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 vote131 views1 answer
Python check if 3 values are equal
Python
0 vote127 views1 answer
Dot operator in python
Python
6 votes129 views1 answer
Python check if number
Python
1 vote133 views1 answer
How to replace a row value in pyspark dataframe
Python
0 vote136 views1 answer
Travis ci .yml for python
Python
-1 vote137 views1 answer
Sudo apt-get install python2-pip
Python
1 vote201 views2 answers
Convertir datetime to timestamp django
Python Django
6 votes149 views3 answers
No matching distribution found for tensorflow==2.2.0
Python
50 votes103 views1 answer
Append to the start of a list python
Python
7 votes135 views4 answers
Python possible combinations
Python