sklearn 计算 tfidf 得到每个词分数

from sklearn.feature_extraction.text import TfidfVectorizer

# 语料库 可以换为其它同样形式的单词
corpus = [
    list(range(-5, 5)),
    list(range(-6,4)),
    list(range(12)),
    list(range(13))]

# corpus = [
#    ['Two', 'wrongs', 'don\'t', 'make', 'a', 'right', '.'],
#    ['The', 'pen', 'is', 'mightier', 'than', 'the', 'sword'],
#    ['Don\'t', 'put', 'all', 'your', 'eggs', 'in', 'one', 'basket', '.']]
    
def dummy_fun(doc):
    return doc
    
tfidf_vec = TfidfVectorizer(
    analyzer='word',
    tokenizer=dummy_fun,
    preprocessor=dummy_fun,
    token_pattern=None)  

# 使用 fit_transform() 得到 TF-IDF 矩阵。此为 scipy 稀疏矩阵
tfidf_matrix = tfidf_vec.fit_transform(corpus)
# print(tfidf_matrix)

# 使用 get_feature_names() 得到不重复的单词
print(tfidf_vec.get_feature_names_out())

# 得到每个单词对应的 ID
print(tfidf_vec.vocabulary_)

# 得到 corpus 中每个词得分
for i in range(len(corpus)):
    column_indexes = [tfidf_vec.vocabulary_[key] for key in corpus[i]]
    tf_idf = tfidf_matrix[i, column_indexes].toarray()[0]
    print(tf_idf)

参考：
Applying scikit-learn TfidfVectorizer on tokenized text
sklearn.feature_extraction.text.TfidfVectorizer