Created
April 27, 2019 19:57
-
-
Save tkazusa/37127320deb9d93acb7d3bda5b0c0b59 to your computer and use it in GitHub Desktop.
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 gensim import corpora, models | |
| from gensim.matutils import corpus2dense, corpus2csc | |
| def tfidfvectorizer(df: pd.DataFrame) -> np.ndarray: | |
| documents = list(train.name) | |
| texts = list(map(lambda x: x.split(), documents)) | |
| dct = corpora.Dictionary(texts) | |
| corpus = [dct.doc2bow(line) for line in texts] | |
| tfidf= models.TfidfModel(corpus) | |
| corpus_tfidf = tfidf[corpus] | |
| return [list(corpus2dense([corpus_tfidf[i], len(dct)])) for i in range(len(corpus_tfidf))] | |
| def tfidfvectorizer(df: pd.DataFrame) -> np.ndarray: | |
| documents = list(df.name) | |
| texts = list(map(lambda x: x.split(), documents)) | |
| dct = corpora.Dictionary(texts) | |
| corpus = [dct.doc2bow(line) for line in texts] | |
| tfidf= models.TfidfModel(corpus) | |
| corpus_tfidf = tfidf[corpus] | |
| return [list(corpus2csc([corpus_tfidf[i]], len(dct))) for i in range(len(corpus_tfidf))] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment