Lucas Chaves Lima lcschv
lcschv
/ PWI_top2vec.py
Last active
March 2, 2023 10:06
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
| from nltk.probability import FreqDist | |
| import math | |
| import pickle | |
| from top2vec import Top2Vec | |
| import numpy as np | |
| from gensim.utils import simple_preprocess | |
| from gensim.parsing.preprocessing import strip_tags | |
| def default_tokenizer(doc): |