Dakota  Version 6.20
Explore and Predict with Confidence
Public Member Functions | Public Attributes | Private Member Functions | Friends | List of all members
DataMethodRep Class Reference

Body class for method specification data. More...

Public Member Functions

 ~DataMethodRep ()
 destructor
 

Public Attributes

String idMethod
 string identifier for the method specification data set (from the id_method specification in MethodIndControl)
 
String modelPointer
 string pointer to the model specification to be used by this method (from the model_pointer specification in MethodIndControl)
 
String lowFidModelPointer
 string to point to the low fidelity model for Bayesian experimental design
 
short methodOutput
 method verbosity control: {SILENT,QUIET,NORMAL,VERBOSE,DEBUG}_OUTPUT (from the output specification in MethodIndControl)
 
size_t maxIterations
 maximum number of iterations allowed for the method (from the max_iterations specification in MethodIndControl)
 
size_t maxRefineIterations
 maximum number of refinement iterations allowed for a uniform/adaptive refinement approach (from the max_refinement_iterations specification in MethodIndControl)
 
size_t maxSolverIterations
 maximum number of internal solver iterations allowed for the method (from the max_solver_iterations specification in MethodIndControl)
 
size_t maxFunctionEvals
 maximum number of function evaluations allowed for the method (from the max_function_evaluations specification in MethodIndControl)
 
bool speculativeFlag
 flag for use of speculative gradient approaches for maintaining parallel load balance during the line search portion of optimization algorithms (from the speculative specification in MethodIndControl)
 
bool methodUseDerivsFlag
 flag for usage of derivative data to enhance the computation of surrogate models (PCE/SC expansions, GP models for EGO/EGRA/EGIE) based on the use_derivatives specification
 
Real constraintTolerance
 tolerance for controlling the amount of infeasibility that is allowed before an active constraint is considered to be violated (from the constraint_tolerance specification in MethodIndControl)
 
bool methodScaling
 flag indicating scaling status (from the scaling specification in MethodIndControl)
 
size_t numFinalSolutions
 number of final solutions returned from the iterator
 
Real convergenceTolerance
 iteration convergence tolerance for the method (from the convergence_tolerance specification in MethodIndControl)
 
bool relativeConvMetric
 controls use of convergence tolerance in a relative (true) or absolute (false) context
 
short statsMetricMode
 mode of computing statistics metrics used for convergence assessment of multilevel/multifidelity refinement processes: active or combined
 
unsigned short methodName
 the method selection: one of the optimizer, least squares, nond, dace, or parameter study methods
 
unsigned short subMethod
 enum value for a sub-method type
 
String subMethodName
 string identifier for a sub-method name within a multi-option method specification (e.g., from meta-iterators)
 
String subModelPointer
 string pointer for a sub-model specification used by a meta-iterator
 
String subMethodPointer
 string pointer for a sub-method specification used by a meta-iterator
 
int iteratorServers
 number of servers for concurrent iterator parallelism (from the iterator_servers specification)
 
int procsPerIterator
 number of processors for each concurrent iterator partition (from the processors_per_iterator specification)
 
short iteratorScheduling
 type of scheduling ({DEFAULT,MASTER,PEER}_SCHEDULING) used in concurrent iterator parallelism (from the iterator_scheduling specification)
 
StringArray hybridMethodNames
 array of methods for the sequential and collaborative hybrid meta-iterators (from the method_name_list specification)
 
StringArray hybridModelPointers
 array of models for the sequential and collaborative hybrid meta-iterators (from the model_pointer_list specification)
 
StringArray hybridMethodPointers
 array of methods for the sequential and collaborative hybrid meta-iterators (from the method_pointer_list specification)
 
String hybridGlobalMethodName
 global method name for embedded hybrids (from the global_method_name specification)
 
String hybridGlobalModelPointer
 global model pointer for embedded hybrids (from the global_model_pointer specification)
 
String hybridGlobalMethodPointer
 global method pointer for embedded hybrids (from the global_method_pointer specification)
 
String hybridLocalMethodName
 local method name for embedded hybrids (from the local_method_name specification)
 
String hybridLocalModelPointer
 local model pointer for embedded hybrids (from the local_model_pointer specification)
 
