Merge pull request #668 from nanto88/master

add Python/cosine_similarity.py

Author: probot-auto-merge[bot]

Python/cosine_similarity.py

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+import numpy as np
+
+def cos_sim(a, b):
+	"""Takes 2 vectors a, b and returns the cosine similarity according 
+	to the definition of the dot product
+	"""
+	dot_product = np.dot(a, b)
+	norm_a = np.linalg.norm(a)
+	norm_b = np.linalg.norm(b)
+	return dot_product / (norm_a * norm_b)
+
+# the counts we computed above
+sentence_m = np.array([1, 1, 1, 1, 0, 0, 0, 0, 0]) 
+sentence_h = np.array([0, 0, 1, 1, 1, 1, 0, 0, 0])
+sentence_w = np.array([0, 0, 0, 1, 0, 0, 1, 1, 1])
+
+# We should expect sentence_m and sentence_h to be more similar
+print(cos_sim(sentence_m, sentence_m)) # 1.0
+print(cos_sim(sentence_m, sentence_h)) # 0.5
+print(cos_sim(sentence_m, sentence_w)) # 0.25