sklearn.CountVectorizer

from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
cv = CountVectorizer()

data = ['l love you', 'dog', 'cat', 'i like baskerball', 'i like apple']
cv_fit = cv.fit_transform(data)
print(cv.transform(['l love YOU']))
print(cv.vocabulary_)

# 获取语料频次
print(cv.get_feature_names())
print(cv_fit.toarray())
print(cv_fit.toarray().sum(axis=0))