是自己的作业,自用
# 建立模型,第一列数据作为X1,然后TV为X2,Radio为X3,Newspaper为X4,最后一行Sales为Y
import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
dataSet = pd.read_csv("C:\\WINDOWS\\System32\\Advertising.csv")
# 取出第2, 3, 4列的数据作为X
data_x = dataSet.iloc[:, 1:4].values
# 取出最后一列的数据作为Y
data_y = dataSet.iloc[:, 4:5].values
# 把X, Y分割成为训练集和测试集
X_train, X_test, Y_train, Y_test = train_test_split(data_x, data_y, test_size=0.3)
model = LinearRegression(fit_intercept=True, normalize=False, copy_X=True, n_jobs=1)
model.fit(X_train, Y_train)
# 输出线性方程的参数
print(model.coef_)
# 输出线性方程的截距
print(model.intercept_)