博雅数据机器学习04

博雅数据机器学习04

线性回归

一元线性回归

import pandas as pd

from sklearn import linear_model

insurance = pd.read_csv('insurance.csv')

age = insurance['age'].values

charges = insurance['charges'].values

# 请在下方作答

# 定义一元线性回归函数

def linearRegression(xArr,yArr):

    mean_x = xArr.mean()

    mean_y = yArr.mean()

    numerator = sum(xArr*yArr) - len(xArr)*mean_x*mean_y

    denominator = sum(xArr*xArr) - len(xArr)*mean_x*mean_x

    w1 = float(numerator)/denominator

    w0 = mean_y - w1*mean_x

    return round(w0,2),round(w1,2)

    

# 模型训练，得到参数值

w0, w1 = linearRegression(age, charges)

# sklearn的训练结果

regr = linear_model.LinearRegression()

regr.fit(age.reshape(-1,1), charges.reshape(-1,1))

print(round(regr.coef_,2))

print(round(regr.intercept_,2))