from sklearn.feature_extraction.text import CountVectorizer
docs=["Python 是 编程 语言"
    "Java 是 编程 语言"
    "Python Python Python"]
vectorizer = CountVectorizer()
bow_matrix = vectorizer.fit_transform(docs)

print("词表:", vectorizer.get_feature_names_out())
print("BoW矩阵:")
print(bow_matrix.toarray())