similarityTextCoefficients 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 4deed5d254b448b0f72730d1d7259e3f6fa44b41
+  data.tar.gz: 526d8ee307d479d0a93121d76430b53b16be8cfc
+SHA512:
+  metadata.gz: eb7649ab9ba6cd423555dc12f108d7c29d08b66fd60b0df83f1dda4448cd5a762b319fc895cce9cd791e943e1364e829bef5e0e668095057e734bf08afaf0e2b
+  data.tar.gz: 1daafe71aaa86253a61fdd09a3bd428fec4c8f9cdd510b25db6e88bc5dfd06cfcbdf5d4c8bcef326a3114823ba70136bf64a6e9267406b988e2f8bf125b8380a

data/lib/similarityTextCoefficients.rb

@@ -0,0 +1,98 @@
+require "set"
+
+class SimilarityTextCoefficients
+
+  def self.dice_coefficient(a, b)
+
+    vectorOne  =  Array.new
+    vectorTwo =  Array.new
+
+    vectorOne=a.split(" ")
+
+    vectorTwo=b.split(" ")
+    newdice = 0
+
+    for x in 0..  vectorTwo.length-1
+
+      for y in 0..  vectorOne.length-1
+
+        a_bigrams = vectorOne[y].each_char.each_cons(2).to_set
+        b_bigrams = vectorTwo[x].each_char.each_cons(2).to_set
+
+        overlap = (a_bigrams & b_bigrams).size
+
+        total = a_bigrams.size + b_bigrams.size
+        dice  = overlap * 2.0 / total
+
+        if newdice == 0
+
+          newdice=dice
+
+        end
+
+        if newdice < dice
+
+          newdice=dice
+
+        end
+
+      end
+
+    end
+
+    newdice
+
+  end
+
+
+  #Index of Jaccard =intersection/ ((numberA+numberB) -intersection )
+  #where
+  #numberA - number of elements in set А
+  #numberB- number of elements in set B
+  #intersection - number of elements in intersecting set
+
+  def self.createJaccardIndex(a,b)
+
+    vectorOne  =  Array.new
+    vectorTwo =  Array.new
+    intersection=0
+
+    contvector=0
+
+    # We get number of itens for each group and put in them in a array One and Two
+
+    vectorOne=a.split(" ")
+
+    vectorTwo=b.split(" ")
+
+    if    vectorOne.length < vectorTwo.length
+
+      numberA= vectorOne.length
+      numberB= vectorTwo.length
+
+    else
+      numberB= vectorOne.length
+      numberA= vectorTwo.length
+    end
+
+    numberA= vectorOne.length
+    numberB= vectorTwo.length
+
+    # We compare each iten inside of each array to obtain: number of elements in intersecting set
+
+    for x in 0..  vectorTwo.length-1
+
+      if ((vectorOne).include?(vectorTwo[x]) == true)
+        intersection+=1
+      end
+
+
+    end
+
+    indexJaccard= intersection.to_f/ ((numberA+numberB) -intersection )
+    return indexJaccard
+
+  end
+
+
+end

metadata

@@ -0,0 +1,47 @@
+--- !ruby/object:Gem::Specification
+name: similarityTextCoefficients
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- Gilberto Flores
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-04-27 00:00:00.000000000 Z
+dependencies: []
+description: Enter two strings and it compares their similarity and gives a score
+  between 0 and 1, when 1 is the similarity
+email: gilbertofp16@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/similarityTextCoefficients.rb
+homepage: http://rubygems.org/gems/SimilarityTextCoefficients
+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: 2.4.6
+signing_key: 
+specification_version: 4
+summary: For text comparations it implements Dice's coefficient and Jaccard's or Tanimoto
+  index
+test_files: []
+has_rdoc: