（一）房价预测

1from sklearn.datasets import load_boston
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import SGDRegressor

plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #用来正常显示负号

x = load_boston().data
y = load_boston().target
print(load_boston().DESCR) #显示数据集的属性

#数据处理

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=33)
#分析回归目标值的差异
print( 'The max target value is ',np.max(y))
print ('The min target value is ',np.min(y))
print ('The average target value is ',np.mean(y))

#标准化
ss_X = StandardScaler()
ss_y = StandardScaler()

X_train = ss_X.fit_transform(X_train)
X_test = ss_X.transform(X_test)

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

#LR模型
lr = LinearRegression()
lr.fit(X_train, y_train)
lr_y_predict = lr.predict(X_test)

#SGDRRegressor
sgdr = SGDRegressor()
sgdr.fit(X_train, y_train)
sgdr_predict = sgdr.predict(X_test)

#第五步：性能测评
#主要是判断预测值与真实值之间的差距，比较直观的评价指标有
#平均绝对值误差MAE(mean absolute error)
#均方误差MSE(mean squared error)
#R-squared评价函数
#使用LinearRegression模型自带的评估模块，并输出评估结果
print ('the value of default measurement of LR：',lr.score(X_test,y_test))
from sklearn.metrics import r2_score,mean_squared_error,mean_absolute_error
print ('the value of R-squared of LR is',r2_score(y_test,lr_y_predict))
#可以使用标准化器中的inverse_transform函数还原转换前的真实值
print ('the MSE of LR is',mean_squared_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(lr_y_predict)))
print ('the MAE of LR is',mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(lr_y_predict)))
#使用SGDRegressor自带的评估模块，并输出评估结果
print ('the value of default measurement of SGDR：',sgdr.score(X_test,y_test))
from sklearn.metrics import r2_score,mean_squared_error,mean_absolute_error
print( 'the value of R-squared of SGDR is',r2_score(y_test,sgdr_predict))
print ('the MSE of SGDR is',mean_squared_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(sgdr_predict)))
print ('the MAE of SGDR is',mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(sgdr_predict)))

#总结：
#从输出结果来看，回归模型自带的评估结果与r2_score的值是一样的，推荐使用第一种方式
#SGDRegressor在性能上表现略逊于LinearRegression，前者是随机梯度下降的方式估计参数，后者是精确解析参数
#在数据量十分庞大（10W+）的时候，推荐使用SGDRegressor