simple cosine similarity

cos_similarity.py

import re, math
from collections import Counter


def sentence_to_vector(text):
     words = WORD.findall(text)
     return Counter(words)


def cos_similarity(text1, text2):
	WORD = re.compile(r'\w+')
	vec1 = text_to_vector(text1)
	vec2 = text_to_vector(text2)
	intersection = set(vec1.keys()) & set(vec2.keys())
	numerator = sum([vec1[x] * vec2[x] for x in intersection])
	sum1 = sum([vec1[x]**2 for x in vec1.keys()])
	sum2 = sum([vec2[x]**2 for x in vec2.keys()])
	denominator = math.sqrt(sum1) * math.sqrt(sum2)
	return float(numerator) / denominator