import random
import torch
from d2l import torch as d2l


def synthetic_data(w, b, num_examples):
    """生成 y = Xw + b + 噪声"""
    X = torch.normal(0, 1, (num_examples, len(w)))
    y = torch.matmul(X, w) + b
    y += torch.normal(0, 0.01, y.shape)  #随机噪音
    return X, y.reshape(-1, 1)


def data_iter(batch_size, features, labels):
    """接受批量大小、特征矩阵和标签向量为输入，生成大小为batch_size的小批量"""
    num_examples = len(features)
    indices = list(range(num_examples))
    # 这些样本是随机读取的，没有特定顺序
    random.shuffle(indices)  #随机打乱样本
    for i in range(0, num_examples, batch_size):
        batch_indices = torch.tensor(indices[i:min(i + batch_size, num_examples)])  #挑选大小为batch_size的小批量
        yield features[batch_indices], labels[batch_indices]


def linreg(X, w, b):
    """线性回归模型"""
    return torch.matmul(X, w) + b  #返回预测值


def square_loss(y_hat, y):
    """均方损失"""
    return (y_hat - y.reshape(y_hat.shape))**2 / 2


def sgd(params, lr, batch_size):
    """小批量随机梯度下降"""
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()



true_w = torch.tensor([2, -3.4]).reshape(-1, 1)
true_b = 4.2
features, labels = synthetic_data(true_w, true_b, 1000)

"""
打印生成数据集的结果
print('features:', features[0], '\nlabels:', labels[0])
d2l.set_figsize()
d2l.plt.scatter(features[:, 1].detach().numpy(), labels.detach().numpy(), 1)
d2l.plt.show()
"""

batch_size = 10
"""
for X, y in data_iter(batch_size, features, labels):
    print(X, '\n', y)
    break
"""

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

#开始训练！
lr = 0.03
num_epochs = 3
net = linreg
loss = square_loss

for epoch in range(num_epochs):
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y) # X 和 y 小批量损失
        l.sum().backward()
        sgd([w, b], lr, batch_size)
    with torch.no_grad():
        train_l = loss(net(features, w, b), labels)
        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}')