机器学习中运用python进行对房子价格的预测代码,数据库直接使用sklearn自带的boston,使用三种方法进行预测,分别是:线性回归直接预测、梯度下降预测、岭回归预测
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
from sklearn.metrics import mean_squared_error
def mylinear():
"""
线性回归直接预测房子价格
:return: None
"""
# 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)
# print(y_train, y_test)
# 进行标准化处理(?)目标值处理?
# 特征值和目标值都必须进行标准化处理,实例化两个标准化API
std_x = StandardScaler()
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))
# estimator预测
# 正规方程求解方式预测结果
lr = LinearRegression()
lr.fit(x_train, y_train)
print(lr.coef_)
# 预测测试集房子价格
y_lr_predict = std_y.inverse_transform(lr.predict(x_test))
print("测试集里面每个房子的预测价格:", 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))
# 梯度下降去预测房价
sgd = SGDRegressor()
sgd.fit(x_train, y_train)
print(sgd.coef_)
# 预测测试集房子价格
y_sgd_predict = std_y.inverse_transform(sgd.predict(x_test))
print("测试集里面每个房子的预测价格:", y_sgd_predict)
print("梯度下降方程的均方误差:", mean_squared_error(std_y.inverse_transform(y_test), y_sgd_predict))
# 岭回归去预测房价
rd = Ridge()
rd.fit(x_train, y_train)
print(rd.coef_)
# 预测测试集房子价格
y_rd_predict = std_y.inverse_transform(rd.predict(x_test))
print("测试集里面每个房子的预测价格:", y_rd_predict)
print("岭回归方程的均方误差:", mean_squared_error(std_y.inverse_transform(y_test), y_rd_predict))
return None
if __name__ == '__main__':
mylinear()