textdistance_hamming_levenshtein_jaccard_string_similarity.py

1import textdistance
2
3# Hamming distance
4# How many symbols are different?
5hamming_dist = textdistance.hamming('test', 'text')
6print(f"Hamming distance: {hamming_dist}")
7
8# Levenshtein distance
9# How many edits (insert, delete, replace) to turn one string into another?
10levenshtein_dist = textdistance.levenshtein('test', 'text')
11print(f"Levenshtein distance: {levenshtein_dist}")
12
13# Jaccard index
14# Similarity based on the intersection of sets of characters
15jaccard_sim = textdistance.jaccard('test', 'text')
16print(f"Jaccard similarity: {jaccard_sim}")
17
18# You can also use object-oriented approach for more options
19lev = textdistance.Levenshtein(qval=2)
20lev_dist_qval = lev('test', 'text')
21print(f"Levenshtein distance (qval=2): {lev_dist_qval}")