bp

import numpy as np
import math
import random
import string
import matplotlib as mpl
import matplotlib.pyplot as plt

def random_number(a, b):
    return (b - a) * random.random() + a


def makematrix(m, n, fill=0.0):
    a = []
    for i in range(m):
        a.append([fill] * n)
    return a


def sigmoid(x):
    return math.tanh(x)


def derived_sigmoid(x):
    return 1.0 - x ** 2


class BPNN:
    def __init__(self, num_in, num_hidden, num_out):
        self.num_in = num_in + 1  
        self.num_hidden = num_hidden + 1  
        self.num_out = num_out

        self.active_in = [1.0] * self.num_in
        self.active_hidden = [1.0] * self.num_hidden
        self.active_out = [1.0] * self.num_out

        self.wight_in = makematrix(self.num_in, self.num_hidden)
        self.wight_out = makematrix(self.num_hidden, self.num_out)

        for i in range(self.num_in):
            for j in range(self.num_hidden):
                self.wight_in[i][j] = random_number(-0.2, 0.2)
        for i in range(self.num_hidden):
            for j in range(self.num_out):
                self.wight_out[i][j] = random_number(-0.2, 0.2)

        self.ci = makematrix(self.num_in, self.num_hidden)
        self.co = makematrix(self.num_hidden, self.num_out)

    def update(self, inputs):
        if len(inputs) != self.num_in - 1:
            raise ValueError('与输入层节点数不符')

        for i in range(self.num_in - 1):
            # self.active_in[i] = sigmoid(inputs[i])  
            self.active_in[i] = inputs[i]  # active_in[]是输入数据的矩阵

        for i in range(self.num_hidden - 1):
            sum = 0.0
            for j in range(self.num_in):
                sum = sum + self.active_in[i] * self.wight_in[j][i]
            self.active_hidden[i] = sigmoid(sum)  # active_hidden[]是处理完输入数据之后存储，作为输出层的输入数据

        for i in range(self.num_out):
            sum = 0.0
            for j in range(self.num_hidden):
                sum = sum + self.active_hidden[j] * self.wight_out[j][i]
            self.active_out[i] = sigmoid(sum)  

        return self.active_out[:]

    def errorbackpropagate(self, targets, lr, m): 
        if len(targets) != self.num_out:
            raise ValueError('与输出层节点数不符！')

        out_deltas = [0.0] * self.num_out
        for i in range(self.num_out):
            error = targets[i] - self.active_out[i]
            out_deltas[i] = derived_sigmoid(self.active_out[i]) * error

        hidden_deltas = [0.0] * self.num_hidden
        for i in range(self.num_hidden):
            error = 0.0
            for j in range(self.num_out):
                error = error + out_deltas[j] * self.wight_out[i][j]
            hidden_deltas[i] = derived_sigmoid(self.active_hidden[i]) * error

        for i in range(self.num_hidden):
            for j in range(self.num_out):
                change = out_deltas[j] * self.active_hidden[i]
                self.wight_out[i][j] = self.wight_out[i][j] + lr * change + m * self.co[i][j]
                self.co[i][j] = change

        for i in range(self.num_in):
            for i in range(self.num_hidden):
                change = hidden_deltas[j] * self.active_in[i]
                self.wight_in[i][j] = self.wight_in[i][j] + lr * change + m * self.ci[i][j]
                self.ci[i][j] = change

        error = 0.0
        for i in range(len(targets)):
            error = error + 0.5 * (targets[i] - self.active_out[i]) ** 2
        return error

    def test(self, patterns):
        for i in patterns:
            print(i[0], '->', self.update(i[0]))

    def weights(self):
        print("输入层权重")
        for i in range(self.num_in):
            print(self.wight_in[i])
        print("输出层权重")
        for i in range(self.num_hidden):
            print(self.wight_out[i])

    def train(self, pattern, itera=100000, lr=0.1, m=0.1):
        for i in range(itera):
            error = 0.0
            for j in pattern:
                inputs = j[0]
                targets = j[1]
                self.update(inputs)
                error = error + self.errorbackpropagate(targets, lr, m)
            if i % 100 == 0:
                print('误差 %-.5f' % error)


def demo():
    patt = [
        [[1, 2, 5], [0]],
        [[1, 3, 4], [1]],
        [[1, 6, 2], [1]],
        [[1, 5, 1], [0]],
        [[1, 8, 4], [1]]
    ]
    n = BPNN(3, 3, 1)
    n.train(patt)
    n.test(patt)
    n.weights()

if __name__ == '__main__':
    demo()