从sklearn输出中获取tf / tfidf

from sklearn.feature_extraction.text import CountVectorizer

# 文本数据
text_data = ['This is an example sentence.',
             'Another example sentence.',
             'Yet another example sentence.']

# 创建CountVectorizer对象
count_vectorizer = CountVectorizer()

# 将文本数据转换为词频矩阵
tf_matrix = count_vectorizer.fit_transform(text_data)

# 获取每个词的列表
feature_names = count_vectorizer.get_feature_names()

# 将词频矩阵转换为数组形式
tf_array = tf_matrix.toarray()

print('词频矩阵：')
print(tf_array)
print('词列表：')
print(feature_names)

词频矩阵：
[[1 1 1 1 0 1 0]
 [1 1 0 1 1 1 0]
 [1 1 0 1 0 1 1]]
词列表：
['an', 'another', 'example', 'is', 'sentence', 'this', 'yet']

from sklearn.feature_extraction.text import TfidfVectorizer

# 文本数据
text_data = ['This is an example sentence.',
             'Another example sentence.',
             'Yet another example sentence.']

# 创建TfidfVectorizer对象
tfidf_vectorizer = TfidfVectorizer()

# 将文本数据转换为tfidf矩阵
tfidf_matrix = tfidf_vectorizer.fit_transform(text_data)

# 获取每个词的列表
feature_names = tfidf_vectorizer.get_feature_names()

# 将tfidf矩阵转换为数组形式
tfidf_array = tfidf_matrix.toarray()

print('tfidf矩阵：')
print(tfidf_array)
print('词列表：')
print(feature_names)

tfidf矩阵：
[[0.45069391 0.45069391 0.45069391 0.45069391 0.         0.45069391
  0.        ]
 [0.45069391 0.45069391 0.         0.45069391 0.59583092 0.45069391
  0.        ]
 [0.45069391 0.45069391 0.         0.45069391 0.         0.45069391
  0.59583092]]
词列表：
['an', 'another', 'example', 'is', 'sentence', 'this', 'yet']