String hybridLocalMethodPointer
 local method pointer for embedded hybrids (from the local_method_pointer specification)
 
Real hybridLSProb
 local search probability for embedded hybrids (from the local_search_probability specification)
 
int concurrentRandomJobs
 number of random jobs to perform in the pareto_set and multi_start meta-iterators (from the random_starts and random_weight_sets specifications)
 
RealVector concurrentParameterSets
 user-specified (i.e., nonrandom) parameter sets to evaluate in the pareto_set and multi_start meta-iterators (from the starting_points and weight_sets specifications)
 
unsigned short softConvLimit
 number of consecutive iterations with change less than convergenceTolerance required to trigger convergence
 
bool surrBasedLocalLayerBypass
 flag to indicate user-specification of a bypass of any/all layerings in evaluating truth response values in SBL.
 
RealVector trustRegionInitSize
 initial trust region sizes in the surrogate-based local method (from the initial_size specification in MethodSBL), one size per surrogate model (notes: no trust region for the truth model; sizes are relative values, e.g., 0.1 = 10% of range of global bounds for each variable
 
Real trustRegionMinSize
 minimum trust region size in the surrogate-based local method (from the minimum_size specification in MethodSBL), if the trust region size falls below this threshold the SBL iterations are terminated (note: if kriging is used with SBL, the min trust region size is set to 1.0e-3 in attempt to avoid ill-conditioned matrixes that arise in kriging over small trust regions)
 
Real trustRegionContractTrigger
 trust region minimum improvement level (ratio of actual to predicted decrease in objective fcn) in the surrogate-based local method (from the contract_threshold specification in MethodSBL), the trust region shrinks or is rejected if the ratio is below this value ("eta_1" in the Conn-Gould-Toint trust region book)
 
Real trustRegionExpandTrigger
 trust region sufficient improvement level (ratio of actual to predicted decrease in objective fn) in the surrogate-based local method (from the expand_threshold specification in MethodSBL), the trust region expands if the ratio is above this value ("eta_2" in the Conn-Gould-Toint trust region book)
 
Real trustRegionContract
 trust region contraction factor in the surrogate-based local method (from the contraction_factor specification in MethodSBL)
 
Real trustRegionExpand
 trust region expansion factor in the surrogate-based local method (from the expansion_factor specification in MethodSBL)
 
short surrBasedLocalSubProbObj
 SBL approximate subproblem objective: ORIGINAL_PRIMARY, SINGLE_OBJECTIVE, LAGRANGIAN_OBJECTIVE, or AUGMENTED_LAGRANGIAN_OBJECTIVE.
 
short surrBasedLocalSubProbCon
 SBL approximate subproblem constraints: NO_CONSTRAINTS, LINEARIZED_CONSTRAINTS, or ORIGINAL_CONSTRAINTS.
 
short surrBasedLocalMeritFn
 SBL merit function type: BASIC_PENALTY, ADAPTIVE_PENALTY, BASIC_LAGRANGIAN, or AUGMENTED_LAGRANGIAN.
 
short surrBasedLocalAcceptLogic
 SBL iterate acceptance logic: TR_RATIO or FILTER.
 
short surrBasedLocalConstrRelax
 SBL constraint relaxation method: NO_RELAX or HOMOTOPY.
 
bool surrBasedGlobalReplacePts
 user-specified method for adding points to the set upon which the next surrogate is based in the surrogate_based_global method.
 
String dlDetails
 string of options for a dynamically linked solver
 
void * dlLib
 handle to dynamically loaded library
 
int verifyLevel
 the verify_level specification in MethodNPSOLDC
 
Real functionPrecision
 the function_precision specification in MethodNPSOLDC and the EPSILON specification in NOMAD
 
Real lineSearchTolerance
 the linesearch_tolerance specification in MethodNPSOLDC
 
Real absConvTol
 absolute function convergence tolerance
 
Real xConvTol
 x-convergence tolerance
 
Real singConvTol
 singular convergence tolerance
 
Real singRadius
 radius for singular convergence test
 
Real falseConvTol
 false-convergence tolerance
 
Real initTRRadius
 initial trust radius
 
int covarianceType
 kind of covariance required
 
bool regressDiag
 whether to print the regression diagnostic vector
 
String searchMethod
 the search_method specification for Newton and nonlinear interior-point methods in MethodOPTPPDC
 
