白话机器学习的数学-线性回归

import numpy as np
import matplotlib.pyplot as plt

# 读入训练数据
train = np.loadtxt('click.csv',delimiter=',',skiprows=1)
train_x = train[:,0]
train_y = train[:,1]
#参数初始化
theta0 = np.random.rand()
theta1 = np.random.rand()
#预测函数
def f(x):
    return theta0 + theta1 * x
#目标函数
def E(x,y):
    return 0.5*np.sum((y-f(x))**2)
#标准化
mu=train_x.mean()
sigma=train_x.std()
def standardize(x):
    return (x-mu)/sigma
train_z = standardize(train_x)
#学习率
ETA=1e-3
#误差的差值
diff=1
#更新次数
count=0
#重复学习
error=E(train_z,train_y)
while diff>1e-2:
    temp0 = theta0 - ETA*sum(f(train_z)-train_y)
    temp1 = theta1 - ETA * sum((f(train_z) - train_y)*train_z)
    theta0 = temp0
    theta1 = temp1
    current_error = E(train_z,train_y)
    diff = error - current_error
    error = current_error
    count +=1
    #log = '第{}次：theta0 = {:.3f},theta1 = {:.3f},差值 = {:.4f}'
    #print(log.format(count,theta0,theta1,diff))

#绘图确认
x = np.linspace(-3, 3, 100)
plt.plot(train_z, train_y, 'o')
plt.plot(x, f(x))
plt.show()
print(f(standardize(100)))
print(f(standardize(200)))
print(f(standardize(300)))