Modelο
- pydantic model dakota.spec.model.ModelSelectionο
Base class for model discriminator wrappers
Show JSON schema
{ "title": "ModelSelection", "description": "Base class for model discriminator wrappers", "type": "object", "properties": {}, "additionalProperties": false }
Generated Pydantic models for model
- class dakota.spec.model.SolutionLevelCost(*, solution_level_cost: list[Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)]])ο
Cost estimates associated with a set of solution control values.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.CostRecoveryMetadata(*, cost_recovery_metadata: str)ο
Identify metadata by label for capturing online cost estimates
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.TrendNone(*, none: Literal[True] = True)ο
No trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalGPTrendConstant(*, constant: Literal[True] = True)ο
Constant trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalGPTrendLinear(*, linear: Literal[True] = True)ο
Use a linear polynomial or trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalGPTrendReducedQuadratic(*, reduced_quadratic: Literal[True] = True)ο
Quadratic polynomials - main effects only
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalGPTrendQuadratic(*, quadratic: Literal[True] = True)ο
Use a quadratic polynomial or trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalGPNugget(*, nugget: Annotated[float, Gt(gt=0.0), PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)])ο
Value for the fixed nugget parameter
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalGPFindNugget(*, find_nugget: int)ο
Use regression to estimate the nugget.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.DakotaTrendConstant(*, constant: Literal[True] = True)ο
Constant trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.DakotaTrendLinear(*, linear: Literal[True] = True)ο
Use a linear polynomial or trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.DakotaTrendReducedQuadratic(*, reduced_quadratic: Literal[True] = True)ο
Quadratic polynomials - main effects only
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SurfpackTrendConstant(*, constant: Literal[True] = True)ο
Constant trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SurfpackTrendLinear(*, linear: Literal[True] = True)ο
Use a linear polynomial or trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SurfpackTrendReducedQuadratic(*, reduced_quadratic: Literal[True] = True)ο
Quadratic polynomials - main effects only
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SurfpackTrendQuadratic(*, quadratic: Literal[True] = True)ο
Use a quadratic polynomial or trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SurfpackNugget(*, nugget: Annotated[float, Gt(gt=0.0), PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)])ο
Specify a nugget to handle ill-conditioning
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SurfpackFindNugget(*, find_nugget: int)ο
Have Surfpack compute a nugget to handle ill-conditioning
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.InterpLinear(*, linear: Literal[True] = True)ο
Linear interpolation
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.InterpCubic(*, cubic: Literal[True] = True)ο
Cubic interpolation
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MovingLeastSquaresConfig(*, import_model: ImportModel | None = None, export_model: ModelPartialSurrogateExportFormatExportModel | None = None, basis_order: Annotated[int, Ge(ge=0)] = 2, weight_function: int = 0)ο
Moving Least Squares surrogate models
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ModelSurrogateGlobalApproxFtConfig(*, start_rank: Annotated[int, Ge(ge=0)] = 2, adapt_rank: Literal[True] | None = None, kick_rank: Annotated[int, Gt(gt=0)] = 1, max_rank: Annotated[int, Ge(ge=0)] = 9223372036854775807, max_cv_rank_candidates: Annotated[int, Ge(ge=0)] = 9223372036854775807, start_order: FtModelOrderStartOrder | None = None, adapt_order: Literal[True] | None = None, kick_order: Annotated[int, Gt(gt=0)] = 1, max_order: Annotated[int, Ge(ge=0)] = 65535, max_cv_order_candidates: Annotated[int, Ge(ge=0)] = 65535, rounding_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 1e-10, arithmetic_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 1e-10, regression_type: FtModelRegressionOptsTypeLs | FtModelRegressionOptsTypeRls2 | None = None, max_solver_iterations: Annotated[int, Ge(ge=0)] = 9223372036854775807, max_cross_iterations: Annotated[int, Ge(ge=0)] = 1, solver_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 1e-10, response_scaling: Literal[True] | None = None, tensor_grid: Literal[True] | None = None)ο
Global surrogate model based on functional tensor train decomposition
