白话机器学习的数学-多项式回归

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]
# 标准化
mu = train_x.mean()
sigma = train_x.std()
def standardize(x):
    return (x - mu)/sigma
train_z = standardize(train_x)

# 初始化参数
theta = np.random.rand(3)
# 学习率
ETA = 1e-3
# 误差的差值
diff = 1

# 创建训练数据的矩阵
def to_matrix(x):
    return  np.vstack([np.ones(x.shape[0]),x,x ** 2]).T
X = to_matrix(train_z)

#预测函数
def f(x):
    return np.dot(x,theta)
#目标函数
def E(x,y):
    return 0.5*np.sum((y-f(x))**2)
#定义均方误差函数
def MSE(x,y):
    return (1/x.shape[0])*sum((y-f(x))**2)
#重复学习
error=E(X,train_y)
errors=[]
while diff >1e-2:
    theta=theta-ETA*np.dot(f(X)-train_y,X)
    current_error=E(X,train_y)
    diff = error-current_error
    error = current_error
    errors.append(MSE(X,train_y))
#绘制拟合曲线
x = np.linspace(-3, 3, 100)
plt.plot(train_z, train_y, 'o')
plt.plot(x, f(to_matrix(x)))
plt.show()
#绘制误差变化图
x = np.arange(len(errors))
plt.plot(x, errors)
plt.show()