5.梯度下降算法的实现-原创手记-慕课网

代码1.

import numpy as np 
import matplotlib.pyplot as plt 
#init some data
x_data = np.arange(-10,11).reshape([21,1])
y_data = np.square(x_data) * 3 + x_data * 4  + 5
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.plot(x_data,y_data,lw = 3)
plt.ion()
plt.show()

start_x = 10
step = 0.02
current_x = start_x

current_y = 3 * current_x * current_x + 4 * current_x + 5
print ("(loop_count,current_x,current_y)")
for i in range(10):
	print (i,current_x,current_y)
	der_f_x = 6 * current_x + 4
	current_x = current_x - step * der_f_x
	current_y = 3 * current_x * current_x + 4 * current_x + 5
	ax.scatter(current_x,current_y)
	plt.pause(0.8)

代码2 梯度下降+线性回归

import numpy as np 
import matplotlib.pyplot as plt 


# init some data 
x_data = np.arange(1, 21).reshape([20, 1])
y_data = x_data*3 + 5
# for polt picture
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data, y_data)
plt.ion()
plt.show()

w1 = 0
b1 = 0
step = 0.001
#损失函数： 预测值和实际值的平方和
def cost_function(y_prediction):
    return 1.0/(2 * 20) * np.sum(np.square(y_prediction - y_data))

y_prediction = x_data * w1 + b1
ax.plot(x_data, y_prediction, 'black', lw=3)
m = 20

print("(i, cost_function)")
for i in range(250):
    
    print(i, cost_function(y_prediction))
    
    #记：梯度下降中的权重w和偏执b公式
    derivative_f_w1 = 1.0/m * np.sum(np.multiply(y_prediction - y_data, x_data))
    derivative_f_b1 = 1.0/m * np.sum(y_prediction - y_data)
   
    #更新权重w和偏执b
    w1 = w1 - step * derivative_f_w1
    b1 = b1 - step * derivative_f_b1
    y_prediction = x_data * w1 + b1    
   # try:
       # ax.lines.remove(lines[0])    
   # except Exception:        
    #	pass
    lines = ax.plot(x_data, y_prediction, 'b-', lw=3)
    plt.pause(0.7)
print('w1:', w1, 'b1:', b1)

代码3 梯度下降+线性回归

import pandas as pd
pga=pd.read_csv('./data/pga.csv')
pga.head()

# Data preprocessing
# Normalize the data
# 1.Mean_Std
pga['distance']=(pga['distance']-pga['distance'].mean())/pga['distance'].std()
pga['accuracy']=(pga['accuracy']-pga['accuracy'].mean())/pga['accuracy'].std()
# 2. Min_Max
#pga['distance']=(pga['distance']-pga['distance'].min())/pga['distance'].max()
#pga['accuracy']=(pga['accuracy']-pga['accuracy'].min())/pga['accuracy'].max()


import matplotlib.pyplot as plt
plt.scatter(pga['distance'],pga['accuracy'])
plt.xlabel('normalized distance')
plt.ylabel('normalized accuracy')
plt.show()

# Use linear model to model this data.
from sklearn.linear_model import LinearRegression
import numpy as np

lr=LinearRegression()
lr.fit(pga.distance[:,np.newaxis],pga['accuracy']) 
#也可以这样写
#lr.fit(pga[['distance']],pga['accuracy']) 
theta0=lr.intercept_
theta1=lr.coef_
print(theta0)
print(theta1)

#calculating cost-function for each theta1
#计算平均累积误差
def cost(x,y,theta0,theta1):
    J=0
    for i in range(len(x)):
        mse=(x[i]*theta1+theta0-y[i])**2
        J+=mse
    return J/(2*len(x))
    
theta0=100
theta1s = np.linspace(-3,2,100)
costs=[]
for theta1 in theta1s:
    costs.append(cost(pga['distance'],pga['accuracy'],theta0,theta1))
plt.plot(theta1s,costs)
plt.show()
print(pga.distance)

#调整theta
def partial_cost_theta0(x,y,theta0,theta1):
    #我们的模型时线性拟合函数：y=theta1*x + theta0，而不是sigmoid函数，当非线性时我们可以用sigmoid
    h=theta1*x+theta0  
    diff=(h-y)
    partial=diff.sum()/len(diff)
    return partial
partial0=partial_cost_theta0(pga.distance,pga.accuracy,1,1)
def partial_cost_theta1(x,y,theta0,theta1):
    h=theta1*x+theta0#我们的模型时线性拟合函数：y=theta1*x + theta0，而不是sigmoid函数，当非线性时我们可以用sigmoid
    diff=(h-y)*x
    partial=diff.sum()/len(diff)
    return partial
partial1=partial_cost_theta1(pga.distance,pga.accuracy,0,5)
print(partial0)
print(partial1)


# In[52]:


def gradient_descent(x,y,alpha=0.1,theta0=0,theta1=0):  #设置默认参数
    #计算成本
    #调整权值
    #计算错误代价，判断是否收敛或者达到最大迭代次数
    most_iterations=1000
    convergence_thres=0.000001 
   
    c=cost(x,y,theta0,theta1)
    costs=[c]
    cost_pre=c+convergence_thres+1.0
    counter=0
    while( (np.abs(c-cost_pre)>convergence_thres) & (counter<most_iterations) ):
        
        update0=alpha*partial_cost_theta0(x,y,theta0,theta1)
        update1=alpha*partial_cost_theta1(x,y,theta0,theta1)
        
        theta0-=update0
        theta1-=update1

        cost_pre=c
        c=cost(x,y,theta0,theta1)
        costs.append(c)
        counter+=1
    return  {'theta0': theta0, 'theta1': theta1, "costs": costs}

print("Theta1 =", gradient_descent(pga.distance, pga.accuracy)['theta1'])
costs=gradient_descent(pga.distance,pga.accuracy,alpha=.01)['costs']
print(gradient_descent(pga.distance, pga.accuracy,alpha=.01)['theta1'])
plt.scatter(range(len(costs)),costs)
plt.show()

# result=gradient_descent(pga.distance, pga.accuracy,alpha=.01)
# print("Theta0 =", result['theta0'])
# print("Theta1 =",  result['theta1'])
# costs=result['costs']
# plt.scatter(range(len(costs)),costs)
# plt.show()

数据集地址：
Gradient-Descent-Algorithm-master
链接：https://pan.baidu.com/s/19UO_sD9dn0_1DTM27MgzCw
提取码：4rqp

参考：机器学习实战之梯度下降算法： https://www.imooc.com/article/39831