calibrator module¶
A discipline evaluating the quality of another one with respect to reference data.
- class gemseo_calibration.calibrator.CalibrationMeasure(output, measure, mesh, weight)
Bases:
tuple
Create new instance of CalibrationMeasure(output, measure, mesh, weight)
- measure
Alias for field number 1
- mesh
Alias for field number 2
- output
Alias for field number 0
- weight
Alias for field number 3
- class gemseo_calibration.calibrator.Calibrator(disciplines, input_names, control_outputs, parameter_names, formulation='MDF', **formulation_options)[source]
Bases:
MDOScenarioAdapter
A discipline with parameters calibrated from reference input-output data.
When it is executed from parameters values, it computes the calibration measure with respect to the reference data, provided through the
CalibrationDiscipline.set_reference_data()
method.Initialize self. See help(type(self)) for accurate signature.
- Parameters:
disciplines (MDODiscipline | list[MDODiscipline]) – The disciplines whose parameters must be calibrated from the reference data.
input_names (str | Iterable[str]) – The names of the inputs to be considered for the calibration.
control_outputs (CalibrationMeasure | Sequence[CalibrationMeasure]) – The names of the outputs used to calibrate the disciplines with the name of the calibration measure and the corresponding weight comprised between 0 and 1 (the weights must sum to 1). When the output is a 1D function discretized over an irregular mesh, the name of the mesh can be provided. E.g.
CalibrationMeasure(output="z", measure="MSE")
CalibrationMeasure(output="z", measure="MSE", weight=0.3)
orCalibrationMeasure(output="z", measure="MSE", mesh="z_mesh")
Lastly,CalibrationMeasure
can be imported fromgemseo-calibration.scenario
.parameter_names (str | Iterable[str]) – The names of the parameters to be calibrated.
formulation (str) –
The name of a formulation to manage the multidisciplinary coupling.
By default it is set to “MDF”.
**formulation_options (Any) – The options of the formulation.
- Raises:
ValueError – If both reset_x0_before_opt and set_x0_before_opt are True.
- add_measure(control_outputs)[source]
Create a new calibration measure and add it to the outputs of the adapter.
- Parameters:
control_outputs (CalibrationMeasure | Iterable[CalibrationMeasure]) – The names of the outputs used to calibrate the disciplines with the name of the calibration measure and the corresponding weight comprised between 0 and 1 (the weights must sum to 1). When the output is a 1D function discretized over an irregular mesh, the name of the mesh can be provided. E.g.
CalibrationMeasure(output="z", measure="MSE")
CalibrationMeasure(output="z", measure="MSE", weight=0.3)
orCalibrationMeasure(output="z", measure="MSE", mesh="z_mesh")
Lastly,CalibrationMeasure
can be imported fromgemseo-calibration.scenario
.- Returns:
The name of the calibration measure applied to the outputs.
- Return type:
- set_reference_data(reference_data)[source]
Pass the reference data to the scenario and to the measures.
- Parameters:
reference_data (DataType) – The reference data with which to compare the discipline.
- Return type:
None
- cache: AbstractCache | None
The cache containing one or several executions of the discipline according to the cache policy.
- data_processor: DataProcessor
A tool to pre- and post-process discipline data.
- exec_for_lin: bool
Whether the last execution was due to a linearization.
- input_grammar: BaseGrammar
The input grammar.
- jac: MutableMapping[str, MutableMapping[str, ndarray | csr_array | JacobianOperator]]
The Jacobians of the outputs wrt inputs.
The structure is
{output: {input: matrix}}
.
- keep_opt_history: bool
Whether to keep databases copies after each execution.
- property maximize_objective_measure: bool
Whether to maximize the calibration measure related to the objectives.
- name: str
The name of the discipline.
- output_grammar: BaseGrammar
The output grammar.
- post_optimal_analysis: PostOptimalAnalysis
The post-optimal analysis.
- re_exec_policy: ReExecutionPolicy
The policy to re-execute the same discipline.
- property reference_data: DataType
The reference data used for the calibration.
- residual_variables: dict[str, str]
The output variables mapping to their inputs, to be considered as residuals; they shall be equal to zero.
- run_solves_residuals: bool
Whether the run method shall solve the residuals.
- scenario: Scenario
The scenario to be adapted.