Last active
May 29, 2024 23:44
-
-
Save ahmetalsan/06596e3f2ea3182e185a to your computer and use it in GitHub Desktop.
python cosine similarity algorithm between two strings
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
import math | |
from collections import Counter | |
def get_cosine(vec1, vec2): | |
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) | |
def get_result(content_a, content_b): | |
text1 = content_a | |
text2 = content_b | |
vector1 = text_to_vector(text1) | |
vector2 = text_to_vector(text2) | |
cosine_result = get_cosine(vector1, vector2) | |
return cosine_result | |
print get_result('I love github', 'Who love github') #0.65565 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
thank you, it does the job well!