company-mapping 0.1.0 → 0.2.0

data/lib/company/mapping/vector_similarity/cosine_similarity.rb

@@ -1,47 +1,35 @@
 module Company
   module Mapping
 
-#Implements Cosine Similarity between two non zero vectors and it measures the cosine of the angle between them.
+    #Implements Cosine Similarity between two non zero vectors and it measures the cosine of the angle between them.
     class CosineSimilarity
 
       #Calculates cosine similarity between two documents. The documents are expressed as vectors of tokens (bag of words model).
       def calculate(doc1, doc2)
-        return (dotProduct(doc1, doc2) / (Math.sqrt(d(doc1)) * Math.sqrt(d(doc2)))).round(4)
-      end
-
-      def info
-        "Implements Cosine Similarity between two non zero vectors and it measures the cosine of the angle between them.\n"
-        +"More info about Cosine Similarity can be found: https://en.wikipedia.org/wiki/Cosine_similarity";
+        (dotProduct(doc1, doc2) / (Math.sqrt(d(doc1)) * Math.sqrt(d(doc2)))).round(4)
       end
 
       protected
       #Calculated the dot product between the two document vectors. The dot product is an algebraic operation
       # that takes two equal-length sequences of numbers (usually coordinate vectors) and returns a single number.
       def dotProduct(doc1, doc2)
-        _common_tokens = findCommonTokens(doc1.keys, doc2.keys)
-        _dot_product = 0.0
-
-        _common_tokens.each do |token|
-          _dot_product += doc2[token] * doc1[token]
+        common_tokens(doc1.keys, doc2.keys).inject(0.0) do |dot_product, token|
+          dot_product + doc2[token] * doc1[token]
         end
-        return _dot_product
       end
 
       #Calculates the magnitude of a vector document
       def d(doc)
-        _d = 0.0
-        doc.keys.each do |term|
-          _d += doc[term]**2.0
+        doc.keys.inject(0.0) do |d, term|
+          d + doc[term]**2.0
         end
-        return _d
       end
 
       #returns the set of common tokens between two document vectors
-      def findCommonTokens(doc1_tokens, doc2_tokens)
+      def common_tokens(doc1_tokens, doc2_tokens)
         common_tokens = Set.new doc1_tokens
-        return common_tokens.intersection(Set.new doc2_tokens)
+        common_tokens.intersection(Set.new doc2_tokens)
       end
     end
-
   end
-end
+end

data/lib/company/mapping/version.rb

@@ -1,5 +1,5 @@
 module Company
   module Mapping
-    VERSION = "0.1.0"
+    VERSION = "0.2.0"
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: company-mapping
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - vasgat
@@ -39,19 +39,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '10.0'
 - !ruby/object:Gem::Dependency
-  name: minitest
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '3.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '3.5'
 description: Given a Corpus of WikiRate Company Names and a new (incoming) Company
   Name, CompanyMapper class, finds the closest match if exists based on the calculated
   tf-idf similarity and a defined threshold.
@@ -78,6 +78,7 @@ files:
 - lib/company/mapping.rb
 - lib/company/mapping/company_mapper.rb
 - lib/company/mapping/document_utils/basic_tokenizer.rb
+- lib/company/mapping/document_utils/company_corpus.rb
 - lib/company/mapping/document_utils/corpus.rb
 - lib/company/mapping/document_utils/text_document.rb
 - lib/company/mapping/tfidf/idf/inverse_document_frequency.rb