Question

how to add n gram code for this program?

import nltk

from textblob import TextBlob

from collections import Counter

from nltk import FreqDist

file=open("veg.txt","r")

rd=file.read()

#sentiment

sentences= nltk.sent_tokenize(rd)

tb=(TextBlob (t).sentiment.polarity for t in rd)

tb=TextBlob(rd)

print(tb.sentiment.polarity)

#ner

words=[]

for sentence in sentences:

words.append(nltk.word_tokenize(sentence))

tags=[]

for word in words:

tags.append(nltk.pos_tag(word))

for tag in tags:

print(nltk.ne_chunk(tag))

#pos

print(tb.tags)

wordlist = rd.split()

wordfreq = []

for w in wordlist:

wordfreq.append(wordlist.count(w))

print("Word Frequency\n" + str(list(zip(wordlist, wordfreq))))

Answer 1

Hello,

Please find the below code to find the NGrams.

I have used the nltk library.

import nltk
from nltk import ngrams
from textblob import TextBlob

file=open("veg.txt","r")
rd=file.read()

#sentiment
sentences= nltk.sent_tokenize(rd)
tb=(TextBlob (t).sentiment.polarity for t in rd)
tb=TextBlob(rd)
print(tb.sentiment.polarity)

#ner
words=[]
for sentence in sentences:
    words.append(nltk.word_tokenize(sentence))
tags=[]
for word in words:
    tags.append(nltk.pos_tag(word))
for tag in tags:
    print(nltk.ne_chunk(tag))

#pos
print(tb.tags)

wordlist = rd.split()
wordfreq = []
for w in wordlist:
    wordfreq.append(wordlist.count(w))
print("Word Frequency\n" + str(list(zip(wordlist, wordfreq))))

#NGrams
n = 6 # Pass any integer value to find the Ngrams of a sentence
sixgrams = ngrams(rd.split(), n)

for grams in sixgrams:
    print("GRAMS : {}".format(grams))

Result:

Let me know if you have any doubts in the comments sections.

Thanks.