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.NeuralNetworkConfig(*, import_model: ImportModel | None = None, export_model: ModelFullSurfpackExportFormatExportModel | None = None, max_nodes: int = 0, range: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 0.0, random_weight: int = 0)ο
Artificial neural network model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.RadialBasisConfig(*, import_model: ImportModel | None = None, export_model: ModelFullSurfpackExportFormatExportModel | None = None, bases: int = 0, max_pts: int = 0, min_partition: int = 0, max_subsets: int = 0)ο
Radial basis function (RBF) model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.BasisOrder(*, basis_order: Annotated[int, Ge(ge=0)])ο
Polynomial order
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.PolynomialLinear(*, linear: Literal[True] = True)ο
Use a linear polynomial or trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.PolynomialQuadratic(*, quadratic: Literal[True] = True)ο
Use a quadratic polynomial or trend function
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.PolynomialCubic(*, cubic: Literal[True] = True)ο
Use a cubic polynomial
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalPolynomialConfig(*, import_model: ImportModel | None = None, export_model: ModelPartialSurrogateExportFormatExportModel | None = None, basis_order: Annotated[int, Ge(ge=0)] = 2, options_file: str | None = None)ο
Use a deterministic polynomial surrogate
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalPythonConfig(*, class_path_and_name: str)ο
Use the experimental python surrogates interface
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.JumpThreshold(*, jump_threshold: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)])ο
Gradient Threshold Parameter of the Optional Discontinuity Detection Capability for the Piecewise Decomposition Option of Global Surrogates
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GradientThreshold(*, gradient_threshold: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)])ο
Gradient Threshold Parameter of the Optional Discontinuity Detection Capability for the Piecewise Decomposition Option of Global Surrogates
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.TotalPoints(*, total_points: int)ο
Specified number of training points
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MinimumPoints(*, minimum_points: Literal[True] = True)ο
Construct surrogate with minimum number of points
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.RecommendedPoints(*, recommended_points: Literal[True] = True)ο
Construct surrogate with recommended number of points
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.CVMetric(*, metric: str = 'root_mean_squared', folds: Annotated[int, Gt(gt=0)] = 10)ο
Choice of error metric to satisfy
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxTruthModelPointer(*, truth_model_pointer: str)ο
A surrogate model pointer that guides a method to whether it should use a surrogate model or compute truth function evaluations
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ReusePointsAll(*, all: Literal[True] = True)ο
Option for
reuse_points- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Region(*, region: Literal[True] = True)ο
Option for
reuse_points- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ReusePointsNone(*, none: Literal[True] = True)ο
Option for
reuse_points- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportBuildPointsFileCustomAnnotatedHeader(*, use_variable_labels: Literal[True] | None = None)ο
Enable header row in custom-annotated tabular file
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportBuildPointsFileAnnotatedConfig(*, use_variable_labels: Literal[True] | None = None)ο
Selects annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxImportBuildPointsFileFreeform(*, freeform: Literal[True] = True)ο
Selects freeform file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxExportApproxPointsFileCustomAnnotatedConfig(*, header: Literal[True] | None = None, eval_id: Literal[True] | None = None, interface_id: Literal[True] | None = None)ο
Selects custom-annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxExportApproxPointsFileAnnotated(*, annotated: Literal[True] = True)ο
Selects annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxExportApproxPointsFileFreeform(*, freeform: Literal[True] = True)ο
Selects freeform file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Folds(*, folds: int)ο
Number of cross validation folds
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Percent(*, percent: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)])ο
Percent data per cross validation fold
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportChallengePointsFileCustomAnnotatedHeader(*, use_variable_labels: Literal[True] | None = None)ο
Enable header row in custom-annotated tabular file
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportChallengePointsFileAnnotatedConfig(*, use_variable_labels: Literal[True] | None = None)ο
