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) #画图用的需要定义x,y轴范围
y = np.arange(-5, 5, 0.1)
Z = np.zeros((len(x), len(y)))
X, Y = np.meshgrid(x, y)
# loss
for i in range(len(x)):
for j in range(len(y)):
b = x[i]
w = y[j]
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)
#先给b和w一个初始值,计算出b和w的偏微分
# linear regression
#b = -120
#w = -4
b=-120
w=-4
lr = 0.0000001
iteration = 100000
b_history = [b]
w_history = [w]
loss_history = []
import time
start = time.time()
for i in range(iteration):
m = float(len(x_d))
grad_b = 0.0
grad_w = 0.0
for n in range(len(x_d)):
y_hat = w * x_d +b#预测的y值
loss = np.dot(y_d - y_hat, y_d - y_hat) / m#矩阵相乘,求损失函数
grad_b =grad_b -2.0 * np.sum(y_d - y_hat) / m
grad_w =grad_w -2.0 * np.dot(y_d - y_hat, x_d) / m
# update param
b -= lr * grad_b
w -= lr * grad_w
b_history.append(b)
w_history.append(w)
loss_history.append(loss)
if i % 10000 == 0:
print("Step %i, w: %0.4f, b: %.4f, Loss: %.4f" % (i, w, b, loss))
end = time.time()
print("大约需要时间:",end-start)
# plot the figure
plt.contourf(x, y, Z, 50, alpha=0.5, cmap=plt.get_cmap('jet')) # 填充等高线
plt.plot([-188.4], [2.67], 'x', ms=12, mew=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'$b$')
plt.ylabel(r'$w$')
plt.title("线性回归")
plt.show()
result:

优化参数后
横坐标是b,纵坐标是w,标记×位最优解,显然,在图中我们并没有运行得到最优解,最优解十分的遥远。那么我们就调大learning rate,lr = 0.00001(调大10倍),得到结果如下图。

结果发现learning rate太大了,结果很不好。
所以我们给b和w特制化两种learning rate
# linear regression
b = -120
w = -4
lr = 1
iteration = 100000
b_history = [b]
w_history = [w]
lr_b=0
lr_w=0
import time
start = time.time()
for i in range(iteration):
b_grad=0.0
w_grad=0.0
for n in range(len(x_data)):
b_grad=b_grad-2.0*(y_data[n]-n-w*x_data[n])*1.0
w_grad= w_grad-2.0*(y_data[n]-n-w*x_data[n])*x_data[n]
lr_b=lr_b+b_grad**2
lr_w=lr_w+w_grad**2
# update param
b -= lr/np.sqrt(lr_b) * b_grad
w -= lr /np.sqrt(lr_w) * w_grad
b_history.append(b)
w_history.append(w)
本文通过实例演示了如何使用Python实现线性回归,包括初始化参数、计算损失函数和梯度下降过程。探讨了不同学习率对模型训练的影响,并介绍了如何为参数b和w定制不同的学习率。
2万+

被折叠的 条评论
为什么被折叠?



