lv distance similarity

lv_similarity.py

import rapidfuzz


def get_confidence_lv(init_data_name: str, document_name: str) -> float:
    edit_distance = rapidfuzz.distance.Levenshtein.distance(init_data_name, document_name)
    similarity = 1 - (edit_distance / max(len(init_data_name), len(document_name)))
    return round(similarity, 2)

input = [
    ("Arjun", "Arjun" ), 
    ("Arjun", "Arun" ), 
    ("Arjun Sunil", "Arjun Sunl" ), 
    ("Arjun Sunil", "Arjun Sunil Mar" ), 
    ("Arjun Sunil", "Arjun Sunil Marc" ), 
    ("Arjun Sunil", "Arjun Sunil Marce" ), 
    ("Arjun Sunil", "Arjun Sunil Marcel" ), 
    ("Arjun Sunil", "Arjun Sunil Marcel O" ), 
    ("Arjun Sunil", "Arjun Sunil Marcel Oc" ), 
]

for i in input:
    print(i[0], i[1], "-->", get_confidence_lv(i[0], i[1]))