Selects annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportChallengePointsFileFreeform(*, freeform: Literal[True] = True)ο
Selects freeform file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Tana(*, tana: Literal[True] = True)ο
Local multi-point model via two-point nonlinear approximation
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Qmea(*, qmea: Literal[True] = True)ο
Multi-point surrogate approximation based on QMEA algorithm
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.LocalConfig(*, taylor_series: bool, truth_model_pointer: str)ο
Build a locally accurate surrogate from data at a single point
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.OrderedModelFidelitiesConfig(*, correction: Correction | None = None, pointers: list[str])ο
Specification of an hierarchy of model fidelities, ordered from low to high.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.TruthModelPointerConfig(*, pointer: str, approximation_models: list[str] | None = None)ο
Pointer to specify a "truth" model, from which to construct a surrogate
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.OptionalInterfacePointer(*, pointer: str, optional_interface_responses_pointer: str | None = None)ο
Pointer to interface that provides non-nested responses
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SubMethodPointerIteratorSchedulingDedicated(*, dedicated: Literal[True] = True)ο
Specify a dedicated scheduler partition for concurrent iterator executions
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SubMethodPointerIteratorSchedulingPeer(*, peer: Literal[True] = True)ο
Specify a peer partition for parallel iterator scheduling
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ActiveSubspaceSampleTypeLhs(*, lhs: Literal[True] = True)ο
Uses Latin Hypercube Sampling (LHS) to sample variables
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ActiveSubspaceSampleTypeRandom(*, random: Literal[True] = True)ο
Uses purely random Monte Carlo sampling to sample variables
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Energy(*, truncation_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 1e-06)ο
Truncate the subspace based on eigenvalue energy
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Minimum(*, minimum: Literal[True] = True)ο
Select subspace to minimize cross-validation error
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.CVRelative(*, relative: Literal[True] = True)ο
Choose subspace with cross-validation error less than tolerance
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Decrease(*, decrease: Literal[True] = True)ο
Choose subspace where cross-validation error stabilizes
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.BuildSurrogate(*, refinement_samples: list[int] | None = None)ο
Construct moving least squares surrogate over active subspace
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MeanValue(*, mean_value: Literal[True] = True)ο
Normalize by sample mean of function values
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MeanGradient(*, mean_gradient: Literal[True] = True)ο
Normalize by sample mean of gradient norms
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.LocalGradient(*, local_gradient: Literal[True] = True)ο
Normalize each gradient sample by its norm
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.TruthModelPointerSGLevel(*, sparse_grid_level: int)ο
Level to use in sparse grid integration or interpolation
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.TruthModelPointerExpansionOrderConfig(*, order: int, collocation_ratio: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)])ο
The (initial) order of a polynomial expansion
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Unranked(*, unranked: Literal[True] = True)ο
Use the unranked method to obtain the rotation matrix
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Ranked(*, ranked: Literal[True] = True)ο
Use the ranked method to obtain the rotation matrix
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.RfDataFile(*, rf_data_file: str)ο
Specify that the random field will be built from a file of data. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.BuildSourceDaceMethodPointer(*, dace_method_pointer: str)ο
Pointer to a DACE method for purposes of generating an ensemble of field responses to be used in estimating a random field model. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SquaredExponential(*, squared_exponential: Literal[True] = True)ο
Specify a squared exponential covariance in the case where the random field is built from an analytic covariance functio. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Exponential(*, exponential: Literal[True] = True)ο
