如何从不同的csv进行线性回归？

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

# 加载CSV文件
data1 = pd.read_csv('file1.csv')
data2 = pd.read_csv('file2.csv')

# 假设两个文件有相同的列结构，合并数据
combined_data = pd.concat([data1, data2], ignore_index=True)

# 数据预处理（例如，处理缺失值）
combined_data = combined_data.dropna()

# 定义自变量和因变量
X = combined_data[['feature1', 'feature2']]  # 自变量
y = combined_data['target']  # 因变量

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 创建线性回归模型
model = LinearRegression()

# 训练模型
model.fit(X_train, y_train)

# 预测测试集结果
y_pred = model.predict(X_test)

# 评估模型
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f'Mean Squared Error: {mse}')
print(f'R² Score: {r2}')