在python中进行文本分类的过采样？

from imblearn.over_sampling import RandomOverSampler
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.svm import SVC
from sklearn.pipeline import make_pipeline

# 假设X是文本特征向量，y是对应的类别标签
X = ...
y = ...

# 使用TF-IDF向量化文本特征
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(X)

# 使用RandomOverSampler进行过采样
sampler = RandomOverSampler()
X_resampled, y_resampled = sampler.fit_resample(X, y)

# 使用分类模型进行训练和预测
model = make_pipeline(SVC())
model.fit(X_resampled, y_resampled)
predictions = model.predict(X)

# 其他后续操作，如性能评估等
...