import re, math from collections import Counter def get_cosine(vec1, vec2): """" :return the cosine of 2 vectors following the math equation from Wikipedia """ 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) if not denominator: return 0.0 else: return float(numerator) / denominator def text_to_vector(text): WORD = re.compile(r'\w+') words = WORD.findall(text) return Counter(words)