scalable_design_space module¶
The design space for the scalable problem.
- class gemseo.problems.scalable.parametric.scalable_design_space.ScalableDesignSpace(discipline_settings=((1, 1), (1, 1)), d_0=1, names_to_default_values=mappingproxy({}), add_uncertain_variables=False)[source]
Bases:
ParameterSpace
The design space for the scalable problem.
It is the space in which the design and coupling variables vary. For all the variables, the lower bound is 0, the upper bound is 1 and the default value is 0.5.
- Parameters:
discipline_settings (Iterable[ScalableDisciplineSettings]) –
The configurations of the different disciplines. If
None
, use a single discipline with defaultScalableDisciplineSettings
.By default it is set to (ScalableDisciplineSettings(d_i=1, p_i=1), ScalableDisciplineSettings(d_i=1, p_i=1)).
d_0 (int) –
The size of the shared design variable \(x_0\).
By default it is set to 1.
names_to_default_values (Mapping[str, NDArray[float]]) –
The default values of the variables.
By default it is set to {}.
add_uncertain_variables (bool) –
Whether to add the uncertain variables impacting the coupling variables as \(y_{i,j}:=y_{i,j}+\epsilon_{i,j}\) where \(\epsilon_{i,j}\) are independent and identically distributed standard Gaussian variables.
By default it is set to False.
Notes
The lengths of
n_local
andn_coupling
must be equal and correspond to the number of scalable disciplines.n_local[i]
(resp.n_coupling[i]
) is the number of local design variables (resp. coupling variables) of the i-th scalable discipline.- dimension: int
The total dimension of the space, corresponding to the sum of the sizes of the variables.
- distribution: ComposedDistribution
The joint probability distribution of the uncertain variables.
- distributions: dict[str, ComposedDistribution]
The marginal probability distributions of the uncertain variables.
These variables are defined as random vectors with independent components.
- normalize: dict[str, ndarray]
The normalization policies of the variables components indexed by the variables names; if True, the component can be normalized.
- variable_types: dict[str, ndarray]
The types of the variables components, which can be any
DesignSpace.DesignVariableType
.