如何使用Sklearn忽略短文档？

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_selection import SelectKBest, chi2

documents = ['This is a short document',
             'This is a longer document with more words',
             'Another short document',
             'Another long document with more words']
labels = [0, 1, 0, 1]  # 标签用于分类任务

vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(documents)

k = 2  # 选择前k个与标签相关性最高的特征
selector = SelectKBest(chi2, k=k)
X_new = selector.fit_transform(X, labels)

feature_indices = selector.get_support(indices=True)

selected_features = [vectorizer.get_feature_names()[index] for index in feature_indices]