Real gradientTolerance
 the gradient_tolerance specification in MethodOPTPPDC
 
Real maxStep
 the max_step specification in MethodOPTPPDC
 
short meritFn
 the merit_function specification for nonlinear interior-point methods in MethodOPTPPDC
 
Real stepLenToBoundary
 the steplength_to_boundary specification for nonlinear interior-point methods in MethodOPTPPDC
 
Real centeringParam
 the centering_parameter specification for nonlinear interior-point methods in MethodOPTPPDC
 
int searchSchemeSize
 the search_scheme_size specification for PDS methods in MethodOPTPPDC
 
Real initStepLength
 the initStepLength choice for nonlinearly constrained APPS in MethodAPPSDC
 
Real contractStepLength
 the contractStepLength choice for nonlinearly constrained APPS in MethodAPPSDC
 
Real threshStepLength
 the threshStepLength choice for nonlinearly constrained APPS in MethodAPPSDC
 
String meritFunction
 the meritFunction choice for nonlinearly constrained APPS in MethodAPPSDC
 
Real constrPenalty
 the constrPenalty choice for nonlinearly constrained APPS in MethodAPPSDC
 
Real smoothFactor
 the initial smoothFactor value for nonlinearly constrained APPS in MethodAPPSDC
 
Real constraintPenalty
 the initial constraint_penalty for COLINY methods in MethodAPPS, MethodSCOLIBDIR, MethodSCOLIBPS, MethodSCOLIBSW and MethodSCOLIBEA
 
bool constantPenalty
 the constant_penalty flag for COLINY methods in MethodSCOLIBPS and MethodSCOLIBSW
 
Real globalBalanceParam
 the global_balance_parameter for the DIRECT method in MethodSCOLIBDIR
 
Real localBalanceParam
 the local_balance_parameter for the DIRECT method in MethodSCOLIBDIR
 
Real maxBoxSize
 the max_boxsize_limit for the DIRECT method in MethodSCOLIBDIR
 
Real minBoxSize
 the min_boxsize_limit for the DIRECT method in MethodSCOLIBDIR and MethodNCSUDC
 
String boxDivision
 the division setting (major_dimension or all_dimensions) for the DIRECT method in MethodSCOLIBDIR
 
bool mutationAdaptive
 the non_adaptive specification for the coliny_ea method in MethodSCOLIBEA
 
bool showMiscOptions
 the show_misc_options specification in MethodSCOLIBDC
 
StringArray miscOptions
 the misc_options specification in MethodSCOLIBDC
 
Real solnTarget
 the solution_target specification in MethodSCOLIBDC
 
Real crossoverRate
 the crossover_rate specification for EA methods in MethodSCOLIBEA
 
Real mutationRate
 the mutation_rate specification for EA methods in MethodSCOLIBEA
 
Real mutationScale
 the mutation_scale specification for EA methods in MethodSCOLIBEA
 
Real mutationMinScale
 the min_scale specification for mutation in EA methods in MethodSCOLIBEA
 
Real initDelta
 the initial_delta specification for APPS/COBYLA/PS/SW methods in MethodAPPS, MethodSCOLIBCOB, MethodSCOLIBPS, and MethodSCOLIBSW
 
Real threshDelta
 the variable_tolerance specification for APPS/COBYLA/PS/SW methods in MethodAPPS, MethodSCOLIBCOB, MethodSCOLIBPS, and MethodSCOLIBSW
 
Real contractFactor
 the contraction_factor specification for APPS/PS/SW methods in MethodAPPS, MethodSCOLIBPS, and MethodSCOLIBSW
 
int newSolnsGenerated
 the new_solutions_generated specification for GA/EPSA methods in MethodSCOLIBEA
 
int numberRetained
 the integer assignment to random, chc, or elitist in the replacement_type specification for GA/EPSA methods in MethodSCOLIBEA
 
bool expansionFlag
 the no_expansion specification for APPS/PS/SW methods in MethodAPPS, MethodSCOLIBPS, and MethodSCOLIBSW
 
int expandAfterSuccess
 the expand_after_success specification for PS/SW methods in MethodSCOLIBPS and MethodSCOLIBSW
 
int contractAfterFail
 the contract_after_failure specification for the SW method in MethodSCOLIBSW
 
int mutationRange
 the mutation_range specification for the pga_int method in MethodSCOLIBEA
 
int totalPatternSize
 the total_pattern_size specification for PS methods in MethodSCOLIBPS
 
bool randomizeOrderFlag
 the stochastic specification for the PS method in MethodSCOLIBPS
 
