python Tfidf更好

Posted 2021-05-09

from sklearn.feature_extraction.text import TfidfVectorizer

tvec = TfidfVectorizer(stop_words='english')
tvec.fit(data_train['data'])
tvecdata = tvec.transform(data_train['data'])

X_train  = pd.DataFrame(tvec.fit_transform(data_train['data']).todense(),columns=tvec.get_feature_names())

print(X_train.shape)
X_test = pd.DataFrame(tvec.transform(data_test['data']).todense(),columns=tvec.get_feature_names())
print(X_test.shape)