Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import pandas as pd
- # импортируйте класс Mystem из библиотеки pymystem3
- from pymystem3 import Mystem
- data = pd.read_csv('/datasets/tweets.csv')
- corpus = data['text'].values.astype('U')
- def lemmatize(text):
- # < напишите код здесь >
- m = Mystem()
- lemmas = m.lemmatize(text)
- return " ".join(lemmas)
- print("Исходный текст:", corpus[0])
- print("Лемматизированный текст:", lemmatize(corpus[0]))
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement