python线性回归算法预测学生成绩

import pandas as pd
import numpy as np
from sklearn.model_se`在这里插入代码片`lection import train_test_split, GridSearchCV
from sklearn.linear_model import Ridge
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt

# 1. 数据加载
data = pd.read_csv('data.csv')
X = data.iloc[:, :2]  # 取前两列作为特征
y = data.iloc[:, 2]  # 取第三列作为目标变量

# 2. 数据预处理
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# 3. 使用GridSearchCV来优化alpha值
# 定义alpha值的候选范围
alpha_candidates = [1e-15, 1e-10, 1e-5, 1e-2, 1, 5, 10, 20]

# 创建岭回归模型
ridge = Ridge()

# 创建GridSearchCV对象
grid_search = GridSearchCV(estimator=ridge, param_grid={'alpha': alpha_candidates}, cv=5,
                           scoring='neg_mean_squared_error')

# 执行网格搜索
grid_search.fit(X_train_scaled, y_train)

# 获取最佳alpha值
best_alpha = grid_search.best_params_['alpha']
print(f"Best alpha: {best_alpha}")

# 使用最佳alpha值训练模型
ridge_best = Ridge(alpha=best_alpha)
ridge_best.fit(X_train_scaled, y_train)

# 进行预测
y_pred = ridge_best.predict(X_test_scaled)

# 评估模型
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error with best alpha: {mse}')

# 注意：这里使用的是负均方误差作为评分指标，因为GridSearchCV默认寻找最大值，而均方误差越小越好，所以取负值。

# 4. 可视化预测结果
plt.scatter(y_test, y_pred, alpha=0.5)  # 绘制实际值与预测值的散点图
plt.xlabel('Actual Values')
plt.ylabel('Predicted Values')
plt.title('Ridge Regression Prediction')

# 绘制理想情况的对角线
lims = [
    np.min([y_test.min(), y_pred.min()]),  # x轴最小值
    np.max([y_test.max(), y_pred.max()]),  # x轴最大值
]
plt.plot(lims, lims, 'k--', alpha=0.75, zorder=0)
plt.xlim(lims)
plt.ylim(lims)

# 显示图形
plt.grid(True)
plt.show()