NLTK Stopwords on CoCalc

https://share.cocalc.com/share/20e4a191-73ea-4921-80e9-0a5d792fc511/nltk-stopwords.ipynb?viewer=share

In [1]:

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

In [2]:

data = "All work and no play makes jack dull boy. All work and no play makes jack a dull boy."
stopWords = set(stopwords.words('english'))
words = word_tokenize(data)
wordsFiltered = []

In [3]:

for w in words:
    if w not in stopWords:
        wordsFiltered.append(w)

print(wordsFiltered)

['All', 'work', 'play', 'makes', 'jack', 'dull', 'boy', '.', 'All', 'work', 'play', 'makes', 'jack', 'dull', 'boy', '.']

In [0]: