from dataset.minist import load_mnist
import numpy as np
from collections import OrderedDict


def softmax(x):
    if x.ndim == 2:
        x = x.T
        x -= np.max(x, axis=0)
        y = np.exp(x) / np.sum(np.exp(x), axis=0)
        return y.T

    x -= np.max(x)
    return np.exp(x) / np.sum(np.exp(x))


def cross_entropy_error(y, t):
    if y.ndim == 1:
        t = t.reshape(1, t.size)
        y = y.reshape(1, y.size)

    if t.size == y.size:
        t = t.argmax(axis=1)

    batch_size = y.shape[0]

    return -np.sum(np.log(y[np.arange(batch_size), t])) / batch_size


class Relu:
    def __init__(self):
        self.mask = None

    def forward(self, x):
        self.mask = (x <= 0)
        out = x.copy()
        out[self.mask] = 0

        return out

    def backward(self, dout):
        dout[self.mask] = 0
        dx = dout

        return dx


class Affine:
    def __init__(self, W, b):
        self.W = W
        self.b = b
        self.x = None
        self.dW = None
        self.Db = None

    def forward(self, x):
        self.x = x
        out = np.dot(x, self.W) + self.b

        return out

    def backward(self, dout):
        dx = np.dot(dout, self.W.T)
        self.dW = np.dot(self.x.T, dout)
        self.db = np.sum(dout, axis=0)

        return dx


class SoftmaxWithLoss:
    def __init__(self):
        self.loss = None
        self.y = None
        self.t = None

    def forward(self, x, t):
        self.t = t
        self.y = softmax(x)
        self.loss = cross_entropy_error(self.y, self.t)

    def backward(self, dout=1):
        batch_size = self.t.shape[0]
        if self.t.size == self.y.size:
            dx = (self.y - self.t) / batch_size
        else:
            dx = self.y.copy()
            dx[np.arrange(batch_size), self.t] -= 1
            dx = dx / batch_size

        return dx


class TwoLayerNet:
    def __init__(self, input_size, hidden_size, output_size,
                 weight_init_std=1.0):
        self.params = OrderedDict()
        self.params['W1'] = weight_init_std * \
                            np.random.randn(input_size, hidden_size) / np.sqrt(input_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W2'] = weight_init_std * \
                            np.random.randn(hidden_size, output_size) / np.sqrt(input_size)
        self.params['b2'] = np.zeros(output_size)

        self.layers = OrderedDict()
        self.layers['Affine1'] = \
            Affine(self.params['W1'], self.params['b1'])
        self.layers['Relu1'] = Relu()
        self.layers['Affine2'] = \
            Affine(self.params['W2'], self.params['b2'])

        self.lastLayer = SoftmaxWithLoss()

    def predict(self, x):
        for layer in self.layers.values():
            x = layer.forward(x)

        return x

    def loss(self, x, t):
        y = self.predict(x)

        return self.lastLayer.forward(y, t)

    def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        t = np.argmax(t, axis=1)

        return np.sum(y == t) / float(x.shape[0])

    def gradient(self, x, t):
        self.loss(x, t)

        dout = 1
        dout = self.lastLayer.backward(dout)

        layers = list(self.layers.values())
        layers.reverse()
        for layer in layers:
            dout = layer.backward(dout)

        grads = {}
        grads['W1'] = self.layers['Affine1'].dW
        grads['b1'] = self.layers['Affine1'].db
        grads['W2'] = self.layers['Affine2'].dW
        grads['b2'] = self.layers['Affine2'].db

        return grads


class SGD:
    def __init__(self, lr=0.1):
        self.lr = lr

    def update(self, params, grads):
        for key in params.keys():
            params[key] -= self.lr * grads[key]


class Momentum:
    def __init__(self, lr=0.1, momentum=0.9):
        self.lr = lr
        self.momentum = momentum
        self.v = None

    def update(self, params, grads):
        if self.v is None:
            self.v = {}
            for key, val in params.items():
                self.v[key] = np.zeros_like(val)

        for key in params.keys():
            self.v[key] = self.momentum * self.v[key] - self.lr * grads[key]
            params[key] += self.v[key]


class AdaGrad:
    def __init__(self, lr=0.1):
        self.lr = lr
        self.h = None

    def update(self, params, grads):
        if self.h is None:
            self.h = {}
            for key, val in params.items():
                self.h[key] = np.zeros_like(val)

        for key in params.keys():
            self.h[key] += grads[key] * grads[key]
            params[key] -= self.lr * grads[key] / (np.sqrt(self.h[key]) + 1e-7)


(x_train, t_train), (x_test, t_test) = \
    load_mnist(normalize=True, one_hot_label=True)

iters_num = 10000
train_size = x_train.shape[0]
batch_size = 100

train_acc_index = []
train_loss_list = []
train_acc_list = []
test_acc_list = []

iter_per_epoch = max(train_size / batch_size, 1)

network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)
# optimizer = SGD()
optimizer = Momentum()
# optimizer = AdaGrad()

for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]

    grad = network.gradient(x_batch, t_batch)

    optimizer.update(network.params, grad)

    loss = network.loss(x_batch, t_batch)
    train_loss_list.append(loss)

    if i % iter_per_epoch == 0:
        train_acc = network.accuracy(x_train, t_train)
        test_acc = network.accuracy(x_test, t_test)
        train_acc_index.append(i)
        train_acc_list.append(train_acc)
        test_acc_list.append(test_acc)

        print("epoc:", i, "    train acc: ", train_acc,
              "    test acc:", test_acc)