从零开始实现线性回归
在Google Colab上实现的完整代码
#1. 导入相关模块
!pip install d2l
!pip install matplotlib_inline
%matplotlib inline
import random
import torch
from d2l import torch as d2l
# 2. 生成数据集
'''X为(x11,x12),y为y1'''
def synthetic_data(w,b,num_examples):
X = torch.normal(0,1,(num_examples,len(w)))
y = torch.matmul(X,w)+b
y += torch.normal(0,0.01,y.shape)
return X,y.reshape((-1,1)) #保证y为一列
true_w = torch.tensor([2,-3.4])
true_b = 4.2
features,labels = synthetic_data(true_w,true_b,1000)
print('features:',features[0],'\nlabels:',labels[0])
d2l.set_figsize()
d2l.plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
# 3. 读取数据集
def data_iter(batch_size, features, labels):
num_examples = len(features)
indices = list(range(num_examples))
# 这些样本是随机读取的,没有特定的顺序
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
w = torch.normal(0,0.01,size=(2,1),requires_grad=True)
b = torch.zeros(1,requires_grad=True)
# 5. 定义线性回归模型
def linreg(X,w,b):
return torch.matmul(X,w)+b
# 6. 定义损失函数
def squared_loss(y_hat,y,batch_size):
return (y_hat-y.reshape(y_hat.shape))**2/(2*batch_size)
# 7. 小批量梯度下降优化算法
def sgd(params,lr):
with torch.no_grad():
for param in params:
param -= lr*param.grad
param.grad.zero_()
# 8.训练
lr = 0.03
num_epochs = 3
net = linreg
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,batch_size)
l.sum().backward()
sgd([w,b],lr)
with torch.no_grad():
train_l = loss(net(features,w,b),labels,batch_size)
print(f'epoch {epoch+1},loss {float(train_l.mean()):f}')
print(f'w的估计误差: {true_w - w.reshape(true_w.shape)}')
print(f'b的估计误差: {true_b - b}')
线性回归的简洁实现
# 1.导入包
import numpy as np
import torch
from torch.utils import data
from d2l import torch as d2l
# 2. 生成数据集
'''X为(x11,x12),y为y1'''
def synthetic_data(w,b,num_examples):
X = torch.normal(0,1,(num_examples,len(w)))
y = torch.matmul(X,w)+b
y += torch.normal(0,0.01,y.shape)
return X,y.reshape((-1,1)) #保证y为一列
true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = d2l.synthetic_data(true_w, true_b, 1000)
# 3. 读取数据集
def load_array(data_arrays, batch_size, is_train=True):
"""构造一个PyTorch数据迭代器,
is_train表示是否希望数据迭代器对象在每个迭代周期内打乱数据"""
dataset = data.TensorDataset(*data_arrays)
return data.DataLoader(dataset, batch_size, shuffle=is_train)
batch_size = 10
data_iter = load_array((features, labels), batch_size)
next(iter(data_iter))
# 4. 定义模型
# nn是神经网络的缩写
from torch import nn
net = nn.Sequential(nn.Linear(2, 1))
# 5. 初始化模型参数
net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)
# 6. 定义损失函数
loss = nn.MSELoss()
# 7. 定义优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.03)
# 8. 训练
num_epochs = 3
for epoch in range(num_epochs):
for X, y in data_iter:
l = loss(net(X) ,y)
trainer.zero_grad()
l.backward()
trainer.step()
l = loss(net(features), labels)
print(f'epoch {epoch + 1}, loss {l:f}')
w = net[0].weight.data
print('w的估计误差:', true_w - w.reshape(true_w.shape))
b = net[0].bias.data
print('b的估计误差:', true_b - b)