如何在Python sklearn CountVectorizer的分析器参数中标识“单词边界”？

from sklearn.feature_extraction.text import CountVectorizer

# 定义一个自定义的分析器函数
def custom_analyzer(text):
    import re
    pattern = r'\b\w+\b'  # 正则表达式匹配单词边界
    tokens = re.findall(pattern, text)
    return tokens

# 创建CountVectorizer对象，并使用自定义的分析器
vectorizer = CountVectorizer(analyzer=custom_analyzer)

# 示例文本
corpus = [
    "This is a sample sentence.",
    "Another example sentence."
]

# 将文本转换为特征向量
X = vectorizer.fit_transform(corpus)

# 输出特征向量
print(vectorizer.get_feature_names())
print(X.toarray())