多元线性回归分析对于商品价格的回归模型

 自变量 #TV：电视类广告支出 #Radio：广播类广告支出 #Newspaper：报纸类广告支出 因变量 #Sales：商品的销量

求解 #上三个因素对于商品价格的回归模型

import pandas as pd
import seaborn as sns  
import matplotlib.pyplot as plt 

data=pd.read_csv("Advertising.csv",header=0)
data.head()

数据理解：

sns.pairplot(data, x_vars=['TV','radio','newspaper'], y_vars='sales', size=7, aspect=0.8, kind='reg')  
plt.show()   

#构建数据集
X=data.drop(['Number','sales'],axis=1)
X.head()

sales=data['sales']
type(sales)

#拆分训练集和测试集
from sklearn.model_selection import train_test_split    
X_train,X_test, y_train, y_test = train_test_split(X, sales, test_size=0.3,random_state=1)  

from sklearn.linear_model import LinearRegression  
linreg = LinearRegression()  
linreg.fit(X_train, y_train)  

print(linreg.intercept_)  
print(linreg.coef_) 

linreg.score(X_test,y_test) #R^2

模型预测

## 判定系数
print("测试集判定系数:", linreg.score(X_test, y_test))

# 均方误差
from sklearn.metrics import mean_squared_error
print("测试集均方误差:", mean_squared_error(y_test, y_pred))

# 判定系数
from sklearn import metrics 
print("测试集均方误差:", metrics.r2_score(y_test, y_pred))