Specify an exponential covariance in the case where the random field is built from an analytic covariance functio. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.KarhunenLoeve(*, karhunen_loeve: Literal[True] = True)ο
Specify Karhunen-Loeve as the expansion form to be used in the random field representation. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExpansionFormPrincipalComponents(*, principal_components: Literal[True] = True)ο
Specify Principal Components as the form of the expansion to be used in the random field representation. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SingleConfig(*, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None, interface_pointer: str | None = None, solution_level_control: str | None = None, cost_model: SolutionLevelCost | CostRecoveryMetadata | None = None)ο
A model with one of each block: variable, interface, and response
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalGPConfig(*, import_model: ImportModel | None = None, export_model: ModelPartialSurrogateExportFormatExportModel | None = None, export_approx_variance_file: ExportApproxVarianceFile | None = None, trend: TrendNone | ExperimentalGPTrendConstant | ExperimentalGPTrendLinear | ExperimentalGPTrendReducedQuadratic | ExperimentalGPTrendQuadratic = <factory>, num_restarts: Annotated[int, ~annotated_types.Gt(gt=1)] = 10, nugget: ExperimentalGPNugget | ExperimentalGPFindNugget | None = None, options_file: str | None = None)ο
Use the Gaussian process regression surrogate from the surrogates module
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GPDakotaConfig(*, point_selection: Literal[True] | None = None, trend: DakotaTrendConstant | DakotaTrendLinear | DakotaTrendReducedQuadratic = <factory>)ο
Select the built in Gaussian Process surrogate
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxGPSurfpackConfig(*, import_model: ImportModel | None = None, export_model: ModelFullSurfpackExportFormatExportModel | None = None, trend: SurfpackTrendConstant | SurfpackTrendLinear | SurfpackTrendReducedQuadratic | SurfpackTrendQuadratic = <factory>, optimization_method: str | None = None, max_trials: Annotated[int | None, ~annotated_types.Gt(gt=0)] = None, nugget: SurfpackNugget | SurfpackFindNugget | None = None, correlation_lengths: list[~typing.Annotated[float, ~pydantic.functional_serializers.PlainSerializer(func=~dakota.spec.base._serialize_dakota_float, return_type=float | str, when_used=json)]] | None = None)ο
Use the Surfpack version of Gaussian Process surrogates
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MarsConfig(*, import_model: ImportModel | None = None, export_model: ModelPartialSurrogateExportFormatExportModel | None = None, max_bases: int = 0, interpolation: InterpLinear | InterpCubic | None = None)ο
Multivariate Adaptive Regression Spline (MARS)
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MovingLeastSquares(*, moving_least_squares: MovingLeastSquaresConfig)ο
Moving Least Squares surrogate models
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Ft(*, function_train: ModelSurrogateGlobalApproxFtConfig)ο
Global surrogate model based on functional tensor train decomposition
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.NeuralNetwork(*, neural_network: NeuralNetworkConfig)ο
Artificial neural network model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.RadialBasis(*, radial_basis: RadialBasisConfig)ο
Radial basis function (RBF) model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxPolynomialConfig(*, import_model: ImportModel | None = None, export_model: ModelFullSurfpackExportFormatExportModel | None = None, order: BasisOrder | PolynomialLinear | PolynomialQuadratic | PolynomialCubic)ο
Polynomial surrogate model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalPolynomial(*, experimental_polynomial: ExperimentalPolynomialConfig)ο
Use a deterministic polynomial surrogate
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalPython(*, experimental_python: ExperimentalPythonConfig)ο
Use the experimental python surrogates interface
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.DomainDecomposition(*, cell_type: str = 'voronoi', support_layers: int = 0, discontinuity_detection: JumpThreshold | GradientThreshold | None = None)ο
Piecewise Domain Decomposition for Global Surrogate Models
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.AutoRefinement(*, max_iterations: Annotated[int, Gt(gt=0)] = 9223372036854775807, max_function_evaluations: Annotated[int, Gt(gt=0)] = 9223372036854775807, convergence_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 0.0001, soft_convergence_limit: Annotated[int, Ge(ge=0)] = 0, cross_validation_metric: CVMetric | None = None)ο
Experimental auto-refinement of surrogate model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ReusePoints(*, reuse_domain: ReusePointsAll | Region | ReusePointsNone)ο
Surrogate model training data reuse control
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxImportBuildPointsFileCustomAnnotatedConfig(*, header: ImportBuildPointsFileCustomAnnotatedHeader | None = None, eval_id: Literal[True] | None = None, interface_id: Literal[True] | None = None)ο
Selects custom-annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxImportBuildPointsFileAnnotated(*, annotated: ImportBuildPointsFileAnnotatedConfig = <factory>)ο
Selects annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxExportApproxPointsFileCustomAnnotated(*, custom_annotated: GlobalApproxExportApproxPointsFileCustomAnnotatedConfig = <factory>)ο
Selects custom-annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Metrics(*, metrics: list[str], cross_validation: Folds | Percent | dict | None = None, press: Literal[True] | None = None)ο
Compute surrogate quality metrics
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportChallengePointsFileCustomAnnotatedConfig(*, header: ImportChallengePointsFileCustomAnnotatedHeader | None = None, eval_id: Literal[True] | None = None, interface_id: Literal[True] | None = None)ο
Selects custom-annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportChallengePointsFileAnnotated(*, annotated: ImportChallengePointsFileAnnotatedConfig = <factory>)ο
Selects annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MultipointConfig(*, type: Tana | Qmea, truth_model_pointer: str)ο
Construct a surrogate from multiple existing training points
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.OrderedModelFidelities(*, ordered_model_fidelities: OrderedModelFidelitiesConfig)ο
Specification of an hierarchy of model fidelities, ordered from low to high.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.EnsembleTruthModelPointer(*, truth_model_pointer: TruthModelPointerConfig)ο
Pointer to specify a "truth" model, from which to construct a surrogate
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SubMethodPointer(*, pointer: str, iterator_servers: Annotated[int | None, Gt(gt=0)] = None, iterator_scheduling: SubMethodPointerIteratorSchedulingDedicated | SubMethodPointerIteratorSchedulingPeer | None = None, processors_per_iterator: Annotated[int | None, Gt(gt=0)] = None, primary_variable_mapping: list[str] | None = None, secondary_variable_mapping: list[str] | None = None, primary_response_mapping: list[Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)]] | None = None, secondary_response_mapping: list[Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)]] | None = None, identity_response_mapping: Literal[True] | None = None)ο
The
sub_method_pointerspecifies the method block for the sub-iterator- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.TruncationMethodCV(*, criterion: Minimum | CVRelative | Decrease | None = None, relative_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 1e-06, decrease_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 1e-06, max_rank: int = -1, exhaustive: Literal[True] | None = None)ο
Truncate the subspace to minimize surrogate cross-validation error
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.TruthModelPointerExpansionOrder(*, expansion_order: TruthModelPointerExpansionOrderConfig)ο
The (initial) order of a polynomial expansion
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.AnalyticCov(*, analytic_covariance: SquaredExponential | Exponential)ο
Use an analytic covariance function for the purposes of generating a random field model. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SingleSelection(*, single: SingleConfig)ο
A model with one of each block: variable, interface, and response
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ExperimentalGP(*, experimental_gaussian_process: ExperimentalGPConfig)ο
Use the Gaussian process regression surrogate from the surrogates module
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxGPDakota(*, dakota: GPDakotaConfig)ο
Select the built in Gaussian Process surrogate
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxGPSurfpack(*, surfpack: GlobalApproxGPSurfpackConfig)ο
Use the Surfpack version of Gaussian Process surrogates
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Mars(*, mars: MarsConfig)ο
Multivariate Adaptive Regression Spline (MARS)
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxPolynomial(*, polynomial: GlobalApproxPolynomialConfig)ο
Polynomial surrogate model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.DaceMethodPointerConfig(*, pointer: str, auto_refinement: AutoRefinement | None = None)ο
Specify a method to gather training data
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxImportBuildPointsFileCustomAnnotated(*, custom_annotated: GlobalApproxImportBuildPointsFileCustomAnnotatedConfig = <factory>)ο
Selects custom-annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxExportApproxPointsFile(*, filename: str, format: GlobalApproxExportApproxPointsFileCustomAnnotated | GlobalApproxExportApproxPointsFileAnnotated | GlobalApproxExportApproxPointsFileFreeform = <factory>)ο
Output file for surrogate model value evaluations
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportChallengePointsFileCustomAnnotated(*, custom_annotated: ImportChallengePointsFileCustomAnnotatedConfig = <factory>)ο
Selects custom-annotated tabular file format
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Multipoint(*, multipoint: MultipointConfig)ο
Construct a surrogate from multiple existing training points
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.Ensemble(*, ensemble: OrderedModelFidelities | EnsembleTruthModelPointer)ο
Ensemble surrogates employ a collection of lower-fidelity models to approximate a truth reference model at reduced cost.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.NestedConfig(*, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None, optional_interface_pointer: OptionalInterfacePointer | None = None, sub_method_pointer: SubMethodPointer)ο
A model whose responses are computed through the use of a sub-iterator
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.TruncationMethod(*, bing_li: Literal[True] | None = None, constantine: Literal[True] | None = None, energy: Energy | None = None, cross_validation: TruncationMethodCV | None = None)ο
Metric that estimates active subspace size
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.AdaptedBasisTruthModelPointer(*, pointer: str, basis_control: TruthModelPointerSGLevel | TruthModelPointerExpansionOrder, dimension: int = 0, rotation_method: Unranked | Ranked = <factory>)ο
Pointer to specify a "truth" model, from which to construct a surrogate
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.RandomFieldConfig(*, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None, build_source: RfDataFile | BuildSourceDaceMethodPointer | AnalyticCov | None = None, expansion_form: KarhunenLoeve | ExpansionFormPrincipalComponents | None = None, expansion_bases: int = 0, truncation_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 1e-06, propagation_model_pointer: str)ο
Experimental capability to generate a random field representation. from data, from simulation runs, or from a covariance matrix. The representation may then be sampled for use as a random field input to another simulation. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxGPConfig(*, export_approx_variance_file: ExportApproxVarianceFile | None = None, gp_implementation: GlobalApproxGPDakota | GlobalApproxGPSurfpack | None = None)ο
Gaussian Process surrogate model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxDaceMethodPointer(*, dace_method_pointer: DaceMethodPointerConfig)ο
Specify a method to gather training data
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxImportBuildPointsFile(*, filename: str, format: GlobalApproxImportBuildPointsFileCustomAnnotated | GlobalApproxImportBuildPointsFileAnnotated | GlobalApproxImportBuildPointsFileFreeform = <factory>, active_only: Literal[True] | None = None)ο
File containing points you wish to use to build a surrogate
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ImportChallengePointsFile(*, filename: str, format: ImportChallengePointsFileCustomAnnotated | ImportChallengePointsFileAnnotated | ImportChallengePointsFileFreeform = <factory>, active_only: Literal[True] | None = None)ο
Datafile of points to assess surrogate quality
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.NestedSelection(*, nested: NestedConfig)ο
A model whose responses are computed through the use of a sub-iterator
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ActiveSubspaceConfig(*, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None, truth_model_pointer: str, initial_samples: int = 0, sample_type: ActiveSubspaceSampleTypeLhs | ActiveSubspaceSampleTypeRandom | None = None, truncation_method: TruncationMethod | None = None, dimension: int = 0, bootstrap_samples: int = 100, build_surrogate: BuildSurrogate | None = None, normalization: MeanValue | MeanGradient | LocalGradient | None = None)ο
Active (variable) subspace model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.AdaptedBasisConfig(*, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None, truth_model_pointer: AdaptedBasisTruthModelPointer, truncation_tolerance: Annotated[float, PlainSerializer(func=_serialize_dakota_float, return_type=float | str, when_used=json)] = 0.9)ο
Basis adaptation model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.RandomFieldSelection(*, random_field: RandomFieldConfig)ο
Experimental capability to generate a random field representation. from data, from simulation runs, or from a covariance matrix. The representation may then be sampled for use as a random field input to another simulation. THIS IS AN EXPERIMENTAL CAPABILITY.