String selectionPressure
 the fitness_type specification for EA methods in MethodSCOLIBEA
 
String replacementType
 the replacement_type specification for EA methods in MethodSCOLIBEA
 
String crossoverType
 the crossover_type specification for EA methods in MethodSCOLIBEA
 
String mutationType
 the mutation_type specification for EA methods in MethodSCOLIBEA
 
String exploratoryMoves
 the exploratory_moves specification for the PS method in MethodSCOLIBPS
 
String patternBasis
 the pattern_basis specification for APPS/PS methods in MethodAPPS and MethodSCOLIBPS
 
String betaSolverName
 beta solvers don't need documentation
 
short evalSynchronize
 the synchronization setting for parallel pattern search methods in MethodSCOLIBPS and MethodAPPS
 
size_t numCrossPoints
 The number of crossover points or multi-point schemes.
 
size_t numParents
 The number of parents to use in a crossover operation.
 
size_t numOffspring
 The number of children to produce in a crossover operation.
 
String fitnessType
 the fitness assessment operator to use.
 
String convergenceType
 The means by which this JEGA should converge.
 
Real percentChange
 The minimum percent change before convergence for a fitness tracker converger.
 
size_t numGenerations
 The number of generations over which a fitness tracker converger should track.
 
Real fitnessLimit
 The cutoff value for survival in fitness limiting selectors (e.g., below_limit selector).
 
Real shrinkagePercent
 The minimum percentage of the requested number of selections that must take place on each call to the selector (0, 1).
 
String nichingType
 The niching type.
 
RealVector nicheVector
 The discretization percentage along each objective.
 
size_t numDesigns
 The maximum number of designs to keep when using the max_designs nicher.
 
String postProcessorType
 The post processor type.
 
RealVector distanceVector
 The discretization percentage along each objective.
 
String initializationType
 The means by which the JEGA should initialize the population.
 
String flatFile
 The filename to use for initialization.
 
String logFile
 The filename to use for logging.
 
int populationSize
 the population_size specification for GA methods in MethodSCOLIBEA
 
bool printPopFlag
 The print_each_pop flag to set the printing of the population at each generation.
 
Real volBoxSize
 the volume_boxsize_limit for the DIRECT method in MethodNCSUDC
 
int numSymbols
 the symbols specification for DACE methods
 
bool mainEffectsFlag
 the main_effects specification for sampling methods in MethodDDACE)
 
bool latinizeFlag
 the latinize specification for FSU QMC and CVT methods in MethodFSUDACE
 
bool volQualityFlag
 the quality_metrics specification for sampling methods (FSU QMC and CVT methods in MethodFSUDACE)
 
IntVector sequenceStart
 the sequenceStart specification in MethodFSUDACE
 
IntVector sequenceLeap
 the sequenceLeap specification in MethodFSUDACE
 
IntVector primeBase
 the primeBase specification in MethodFSUDACE
 
int numTrials
 the numTrials specification in MethodFSUDACE
 
String trialType
 the trial_type specification in MethodFSUDACE
 
int randomSeed
 the seed specification for COLINY, NonD, & DACE methods
 
SizetArray randomSeedSeq
 the seed_sequence specification for multilevel UQ methods
 
Real initMeshSize
 the initMeshSize choice for NOMAD in MethodNOMADDC
 
Real minMeshSize
 the minMeshSize choice for NOMAD in MethodNOMADDC
 
String historyFile
 the HISTORY_FILE specification for NOMAD
 
String displayFormat
 the DISPLAY_STATS specification for NOMAD
 
Real vns
 the VNS specification for NOMAD
 
int neighborOrder
 the NEIGHBOR_ORDER specification for NOMAD
 
bool showAllEval
 the DISPLAY_ALL_EVAL specification for NOMAD
 
String useSurrogate
 the HAS_SGTE specification for NOMAD
 
int maxCrossIterations
 maximum number of cross iterations
 
Real solverTol
 optimization tolerance for FT regression
 
Real solverRoundingTol
 Rounding tolerance for FT regression.
 
