import pandas as pd from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.naive_bayes import GaussianNB from sklearn.model_selection import train_test_split from sklearn.feature_extraction.text import TfidfVectorizer # df1是经过预处理后的数据集，包含content_clean和category两列 X = df1['content_clean'] y = df1['category'] # 将数据集划分为训练集和测试集 train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.2,) # 向量化文本 vectorizer = TfidfVectorizer() train_vectors = vectorizer.fit_transform(train_X) test_vectors = vectorizer.transform(test_X) # X_dense = X.toarray() classifier=GaussianNB().fit(train_vectors, train_labels)

在上述代码中，有一行代码 `classifier=GaussianNB().fit(train_vectors, train_labels)` 中的 `train_labels` 变量未被定义。应该将其改为 `train_y`，即 `classifier=GaussianNB().fit(train_vectors, train_y)`。

此外，代码中导入了两次 `TfidfVectorizer`，只需要导入一次即可：

import pandas as pd 
from sklearn.feature_extraction.text import TfidfVectorizer 
from sklearn.naive_bayes import GaussianNB 
from sklearn.model_selection import train_test_split 

# df1是经过预处理后的数据集，包含content_clean和category两列 
X = df1['content_clean'] 
y = df1['category'] 

# 将数据集划分为训练集和测试集 
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.2,) 

# 向量化文本 
vectorizer = TfidfVectorizer() 
train_vectors = vectorizer.fit_transform(train_X) 
test_vectors = vectorizer.transform(test_X) 

# 训练分类器 
classifier = GaussianNB().fit(train_vectors, train_y)

这样修改后，代码应该可以正确运行了。