多元线性模型

#_*_coding:utf-8_*_

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib as mpl   #显示中文
from sklearn.model_selection import train_test_split   #划分数据集
from sklearn.linear_model import LinearRegression   #线性回归
from sklearn import metrics
import numpy as np


def model():
    pd_data=pd.read_csv("C:/Users/Rooobins/Desktop/data.csv")
    X=pd_data.loc[:,("Area","Num")]
    y=pd_data.loc[:,"Money"]
    X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=100)
    linreg=LinearRegression()
    model_Line=linreg.fit(X_train,y_train)
    print(model_Line)
    print(linreg.intercept_)  #训练后模型截距
    print(linreg.coef_)    #训练后模型权重（特征个数无变化）


    #模型预测
    y_pred=linreg.predict(X_test)
    print(y_pred)

    #总差值
    sum_mean=0
    for i in range(len(y_pred)):
        sum_mean+=(y_pred[i]-y_test.values[i])**2
    sum_erro=np.sqrt(sum_mean/len(y_pred))
    print("RMSE BY HAND : ",sum_erro)

    #模型评估
    plt.figure()
    plt.plot(range(len(y_pred)),y_pred,'b',label="predict")
    plt.plot(range(len(y_pred)),y_test,'r',label="test")
    plt.legend(loc="upper right")   #显示图中标签
    plt.xlabel("The number of sales")
    plt.ylabel("value of sales")
    plt.show()



def main():
    model()


if __name__=="__main__":
    main()