目录
1.梯度下降作业
1.单元函数
1.手写版本
2.代码版本
1.
import numpy as np
import matplotlib.pyplot as plt
# f的函数值
def f(x):
return x ** 2 * 0.5 -2 * x + 3
def d_f(x):
return (x - 2)
#定义梯度下降算法
def gradient_descent():
times = 100 # 迭代次数
alpha = 0.1 # 学习率
x =10# 设定x的初始值
x_axis = np.linspace(-10, 10) #设定x轴的坐标系
fig = plt.figure(1,figsize=(5,5)) #设定画布大小
ax = fig.add_subplot(1,1,1) #设定画布内只有一个图
ax.set_xlabel('X', fontsize=14)
ax.set_ylabel('Y', fontsize=14)
ax.plot(x_axis,f(x_axis)) #作图
#进行迭代
for i in range(times):
x1 = x
y1= f(x)
print("第%d次迭代:x=%f,y=%f" % (i + 1, x, y1))
x = x - alpha * d_f(x) #更新x
y = f(x) #更新y
ax.plot([x1,x], [y1,y], 'ko', lw=1, ls='-', color='coral')
plt.show()
if __name__ == "__main__":
gradient_descent()
结果:
2.
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
#求fx的函数值
def fx(x, y):#定义函数
return (x - 10) ** 2 + (y - 10) ** 2
def d_fx(x,y):#对x的偏导
return 2 * (x - 10)
def d_fy(x,y):#对y的偏导
return 2 * (y - 10)
def gradient_descent():
times = 100 # 迭代次数
alpha = 0.1 # 学习率
x = 20 # x的初始值
y = 20 # y的初始值
#绘图操作
fig = Axes3D(plt.figure()) # 将画布设置为3D
axis_x = np.linspace(0, 20, 100)#设置X轴取值范围
axis_y = np.linspace(0, 20, 100)#设置Y轴取值范围
axis_x, axis_y = np.meshgrid(axis_x, axis_y) #将数据转化为网格数据
z = fx(axis_x, axis_y)#计算Z轴数值
fig.set_xlabel('X', fontsize=14)
fig.set_ylabel('Y', fontsize=14)
fig.set_zlabel('Z', fontsize=14)
fig.view_init(elev=60,azim=300)#设置3D图的俯视角度,方便查看梯度下降曲线
fig.plot_surface(axis_x, axis_y, z, rstride=1, cstride=1, cmap=plt.get_cmap('rainbow')) #作出底图
#计算极值
for i in range(times):
x1 = x
y1 = y
f1 = fx(x, y)
print("第%d次迭代:x=%f,y=%f,f=%f" % (i + 1, x1, y1, f1))
#print(f"第{i+1}次迭代: x={x} y={y} fxy={f1}")
x = x - alpha * 2 * d_fx(x,y)#更新x
y = y - alpha * 2 * d_fy(x,y)#更新y
f = fx(x, y)#更新f
fig.plot([x1, x], [y1, y], [f1, f], 'ko', lw=2, ls='-')#绘制点
plt.show()#展示图像
if __name__ == "__main__":
gradient_descent()
2.线性回归作业
# 房屋价格与面积
# 序号:1 2 3 4 5 6 7
# 面积:150 200 250 300 350 400 600
# 价格:6450 7450 8450 9450 11450 15450 18450
import matplotlib.pyplot as plt
import matplotlib
from math import pow
from random import uniform
import random
x0 = [150, 200, 250, 300, 350, 400, 600]
y0 = [6450, 7450, 8450, 9450, 11450, 15450, 18450]
# 为了方便计算,将所有数据缩小 100 倍
x = [1.50, 2.00, 2.50, 3.00, 3.50, 4.00, 6.00]
y = [64.50, 74.50, 84.50, 94.50, 114.50, 154.50, 184.50]
# 线性回归函数为 y=theta0+theta1*x
# 参数定义
theta0 = 0.1 # 对 theata0 赋值
theta1 = 0.1 # 对 theata1 赋值
alpha = 0.1 # 学习率
m = len(x)
count0 = 0
theta0_list = []
theta1_list = []
# 使用批量梯度下降法
for num in range(10000):
count0 += 1
diss = 0 # 误差
deriv0 = 0 # 对 theata0 导数
deriv1 = 0 # 对 theata1 导数
# 求导
for i in range(m):
deriv0 += (theta0 + theta1 * x[i] - y[i]) / m
deriv1 += ((theta0 + theta1 * x[i] - y[i]) / m) * x[i]
# 更新 theta0 和 theta1
for i in range(m):
theta0 = theta0 - alpha * ((theta0 + theta1 * x[i] - y[i]) / m)
theta1 = theta1 - alpha * ((theta0 + theta1 * x[i] - y[i]) / m) * x[i]
# 求损失函数 J (θ)
for i in range(m):
diss = diss + (1 / (2 * m)) * pow((theta0 + theta1 * x[i] - y[i]), 2)
theta0_list.append(theta0 * 100)
theta1_list.append(theta1)
# 如果误差已经很小,则退出循环
if diss <= 100:
break
theta0 = theta0 * 100 # 前面所有数据缩小了 100 倍,所以求出的 theta0 需要放大 100 倍,theta1 不用变
# 使用随机梯度下降法
theta2 = 0.1 # 对 theata2 赋值
theta3 = 0.1 # 对 theata3 赋值
count1 = 0
theta2_list = []
theta3_list = []
for num in range(10000):
count1 += 1
diss = 0 # 误差
deriv2 = 0 # 对 theata2 导数
deriv3 = 0 # 对 theata3 导数
# 求导
for i in range(m):
deriv2 += (theta2 + theta3 * x[i] - y[i]) / m
deriv3 += ((theta2 + theta3 * x[i] - y[i]) / m) * x[i]
# 更新 theta0 和 theta1
for i in range(m):
theta2 = theta2 - alpha * ((theta2 + theta3 * x[i] - y[i]) / m)
theta3 = theta3 - alpha * ((theta2 + theta3 * x[i] - y[i]) / m) * x[i]
# 求损失函数 J (θ)
rand_i = random.randrange(0, m)
diss = diss + (1 / (2 * m)) * pow((theta2 + theta3 * x[rand_i] - y[rand_i]), 2)
theta2_list.append(theta2 * 100)
theta3_list.append(theta3)
# 如果误差已经很小,则退出循环
if diss <= 0.001:
break
theta2 = theta2 * 100
print("批量梯度下降最终得到theta0={},theta1={}".format(theta0, theta1))
print(" 得到的回归函数是:y={}+{}*x".format(theta0, theta1))
print("随机梯度下降最终得到theta0={},theta1={}".format(theta2, theta3))
print(" 得到的回归函数是:y={}+{}*x".format(theta2, theta3))
# 画原始数据图和函数图
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
plt.plot(x0, y0, 'bo', label='数据', color='black')
plt.plot(x0, [theta0 + theta1 * x for x in x0], label='批量梯度下降', color='red')
plt.plot(x0, [theta2 + theta3 * x for x in x0], label='随机梯度下降', color='blue')
plt.xlabel('x(面积)')
plt.ylabel('y(价格)')
plt.legend()
plt.show()
plt.scatter(range(count0), theta0_list, s=1)
plt.scatter(range(count0), theta1_list, s=1)
plt.xlabel('上方为theta0,下方为theta1')
plt.show()
plt.scatter(range(count1), theta2_list, s=3)
plt.scatter(range(count1), theta3_list, s=3)
plt.xlabel('上方为theta0,下方为theta1')
plt.show()