import numpy as np
from functions import *

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, d_out):
        dx = np.dot(d_out, self.W.T)
        self.dW = np.dot(self.x.T, d_out)
        self.db = np.sum(d_out, 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)
        
        return self.loss
    
    def backward(self, d_out=1):
        batch_size = self.t.shape[0]
        dx = (self.y - self.t) / batch_size
        
        return dx

from gradient import numerical_gradient
from functions import *
from collections import OrderedDict
from dataset import load_mnist

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, d_out):
        d_out[self.mask] = 0
        d_x = d_out
        
        return d_x

class TwoLayerNet:
    def __init__(self, input_size, hidden_size, output_size, weight_init_std = .01):
        self.params = {}
        self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W2'] = weight_init_std * np.random.randn(hidden_size, output_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.lastlayers = 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.lastlayers.forward(y, t)
    
    def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        if t.ndim != 1 : t = np.argmax(t, axis=1)
            
        accuracy = np.sum(y == t) / float(x.shape[0])
        return accuracy
    
    def numerical_gradient(self, x, t):
        loss_W = lambda W: self.loss(x, t)
        
        grads = {}
        grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
        grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
        grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
        grads['b2'] = numerical_gradient(loss_W, self.params['b2'])
        return grads
    
    def gradient(self, x, t):
        # forward
        self.loss(x, t)
        
        # backward
        d_out = 1
        d_out = self.lastlayers.backward(d_out)
        
        layers = list(self.layers.values())
        layers.reverse()
        for layer in layers:
            d_out = layer.backward(d_out)
            
        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
       

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

network = TwoLayerNet(input_size = 784, hidden_size = 50, output_size = 10)

x_batch = x_train[:3]
t_batch = t_train[:3]

grad_numerical = network.numerical_gradient(x_batch, t_batch)
grad_backprop = network.gradient(x_batch, t_batch)

for key in grad_numerical.keys():
    diff = np.average(np.abs(grad_backprop[key] - grad_numerical[key]))
    print(key + ':' + str(diff))

epochs = 10000
train_size = x_train.shape[0]
batch_size = 100
lr = 0.1

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

iter_per_epoch = max(train_size / batch_size, 1)

for epoch in range(epochs+1):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]
    
    # back propagation
    grad = network.gradient(x_batch, t_batch)
    
    #
    for key in ('W1','b1','W2','b2'):
        network.params[key] -= lr * grad[key]
        
    loss = network.loss(x_batch, t_batch)
    train_loss_list.append(loss)
    
    if epoch % iter_per_epoch == 0:
        train_acc = network.accuracy(x_train, t_train)
        test_acc = network.accuracy(x_test, t_test)
        train_acc_list.append(train_acc)
        test_acc_list.append(test_acc)
        print('Epoch {}/{}, Train_acc : {:4f}, Test_acc : {:4f}'.format(epoch, epochs, train_acc, test_acc))