线性回归+梯度下降代码复习

import numpy as np
import matplotlib.pyplot as plt

x_data = [1.0,2.0,3.0]
y_data = [3.0,5.0,7.0]

def forward(x):
    return x * w   #定义回归模型

def loss(x,y):
    y_pred = forward(x)   #求模型对于的y值
    return (y_pred - y) ** 2

w_list = []   #定义空列表，用来储存随机取得的权重值
mse_list = []   #用来存储求得的损失值

for w in np.arange(0.0,4.1,0.1):
    print("w",w)
    l_sum = 0
    for x,y in zip(x_data,y_data):
        y_pred = forward(x)
        loss_val = loss(x,y)
        l_sum += loss_val
        print("\t",x,y,y_pred,loss_val)
    print("MSE=",l_sum / 3)
    w_list.append(w)
    mse_list.append(l_sum / 3)

plt.plot(w_list,mse_list)
plt.xlabel("w")
plt.ylabel("loss")
plt.show()

import numpy as np
import matplotlib.pyplot as plt

x_data = [1.0,2.0,3.0]
y_data = [3.0,5.0,7.0]

def forward(x):
    return x * w + b   #定义回归模型

def loss(x,y):
    y_pred = forward(x)   #求模型对于的y值
    return (y_pred - y) * (y_pred -y)

w_list = []   #定义空列表，用来储存随机取得的权重值
mse_list = []   #用来存储求得的损失值
b_list = []

for w in np.arange(0.0,4.1,0.1):
    for b in np.arange(0,4.1,0.1):
        print("b=",b)
        print("w=",w)
        l_sum = 0
        for x,y in zip(x_data,y_data):
            y_pred = forward(x)
            loss_val = loss(x,y)
            l_sum += loss_val
            print("\t",x,y,y_pred,loss_val)
        print("MSE=",l_sum / 3)
        w_list.append(w)
        mse_list.append(l_sum / 3)
        b_list.append(b)

from mpl_toolkits.mplot3d import Axes3D    
ax = Axes3D(plt.figure())              # fig = plt.figure()# ax = Axes3D(fig) 
ax.plot_trisurf(w_list,b_list,mse_list)        #plt.plot()
ax.set_xlabel("w")
ax.set_ylabel('b')
ax.set_zlabel("loss")
plt.show()

# # 2.梯度下降
import matplotlib.pyplot as plt

x_data = [1.0,2.0,3.0]
y_data = [2.0,4.0,6.0]

w = 0.5#猜测初始权值

def forward(x):
    return x * w

def cost(xs,ys):
    cost = 0
    for x,y in zip(xs,ys):
        y_pred =forward(x)
        cost += (y_pred - y)**2
    return cost / len(xs)

def gradient(xs,ys):
    grad = 0
    for x,y in zip(xs,ys):
        grad +=2*x*(x*w-y)
    return grad / len(xs)

epoch_list = []
loss_list = []
print("Predict(before training)",4,forward(4))

for epoch in range(100):
    cost_val = cost(x_data,y_data)
    grad = gradient(x_data,y_data)
    w -= 0.01 * grad
    print("Epoch:",epoch,"w=",w,"loss=",cost_val)
    epoch_list.append(epoch)
    loss_list.append(cost_val)
print("Predict (after training)",4,forward(4))

plt.plot(epoch_list,loss_list)
plt.ylabel("loss")
plt.xlabel("epoch")
plt.show()

import matplotlib.pyplot as plt
import numpy as np

x_data = [1.0,2.0,3.0]
y_data = [3.0,5.0,7.0]

w = 3

def forward(x):
    for b in np.arange(0,4.1,0.1):
        return x * w + b

def loss(xs,ys):
    y_pred = forward(x)
    return (y_pred - y)**2
     

def gradient(xs,ys):
    return 2*x*(x*w-y)

epoch_list = []
loss_list = []
b_list = []

print("Predict(before training)",4,forward(4))

for b in np.arange(0,4.1,0.1):
    for epoch in range(100):
        for x,y in zip(x_data,y_data):
            grad = gradient(x,y)
            w -= 0.1*grad
            print("\t grad:",x,y,grad)
            l=loss(x,y)
        
        print("Epoch:",epoch,"w=",w,"loss=",l,"b=",b)
        epoch_list.append(epoch)
        loss_list.append(l)
        b_list.append(b)
    print("Predict (after training)",4,forward(4))

from mpl_toolkits.mplot3d import Axes3D
ax = Axes3D(plt.figure())
ax.set_ylabel("b")
ax.set_xlabel('epoch')
ax.set_zlabel("loss")
ax.plot_trisurf(epoch_list,b_list,loss_list)
plt.show()