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

62 votes172 views6 answers
Python for loop with index
Python
0 vote165 views2 answers
Python get module name
Python
1 vote184 views1 answer
Python background function
Python
0 vote185 views1 answer
Check if cuda is present in torch
Python
4 votes179 views2 answers
Primary key django model
Python
0 vote187 views1 answer
Removes all the elements from a linked list python
Python
0 vote167 views1 answer
Python scheduler
Python
0 vote203 views1 answer
Site:github.com python ssh
Python
2 votes189 views1 answer
How to insert a variable into a string without breaking up the string in python
Python
14 votes229 views1 answer
Average value of list elements in python
Python