import numpy as np
import torch
from torch.utils import data
from d2l import torch as d2l
from torch import nn


# 生成线性样本
def synthetic_data(w, b, num_examples):
    """生成y = Xw + b + e"""
    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))


true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = d2l.synthetic_data(true_w, true_b, 1000)


# 调用框架现有的API来读取数据
def load_array(data_arrays, batch_size, is_train=True):
    """
    构造一个PyTorch数据迭代器
    :param data_arrays:
    :param batch_size:
    :param is_train:
    :return:
    """
    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))

net = nn.Sequential(nn.Linear(2, 1))
net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)
# 计算均方误差使用的MSELoss类，也称为平方范数
loss = nn.MSELoss()
# 实例化SGD实例
trainer = torch.optim.SGD(net.parameters(), lr=0.03)


# 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}')