七、(3)线性回归——波士顿房价预测(解决过拟合)
线性回归——波士顿房价预测
1、运行正规方程代码,观察结果。
# -*- coding: utf-8 -*-
"""
Created on Sat May 25 19:28:12 2019
@author: sun
"""
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.externals import joblib
from sklearn.metrics import mean_squared_error
import pandas as pd
def mylinear():
"""
线性回归直接预测房子价格
:return: None
"""
# 获取数据
titan = pd.read_csv(r"./波士顿原数据.csv",engine='python')
# 处理数据,找出特征值和目标值
data = titan[['crim','zn','indus','chas','nox','rm','age','dis','rad','tax','ptratto','b','lstat']]
target = titan['medv']
# 分割数据集到训练集和测试集
x_train, x_test, y_train, y_test = train_test_split(data, target, test_size=0.25)
#print( y_train, y_test)
# 进行标准化处理(?) 目标值处理?
# 特征值和目标值是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_)
# # 预测测试集的房子价格
y_lr_predict = std_y.inverse_transform(lr.predict(x_test))
#
#print("正规方程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(