基于Scikit-learn的多元线性回归模型构建与验证

废话不多说，直接上代码

# import numpy as np
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
import joblib  # 用于保存和加载模型

# 1. 导入数据（假设你有一个包含特征和目标值的CSV文件）
# 例如，data.csv 中有若干特征列和一个名为 'target' 的目标列
data = pd.read_csv('FuelConsumptionCo21.csv')

# 2. 准备数据
# 分离特征和目标值
X = data.drop('target', axis=1)
y = data['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)

# 3. 创建并训练模型
model = LinearRegression()
model.fit(X_train, y_train)

print(model.coef_)
print(model.intercept_)

# 4. 进行预测并评估模型
y_pred = model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')


# 5. 保存模型
joblib.dump(model, 'linear_regression_model.pkl')

# 6. 加载模型（可选，验证模型是否正确保存和加载）
loaded_model = joblib.load('linear_regression_model.pkl')
loaded_y_pred = loaded_model.predict(X_test)
loaded_mse = mean_squared_error(y_test, loaded_y_pred)
print(f'Mean Squared Error after loading: {loaded_mse}')

原始数据是汽车 二氧化碳污染指标排放，数据如下

ENGINESIZE	CYLINDERS	FUELCONSUMPTION_CITY	FUELCONSUMPTION_HWY	FUELCONSUMPTION_COMB	FUELCONSUMPTION_COMB_MPG	target
2	4	9.9	6.7	8.5	33	196
2.4	4	11.2	7.7	9.6	29	221
1.5	4	6	5.8	5.9	48	136
3.5	6	12.7	9.1	11.1	25	255
3.5	6	12.1	8.7	10.6	27	244
3.5	6	11.9	7.7	10	28	230
3.5	6	11.8	8.1	10.1	28	232
3.7	6	12.8	9	11.1	25	255
3.7	6	13.4	9.5	11.6	24	267
2.4	4	10.6	7.5	9.2	31	212
2.4	4	11.2	8.1	9.8	29	225
3.5	6	12.1	8.3	10.4	27	239
5.9	12	18	12.6	15.6	18	359
5.9	12	18	12.6	15.6	18	359
4.7	8	17.4	11.3	14.7	19	338
4.7	8	18.1	12.2	15.4	18	354
4.7	8	17.4	11.3	14.7	19	338
4.7	8	18.1	12.2	15.4	18	354
5.9	12	18	12.6	15.6	18	359
2	4	9.9	7.4	8.8	32	202
2	4	11.5	8.1	10	28	230
2	4	10.8	7.5	9.3	30	214