#词表为["Python", "是", "编程", "语言", "Java"]；
#Doc1 向量[1,1,1,1,0]，Doc2 向量[0,1,1,1,1]，Doc3 向量[3,0,0,0,0];
from sklearn.feature_extraction.text import TfidfVectorizer

docs = ["Python 编程", "Java 编程", "Python Python"]
tfidf = TfidfVectorizer()
matrix = tfidf.fit_transform(docs)

print("词表:", tfidf.get_feature_names_out())
print("TF-IDF矩阵:")
print(matrix.toarray())