from numpy import exp, array, random, dot


class NeuralNetwork():
    def __init__(self):

        random.seed(2)


        self.synaptic_weights = 2 * random.random((1, 5)) - 1

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

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

    def train(self, training_set_inputs, training_set_outputs, number_of_training_iterations):
        for iteration in range(number_of_training_iterations):
            output = self.think(training_set_inputs)

            error = training_set_outputs - output

            adjustment = dot(training_set_inputs.T, error * self.__sigmoid_derivative(output))

            self.synaptic_weights += adjustment

   def think(self, inputs):
    # Pass inputs through our neural network (our single neuron).
    return self.__sigmoid(dot(inputs, self.synaptic_weights))


if __name__ == "__main__":

    neural_network = NeuralNetwork()

    print ("Random starting synaptic weights: ")
    print (neural_network.synaptic_weights)

    training_set_inputs = array([[0], [30], [45], [60], [90]])
    training_set_outputs = array([[0], [0.5], [0.707], [0.866], [1]]).T

    neural_network.train(training_set_inputs, training_set_outputs, 10000)

    print ("New synaptic weights after training: ")
    print (neural_network.synaptic_weights)

    print ("Considering new situation 56 -> ?: ")
    print (neural_network.think(array([56])))