欠拟合，过拟合，岭回归

 

alpha:0~1 1~10

完整代码：

import pandas as pd
from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression, SGDRegressor, Ridge
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import numpy as np
# 回归评估
from sklearn.metrics import mean_squared_error
def mylinear():
    """"
    线性回归直接预测房子价格
    """
    # 获取数据
    lb = load_boston()
    # 分割数据
    x_train, x_test, y_train, y_test = train_test_split(lb.data, lb.target, test_size=0.25)
    print(y_train,y_test)
    # 特征值和目标值都必须进行标准化处理，实例化两个API
    # 特征值标准化
    std_x = StandardScaler()
    x_train = std_x.fit_transform(x_train)
    x_test = std_x.transform(x_test)
    # 目标值标准化处理
    std_y = StandardScaler()

    y_train = std_y.fit_transform(np.array(y_train).reshape(-1, 1))
    y_test = std_y.transform(np.array(y_test).reshape(-1, 1))
    # estimastor预测
    # 正规方程预测求解方式
    lr = LinearRegression()
    lr.fit(x_train, y_train)
    print(lr.coef_)
    # 预测测试集的房价价格
    # 原始数据
    # y_lr_predict = std_y.inverse_transform(lr.predict(x_test))
    # 标准化后的数据
    y_lr_predict =lr.predict(x_test)

    print("正规方程测试集里面每个房子的预测价格为:", y_lr_predict)
    print("正规方程的均方误差:", mean_squared_error(std_y.inverse_transform(y_test),y_lr_predict))
#   梯度下降进行房价预测
    sgd = SGDRegressor()
    sgd.fit(x_train, y_train)
    print(sgd.coef_)
    # 预测测试集的房价价格
    y_sgd_predict = sgd.predict(x_test)
    print("梯度下降测试集里面每个房子的预测价格为2:", y_sgd_predict)
    print("梯度下降的均方误差:", mean_squared_error(std_y.inverse_transform(y_test),y_sgd_predict))

    # 岭回归进行房价预测
    rd = Ridge(alpha=1.0)
    rd.fit(x_train, y_train)
    print(rd.coef_)
    # 预测测试集的房价价格
    y_rd_predict = std_y.inverse_transform(rd.predict(x_test))
    print("岭回归测试集里面每个房子的预测价格为2:", y_rd_predict)
    print("岭回归的均方误差:", mean_squared_error(std_y.inverse_transform(y_test), y_rd_predict))

    return None
if __name__ == "__main__":
    mylinear()

运行结果：