DataReal

class aixd.data.DataReal(name: str, dim: int | None = 1, min_value: float | None = None, max_value: float | None = None, mask: List[float] | None = None, unit: str | None = None, transformations: List[str] | List[DataObjectTransform] | None = None)

Bases: DataObject

Real data type.

Parameters:

• name (str) – Name of the data object.

• dim (int, optional, default=1) – Dimensionality of the data object, or different columns to perform the split on.

• min_value (float) – Lower bound for the domain, used for certain transformations and sampling.

• min_value (float) – Upper bound for the domain, used for certain transformations and sampling.

• mask – Values to mask in the domain

• unit (str, optional, default=None) – Unit of the data object (e.g. m, kg. m^2, m/s^2 etc.). Use ^ to indicate powers (e.g. m^2), and _ to indicate subscripts (e.g. m_1).

• transformations (Union[List[str], List[DataObjectTransform]], optional, default=None) – List of transformations to be applied to the data object.

Methods

copy	Returns a copy of the object.
get_activation_outhead	Tries to interfere the activation function for the output head, based on the last transformation.
get_loss_evaluation	Returns the evaluation loss function for this feature.
get_ml_heads	Returns a fully-connected head for encoding and decoding this feature.
get_objective	Returns the loss function for approximating this feature.