From c90644211e214a50f6fdb3a936bf247f45f1f4be Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Fri, 13 May 2016 13:38:24 +0200
Subject: compound tests fixed

---
 lib/similarity.rb | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)
 create mode 100644 lib/similarity.rb

(limited to 'lib/similarity.rb')

diff --git a/lib/similarity.rb b/lib/similarity.rb
new file mode 100644
index 0000000..f25d4c3
--- /dev/null
+++ b/lib/similarity.rb
@@ -0,0 +1,46 @@
+module OpenTox
+  module Algorithm
+
+    class Vector
+      def self.dot_product(a, b)
+        products = a.zip(b).map{|a, b| a * b}
+        products.inject(0) {|s,p| s + p}
+      end
+
+      def self.magnitude(point)
+        squares = point.map{|x| x ** 2}
+        Math.sqrt(squares.inject(0) {|s, c| s + c})
+      end
+    end
+
+    class Similarity
+
+      def self.tanimoto a, b
+        ( a & b).size/(a|b).size.to_f
+      end
+
+      def self.euclid a, b
+        sq = a.zip(b).map{|a,b| (a - b) ** 2}
+        Math.sqrt(sq.inject(0) {|s,c| s + c})
+      end
+
+      # http://stackoverflow.com/questions/1838806/euclidean-distance-vs-pearson-correlation-vs-cosine-similarity
+      def self.cosine a, b
+        Algorithm::Vector.dot_product(a, b) / (Algorithm::Vector.magnitude(a) * Algorithm::Vector.magnitude(b))
+      end
+
+      def self.weighted_cosine(a, b, w)
+        dot_product = 0
+        magnitude_a = 0
+        magnitude_b = 0
+        (0..a.size-1).each do |i|
+          dot_product += w[i].abs*a[i]*b[i]
+          magnitude_a += w[i].abs*a[i]**2
+          magnitude_b += w[i].abs*b[i]**2
+        end
+        dot_product/Math.sqrt(magnitude_a*magnitude_b)
+      end
+
+    end
+  end
+end
-- 
cgit v1.2.3