python 岭回归

from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression,SGDRegressor,Ridge
from sklearn.metrics import mean_squared_error
```python
def linear3():
    """岭回归的优化方法（损失函数最小值）对波士顿房价进行预测"""
    #导入数据
    boston = load_boston()
    print("特征数量：\n",boston.data.shape)
    #划分数据
    x_train,x_test,y_train,y_test =train_test_split(boston.data,boston.target,random_state=22)
    #标准化特征
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)
    #预估器
    estimator = Ridge(max_iter=100000,alpha=0.2)
    estimator.fit(x_train,y_train)
    #得出模型
    print("岭回归——权重系数为：\n",estimator.coef_)
    print("岭回归——偏置为：\n",estimator.intercept_)
    #模型评估
    y_predict = estimator.predict(x_test)
    print("预测值为:\n",y_predict)
    error = mean_squared_error(y_test,y_predict)
    print("岭回归——均方误差为：\n",error)
    return 0
if __name__ == '__main__':
    linear3()

岭回归是加了正则化的线性回归。
为了消除线性回归可能产生的过拟合。正则化：在损失函数中加入惩罚系数和惩罚项。