def run(self):
#First let's read our config file, in this case a yaml file
yaml = yamlFile.ReadYaml()
#Initialization of storage class, passing the configuration
storage = dbStorage.Storage(yaml)
#Initialization of the Genetic algorithm for seeking the solution
genetic = algorithm.GeneticAlgorithm(self.__queens)
#Finally , print the solution
myPrinter = printer.Printer(genetic, storage)
def loadDataset():
dataset = fh.readFile(globals.INPUT_FILE)
ga = GA.GeneticAlgorithm(globals.CROSSOVER_RATE)
# individuo = GA.Individual(4, 0)
# ind.printIndividual()
population = GA.Population()
ind_count = 0
jump = 0
# Itera sobre cada um dos individuos da populacao
for ind in range(globals.MAX_INDIVIDUALS):
# Salto para corrigir a posicao da linha no dataset
jump = ind * globals.LINES_PER_SINGLE_INDIVIDUAL
# Para cada uma das caracteristicas
for i in range(globals.LINES_PER_SINGLE_INDIVIDUAL):
if i == globals.WINDOW:
for j in range(len(dataset[0])):
population.getIndividual(ind).setWindow(
j, dataset[i + jump][j])
population.getIndividual(ind).setWeight(j)
elif i == globals.KLINE:
for j in range(len(dataset[i])):
population.getIndividual(ind).setKline(
j, dataset[i + jump][j])
elif i == globals.REQUEST_BEGINNING:
for j in range(len(dataset[i])):
population.getIndividual(ind).setReqBegin(
j, dataset[i + jump][j])
elif i == globals.REQUEST_ENDING:
for j in range(len(dataset[i])):
population.getIndividual(ind).setReqEnd(
j, dataset[i + jump][j])
elif i == globals.STATION:
for j in range(len(dataset[i])):
population.getIndividual(ind).setStation(
j, dataset[i + jump][j])
elif i == globals.WINDOW_BEGINNING:
for j in range(len(dataset[i])):
population.getIndividual(ind).setWindowBegin(
j, dataset[i + jump][j])
elif i == globals.WINDOW_ENDING:
for j in range(len(dataset[i])):
population.getIndividual(ind).setWindowEnd(
j, dataset[i + jump][j])
return population
def initGA(dimensions, population_size, i_max, tournament_size, parent_num,
precision, encoder, stride):
"""
starts Simulated Annealing for each blackbox and writes output to csv file
Parameters
----------
dimensions : dictionary
key: blackbox_id
value: size of input vector
Returns
-------
None.
"""
for bb_id, bb_dim in dimensions.items():
process = runBlackBox(bb_id)
gaInstance = ga.GeneticAlgorithm(population_size, i_max,
tournament_size, parent_num,
precision, encoder, stride)
gaInstance.initGA(process, bb_dim)
writeCSV(gaInstance.avg, bb_id, encoder)
process.terminate()
def setUp(self):
self.ga = geneticAlgorithm.GeneticAlgorithm(0)
# the tolerance of the times of camera off
Kca = 3
if __name__ == "__main__":
# Create a 3D Occupancy Grid
print(
'\033[94m Generating random occupancy grid and objectives... \033[0m')
occ_grid, obstacle_num = map_generate(grid_x, grid_y, grid_z,
starting_point, end_point,
safety_threshold, privacy_threshold)
print(occ_grid)
pri_grid, privacy_sum = privacy_init(grid_x, grid_y, grid_z, occ_grid,
privacy_radius)
print(pri_grid)
objectives = [end_point]
alg = gA.GeneticAlgorithm(population, 0.00001, 5, 2, 40, grid_map)
print('\033[94m Generating random initial solutions... \033[0m')
paths = alg.init_population(starting_point, objectives, Kca)
for p in range(len(paths)):
paths[p].fitness = alg.get_fitness(paths[p], occ_grid, pri_grid,
starting_point, end_point,
privacy_sum, obstacle_num)
max_p = max(paths, key=lambda x: x.fitness)
max_f = -5
count = 0
fitnv = []
print(len(paths))