hyperparameter

Interface function to get the correct type of hyperparameter.

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

Bases: JSONSerializable

Base class for all hyperparameters.

Will always return the correct subclass of hyperparameter.

Parameters:

  • hotype (string) –

    Type of hyperparameter. Currently supported:

    • optuna: Hyperparameter for HyperOptOptuna.

    • oat: Hyperparameter for HyperOptOAT.

    • naswot: Hyperparameter for HyperOptNASWOT.

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

opttype

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.

Type:

string

name

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.

Type:

string

low

Lower bound for numerical parameter.

Type:

float or int

high

Higher bound for numerical parameter.

Type:

float or int

choices

List of possible choices (for categorical parameter).

Type:

list