12311k

Untitled

Feb 24th, 2020
1,903
0
Never
1
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 0.38 KB | None | 0 0
  1. import pandas as pd
  2. from pymystem3 import Mystem
  3.  
  4. data = pd.read_csv('/datasets/tweets.csv')
  5. corpus = data['text'].values.astype('U')
  6.  
  7. def lemmatize(text):
  8. m = Mystem()
  9. lemm_list = m.lemmatize(text)
  10. lemm_text = "".join(lemm_list)
  11.  
  12. return lemm_text
  13.  
  14. print("Исходный текст:", corpus[0])
  15. print("Лемматизированный текст:", lemmatize(corpus[0]))
Advertisement
Comments
  • # text 0.49 KB | 0 0
    1. import pandas as pd
    2. from pymystem3 import Mystem # импортируйте класс Mystem из библиотеки pymystem3
    3.  
    4. data = pd.read_csv('/datasets/tweets.csv')
    5. corpus = data['text'].values.astype('U')
    6.  
    7. def lemmatize(text):
    8. m = Mystem()
    9. lemm = Mystem().lemmatize(text)
    10.  
    11. return ''.join(lemm) # < напишите код здесь >
    12.  
    13. print("Исходный текст:", corpus[0])
    14. print("Лемматизированный текст:", lemmatize(corpus[0]))
    15.  
Add Comment
Please, Sign In to add comment