import torch
from IPython import display
from d2l import torch as d2l


batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
num_inputs = 784
num_outputs = 10
# w：均值为0，方差为0.01，形状中，行数为num_inputs，列数为num_outputs
w = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)

# 给定一个矩阵X，可以对所有元素求和
X = torch.tensor([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
X.sum(0, keepdim=True), X.sum(1, keepdim=True)


# 实现softmax
def softmax(X):
    X_exp = torch.exp(X)
    partition = X_exp.sum(1, keepdim=True)
    return X_exp / partition


# 实现softmax回归模型
def net(X):
    return softmax(torch.matmul(X.reshape((-1, w.shape[0]), w)) + b)


# 创建一个数据y_hat，其中包含2个样本在3个类别的预测频率，使用y作为y_hat中概率的索引
y = torch.tensor([0, 2])
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y_hat[[0, 1], y]


# 实现交叉熵损失函数
def cross_entropy(y_hat, y):
    return -torch.log(y_hat[range(len(y_hat)), y])


cross_entropy(y_hat, y)


def accuracy(y_hat, y):
    """
    计算预测正确的数量
    :param y_hat:预测值
    :param y:真实值
    :return:分类正确类别数
    """
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = y_hat.argmax(axis=1)
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())


accuracy(y_hat, y) / len(y)


# 评估任意模型net的准确率
def evaluate_accuracy(net, data_iter):
    """
    计算在指定数据集上模型的精度
    :param net:
    :param data_iter:
    :return:
    """
    if isinstance(net, torch.nn.Module):
        net.eval()  #
    metric = Accumulator(2)
    for X, y in data_iter:
        metric.add(accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]


# 在Accumulator实例中创建了2个变量，用于分别存储正确预测的数量和预测的总数量
class Accumulator:
    """
    在n个变量上累加
    """
    def __init__(self, n):
        self.data = [0.0] * n

    def add(self, *args):
        self.data = [a + float(b) for a, b in zip(self.data, args)]

    def reset(self):
        self.data = [0.0] * len(self.data)

    def __getitem__(self, idx):
        return self.data[idx]


evaluate_accuracy(net, test_iter)


# softmax回归的训练
def train_epoch_ch3(net, train_iter, loss, updater):
    if isinstance(net, torch.nn.Module):
        net.train()
    metric = Accumulator(3)
    for X, y in train_iter:
        y_hat = net(X)
        l = loss(y_hat, y)
        if isinstance(updater, torch.optim.Optimizer):
            updater.zero_grad()
            l.backward()
            updater.step()
            metric.add(
                float(1) * len(y), accuracy(y_hat, y),
                y.size().numel()
            )
        else:
            l.sum().backward()
            updater(X.shape[0])
            metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
    return metric[0] / metric[2], metric[1] / metric[2]


# 定义一个在动画绘制数据的使用程序类
class Animator:
    def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None, ylim=None, xscale='linear',
                 yscale='linear', fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1, figsize=(3.5, 2.5)):
        if legend is None:
            legend = []
        d2l.use_svg_display()
        self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize)
        if nrows*ncols == 1:
            self.axes = [self.axes, ]
        self.config_axes = lambda: d2l.set_axes(self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
        self.X, self.Y, self.fmts = None, None, fmts

        def add(self, x, y):
            if not hasattr(y, "__len__"):
                y = [y]
            n = len(y)
            if not hasattr(x, "__len__"):
                x = [x] * n
            if not self.X:
                self.X = [[] for _ in range(n)]
            if not self.Y:
                self.Y = [[] for _ in range(n)]
            for i, (a, b) in enumerate(zip(x, y)):
                if a is not None and b is not None:
                    self.X[i].append(a)
                    self.Y[i].append(b)
            self.axes[0].cla()
            for x, y, fmt in zip(self.X, self.Y, self.fmts):
                self.axes[0].plot(x, y, fmt)
            self.config_axes()
            display.display(self.fig)
            display.clear_output(wait=True)


# 训练函数
def train_ch3(net, test_iter, loss, num_epochs, updater):
    animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9], legend=['train loss', 'train acc', 'test acc'])
    for epoch in range(num_epochs):
        train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
        test_acc = evaluate_accuracy(net, test_iter)
        animator.add(epoch+1, train_metrics+(test_acc,))
    train_loss, train_acc = train_metrics
    assert train_loss < 0.5, train_loss
    assert train_acc<=1 and train_acc>0.7, train_acc
    assert test_acc<=1 and test_acc>0.7, test_acc


lr = 0.1


def updater(batch_size):
    return d2l.sgd([w, b], lr, batch_size)


num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)
d2l.plt.show()