信息安全管理作业-L

import math
import random

def dot_product(v1, v2):
    return sum(x*y for x, y in zip(v1, v2))

def vector_add(v1, v2):
    return [x+y for x, y in zip(v1, v2)]

def scalar_vector_product(scalar, vector):
    return [scalar * x for x in vector]

def matrix_vector_product(matrix, vector):
    return [dot_product(row, vector) for row in matrix]

def transpose(matrix):
    return list(map(list, zip(*matrix)))
def output(ans):
    a=int(ans*100+0.5)
    print('%.2f' % (a/100))
class NeuralNet(object):
    def __init__(self):
        self.synaptic_weights = [0.5] * 6

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

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

    def train(self, inputs, outputs, training_iterations):
        for iteration in range(training_iterations):
            output = self.learn(inputs)
            error = [o - out for o, out in zip(outputs, output)]
            adjustments = []
            for i, inp in enumerate(transpose(inputs)):
                adjustments.append(sum(error[j] * self.__sigmoid_derivative(output[j]) * inp[j] for j in range(len(inp))))
            self.synaptic_weights = vector_add(self.synaptic_weights, adjustments)

    def learn(self, inputs):
        result = matrix_vector_product(inputs, self.synaptic_weights)
        return [self.__sigmoid(x) for x in result]

if __name__ == "__main__":
    neural_network = NeuralNet()

    inputs = [
        [0.4, 0.3, 0.4, 0.6, 0.5, 0.3],
        [0.3, 0.5, 0.8, 0.4, 0.2, 0.5],
        [0.5, 0.6, 0.2, 0.8, 0.7, 0.5],
        [0.4, 0.3, 0.4, 0.2, 0.3, 0.4],
        [0.3, 0.2, 0.3, 0.2, 0.2, 0.4],
        [0.4, 0.3, 0.4, 0.6, 0.5, 0.4],
        [0.7, 0.6, 0.8, 0.7, 0.8, 0.6],
        [0.3, 0.2, 0.3, 0.2, 0.4, 0.2]
    ]
    outputs = [0.38, 0.45, 0.62, 0.38, 0.26, 0.47, 0.75, 0.24]

    neural_network.train(inputs, outputs, 11000)



    test_input = [float(x) for x in input().split()]

    #test_input = [float(x) for x in input("").replace(',', ' ').split()]
    #print(neural_network.learn([test_input]))
    #test_input = [float(x) for x in input("").replace(',', ' ').split()]
    result = neural_network.learn([test_input])[0]

    #print(f"{result:.2f}")
   # print(format( result, '.2f'))
    #print(neural_network.learn([[0.5, 0.4, 0.5, 0.6, 0.4, 0.4]]))

    output(result)