P3回归模型
主要针对回归的定义、回归模型的三个构建步骤及优化模型的三个步骤进行说明,在优化模型中,构建一元N次线性模型和增加特征值的方法都有可能带来过拟合的问题,对过拟合的规律进行了说明。本节含有较多公式推理,未做叙述。P3内容见图片。
P4回归案例的计算
代码链接:回归代码演示
import numpy as np
import matplotlib.pyplot as plt
from pylab import mpl
# matplotlib没有中文字体,动态解决
plt.rcParams['font.sans-serif'] = ['Simhei'] # 显示中文
mpl.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题
x_data = [338., 333., 328., 207., 226., 25., 179., 60., 208., 606.]
y_data = [640., 633., 619., 393., 428., 27., 193., 66., 226., 1591.]
x_d = np.asarray(x_data)
y_d = np.asarray(y_data)
x = np.arange(-200, -100, 1)
y = np.arange(-5, 5, 0.1)
Z = np.zeros((len(x), len(y)))
X, Y = np.meshgrid(x, y) # 生成网格点坐标矩阵
# loss
for i in range(len(x)):
for j in range(len(y)):
b = x[i]
w = y[i]
Z[j][i] = 0 # # meshgrid吐出结果:y为行,x为列
for n in range(len(x_data)):
Z[j][i] += (y_data[n] - b - w * x_data[n]) ** 2
Z[j][i] /= len(x_data)
# 计算梯度微分的函数getGrad()
def getGrad(b,w):
# initial b_grad and w_grad
b_grad = 0.0
w_grad = 0.0
for i in range(10):
b_grad += (-2.0) * (y_data[i] - (b + w * x_data[i]))
w_grad += (-2.0 * x_data[i]) * (y_data[i] - (b + w * x_data[i]))
return (b_grad,w_grad)
# 开始训练
# y_data = b + w * x_data
b = -120 # initial b
w = -4 # initial w
lr = 0.0000001 # learning rate
iteration = 100000 # 这里直接规定了迭代次数,而不是一直运行到b_grad和w_grad都为0(事实证明这样做不太可行)
# store initial values for plotting,我们想要最终把数据描绘在图上,因此存储过程数据
b_history = [b]
w_history = [w]
# iterations
for i in range(iteration):
# get new b_grad and w_grad
b_grad,w_grad=getGrad(b,w)
# update b and w
b -= lr * b_grad
w -= lr * w_grad
#store parameters for plotting
b_history.append(b)
w_history.append(w)
# plot the figure
plt.contourf(x, y, Z, 50, alpha=0.5, cmap=plt.get_cmap('jet'))
plt.plot([-188.4],[2.67],'x',ms=12, markeredgewidth=3, color='orange')
plt.plot(b_history, w_history,'o-',ms=3,lw=1.5,color='black')
plt.xlim(-200, -100)
plt.ylim(-5,5)
plt.xlabel(r'$b$',fontsize=16)
plt.ylabel(r'$w$',fontsize=16)
plt.show()
给b和w特制化两种learning rate:
# y_data = b + w * x_data
b = -120 # initial b
w = -4 # initial w
lr = 1 # learning rate 放大10倍
lr_b = 0 # b learning rate
lr_w = 0 # b w learning rate
iteration = 100000 # 这里直接规定了迭代次数,而不是一直运行到b_grad和w_grad都为0(事实证明这样做不太可行)
# store initial values for plotting,我们想要最终把数据描绘在图上,因此存储过程数据
b_history = [b]
w_history = [w]
# iterations
for i in range(iteration):
# get new b_grad and w_grad
b_grad,w_grad=getGrad(b,w)
# update b and w
lr_b = lr_b + b_grad ** 2
lr_w = lr_w + w_grad ** 2
b -= lr / np.sqrt(lr_b) * b_grad
w -= lr / np.sqrt(lr_w) * w_grad
#store parameters for plotting
b_history.append(b)
w_history.append(w)
# plot the figure
plt.contourf(x, y, Z, 50, alpha=0.5, cmap=plt.get_cmap('jet'))
plt.plot([-188.4],[2.67],'x',ms=12, markeredgewidth=3, color='orange')
plt.plot(b_history, w_history,'o-',ms=3,lw=1.5,color='black')
plt.xlim(-200, -100)
plt.ylim(-5,5)
plt.xlabel(r'$b$',fontsize=16)
plt.ylabel(r'$w$',fontsize=16)
plt.show()