optimization package

Submodules

optimization.optimizer_interface module

class optimization.optimizer_interface.OptunaOptimizer[source]

Bases: ABC

abstract optimize(objective_function)[source]

Optimize a model given objective function using Optuna.

Parameters:

objective_function (Callable[[Trial], float]) – The objective function to optimize.

Returns:

The best parameters found by the optimizer.

Return type:

Dict

optimization.optuna_base_optimizer module

class optimization.optuna_base_optimizer.OptunaBaseOptimizer(optimization_params, n_trials=100, direction='minimize', pruner=None, save_dir=None)[source]

Bases: OptunaOptimizer

Parameters:

  • optimization_params (Dict) – A dictionary containing the parameters to optimize.

  • n_trials (int) – The number of trials to run. Default is 100.

  • direction (str) – The direction to optimize. Can be ‘minimize’ or ‘maximize’. Default is ‘minimize’.

  • pruner (optuna.pruners.BasePruner) – The pruner to use. Default is None.

  • save_dir (str) – The directory to save the best parameters. Default is None.

property optimization_params: Dict

Get the optimization parameters.

optimize(objective_function)[source]

Optimize a model given objective function using Optuna.

Parameters:

objective_function (Callable[[Trial], float]) – The objective function to optimize.

Returns:

The best parameters found by the optimizer.

Return type:

Dict

Module contents