# Python backpropagation neural network 16 first prime numbers simulation
# Originally from http://a...content-available-to-author-only...x.com/nas/python/bpnn.py

import math
import random
import string

random.seed(0)

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

def makeMatrix(I, J, fill=0.0):
    m = []
    for i in range(I):
        m.append([fill]*J)
    return m

# Orginally tanh, changed to unipolar sigmoid function
def sigmoid(x):
    return 1 / (1 + math.exp(-x))

# derivative of unipolar sigmoid function
def dsigmoid(y):
    return y - y**2

class NN:
    def __init__(self, ni, nh, no):
        self.ni = ni + 1 # +1 for bias node
        self.nh = nh
        self.no = no

        self.ai = [1.0]*self.ni
        self.ah = [1.0]*self.nh
        self.ao = [1.0]*self.no
        
        self.wi = makeMatrix(self.ni, self.nh)
        self.wo = makeMatrix(self.nh, self.no)

        for i in range(self.ni):
            for j in range(self.nh):
                self.wi[i][j] = rand(-0.2, 0.2)
        for j in range(self.nh):
            for k in range(self.no):
                self.wo[j][k] = rand(-2.0, 2.0)

        self.ci = makeMatrix(self.ni, self.nh)
        self.co = makeMatrix(self.nh, self.no)

    def update(self, inputs):
        if len(inputs) != self.ni-1:
            raise ValueError('wrong number of inputs')

        for i in range(self.ni-1):
            self.ai[i] = inputs[i]

        for j in range(self.nh):
            sum = 0.0
            for i in range(self.ni):
                sum = sum + self.ai[i] * self.wi[i][j]
            self.ah[j] = sigmoid(sum)

        for k in range(self.no):
            sum = 0.0
            for j in range(self.nh):
                sum = sum + self.ah[j] * self.wo[j][k]
            self.ao[k] = sigmoid(sum)

        return self.ao[:]


    def backPropagate(self, targets, N, M):
        if len(targets) != self.no:
            raise ValueError('wrong number of target values')

        output_deltas = [0.0] * self.no
        for k in range(self.no):
            error = targets[k]-self.ao[k]
            output_deltas[k] = dsigmoid(self.ao[k]) * error

        hidden_deltas = [0.0] * self.nh
        for j in range(self.nh):
            error = 0.0
            for k in range(self.no):
                error = error + output_deltas[k]*self.wo[j][k]
            hidden_deltas[j] = dsigmoid(self.ah[j]) * error

        for j in range(self.nh):
            for k in range(self.no):
                change = output_deltas[k]*self.ah[j]
                self.wo[j][k] = self.wo[j][k] + N*change + M*self.co[j][k]
                self.co[j][k] = change

        for i in range(self.ni):
            for j in range(self.nh):
                change = hidden_deltas[j]*self.ai[i]
                self.wi[i][j] = self.wi[i][j] + N*change + M*self.ci[i][j]
                self.ci[i][j] = change

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

    # changed to display prime numbers test
    def test(self, patterns):
        for p in patterns:
            output = self.update(p[0])
            number = p[0][0] * 8 + p[0][1] * 4 + p[0][2] * 2 + p[0][3]
            prime = round(p[1][0]) * 32 + round(p[1][1]) * 16 + round(p[1][2]) * 8 \
            + round(p[1][3]) * 4 + round(p[1][4]) * 2 + round(p[1][5])
            print('%d -> %d' % (number + 1, int(prime)))

    def train(self, patterns, iterations=1000, N=0.5, M=0.1):
        # N: learning rate
        # M: momentum factor
        for i in range(iterations):
            error = 0.0
            for p in patterns:
                inputs = p[0]
                targets = p[1]
                self.update(inputs)
                error = error + self.backPropagate(targets, N, M)
            if i % 100 == 0:
                print('error %-.5f' % error)


def demo():
    # Teach network prime number function
    pat = [
        [[0,0,0,0], [0,0,0,0,1,0]], #2
        [[0,0,0,1], [0,0,0,0,1,1]], #3
        [[0,0,1,0], [0,0,0,1,0,1]], #5
        [[0,0,1,1], [0,0,0,1,1,1]], #7
        [[0,1,0,0], [0,0,1,0,1,1]], #11
        [[0,1,0,1], [0,0,1,1,0,1]], #13
        [[0,1,1,0], [0,1,0,0,0,1]], #17
        [[0,1,1,1], [0,1,0,0,1,1]], #19
        [[1,0,0,0], [0,1,0,1,1,1]], #23
        [[1,0,0,1], [0,1,1,1,0,1]], #29
        [[1,0,1,0], [0,1,1,1,1,1]], #31
        [[1,0,1,1], [1,0,0,1,0,1]], #37
        [[1,1,0,0], [1,0,1,0,0,1]], #41
        [[1,1,0,1], [1,0,1,0,1,1]], #43
        [[1,1,1,0], [1,0,1,1,1,1]], #47
        [[1,1,1,1], [1,1,0,1,0,1]], #53
    ]

    n = NN(4, 8, 6)
    n.train(pat, 3000)
    n.test(pat)

if __name__ == '__main__':
    demo()