remove stopwords and tokenize for collocationbigramfinder NLTK

Question

I keep getting this error

sub
    return _compile(pattern, flags).sub(repl, string, count)
TypeError: expected string or buffer

when i try to run this script. Not sure what is wrong. I am essentially reading from a text file, filtering out the stopwords and tokenizing them using NLTK.

import nltk
from nltk.collocations import *
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords

stopset = set(stopwords.words('english'))
bigram_measures = nltk.collocations.BigramAssocMeasures()
trigram_measures = nltk.collocations.TrigramAssocMeasures()


text_file=open('sentiment_test.txt', 'r')
lines=text_file.readlines()
filtered_words = [w for w in lines if not w in stopwords.words('english')]
print filtered_words
tokens=word_tokenize(str(filtered_words)
print tokens
finder = BigramCollocationFinder.from_words(tokens)

Any help would be much appreciated.

Solution

I am presuming that sentiment_test.txt is just plain text, and not a specific format. You are trying to filter lines and not words. You should first tokenize and then filter the stopwords.

from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords

stopset = set(stopwords.words('english'))

with open('sentiment_test.txt', 'r') as text_file:
    text = text_file.read()
    tokens=word_tokenize(str(text))
    tokens = [w for w in tokens if not w in stopset]
    print tokens

Hope this helps.