Real statsRoundingTol
 arithmetic (rounding) tolerance for FT sums and products
 
unsigned short startOrder
 starting polynomial order
 
unsigned short kickOrder
 polynomial order increment when adapting
 
unsigned short maxOrder
 maximum order of basis polynomials
 
bool adaptOrder
 whether or not to adapt order by cross validation
 
size_t startRank
 starting rank
 
size_t kickRank
 rank increment when adapting
 
size_t maxRank
 maximum rank
 
bool adaptRank
 whether or not to adapt rank
 
size_t maxCVRankCandidates
 maximum number of cross-validation candidates for adaptRank
 
unsigned short maxCVOrderCandidates
 maximum number of cross-validation candidates for adaptOrder
 
short c3AdvanceType
 quantity to increment (start rank, start order, max rank, max order, max rank + max order) for FT (uniform) p-refinement
 
UShortArray startOrderSeq
 starting polynomial order
 
SizetArray startRankSeq
 starting rank
 
int numSamples
 the samples specification for NonD & DACE methods
 
bool fixedSeedFlag
 flag for fixing the value of the seed among different NonD/DACE sample sets. This results in the use of the same sampling stencil/pattern throughout an execution with repeated sampling.
 
bool fixedSequenceFlag
 flag for fixing the sequence for Halton or Hammersley QMC sample sets. This results in the use of the same sampling stencil/pattern throughout an execution with repeated sampling.
 
bool vbdFlag
 the var_based_decomp specification for computing Sobol' indices via either PCE or sampling
 
Real vbdDropTolerance
 the var_based_decomp tolerance for omitting Sobol' indices computed via either PCE or sampling
 
unsigned short vbdViaSamplingMethod
 Sampling method for computing Sobol indices: Mahadevan (default) or Saltelli.
 
int vbdViaSamplingNumBins
 Number of bins to use in case the Mahadevan method is selected (default is the square root of the number of samples)
 
bool backfillFlag
 the backfill option allows one to augment in LHS sample by enforcing the addition of unique discrete variables to the sample
 
bool pcaFlag
 Flag to specify the calculation of principal components when using LHS.
 
Real percentVarianceExplained
 The percentage of variance explained by using a truncated number of principal components in PCA.
 
bool wilksFlag
 Flag to specify use of Wilks formula to calculate num samples.
 
unsigned short wilksOrder
 Wilks order parameter.
 
Real wilksConfidenceLevel
 Wilks confidence interval parameter.
 
short wilksSidedInterval
 Wilks sided interval type.
 
bool rank1LatticeFlag
 Flag to indicate rank-1 lattice sampling.
 
bool noRandomShiftFlag
 Flag to indicate randomization of rank-1 lattice rule.
 
int log2MaxPoints
 (log2 of) maximum number of points of low-discrepancy generator
 
IntVector generatingVector
 Inline generating vector of the rank-1 lattice rule.
 
String generatingVectorFileName
 Name of file with generating vector.
 
bool kuo
 Predefined generating vectors.
 
bool cools_kuo_nuyens
 
bool naturalOrdering
 Ordering of the lattice points.
 
bool radicalInverseOrdering
 
bool digitalNetFlag
 Flag to indicate digital net sampling.
 
bool noDigitalShiftFlag
 Flag to indicate randomization of digital net.
 
bool noScramblingFlag
 Flag to indicate scrambling of the digital net.
 
bool mostSignificantBitFirst
 Flag to indicate integers in generating matrices are stored with most significant bit first.
 
bool leastSignificantBitFirst
 Flag to indicate integers in generating matrices are stored with least significant bit first.
 
int numberOfBits
 Number of bits in each integer in the generating matrices.
 
int scrambleSize
 Number of rows in the linear scramble matrix.
 
IntVector generatingMatrices
 Inline generating matrices of the digital net.
 
String generatingMatricesFileName
 Name of file with generating matrices.
 
bool joe_kuo
 Predefined generating matrices.
 
bool sobol_order_2
 
bool grayCodeOrdering
 Ordering of the digital net points.
 
bool stdRegressionCoeffs
 flag indicating the calculation/output of standardized regression coefficients
 
bool toleranceIntervalsFlag
 Flag to specify use of double sided tolerance interval equivalent normal.
 
