如何从0开始创建一个线性回归模型（附代码）

虽然在实际应用中不一定会用到从0建立一个线性模型，但是为了更好的了解各部分的功能，我们从0建立一个线性回归模型

1、导入相应的包

%matplotlib inline#默认嵌入到notebook里面

import random

import torch

from d2l import torch as d2l

1. 生成数据集

def synthetic_data(w,b,num_examples):

    '''根据带有噪声的线性模型构造一个人造数据集

    生成y = Xw +b+噪声'''

    x = torch.normal(0,1,(num_examples,len(w)))#均值为0方差为1的随机数，n个样本，len（w）列

    y = torch.matmul(X,w)+b#matmul矩阵运算

    y+= torch.normal(0,0.01,y.shape)#噪音函数

    return X,y.reshape((-1,1))#-1表示自动计算维度的大小

true_w = torch.tensor([2,-3.4])

true_b = 4.2

features,labels = synthetic_data(true_w,true_b,1000)

3、读取数据

#读取数据

def data_iter(batch_size,features,labels):

    num_examples = len(features)

    indices = list(range(num_examples))

    random.shuffle(indices)

    for i in range(0,num_examples,batch_size):

        batch_indices = torch.tensor(

            indices[i:min(i+batch_size,num_examples)])

        yield features[batch_indices],labels[batch_indices]

batch_size = 10

for X,y in data_iter(batch_size,features,labels):

    print(X,'\n',y)

Break

4、初始化模型参数

#初始化模型参数

w = torch.normal(0,0.01,size=(2,1),requires_grad= True)

b = torch.zeros(1,requires_grad = True)

6、定义模型

def linger(X,w,b):

    return torch.matmul(X,y)+b

7、定义损失函数

def squared_loss(y_hat,y):

    return (y_hat-y.reshape(y_hat.shape))**2/2

1. 定义优化算法

def sgd(params,lr,batch_size):

    for param in params:

        param -= lr*param.grad/batch_size

        param.grad.zero_()

1. 训练过程

#设置超参数

lr =0.03

num_epochs=3

net = linger

loss = squared_loss

for epoch in range(num_epochs):

    for X,y in data_iter(batch_size,features,labels):

        l = loss(net(X,w,b),y)

        l.sum().backward()

        sgd([w,b],lr,batch_size)#使用参数的梯度更新参数

    with torch.no_grad():

        train_l = loss(net(features,w,b),labels)

        print(f'epoch{epoch+1},loss{float(train_l.mean()):f}')