scklearn

import numpy as np
import pandas as pd
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

加载波士顿房价数据集

boston = load_boston()
X = pd.DataFrame(boston.data, columns=boston.feature_names)
y = boston.target

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

y_pred = model.predict(X_test)

计算均方误差

mse = mean_squared_error(y_test, y_pred)
print(f"均方误差: {mse}")