def _run_mo(self):
""" Runs a multi objective EA optimization
"""
self.ea_problem.reset_initial_population_counter()
if self.algorithm_name in moea_map.keys():
f = moea_map[self.algorithm_name]
else:
if self.ea_problem.number_of_objectives > 2:
self.algorithm_name == 'NSGAIII'
else:
f = moea_map['SPEA2']
args = {
'problem': self.ea_problem,
'population_size': self.population_size,
'mutation': self.mutation,
'crossover': self.crossover,
'termination_criterion': StoppingByEvaluations(max_evaluations=self.max_evaluations)
}
if self.mp:
args['population_evaluator'] = get_evaluator(self.ea_problem)
print(f"Running {self.algorithm_name}")
if self.algorithm_name == 'NSGAIII':
args['reference_directions'] = UniformReferenceDirectionFactory(self.ea_problem.number_of_objectives,
n_points=self.population_size-1)
algorithm = NSGAIII(**args)
else:
args['offspring_population_size'] = self.population_size
algorithm = f(**args)
if self.visualizer:
algorithm.observable.register(observer=VisualizerObserver())
algorithm.observable.register(observer=PrintObjectivesStatObserver())
algorithm.run()
result = algorithm.solutions
return result
problem=problem,
population_size=Configuration.population,
reference_directions=UniformReferenceDirectionFactory(
Configuration.goal_num, n_points=Configuration.population - 1),
# offspring_population_size = Configuration.population,
mutation=PolynomialMutation(probability=1.0 /
problem.number_of_variables,
distribution_index=20),
crossover=SBXCrossover(probability=1.0, distribution_index=20),
termination_criterion=StoppingByEvaluations(
max_evaluations=max_evaluations)
# termination_criterion = StoppingByQualityIndicator(quality_indicator=HyperVolume, expected_value=1,
# degree=0.9)
# selection = BinaryTournamentSelection()
)
"""==========================调用算法模板进行种群进化========================="""
progress_bar = ProgressBarObserver(max=max_evaluations)
algorithm.observable.register(progress_bar)
algorithm.run()
front = algorithm.get_result()
"""==================================输出结果=============================="""
# Save results to file
print_function_values_to_file(
front, os.path.join(target_dir, '/FUN.' + algorithm.label))
print_variables_to_file(
front, os.path.join(target_dir, '/VAR.' + algorithm.label))
print(f'Algorithm: ${algorithm.get_name()}')
print(f'Problem: ${problem.get_name()}')
print(f'Computing time: ${algorithm.total_computing_time}')