gemseo.mlearning.regression.algos.base_fce_settings module#

Base settings of functional chaos expansion model.

Settings BaseFCERegressor_Settings(*, transformer=<factory>, parameters=<factory>, input_names=(), output_names=(), degree=2, learn_jacobian_data=False, use_special_jacobian_data=False)[source]#

Bases: BaseRegressorSettings

Base settings for functional chaos expansion (FCE) models.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

  • transformer (Mapping[str, Any]) --

    By default it is set to <factory>.

  • parameters (Mapping[str, Any]) --

    By default it is set to <factory>.

  • input_names (Sequence[str]) --

    By default it is set to ().

  • output_names (Sequence[str]) --

    By default it is set to ().

  • degree (Annotated[int, Gt(gt=0)]) --

    By default it is set to 2.

  • learn_jacobian_data (bool) --

    By default it is set to False.

  • use_special_jacobian_data (bool) --

    By default it is set to False.

Return type:

None

degree: PositiveInt = 2#

The maximum total degree of the FCE.

Constraints:

  • gt = 0

learn_jacobian_data: bool = False#

Whether to learn the Jacobian data from training dataset.

The training dataset cannot contain both Jacobian data and special Jacobian data.

The options learn_jacobian_data and use_special_jacobian_data

are not compatible.

use_special_jacobian_data: bool = False#

Whether to use the special Jacobian data from training dataset.

Special Jacobian data are samples of partial derivatives with respect to variables that are not inputs of the FCE.

The training dataset cannot contain both Jacobian data and special Jacobian data.

The options use_special_jacobian_data and learn_jacobian_data

are not compatible.