线性回归

线性回归

• 目标函数：
  
• 损失函数
  
  
  
  
• sklearn.linear_model.LinearRegression
  
  
• sklearn.linear_model.SGDRegressor

eg:以波士顿房价数据为例

import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
import random
from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression,SGDRegressor

#数据集划分
data=load_boston()
x_train,x_test,y_train,y_test=train_test_split(data.data,data.target,test_size=0.25)

#特征值和目标值都必须进行标准化，实例两个标准化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)
#标签值标准化
std_y=StandardScaler()
y_train=std_y.fit_transform(y_train.reshape(-1,1)) #特别注意，必须为二维的数组，所以用reshape（-1,1）进行转换
y_test=std_y.transform(y_test.reshape(-1,1))

#实例化Lr
lr=LinearRegression()
result=lr.fit(x_train,y_train)

#查看系数
result.coef_

#用std_y对result.predict()进行标准化复原，查看预测值
std_y.inverse_transform(result.predict(x_test))

#查看MSE值
from sklearn.metrics import mean_squared_error
#传入y和yhat
mean_squared_error(std_y.inverse_transform(y_test),std_y.inverse_transform(result.predict(x_test)))

简单应用SGDRegressor

#实例化SGD
SGD=SGDRegressor()
result=SGD.fit(x_train,y_train)

#查看系数
result.coef_

#用std_y对result.predict()进行标准化复原，查看预测值
std_y.inverse_transform(result.predict(x_test))


#查看MSE值
from sklearn.metrics import mean_squared_error
#传入y和yhat
mean_squared_error(std_y.inverse_transform(y_test),std_y.inverse_transform(result.predict(x_test)))