Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- data['locality_name'] = data['locality_name'].apply(lambda x: x.replace('ё', 'е'))
- from pymystem3 import Mystem
- m = Mystem()
- name_unique = data['locality_name'].unique()
- name_unique = ' '.join(name_unique)
- lemmas_name = m.lemmatize(name_unique)
- from collections import Counter
- print(Counter(lemmas_name)) # посмотрим основные леммы, на основании которых выделим категории населенных пунктов
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement