ContinuousLinearConstraint

class baybe.constraints.continuous.ContinuousLinearConstraint

Bases: ContinuousConstraint

Class for continuous linear constraints.

Continuous linear constraints use parameter lists and coefficients to define in-/equality constraints over a continuous parameter space.

Public methods

__init__(parameters, operator[, ...])	Method generated by attrs for class ContinuousLinearConstraint.
from_dict(dictionary)	Create an object from its dictionary representation.
from_json(string)	Create an object from its JSON representation.
summary()	Return a custom summarization of the constraint.
to_botorch(parameters[, idx_offset, batch_size])	Cast the constraint in a format required by botorch.
to_dict()	Create an object's dictionary representation.
to_json()	Create an object's JSON representation.

Public attributes and properties

operator	Defines the operator used in the equation.
coefficients	In-/equality coefficient for each entry in parameters.
rhs	Right-hand side value of the in-/equality.
is_interpoint	Flag for defining an interpoint constraint.
eval_during_augmentation	Class variable encoding whether the constraint could be considered during data augmentation.
eval_during_creation	Class variable encoding whether the condition is evaluated during creation.
eval_during_modeling	Class variable encoding whether the condition is evaluated during modeling.
is_continuous	Boolean indicating if this is a constraint over continuous parameters.
is_discrete	Boolean indicating if this is a constraint over discrete parameters.
is_eq	Whether this constraint models an equality (assumed inequality otherwise).
numerical_only	Class variable encoding whether the constraint is valid only for numerical parameters.
parameters	The list of parameters used for the constraint.

__init__(parameters: list[str], operator: str, coefficients=NOTHING, rhs=0.0, interpoint: bool = False)

Method generated by attrs for class ContinuousLinearConstraint.

For details on the parameters, see Public attributes and properties.

classmethod from_dict(dictionary: dict)

Create an object from its dictionary representation.

Parameters:

dictionary (dict) – The dictionary representation.

Return type:

TypeVar(_T, bound= SerialMixin)

Returns:

The reconstructed object.

classmethod from_json(string: str)

Create an object from its JSON representation.

Parameters:

string (str) – The JSON representation of the object.

Return type:

TypeVar(_T, bound= SerialMixin)

Returns:

The reconstructed object.

summary()

Return a custom summarization of the constraint.

Return type:

dict

to_botorch(parameters: Sequence[NumericalContinuousParameter], idx_offset: int = 0, *, batch_size: int | None = None)

Cast the constraint in a format required by botorch.

Used in calling optimize_acqf_* functions, for details see botorch.optim.optimize.optimize_acqf()

Parameters:

• parameters (Sequence[NumericalContinuousParameter]) – The parameter objects of the continuous space.

• idx_offset (int) – Offset to the provided parameter indices.

• batch_size (int | None) – The batch size used for the recommendation. Necessary for interpoint constraints as indices need to be adjusted. Ignored by all other constraints.

Return type:

tuple[Tensor, Tensor, float]

Returns:

The tuple required by botorch.

to_dict()

Create an object’s dictionary representation.

Return type:

dict

Returns:

The dictionary representation of the object.

to_json()

Create an object’s JSON representation.

Return type:

str

Returns:

The JSON representation as a string.

coefficients: tuple[float, ...]

In-/equality coefficient for each entry in parameters.

eval_during_augmentation: ClassVar[bool] = False

Class variable encoding whether the constraint could be considered during data augmentation.

eval_during_creation: ClassVar[bool] = False

Class variable encoding whether the condition is evaluated during creation.

eval_during_modeling: ClassVar[bool] = True

Class variable encoding whether the condition is evaluated during modeling.

property is_continuous: bool

Boolean indicating if this is a constraint over continuous parameters.

property is_discrete: bool

Boolean indicating if this is a constraint over discrete parameters.

property is_eq

Whether this constraint models an equality (assumed inequality otherwise).

is_interpoint: bool

Flag for defining an interpoint constraint.

While intrapoint constraints impose conditions on each individual point of a batch, interpoint constraints do so across the points of the batch. That is, an interpoint constraint of the form x <= 100 encodes that the sum of the values of the parameter x across all points in the batch must be less than or equal to 100.

numerical_only: ClassVar[bool] = True

Class variable encoding whether the constraint is valid only for numerical parameters.

operator: str

Defines the operator used in the equation. Internally this will negate rhs and coefficients for <=.

parameters: list[str]

The list of parameters used for the constraint.

rhs: float

Right-hand side value of the in-/equality.