Created
June 8, 2020 18:10
-
-
Save josepdecid/48974807a83aa07dd541a25074891813 to your computer and use it in GitHub Desktop.
N-gram distance 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
def get_n_grams(s, n): | |
n_grams = [] | |
i = 0 | |
while i + n <= len(s): | |
n_grams.append(s[i:i + n]) | |
i += 1 | |
return set(n_grams) | |
def n_gram_distance(s1, s2, n, case_sensitive=False): | |
if not case_sensitive: | |
s1 = s1.lower() | |
s2 = s2.lower() | |
n_grams_s1 = get_n_grams(s1, n) | |
n_grams_s2 = get_n_grams(s2, n) | |
distance = 2 * len(n_grams_s1.intersection(n_grams_s2)) / (len(n_grams_s1) + len(n_grams_s2)) | |
print(f'{2}-grams') | |
print(n_grams_s1) | |
print(n_grams_s2) | |
print(distance) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment