监督学习之随机梯度下降法20211112

import numpy as np
import random
import math
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D 

seita0 = random.randint(0,1)
seita1 = random.randint(0,1)
seita2 = random.randint(0,1)
eg = 1e-4
alpha = 0.01
delta0 = 1
delta1 = 1
delta2 = 1
x1 = np.array([2104,1600,2400,1416,3000])
x2 = np.array([3,3,3,2,4])
t = np.array([400,330,369,232,540])
h = 0
  
if delta0>eg or delta1>eg or delta2>eg:
    
    i = random.randint(0,4)
    h = seita0 + seita1*x1[i] + seita2*x2[i]
    delta0 = h - t[i]
    delta1 = (h - t[i] + delta0)*x1[i]
    delta2 = ((h - t[i])*4)*x2[i]

else:   
    seita0 = seita0 - alpha*delta0
    seita1 = seita1 - alpha*delta1
    seita2 = seita2 - alpha*delta2
    
print(seita0,seita1,seita2)

fig0=plt.figure() 
ax=Axes3D(fig0)
X1,X2=np.mgrid[0:10000:500j, 0:50:500j]
h=seita0+(seita1*X1+seita2*X2)
plt.title("houseprice") 
ax.plot_surface(X1, X2, h , rstride=1, cstride=1, cmap=plt.cm.coolwarm, alpha=0.5) 
ax.set_xlabel('square', color='b')
ax.set_ylabel('room', color='g')
ax.set_zlabel('price', color='r')
plt.show()

2.64813275 8722.93412981 21.78034944