optimod package

Module contents

Optimization package.

The aim of the optimod package is to perform optimization.

optimod.get_operator(name, setup)

Text.

Parameters:
  • name (str) – Operator name to retrieve.
  • setup (dict) – Optimization setup parameters.
Returns:

Retrieved operator.
Return type:

operator ()
optimod.set_algorithm(name, no_obj, setup)

Text.

Parameters:
  • name (str) – Name of the optimization algorithm.
  • n_obj (int) – Number of objectives.
  • setup (dict) – Optimization setup parameters.
Returns:

Optization algorithm object.
Return type:

algorithm ()
optimod.set_optimization(no_obj)

Set the selected optimization technique.

Parameters:n_obj (int) – Number of objectives.
Returns:Optization algorithm object. termination (): Termination object.
Return type:algorithm ()
optimod.solve_problem(problem, algorithm, termination, direct)

Solve the defined problem.

Parameters:
  • problem (datamod.problems.Custom) – Problem to solve.
  • () (termination) – Optimization algorithm.
  • () – Termination method.
  • direct (bool) – Whether this is a direct optimization run.
Returns:

Results object.
Return type:

res (pymoo.model.result.Result)

Notes

Save_history will work with ANN surrogate from Tensorflow only if line 290 in site-packagespymoomodellgorithm is changed from deepcopy to copy. Optional seed not implemented.

optimod.unnormalize_res(res, norm_in, norm_out)

Unnormliazes results.

Parameters:
  • res (pymoo.model.result.Result) – Results object (unnormalized).
  • norm_in (np.array) – Input normalization factors.
  • norm_out (np.array) – Output normalization factors.
Returns:

Results object (normalized).
Return type:

res (pymoo.model.result.Result)

Notes

Implemented for: F,X.