在scikit-learn中实现词袋

from sklearn.feature_extraction.text import CountVectorizer

# 文本数据
corpus = [
    'This is the first document.',
    'This document is the second document.',
    'And this is the third one.',
    'Is this the first document?'
]

# 创建CountVectorizer对象
vectorizer = CountVectorizer()

# 对文本数据进行特征提取
X = vectorizer.fit_transform(corpus)

# 获取词袋模型中的所有词
words = vectorizer.get_feature_names()

# 打印词袋模型中的词
print(words)

# 打印词频矩阵
print(X.toarray())

['and', 'document', 'first', 'is', 'one', 'second', 'the', 'third', 'this']
[[0 1 1 1 0 0 1 0 1]
 [0 2 0 1 0 1 1 0 1]
 [1 0 0 1 1 0 1 1 1]
 [0 1 1 1 0 0 1 0 1]]