Created
January 17, 2022 20:48
-
-
Save eileen-code4fun/d7698cbfd7fd3451a7dfd5e1acdaff4d to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| from nltk.stem import PorterStemmer | |
| from nltk.stem import WordNetLemmatizer | |
| def lower_remove_punctuation_stem(txt): | |
| txt = lower_remove_punctuation(txt) | |
| ps = PorterStemmer() | |
| words = [ps.stem(w) for w in txt.split()] | |
| return ' '.join(words) | |
| def lower_remove_punctuation_lemmatize(txt): | |
| txt = lower_remove_punctuation(txt) | |
| lemmatizer = WordNetLemmatizer() | |
| words = [lemmatizer.lemmatize(w) for w in txt.split()] | |
| return ' '.join(words) | |
| # Use preprocess to create respective training and test datasets. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment