Extract bigrams python

from nltk import word_tokenize 
from nltk.util import ngrams


text = ['cant railway station', 'citadel hotel', 'police stn']
for line in text:
    token = nltk.word_tokenize(line)
    bigram = list(ngrams(token, 2))

    # the '2' represents bigram...you can change it to get ngrams with different size

Source: stackoverflow.com

Similar codes

0 vote289 views1 answer
Pytest loop
Python
4 votes341 views2 answers
Discord py color
Python
1 vote322 views1 answer
Implicit conversion in python example
Python
0 vote334 views1 answer
Deep clone 2d list python
Python
1 vote313 views1 answer
Sftp python
Python
0 vote366 views1 answer
Flask return 404
Python Flask
0 vote354 views1 answer
Python webdriver open with chrome extension
Python
-1 vote311 views1 answer
Receipt ocr python
Python
10 votes344 views2 answers
Print key of dictionary python
Python
0 vote328 views1 answer
Reading a file line by line using a generator
Python