hyperparameter_optuna

Hyperparameter to use with optuna.

class HyperparameterOptuna(hotype=None, opttype='float', name='', low=0, high=0, choices=None)[source]

Bases: Hyperparameter

Represents an optuna parameter.

Parameters:

  • opttype (string) –

    Datatype of the hyperparameter. Follows optunas naming convetions. In principle supported are:

    • float

    • int

    • categorical (list)

    Float and int are not available for OA based approaches at the moment.

  • name (string) – Name of the hyperparameter. Please note that these names always have to be distinct; if you e.g. want to investigate multiple layer sizes use e.g. ff_neurons_layer_001, ff_neurons_layer_002, etc. as names.

  • low (float or int) – Lower bound for numerical parameter.

  • high (float or int) – Higher bound for numerical parameter.

  • choices – List of possible choices (for categorical parameter).

get_categorical(trial: optuna.trial.Trial)[source]

Extract categorical (string) hyperparameter from an optuna Trial.

Parameters:

trial (optuna.trial.Trial) – Optuna trial, from which the hyperparameter value should be extracted.

Returns:

return_value – Return value is based on type of hyperparameter.

Return type:

string

get_float(trial: optuna.trial.Trial)[source]

Extract float hyperparameter from an optuna Trial.

Parameters:

trial (optuna.trial.Trial) – Optuna trial, from which the hyperparameter value should be extracted.

Returns:

return_value – Return value is based on type of hyperparameter.

Return type:

float, int or string

get_int(trial: optuna.trial.Trial)[source]

Extract integer hyperparameter from an optuna Trial.

Parameters:

trial (optuna.trial.Trial) – Optuna trial, from which the hyperparameter value should be extracted.

Returns:

return_value – Return value is based on type of hyperparameter.

Return type:

int

get_parameter(trial: optuna.trial.Trial)[source]

Extract current value of hyperparameter from an optuna Trial.

Parameters:

trial (optuna.trial.Trial) – Optuna trial, from which the hyperparameter value should be extracted.

Returns:

return_value – Return value is based on type of hyperparameter.

Return type:

float, int or string