import numpy as np

trg_inputs = np.array([[0,0,1], [1,1,1],[1,0,1],[0,1,1]])
trg_outputs = np.array([[0,1,1,0]]).T

# single layer
class NeuralNetwork:
    def __init__(self):
        np.random.seed(1)
        self.synaptic_weights = 2 * np.random.random((3,1)) - 1 #the randomiser gives values between 0 and 1

    def __sigmoid(self, x):
        return 1/(1+np.exp(-x))

    def __sigmoid_derivative(self, x):
        return x*(1-x)

    def train(self, trg_inputs, trg_outputs,iter_n):
        for iteration in range(iter_n):
            raw, output = self.predict(trg_inputs)
            error = trg_outputs - output
            adj = np.dot(trg_inputs.T , error * self.__sigmoid_derivative(raw))
            self.synaptic_weights += adj

    def predict(self,inputs):
        raw = np.dot(inputs, self.synaptic_weights)
        return raw, self.__sigmoid(raw)