metamod package

Module contents

Surrogate package.

The aim of the metamod package is to produce and run a surrogate model.

metamod.cross_validate(data, iteration, best_hp)

Train the defined surrogate on the provided data.

Parameters:
  • data (datamod.get_data) – Training samples.
  • iteration (int) – Iteration number.
  • best_hp (kerastuner.engine.hyperparameters.HyperParameters) – Optimal hyperparameters.
Returns:

List of cross validation surrogates.
Return type:

surrogates (list)
metamod.optimize_hyperparameters(data, iteration)

Train the defined surrogate on the provided data.

Parameters:
  • data (datamod.get_data) – Training samples.
  • iteration (int) – Iteration number.
Returns:

Optimal hyperparameters.
Return type:

best_hp (kerastuner.engine.hyperparameters.HyperParameters)
metamod.reload_info()

Get information about the problem.

Returns:Input parameter allowable ranges. dim_in (int): Number of input dimensions. dim_out (int): Number of output dimensions. n_constr (int): Number of constraints.
Return type:range_in (np.array)
metamod.set_surrogate(name, dim_in, dim_out)

Select the desired surrogate model.

Parameters:
  • name (str) – Name of the surrogate.
  • dim_in (int) – Number of input dimensions.
  • dim_out (int) – Number of output dimensions.
Returns:

Initialized surrogate model.
Return type:

surrogate (object)
Raises:

NameError – If the surrogate is not defined-
metamod.train_surrogate(data, best_hp)
Parameters:
  • data (datamod.get_data) – Training samples.
  • best_hp (kerastuner.engine.hyperparameters.HyperParameters) – Optimal hyperparameters.
Returns:

Surroggate trained on all training samples.
Return type:

model (object)