在python中实现次梯度随机下降

我想用一个代价函数实现次梯度和随机下降，计算为数据找到一个完美分类器所需的迭代次数，以及权重（w）和偏差（b）。 数据集是四维的

这是我的成本函数

我得到了成本函数的导数，这里是：

当我运行我的代码时，我会遇到很多错误，请有人帮忙

这是我用python编写的代码

import numpy as np

learn_rate = 1
w = np.zeros((4,1))
b = 0
M = 1000

data = '/Users/labuew/Desktop/dataset.data'

#calculating the gradient

def cal_grad_w(data, w, b):
    for i in range (M):
        sample = data[i,:]
        Ym = sample[-1]
        Xm = sample[0:4]
        if -Ym[i]*(w*Xm+b) >= 0:
            tmp = 1.0
        else:
            tmp = 0
        value = Ym[i]*Xm*tmp
        sum = sum +value
    return sum
def cal_grad_b(data, w, b):
    for i in range (M):
        sample = data[i,:]
        Ym = sample[-1]
        Xm = sample[0:4]
        if -Ym*(w*Xm+b) >= 0:
            tmp = 1.0
        else:
            tmp = 0
        value = Ym[i]*x*tmp
        sum = sum +value
    return sum

if __name__ == '__main__':
    counter = 0
    while 1:
        counter +=1
        dw = cal_grad_w(data, w, b)
        db = cal_grad_b(data, w, b)
        if dw == 0 and db == 0:
            break
        w = w - learn_rate*dw
        b = b - learn_rate *dw
    print(counter,w,b)

---

是否缺少numpy加载功能

data=np.load（'/Users/labuew/Desktop/dataset.data'）

看起来你在做字符串上的数字运算

也

还有4个维度意味着Ym=Xm[3]？您的数据是否为2级，第二级为维度5？[0:4]包括第四维度，即

z = [1,2,3,4]
z[0:4] = [1,2,3,4]

这是我最好的猜测。我对您的数据格式进行了一些有根据的猜测

import numpy as np

learn_rate = 1
w = np.zeros((1,4))
b = 0
M = 1000

#Possible format
#data = np.load('/Users/labuew/Desktop/dataset.data')

#Assumed format
data = np.ones((1000,5))

#calculating the gradient

def cal_grad_w(data, w, b):
    sum = 0
    for i in range (M):
        sample = data[i,:]
        Ym = sample[-1]
        Xm = sample[0:4]
        if -1*Ym*(np.matmul(w,Xm.reshape(4,1))+b) >= 0:
            tmp = 1.0
        else:
            tmp = 0
        value = Ym*Xm*tmp
        sum = sum +value
    return sum.reshape(1,4)
def cal_grad_b(data, w, b):
    sum = 0 
    for i in range (M):
        sample = data[i,:]
        Ym = sample[-1]
        Xm = sample[0:4]
        if -1*Ym*(np.matmul(w,Xm.reshape(4,1))+b) >= 0:
            tmp = 1.0
        else:
            tmp = 0
        value = Ym*tmp
        sum = sum +value
    return sum

if __name__ == '__main__':
    counter = 0
    while 1:
        counter +=1
        dw = cal_grad_w(data, w, b)
        db = cal_grad_b(data, w, b)
        if dw.all() == 0 and db == 0:
            break
        w = w - learn_rate*dw
        b = b - learn_rate*db
        print([counter,w,b])

---

输入虚拟数据，因为我不知道格式。

当我运行代码时，我得到了这个错误；TypeError：字符串索引必须是整数，而不是元组数据是这种形式的我的数据是这种形式的，大约2000行-4.617544237，-2.469679381，-1.967660787,1.813355506，-1-1-1.110968984，-2.592819511,1.149164575,0.572509318，-1。好的，那么你需要做一些字符串解析，然后可能data=np.array（data.split（））？

import numpy as np

learn_rate = 1
w = np.zeros((1,4))
b = 0
M = 1000

#Possible format
#data = np.load('/Users/labuew/Desktop/dataset.data')

#Assumed format
data = np.ones((1000,5))

#calculating the gradient

def cal_grad_w(data, w, b):
    sum = 0
    for i in range (M):
        sample = data[i,:]
        Ym = sample[-1]
        Xm = sample[0:4]
        if -1*Ym*(np.matmul(w,Xm.reshape(4,1))+b) >= 0:
            tmp = 1.0
        else:
            tmp = 0
        value = Ym*Xm*tmp
        sum = sum +value
    return sum.reshape(1,4)
def cal_grad_b(data, w, b):
    sum = 0 
    for i in range (M):
        sample = data[i,:]
        Ym = sample[-1]
        Xm = sample[0:4]
        if -1*Ym*(np.matmul(w,Xm.reshape(4,1))+b) >= 0:
            tmp = 1.0
        else:
            tmp = 0
        value = Ym*tmp
        sum = sum +value
    return sum

if __name__ == '__main__':
    counter = 0
    while 1:
        counter +=1
        dw = cal_grad_w(data, w, b)
        db = cal_grad_b(data, w, b)
        if dw.all() == 0 and db == 0:
            break
        w = w - learn_rate*dw
        b = b - learn_rate*db
        print([counter,w,b])