lib/ai4r/data/proximity.rb in ai4r-1.5 vs lib/ai4r/data/proximity.rb in ai4r-1.6

@@ -72,9 +72,27 @@
           count += 1 if a[i] != b[i]
         end
         return count
       end
       
+      # The "Simple matching" distance between two attribute sets is given 
+      # by the number of values present on both vectors.
+      # If sets a and b have lengths da and db then:
+      # 
+      #  S = 2/(da + db) * Number of values present on both sets
+      #  D = 1.0/S - 1
+      # 
+      # Some considerations: 
+      # * a and b must not include repeated items
+      # * all attributes are treated equally
+      # * all attributes are treated equally
+      def self.simple_matching_distance(a,b)
+        similarity = 0.0
+        a.each {|item| similarity += 2 if b.include?(item)}
+        similarity /= (a.length + b.length)
+        return 1.0/similarity - 1
+      end      
+      
     end
     
   end
   
 end
\ No newline at end of file