欠拟合：
    -训练集表现不好，而且训练集以外的数据也表现不好
    -原因：
        -数据特征太少
        -交叉验证：训练集结果表现不行
    -解决：增加数据特征
过拟合：
    -训练集表现很好，但在训练集以外的数据集表现不好
    -原因：
        -数据特征过多
        -测试集表现不行
    -解决：
        -进行特征选择，消除关联性大的特征
        -交叉验证
        -正则化

sklearn.linear_model.Ridge

# -*- coding: utf-8 -*-
from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression, SGDRegressor, Ridge
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
# 加载数据
boston = load_boston()
# 训练集，测试集拆分
X_train, X_test, y_train, y_test = train_test_split(
    boston.data, boston.target, test_size=0.25)
# 数据标准化处理
# 特征值 标准化
std_x = StandardScaler()
X_train = std_x.fit_transform(X_train)
X_test = std_x.transform(X_test)
# 目标值 标准化
std_y = StandardScaler()
y_train = std_y.fit_transform(y_train.reshape(-1, 1))
y_test = std_y.transform(y_test.reshape(-1, 1))
# 正规方程
lr = LinearRegression()
lr.fit(X_train, y_train)
print(lr.coef_)
y_lr_predict = std_y.inverse_transform(lr.predict(X_test))
# 梯度下降
sgd = SGDRegressor()
sgd.fit(X_train, y_train)
print(sgd.coef_)
y_sgd_predict = std_y.inverse_transform(sgd.predict(X_test))
# 岭回归
ridge = Ridge()
ridge.fit(X_train, y_train)
print(ridge.coef_)
y_ridge_predict = std_y.inverse_transform(ridge.predict(X_test))
# 均方误差
lr_mse = mean_squared_error(std_y.inverse_transform(y_test), y_lr_predict)
sgd_mse = mean_squared_error(std_y.inverse_transform(y_test), y_sgd_predict)
ridge_mse = mean_squared_error(std_y.inverse_transform(y_test), y_ridge_predict)
print(lr_mse)
print(sgd_mse)
print(ridge_mse)
"""
20.887918065953176
21.059487199230684
20.87817117552608
"""