dfo_optimisation.py

def create_random_population(size):
    return np.random.random((size, 10))


for iteration in range(50):
    size = 100
    disturbance_threshold = 0.01

    lower = -1.0
    upper = 1.0
    iteration_amount = 100

    population = create_random_population(size)

    all_time_best = None
    all_time_best_score = np.finfo(np.float32).max

    best_neighbour = np.zeros_like(population[0])

    done = False

    while not done:

        fitnesses = np.array([get_fitness(p) for p in population])

        swarms_best_index = np.argmin(fitnesses)
        swarms_best = population[swarms_best_index]

        if np.amin(fitnesses) < all_time_best_score:
            all_time_best_score = np.amin(fitnesses)
            all_time_best = swarms_best

            if all_time_best_score == 0:
                done = True
                break

        r = np.random.uniform(0.0, 1.0, population.shape)

        for i, p in enumerate(population):
            left = (i - 1) if i is not 0 else len(population) - 1
            right = (i + 1) if i is not (len(population) - 1) else 0

            best_neighbour = population[left] if fitnesses[left] < fitnesses[right] else population[right]

            for x in range(len(p)):
                if r[i][x] < disturbance_threshold:
                    p[x] = np.random.uniform(lower, upper)
                else:
                    update = swarms_best[x] - best_neighbour[x]
                    p[x] = best_neighbour[x] + np.random.uniform(0.0, 1.0) * update


    solution = np.argsort(all_time_best) + 1
    print('\nattempt', iteration)
    print('    * fly solution:       ', solution)
    print('    * difference sum:     ', abs(36 - np.sum(solution[:5])))
    print('    * difference product: ', abs(360 - np.product(solution[-5:])))

    
#------------------------------------------------------------
# Code Ouput
#------------------------------------------------------------
# attempt 0
#     * fly solution:        [ 7  8 10  2  9  3  5  4  6  1]
#     * difference sum:      0
#     * difference product:  0
# 
# attempt 1
#     * fly solution:        [10  9  8  7  2  1  5  4  6  3]
#     * difference sum:      0
#     * difference product:  0
# 
# attempt 2
#     * fly solution:        [ 8  7  9 10  2  3  5  1  6  4]
#     * difference sum:      0
#     * difference product:  0
# 
# attempt 3
#     * fly solution:        [ 2  9  8  7 10  1  5  3  6  4]
#     * difference sum:      0
#     * difference product:  0
# 
# attempt 4
#     * fly solution:        [ 7 10  8  2  9  3  1  6  4  5]
#     * difference sum:      0
#     * difference product:  0