def test_find_glocal_minimum_for_michaelwicz_function(self):
michaelwicz_function_wrapper = MichaelwiczFunctionWrapper()
number_of_variables = 2
objective = "minimization"
simplified_particle_swarm_optimization = SimplifiedParticleSwarmOptimization(
michaelwicz_function_wrapper, number_of_variables, objective)
number_of_particiles = 20
number_of_iterations = 15
social_coefficient = 0.5
random_variable_coefficient = 0.2
result = simplified_particle_swarm_optimization.search(
number_of_particiles=number_of_particiles,
number_of_iterations=number_of_iterations,
social_coefficient=social_coefficient,
random_variable_coefficient=random_variable_coefficient)
self.assertAlmostEqual(result["best_decision_variable_values"][0],
2.1701,
delta=1)
self.assertAlmostEqual(result["best_decision_variable_values"][1],
1.5703,
delta=1)
self.assertAlmostEqual(result["best_objective_function_value"],
-1.7843,
delta=1)
def execute_simplified_particle_swarm_optimization(args):
objective_function = instantiate_objective_function(
args.objective_function)
from metaheuristic_algorithms.simplified_particle_swarm_optimization import SimplifiedParticleSwarmOptimization
simplified_particle_swarm_optimization = SimplifiedParticleSwarmOptimization(
objective_function, args.number_of_variables, args.objective)
result = simplified_particle_swarm_optimization.search(
number_of_particiles=args.number_of_particiles,
number_of_iterations=args.number_of_iterations,
social_coefficient=args.social_coefficient,
random_variable_coefficient=args.random_variable_coefficient)
print('best_decision_variable_values=',
result["best_decision_variable_values"])
print('best_objective_function_value=',
result["best_objective_function_value"])
