CADETProcess.optimization.OptimizationResults

class CADETProcess.optimization.OptimizationResults(success, exit_flag, exit_message, time_elapsed, cpu_time, system_information)

Optimization results.

Attributes:

optimization_problemOptimizationProblem

Optimization problem.

optimizerOptimizerBase

Optimizer used to optimize the OptimizationProblem.

successbool

True if optimization was successfully terminated. False otherwise.

exit_flagint

Information about the solver termination.

exit_messagestr

Additional information about the solver status.

time_elapsedfloat

Execution time of simulation.

cpu_timefloat

CPU run time, taking into account the number of cores used for the optimiation.

system_informationdict

Information about the system on which the optimization was performed.

xlist

np.ndarray: Optimal points in untransformed space.

fnp.ndarray

np.ndarray: Objective function values of optimal points.

gnp.ndarray

np.ndarray: Nonlinear constraint function values of optimal points.

population_lastPopulation

Population: Final population.

pareto_frontParetoFront

ParetoFront: Final Pareto front.

meta_frontParetoFront

Population: Meta front.

Methods

check_required_parameters()	Verify if all required parameters are set.
load_results(file_name)	Update optimization results from an HDF5 checkpoint file.
plot_convergence([target, plot_avg, ...])	Plot the convergence of optimization metrics over evaluations.
plot_figures()	Plot result figures.
plot_objectives([plot_pareto, ax, ...])	Plot objective function values for all optimization generations.
plot_pairwise([plot_evolution, ax, ...])	Pairwise of all optimization variables.
plot_pareto([plot_pareto, plot_evolution, ...])	Plot Pareto fronts for each generation in the optimization.
save_results(file_name)	Save results to H5 file.
setup_csv()	Create csv files for optimization results.
to_dict()	Convert Results to a dictionary.
update(new)	Update Results.
update_from_dict(data)	Update internal state from dictionary.
update_meta(meta_front)	Update meta front with new population.
update_pareto([pareto_new])	Update pareto front with new population.