sklearn中梯度下降法和正规方程在神经网络中的应用

coding=utf-8

“”"
author:lei
function:
“”"

from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression, SGDRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error

def mylinear():
“”"
线性回归直接预测房子价格
:return:
“”"
# 获取数据
lb = load_boston()

# 分割数据集到训练集和测试集
x_train, x_test, y_train, y_test = train_test_split(lb.data, lb.target, test_size=0.25)

# 进行标准化处理，特征值和目标值进行标准化处理，实例化两个标准化API
std_x = StandardScaler()

# 训练集
x_train = std_x.fit_transform(x_train)
x_test = std_x.transform(x_test)

# 目标值
std_y = StandardScaler()

y_train = std_y.fit_transform(y_train.reshape(-1, 1))
y_test = std_y.transform(y_test.reshape(-1, 1))

# 使用正规方程求解方式预测结果
lr = LinearRegression()

lr.fit(x_train, y_train)

# print(lr.coef_)  # 回归并没有准确率进行评估，预测值和真实值的偏差

# 预测测试集的房子价格 将原来的值预测出来
y_predict = std_y.inverse_transform(lr.predict(x_test))

# print(y_predict)
print("正规方程的均方误差:", mean_squared_error(std_y.inverse_transform(y_test), y_predict))

# 梯度下降预测房价
sgd = SGDRegressor()

sgd.fit(x_train, y_train)

# 预测测试集的房子价格
y_predict2 = std_y.inverse_transform(sgd.predict(x_test))

# print("sgd预测的房子价格为：", y_predict)
print("梯度下降的均方误差：", mean_squared_error(std_y.inverse_transform(y_test), y_predict2))

if name == ‘main’:
mylinear()