©2020-2024 ioDraw All rights reserved,
Privacy Policy
最小二乘法的原理与要解决的问题
最小二乘法的矩阵法解法
最小二乘法的几何解释
最小二乘法的局限性和适用场景
最小二乘法的python实战
import numpy as np import scipy as sp from scipy.optimize import leastsq
import matplotlib.pyplot as plt %matplotlib inline
# 目标函数 def real_func(x): return np.sin(2*np.pi*x) #多项式 #ps:
numpy.polyld([1,2,3]) 生成 $1x^2+2x^1+3x^0$* def fit_func(p, x): f = np.poly1d(p)
return f(x) # 残差 def residuals_func(p, x, y): ret = fit_func(p, x) - y
return ret
# 十个点 x = np.linspace(0, 1, 10) x_points = np.linspace(0, 1, 1000) #
加上正态分布噪音的目标函数的值 y_ = real_func(x) y = [np.random.normal(0, 0.1)+y1 for y1 in y_]
def fitting(M=0): """ n 为 多项式的次数 """ # 随机初始化多项式参数 p_init =
np.random.rand(M+1) # 最小二乘法 p_lsq = leastsq(residuals_func, p_init, args=(x,
y)) print('Fitting Parameters:', p_lsq[0]) # 可视化 plt.plot(x_points,
real_func(x_points), label='real') plt.plot(x_points, fit_func(p_lsq[0],
x_points), label='fitted curve') plt.plot(x, y, 'bo', label='noise')
plt.legend() return p_lsq
# M=0 p_lsq_0 = fitting(M=0) Fitting Parameters: [0.01914362]
# M=1 p_lsq_1 = fitting(M=1) Fitting Parameters: [-1.44035975 0.73932349]
# M=3 p_lsq_3 = fitting(M=3) Fitting Parameters: [ 23.32730356 -34.84982011
11.69490865 -0.04614352]
# M=9 p_lsq_9 = fitting(M=9) Fitting Parameters: [-7.72885226e+03
3.20354672e+04 -5.42647096e+04 4.81881349e+04 -2.38777532e+04 6.47385739e+03
-8.52906000e+02 1.74436725e+01 9.47089325e+00 1.35011754e-02]
当M=9时，多项式曲线通过了每个数据点，但是造成了过拟合
正则化
结果显示过拟合， 引入正则化项(regularizer)，降低过拟合
[公式]
回归问题中，损失函数是平方损失，正则化可以是参数向量的L2范数,也可以是L1范数。
L1: regularization*abs(p) L2: 0.5 * regularization * np.square(p)
regularization = 0.0001 def residuals_func_regularization(p, x, y): ret =
fit_func(p, x) - y ret = np.append(ret,
np.sqrt(0.5*regularization*np.square(p))) # L2范数作为正则化项 return ret
# 最小二乘法,加正则化项 p_init = np.random.rand(9+1) p_lsq_regularization =
leastsq(residuals_func_regularization, p_init, args=(x, y))
plt.plot(x_points, real_func(x_points), label='real') plt.plot(x_points,
fit_func(p_lsq_9[0], x_points), label='fitted curve') plt.plot(x_points,
fit_func(p_lsq_regularization[0], x_points), label='regularization')
plt.plot(x, y, 'bo', label='noise') plt.legend() <matplotlib.legend.Legend at
0x214a6542b08>