resumematcher / scripts /utils /tf_idf.py
March
first
46917c3
Raw History Blame Contribute Delete
248 Bytes
from sklearn.feature_extraction.text import TfidfVectorizer
def do_tfidf(token):
tfidf = TfidfVectorizer(max_df=0.05, min_df=0.002)
words = tfidf.fit_transform(token)
sentence = " ".join(tfidf.get_feature_names())
return sentence