lib/ai4r/data/proximity.rb in ai4r-1.12 vs lib/ai4r/data/proximity.rb in ai4r-1.13

@@ -90,9 +90,31 @@
         a.each {|item| similarity += 2 if b.include?(item)}
         similarity /= (a.length + b.length)
         return 1.0/similarity - 1
       end      
       
+      # Cosine similarity is a measure of similarity between two vectors 
+      # of an inner product space that measures the cosine of the 
+      # angle between them (http://en.wikipedia.org/wiki/Cosine_similarity).
+      # 
+      # Parameters a and b are vectors with continuous attributes.
+      #
+      # D = sum(a[i] * b[i]) / sqrt(sum(a[i]**2)) * sqrt(sum(b[i]**2))
+      def self.cosine_distance(a,b)
+        dot_product = 0.0
+        norm_a = 0.0
+        norm_b = 0.0
+        magnitude = 0.0
+        
+        a.each_index do |i|
+          dot_product += a[i] * b[i]
+          norm_a += a[i] ** 2
+          norm_b += b[i] ** 2
+        end
+        
+        magnitude = Math.sqrt(norm_a) * Math.sqrt(norm_b)
+        return 1 - (dot_product / magnitude)
+      end
     end
     
   end
   
 end