博雅数据机器学习05

博雅数据机器学习05

多元线性回归

from sklearn import linear_model

from numpy import mat, linalg, column_stack, ones

import pandas as pd

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

# 请在下方作答 #

# 定义多元线性回归函数

def linearRegression(xArr,yArr):

    xMat = mat(xArr)

    yMat = mat(yArr).T

    xTx = xMat.T*xMat

    if linalg.det(xTx) == 0.0:

        print("singular matrix, can't do inverse")

    ws = linalg.solve(xTx, xMat.T*yMat)

    return ws

# 模型训练，得到参数值

X = insurance[['age', 'bmi', 'children']].values

X = column_stack((X,ones(X.shape[0])))

y = insurance['charges']

ws = linearRegression(X, y)

# sklearn的训练结果

regr = linear_model.LinearRegression()

regr.fit(X, y)

print(regr.coef_)

print(regr.intercept_)