Objective¶
- class baybe.objective.Objective[source]¶
Bases:
SerialMixin
Class for managing optimization objectives.
Public methods
__init__
(mode, targets[, weights, combine_func])Method generated by attrs for class Objective.
from_dict
(dictionary)Create an object from its dictionary representation.
from_json
(string)Create an object from its JSON representation.
to_dict
()Create an object's dictionary representation.
to_json
()Create an object's JSON representation.
transform
(data)Transform targets from experimental to computational representation.
Public attributes and properties
The optimization mode.
The list of targets used for the objective.
The weights used to balance the different targets.
The function used to combine the different targets.
- __init__(mode: Literal['SINGLE', 'DESIRABILITY'], targets: list[Target], weights: list[float] = NOTHING, combine_func: Literal['MEAN', 'GEOM_MEAN'] = 'GEOM_MEAN')¶
Method generated by attrs for class Objective.
For details on the parameters, see Public attributes and properties.
- to_json()¶
Create an object’s JSON representation.
- Return type:
- Returns:
The JSON representation as a string.
- transform(data: DataFrame)[source]¶
Transform targets from experimental to computational representation.
- Parameters:
data (
DataFrame
) – The data to be transformed. Must contain all target values, can contain more columns.- Return type:
- Returns:
A new dataframe with the targets in computational representation. Columns will be as in the input (except when objective mode is
DESIRABILITY
).- Raises:
ValueError – If the specified averaging function is unknown.