Last active
May 28, 2018 11:16
-
-
Save RamonYeung/96775a555a5cb8686b79ab8f19d712b3 to your computer and use it in GitHub Desktop.
Here is a list of stop words in English and it is taken from nltk.corpus.stopwords
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Here is a list of stop words in English and it is taken from nltk.corpus.stopwords | |
# requirements: NLTK==3.2.4 | |
stop_words = ['a', 'about', 'above', 'after', 'again', 'against', 'ain', 'all', 'am', 'an', 'and', 'any', 'are', 'aren', "aren't", 'as', 'at', | |
'be', 'because', 'been', 'before', 'being', 'below', 'between', 'both', 'but', 'by', | |
'can', 'couldn', "couldn't", | |
'd', 'did', 'didn', "didn't", 'do', 'does', 'doesn', "doesn't", 'doing', 'don', "don't", 'down', 'during', | |
'each', | |
'few', 'for', 'from', 'further', | |
'had', 'hadn', "hadn't", 'has', 'hasn', "hasn't", 'have', 'haven', "haven't", 'having', 'he', 'her', 'here', 'hers', 'herself', 'him', 'himself', 'his', 'how', | |
'i', 'if', 'in', 'into', 'is', 'isn', "isn't", 'it', "it's", 'its', 'itself', | |
'just', | |
'll', | |
'm', 'ma', 'me', 'mightn', "mightn't", 'more', 'most', 'mustn', "mustn't", 'my', 'myself', | |
'needn', "needn't", 'no', 'nor', 'not', 'now', | |
'o', 'of', 'off', 'on', 'once', 'only', 'or', 'other', 'our', 'ours', 'ourselves', 'out', 'over', 'own', | |
're', | |
's', 'same', 'shan', "shan't", 'she', "she's", 'should', "should've", 'shouldn', "shouldn't", 'so', 'some', 'such', | |
't', 'than', 'that', "that'll", 'the', 'their', 'theirs', 'them', 'themselves', 'then', 'there', 'these', 'they', 'this', 'those', 'through', 'to', 'too', | |
'under', 'until', 'up', | |
've', 'very', | |
'was', 'wasn', "wasn't", 'we', 'were', 'weren', "weren't", 'what', 'when', 'where', 'which', 'while', 'who', 'whom', 'why', 'will', 'with', 'won', "won't", 'wouldn', "wouldn't", | |
'y', 'you', "you'd", "you'll", "you're", "you've", 'your', 'yours', 'yourself', 'yourselves'] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment