线性回归python实操_python之线性回归

#coding=gbk

import numpy as np

from numpy.linalg import inv

from numpy importdot

from numpy importmat

import pandas as pd

#获取X和Y向量

dataset = pd.read_csv('data.csv')

#print(dataset)

temp = dataset.iloc[:,0:3]#取数据集中

temp['x0'] = 1#截距

X = temp.iloc[:,[3,0,1,2]]

Y = dataset.iloc[:,3].values.reshape(200,1)

#Y =dataset.iloc[:,3].values.reshape(200,1)

#print(Y)

#最小二乘法

theta = dot(dot(inv(dot(X.T,X)),X.T),Y)

print("最小二乘法计算theta:\n",theta.reshape(4,1))

#梯度下降法

theta = np.array([1.,1.,1.,1.]).reshape(4,1)

alpha = 0.02#学习率

temp = theta #缓存，一块同步更新，很重要

X0 = X.iloc[:,0].values.reshape(len(Y),1)

X1 = X.iloc[:,1].values.reshape(len(Y),1)

X2 = X.iloc[:,2].values.reshape(len(Y),1)

X3 = X.iloc[:,3].values.reshape(len(Y),1)

for i in range(10000):

temp[0] = theta[0] + alpha*np.sum((Y-dot(X,theta))*X0)/200.

temp[1] = theta[1] + alpha*np.sum((Y-dot(X,theta))*X1)/200.

temp[2] = theta[2] + alpha*np.sum((Y-dot(X,theta))*X2)/200.

temp[3] = theta[3] + alpha*np.sum((Y-dot(X,theta))*X3)/200.

theta = temp

print ("梯度下降法计算theta:",theta)