We can import stopwords from nltk.corpus as below. With that, We exclude stopwords with Python’s list comprehension and pandas.DataFrame.apply.
# Import stopwords with nltk.
from nltk.corpus import stopwords
stop = stopwords.words('english')
pos_tweets = [('I love this car', 'positive'),
('This view is amazing', 'positive'),
('I feel great this morning', 'positive'),
('I am so excited about the concert', 'positive'),
('He is my best friend', 'positive')]
test = pd.DataFrame(pos_tweets)
test.columns = ["tweet","class"]
# Exclude stopwords with Python's list comprehension and pandas.DataFrame.apply.
test['tweet_without_stopwords'] = test['tweet'].apply(lambda x: ' '.join([word for word in x.split() if word not in (stop)]))
print(test)
# Out[40]:
# tweet class tweet_without_stopwords
# 0 I love this car positive I love car
# 1 This view is amazing positive This view amazing
# 2 I feel great this morning positive I feel great morning
# 3 I am so excited about the concert positive I excited concert
# 4 He is my best friend positive He best friend
It can also be excluded by using pandas.Series.str.replace.
pat = r'\b(?:{})\b'.format('|'.join(stop))
test['tweet_without_stopwords'] = test['tweet'].str.replace(pat, '')
test['tweet_without_stopwords'] = test['tweet_without_stopwords'].str.replace(r'\s+', ' ')
# Same results.
# 0 I love car
# 1 This view amazing
# 2 I feel great morning
# 3 I excited concert
# 4 He best friend
If you can not import stopwords, you can download as follows.
import nltk
nltk.download('stopwords')
Another way to answer is to import text.ENGLISH_STOP_WORDS from sklearn.feature_extraction.
# Import stopwords with scikit-learn
from sklearn.feature_extraction import text
stop = text.ENGLISH_STOP_WORDS
Notice that the number of words in the scikit-learn stopwords and nltk stopwords are different.