25
 class TfIdfSimilarity::TermCountModel
   include TfIdfSimilarity::MatrixMethods
 
@@ -63,7 +59,7 @@ class TfIdfSimilarity::TermCountModel
       when :gsl, :narray
         row(index).sum
       when :nmatrix
-        row(index).each.reduce(0, :+)
+        row(index).each.reduce(0, :+) # NMatrix's `sum` method is slower
       else
         vector = row(index)
         unless vector.respond_to?(:reduce)

data/lib/tf-idf-similarity/tf_idf_model.rb

@@ -1,8 +1,6 @@
-# A document-term matrix using either the tf*idf or BM25 functions.
+# A document-term matrix using the tf*idf function.
 #
 # @see http://lucene.apache.org/core/4_0_0-BETA/core/org/apache/lucene/search/similarities/TFIDFSimilarity.html
-# @see http://lucene.apache.org/core/4_0_0-BETA/core/org/apache/lucene/search/similarities/BM25Similarity.html
-# @see http://en.wikipedia.org/wiki/Okapi_BM25
 class TfIdfSimilarity::TfIdfModel
   include TfIdfSimilarity::MatrixMethods
 
@@ -12,11 +10,9 @@ class TfIdfSimilarity::TfIdfModel
   # @param [Array<TfIdfSimilarity::Document>] documents documents
   # @param [Hash] opts optional arguments
   # @option opts [Symbol] :library :gsl, :narray, :nmatrix or :matrix (default)
-  # @option opts [Symbol] :function :tfidf (default) or :bm25
   def initialize(documents, opts = {})
     @model = TfIdfSimilarity::TermCountModel.new(documents, opts)
     @library = (opts[:library] || :matrix).to_sym
-    @function = (opts[:function] || :tfidf).to_sym
 
     array = Array.new(terms.size) do |i|
       idf = inverse_document_frequency(terms[i])
@@ -34,11 +30,7 @@ class TfIdfSimilarity::TfIdfModel
   # @return [Float] the term's inverse document frequency
   def inverse_document_frequency(term)
     df = @model.document_count(term)
-    if @function == :bm25
-      log((documents.size - df + 0.5) / (df + 0.5))
-    else
-      1 + log(documents.size / (df + 1.0))
-    end
+    1 + log(documents.size / (df + 1.0))
   end
   alias_method :idf, :inverse_document_frequency
 
@@ -47,15 +39,9 @@ class TfIdfSimilarity::TfIdfModel
   # @param [Document] document a document
   # @param [String] term a term
   # @return [Float] the term's frequency in the document
-  #
-  # @note Like Lucene, we use a b value of 0.75 and a k1 value of 1.2.
   def term_frequency(document, term)
     tf = document.term_count(term)
-    if @function == :bm25
-      (tf * 2.2) / (tf + 0.3 + 0.9 * documents.size / @model.average_document_size)
-    else
-      sqrt(tf)
-    end
+    sqrt(tf)
   end
   alias_method :tf, :term_frequency
 
@@ -73,8 +59,7 @@ class TfIdfSimilarity::TfIdfModel
   #
   # @return [GSL::Matrix,NMatrix,Matrix] a similarity matrix
   # @note Columns are normalized to unit vectors, so we can calculate the cosine
-  #   similarity of all document vectors. BM25 doesn't normalize columns, but
-  #   BM25 wasn't written with this use case in mind.
+  #   similarity of all document vectors.
   def similarity_matrix
     multiply_self(normalize)
   end

data/lib/tf-idf-similarity/token.rb

@@ -16,29 +16,16 @@ class TfIdfSimilarity::Token < String
   #
   # @return [Boolean] whether the string is a token
   def valid?
-    if RUBY_VERSION < '1.9'
-      !self[%r{
-        \A
-          (
-           \d           | # number
-           [[:cntrl:]]  | # control character
-           [[:punct:]]  | # punctuation
-           [[:space:]]    # whitespace
-          )+
-        \z
-      }x]
-    else
-      !self[%r{
-        \A
-          (
-           \d           | # number
-           \p{Cntrl}    | # control character
-           \p{Punct}    | # punctuation
-           \p{Space}      # whitespace
-          )+
-        \z
-      }x] # The Ruby 1.8 parser will complain about this regular expression.
-    end
+    !self[%r{
+      \A
+        (
+         \d           | # number
+         [[:cntrl:]]  | # control character
+         [[:punct:]]  | # punctuation
+         [[:space:]]    # whitespace
+        )+
+      \z
+    }x]
   end
 
   # Returns a lowercase string.

data/lib/tf-idf-similarity/version.rb

@@ -1,3 +1,3 @@
 module TfIdfSimilarity
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

data/td-idf-similarity.gemspec

@@ -9,6 +9,7 @@ Gem::Specification.new do |s|
   s.email       = ["info@opennorth.ca"]
   s.homepage    = "http://github.com/opennorth/tf-idf-similarity"
   s.summary     = %q{Calculates the similarity between texts using tf*idf}
+  s.license     = 'MIT'
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
@@ -19,4 +20,5 @@ Gem::Specification.new do |s|
   s.add_development_dependency('rspec', '~> 2.10')
   s.add_development_dependency('rake')
   s.add_development_dependency('coveralls')
+  s.add_development_dependency('mime-types', '~> 1.25') # 2.0 requires Ruby 1.9.2
 end

metadata

@@ -1,85 +1,102 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: tf-idf-similarity
-version: !ruby/object:Gem::Version 
-  hash: 27
-  prerelease: 
-  segments: 
-  - 0
-  - 1
-  - 0
-  version: 0.1.0
+version: !ruby/object:Gem::Version
+  version: 0.1.1
 platform: ruby
-authors: 
+authors:
 - Open North
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2013-06-03 00:00:00 -04:00
-default_executable: 
-dependencies: 
-- !ruby/object:Gem::Dependency 
-  name: rspec
+date: 2014-03-28 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: unicode_utils
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
   prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
-    none: false
-    requirements: 
-    - - ~>
-      - !ruby/object:Gem::Version 
-        hash: 23
-        segments: 
-        - 2
-        - 10
-        version: "2.10"
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.10'
   type: :development
-  version_requirements: *id001
-- !ruby/object:Gem::Dependency 
-  name: rake
   prerelease: false
-  requirement: &id002 !ruby/object:Gem::Requirement 
-    none: false
-    requirements: 
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.10'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
     - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
-        version: "0"
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :development
-  version_requirements: *id002
-- !ruby/object:Gem::Dependency 
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
   name: coveralls
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
   prerelease: false
-  requirement: &id003 !ruby/object:Gem::Requirement 
-    none: false
-    requirements: 
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
     - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
-        version: "0"
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mime-types
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.25'
   type: :development
-  version_requirements: *id003
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.25'
 description: 
-email: 
+email:
 - info@opennorth.ca
 executables: []
-
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
-- .gitignore
-- .travis.yml
-- .yardopts
+files:
+- ".gitignore"
+- ".travis.yml"
+- ".yardopts"
 - Gemfile
 - LICENSE
 - README.md
 - Rakefile
 - USAGE
 - lib/tf-idf-similarity.rb
+- lib/tf-idf-similarity/bm25_model.rb
 - lib/tf-idf-similarity/document.rb
 - lib/tf-idf-similarity/extras/document.rb
 - lib/tf-idf-similarity/extras/tf_idf_model.rb
@@ -95,41 +112,31 @@ files:
 - spec/tf_idf_model_spec.rb
 - spec/token_spec.rb
 - td-idf-similarity.gemspec
-has_rdoc: true
 homepage: http://github.com/opennorth/tf-idf-similarity
-licenses: []
-
+licenses:
+- MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: 
-rubygems_version: 1.6.2
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Calculates the similarity between texts using tf*idf
-test_files: 
+test_files:
 - spec/document_spec.rb
 - spec/extras/tf_idf_model_spec.rb
 - spec/spec_helper.rb