import numpy as np
import gzip
import pickle
import pandas as pd

class Network(object):
    
    def __init__(self, sizes):
        self.num_layers = len(sizes)
        self.sizes = sizes
        self.biases = [np.random.randn(y, 1) for y in sizes[1:]]
        self.weights = [np.random.randn(y, x) for x,y in zip(sizes[:-1], sizes[1:])]
        
        
        




    def feedforward(self, a):
        
        for b, w in zip(self.biases, self.weights):
            a = sigmoid(np.dot(w, a) + b)
        
        return a
    
    
    def SGD(self, training_data, epochs, mini_batch_size, eta, k, test_data=None):
        if test_data: 
            n_test = len(test_data)

        for j in range(epochs):
            np.random.shuffle(training_data)
            k_fold = self.k_fold_split(training_data, k)

            for fold in range(k):
                validation_data = k_fold[fold]
                train_data = [item for sublist in k_fold[:fold] + k_fold[fold + 1:] for item in sublist]

                for mini_batch in [train_data[k:k+mini_batch_size] for k in range(0, len(train_data), mini_batch_size)]:
                    self.update_mini_batch(mini_batch, eta)
                
                print(f"Epoch {j}, Fold {fold}: {self.evaluate(validation_data)}/{len(validation_data)}")
            
            if test_data:
                print(f"Epoch {j}: {self.evaluate(test_data)}/{n_test}")

    def k_fold_split(self, data, k):
        fold_size = len(data) // k
        return [data[i*fold_size:(i+1)*fold_size] for i in range(k)]
    
    def update_mini_batch(self, mini_batch, eta):
        nabla_b = [np.zeros(b.shape) for b in self.biases]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        
        for x, y in mini_batch:
            delta_nabla_b, delta_nabla_w = self.backdrop(x, y)
            
            nabla_b = [nb+dnb for nb, dnb in zip(nabla_b, delta_nabla_b)]
            nabla_w = [nw+dnw for nw, dnw in zip(nabla_w, delta_nabla_w)]
            
            self.weights = [w-(eta/len(mini_batch))*nw for w, nw in zip(self.weights, nabla_w)]
            self.biases = [b-(eta/len(mini_batch))*nb for b, nb in zip(self.biases, nabla_b)]

    def evaluate(self, test_data): 
        test_results = [(np.argmax(self.feedforward(x)), np.argmax(y)) for (x, y) in test_data]
        return sum(int(x == y) for (x, y) in test_results)
    
    def cost_derivative(self, output_activations, y):
        return output_activations - y
        
    def backdrop(self, x, y):
        nabla_b = [np.zeros(b.shape) for b in self.biases]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        activation = x
        activations = [x]
        zs = []
        
        for b, w in zip(self.biases, self.weights):
            z = np.dot(w, activation)+b
            zs.append(z)
            activation = sigmoid(z)
            activations.append(activation)
        delta = self.cost_derivative(activations[-1], y) * sigmoid_prime(zs[-1])
        nabla_b[-1] = delta
        nabla_w[-1] = np.dot(delta, activations[-2].transpose())
            
        for l in range(2, self.num_layers):
            z = zs[-l]
            sp = sigmoid_prime(z)
            delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
            nabla_b[-l] = delta
            nabla_w[-l] = np.dot(delta, activations[-l-1].transpose())
        return (nabla_b, nabla_w)


def sigmoid(z):
        sig = np.zeros_like(z)
        sig[z >= 0] = 1 / (1 + np.exp(-z[z >= 0]))
        sig[z < 0] = np.exp(z[z < 0]) / (1 + np.exp(z[z < 0]))
        return sig            

def sigmoid_prime(z):   
    return sigmoid(z)*(1-sigmoid(z))





def load_data():
    with gzip.open('C:\\Users\\tt235\\Desktop\\Code\\code\\代码复现\\BP神经网络\\mnist.pkl.gz', 'rb') as f:
        training_data, validation_data, test_data = pickle.load(f, encoding='latin1')

    return (training_data, validation_data, test_data)

def load_data_wrapper():
    tr_d, va_d, te_d = load_data()
    training_inputs = [np.reshape(x, (784, 1)) for x in tr_d[0]]
    training_results = [vectorized_result(y) for y in tr_d[1]]
    training_data = list(zip(training_inputs, training_results))
    validation_inputs = [np.reshape(x, (784, 1)) for x in va_d[0]]
    validation_data = list(zip(validation_inputs, va_d[1]))
    test_inputs = [np.reshape(x, (784, 1)) for x in te_d[0]]
    test_results = [vectorized_result(y) for y in te_d[1]]
    test_data = list(zip(test_inputs, test_results))
    return (training_data, validation_data, test_data)

def vectorized_result(j):
    e = np.zeros((10, 1))
    e[j] = 1.0
    return e


training_data, validation_data, test_data = load_data_wrapper()
net = Network([784, 41, 10])

net.SGD(training_data, 3, 8, 3.0, 5, test_data=test_data)