def main() -> None:
class NSGA2b(NSGAII[S, R]):
def is_stopping_condition_reached(self):
# Re-define the stopping condition
reached = [False, True][self.get_current_computing_time() > 4]
if reached:
logger.info("Stopping condition reached!")
return reached
problem = Fonseca()
algorithm = NSGA2b[FloatSolution, List[FloatSolution]](
problem,
population_size=100,
max_evaluations=25000,
mutation=Polynomial(1.0 / problem.number_of_variables,
distribution_index=20),
crossover=SBX(1.0, distribution_index=20),
selection=BinaryTournament(RankingAndCrowdingDistanceComparator()))
algorithm.run()
result = algorithm.get_result()
SolutionListOutput[FloatSolution].print_function_values_to_file(
"FUN." + problem.get_name(), result)
logger.info("Algorithm (continuous problem): " + algorithm.get_name())
logger.info("Problem: " + problem.get_name())
def test_NSGAII(self):
NSGAII(
problem=self.problem,
population_size=self.population_size,
offspring_population_size=self.offspring_size,
mutation=self.mutation,
crossover=self.crossover,
selection=BinaryTournamentSelection(comparator=RankingAndCrowdingDistanceComparator()),
termination_criterion=StoppingByEvaluations(max=1000)
).run()
def configure_experiment(problems: dict, n_run: int):
jobs = []
max_evaluations = 25000
for run in range(n_run):
for problem_tag, problem in problems.items():
jobs.append(
Job(
algorithm=NSGAII(
problem=problem,
population_size=100,
offspring_population_size=100,
mutation=PolynomialMutation(
probability=1.0 / problem.number_of_variables,
distribution_index=20),
crossover=SBXCrossover(probability=1.0,
distribution_index=20),
selection=BinaryTournamentSelection(
comparator=RankingAndCrowdingDistanceComparator()),
termination_criterion=StoppingByEvaluations(
max=max_evaluations)),
algorithm_tag='NSGAII',
problem_tag=problem_tag,
run=run,
))
jobs.append(
Job(
algorithm=GDE3(problem=problem,
population_size=100,
cr=0.5,
f=0.5,
termination_criterion=StoppingByEvaluations(
max=max_evaluations)),
algorithm_tag='GDE3',
problem_tag=problem_tag,
run=run,
))
jobs.append(
Job(
algorithm=SMPSO(
problem=problem,
swarm_size=100,
mutation=PolynomialMutation(
probability=1.0 / problem.number_of_variables,
distribution_index=20),
leaders=CrowdingDistanceArchive(100),
termination_criterion=StoppingByEvaluations(
max=max_evaluations)),
algorithm_tag='SMPSO',
problem_tag=problem_tag,
run=run,
))
return jobs
def main() -> None:
problem = Kursawe()
algorithm = NSGAII[FloatSolution, List[FloatSolution]](
problem=problem,
population_size=100,
max_evaluations=25000,
mutation=Polynomial(1.0/problem.number_of_variables, distribution_index=20),
crossover=SBX(1.0, distribution_index=20),
selection = BinaryTournament(RankingAndCrowdingDistanceComparator()))
algorithm.run()
result = algorithm.get_result()
SolutionListOutput[FloatSolution].print_function_values_to_file("FUN."+problem.get_name(), result)
logger.info("Algorithm (continuous problem): " + algorithm.get_name())
logger.info("Problem: " + problem.get_name())
def main() -> None:
problem = ZDT1()
algorithm = NSGAII[FloatSolution, List[FloatSolution]](
problem,
population_size = 100,
max_evaluations = 25000,
mutation = Polynomial(1.0/problem.number_of_variables, distribution_index=20),
crossover = SBX(1.0, distribution_index=20),
selection = BinaryTournament(RankingAndCrowdingDistanceComparator()))
observer = BasicAlgorithmConsumer(1000)
algorithm.observable.register(observer=observer)
algorithm.run()
result = algorithm.get_result()
SolutionListOutput[FloatSolution].print_function_values_to_file("FUN."+problem.get_name(), result)
logger.info("Algorithm (continuous problem): " + algorithm.get_name())
logger.info("Problem: " + problem.get_name())
logger.info("Computing time: " + str(algorithm.total_computing_time))
def setUp(self):
self.comparator = RankingAndCrowdingDistanceComparator()
filename='../../../resources/reference_front/{}.pf'.format(
problem.get_name()))
reference_point = [0.8, 0.5]
max_evaluations = 25000
algorithm = NSGAII(
problem=problem,
population_size=100,
offspring_population_size=100,
mutation=PolynomialMutation(probability=1.0 /
problem.number_of_variables,
distribution_index=20),
crossover=SBXCrossover(probability=1.0, distribution_index=20),
selection=BinaryTournamentSelection(
comparator=RankingAndCrowdingDistanceComparator()),
dominance_comparator=GDominanceComparator(reference_point),
termination_criterion=StoppingByEvaluations(max=max_evaluations))
algorithm.observable.register(observer=ProgressBarObserver(
max=max_evaluations))
algorithm.observable.register(
observer=VisualizerObserver(reference_front=problem.reference_front,
reference_point=(reference_point)))
algorithm.run()
front = algorithm.get_result()
# Plot front
plot_front = Plot(plot_title='Pareto front approximation',
axis_labels=problem.obj_labels,
from jmetal.problem import DTLZ2
from jmetal.util.comparator import RankingAndCrowdingDistanceComparator, DominanceComparator
from jmetal.util.observer import ProgressBarObserver, VisualizerObserver
if __name__ == '__main__':
problem = DTLZ2()
problem.reference = '../../resources/reference_front/DTLZ2.3D.pf'
max_evaluations = 25000
algorithm = NSGAII(
problem=problem,
population_size=100,
offspring_population_size=100,
mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
crossover=SBXCrossover(probability=1.0, distribution_index=20),
selection=BinaryTournamentSelection(comparator=RankingAndCrowdingDistanceComparator()),
termination_criterion=StoppingByEvaluations(max=max_evaluations),
dominance_comparator=DominanceComparator()
)
algorithm.observable.register(observer=ProgressBarObserver(max=max_evaluations))
algorithm.observable.register(observer=VisualizerObserver(reference_front=problem.reference_front))
algorithm.run()
front = algorithm.get_result()
label = algorithm.get_name() + "." + problem.get_name()
algorithm_name = label
# Plot front
plot_front = Plot(plot_title='Pareto front approximation', axis_labels=problem.obj_labels)
plot_front.plot(front, label=label, filename=algorithm_name)