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxGP(*, gaussian_process: GlobalApproxGPConfig)ο
Gaussian Process surrogate model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.ActiveSubspaceSelection(*, active_subspace: ActiveSubspaceConfig)ο
Active (variable) subspace model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.AdaptedBasisSelection(*, adapted_basis: AdaptedBasisConfig)ο
Basis adaptation model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalApproxConfig(*, correction: Correction | None = None, type: ExperimentalGP | GlobalApproxGP | Mars | MovingLeastSquares | Ft | NeuralNetwork | RadialBasis | GlobalApproxPolynomial | ExperimentalPolynomial | ExperimentalPython, domain_decomposition: DomainDecomposition | None = None, build_points: TotalPoints | MinimumPoints | RecommendedPoints | None = None, build_data: GlobalApproxDaceMethodPointer | GlobalApproxTruthModelPointer | None = None, reuse_points: ReusePoints | None = None, import_build_points_file: GlobalApproxImportBuildPointsFile | None = None, export_approx_points_file: GlobalApproxExportApproxPointsFile | None = None, use_derivatives: Literal[True] | None = None, metrics: Metrics | None = None, import_challenge_points_file: ImportChallengePointsFile | None = None)ο
Select a surrogate model with global support
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.SurrogateFunctionIndicesMixin(*, id_surrogates: list[int] | None = None)ο
Shared response-function selection for data-fit surrogate models
- model_config = {'extra': 'forbid', 'json_schema_extra': <function DakotaBaseModel.__init_subclass__.<locals>.combined_schema_extra>, 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalSurrogateConfig(*, correction: Correction | None = None, type: ExperimentalGP | GlobalApproxGP | Mars | MovingLeastSquares | Ft | NeuralNetwork | RadialBasis | GlobalApproxPolynomial | ExperimentalPolynomial | ExperimentalPython, domain_decomposition: DomainDecomposition | None = None, build_points: TotalPoints | MinimumPoints | RecommendedPoints | None = None, build_data: GlobalApproxDaceMethodPointer | GlobalApproxTruthModelPointer | None = None, reuse_points: ReusePoints | None = None, import_build_points_file: GlobalApproxImportBuildPointsFile | None = None, export_approx_points_file: GlobalApproxExportApproxPointsFile | None = None, use_derivatives: Literal[True] | None = None, metrics: Metrics | None = None, import_challenge_points_file: ImportChallengePointsFile | None = None, id_surrogates: list[int] | None = None, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None)ο
An empirical model with global support, created from data or a submodel
- model_config = {'extra': 'forbid', 'json_schema_extra': <function DakotaBaseModel.__init_subclass__.<locals>.combined_schema_extra>, 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.GlobalSurrogateSelection(*, global_surrogate: GlobalSurrogateConfig)ο
An empirical model with global support, created from data or a submodel
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MultipointSurrogateConfig(*, type: Tana | Qmea, truth_model_pointer: str, id_surrogates: list[int] | None = None, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None)ο
A surrogate constructed from multiple existing training points
- model_config = {'extra': 'forbid', 'json_schema_extra': <function DakotaBaseModel.__init_subclass__.<locals>.combined_schema_extra>, 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.MultipointSurrogateSelection(*, multipoint_surrogate: MultipointSurrogateConfig)ο
A surrogate constructed from multiple existing training points
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.LocalSurrogateConfig(*, taylor_series: bool, truth_model_pointer: str, id_surrogates: list[int] | None = None, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None)ο
A locally accurate surrogate constructed from data at a single point
- model_config = {'extra': 'forbid', 'json_schema_extra': <function DakotaBaseModel.__init_subclass__.<locals>.combined_schema_extra>, 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.LocalSurrogateSelection(*, local_surrogate: LocalSurrogateConfig)ο
A locally accurate surrogate constructed from data at a single point
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.EnsembleSurrogateConfig(*, id_model: str | None = None, variables_pointer: str | None = None, responses_pointer: str | None = None, hierarchical_tagging: Literal[True] | None = None, ensemble: OrderedModelFidelities | EnsembleTruthModelPointer)ο
A surrogate ensemble of lower-fidelity models and a truth model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models
- class dakota.spec.model.EnsembleSurrogateSelection(*, ensemble_surrogate: EnsembleSurrogateConfig)ο
An ensemble surrogate of lower-fidelity models and a truth model
- model_config = {'extra': 'forbid', 'protected_namespaces': (), 'str_strip_whitespace': True, 'use_enum_values': True, 'validate_assignment': True}ο
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- universal_validator()ο
Example universal validator that runs for all models