Real tiCoverage
 Coverage parameter for the calculation of double sided tolerance interval equivalent normal.
 
Real tiConfidenceLevel
 Confidence level parameter for the calculation of double sided tolerance interval equivalent normal.
 
bool respScalingFlag
 flag to indicate bounds-based scaling of current response data set prior to build in surrogate-based methods; important for ML/MF data fits of decaying discrepancy data using regression with absolute tolerances
 
unsigned short vbdOrder
 a sub-specification of vbdFlag: interaction order limit for calculation/output of component VBD indices
 
short covarianceControl
 restrict the calculation of a full response covariance matrix for high dimensional outputs: {DEFAULT,DIAGONAL,FULL}_COVARIANCE
 
String rngName
 the basic random-number generator for NonD
 
short refinementType
 refinement type for stochastic expansions from dimension refinement keyword group
 
short refinementControl
 refinement control for stochastic expansions from dimension refinement keyword group
 
short nestingOverride
 override for default point nesting policy: NO_NESTING_OVERRIDE, NESTED, or NON_NESTED
 
short growthOverride
 override for default point growth restriction policy: NO_GROWTH_OVERRIDE, RESTRICTED, or UNRESTRICTED
 
short expansionType
 enumeration for u-space type that defines u-space variable targets for probability space transformations: EXTENDED_U (default), ASKEY_U, PARTIAL_ASKEY_U, STD_NORMAL_U, or STD_UNIFORM_U
 
bool piecewiseBasis
 boolean indicating presence of piecewise keyword
 
short expansionBasisType
 enumeration for type of basis in sparse grid interpolation (Pecos::{NODAL,HIERARCHICAL}_INTERPOLANT) or regression (Pecos::{TENSOR_PRODUCT,TOTAL_ORDER,ADAPTED}_BASIS).
 
UShortArray quadratureOrderSeq
 the quadrature_order_sequence specification in MethodNonDPCE and MethodNonDSC
 
UShortArray sparseGridLevelSeq
 the sparse_grid_level_sequence specification in MethodNonDPCE and MethodNonDSC
 
UShortArray expansionOrderSeq
 the expansion_order_sequence specification in MethodNonDPCE
 
SizetArray collocationPointsSeq
 the collocation_points_sequence specification in MethodNonDPCE
 
SizetArray expansionSamplesSeq
 the expansion_samples_sequence specification in MethodNonDPCE
 
unsigned short quadratureOrder
 the quadrature_order specification in MethodNonDPCE and MethodNonDSC
 
unsigned short sparseGridLevel
 the sparse_grid_level specification in MethodNonDPCE and MethodNonDSC
 
unsigned short expansionOrder
 the expansion_order specification in MethodNonDPCE
 
size_t collocationPoints
 the collocation_points specification in MethodNonDPCE
 
size_t expansionSamples
 the expansion_samples specification in MethodNonDPCE
 
RealVector anisoDimPref
 the dimension_preference specification for tensor and sparse grids and expansion orders in MethodNonDPCE and MethodNonDSC
 
unsigned short cubIntOrder
 the cubature_integrand specification in MethodNonDPCE
 
Real collocationRatio
 the collocation_ratio specification in MethodNonDPCE
 
Real collocRatioTermsOrder
 order applied to the number of expansion terms when applying or computing the collocation ratio within regression PCE; based on the ratio_order specification in MethodNonDPCE
 
short regressionType
 type of regression: LS, OMP, BP, BPDN, LARS, or LASSO
 
short lsRegressionType
 type of least squares regression: SVD or EQ_CON_QR
 
RealVector regressionNoiseTol
 noise tolerance(s) for OMP, BPDN, LARS, and LASSO
 
Real regressionL2Penalty
 L2 regression penalty for a variant of LASSO known as the elastic net method (default of 0 gives standard LASSO)
 
bool crossValidation
 flag indicating the use of cross-validation across expansion orders (given a prescribed maximum order) and, for some methods, noise tolerances
 
bool crossValidNoiseOnly
 flag indicating the restriction of cross-validation to estimate only the most effective noise tolerance; used to reduce cost from performing CV over both noise tolerances and expansion orders
 
unsigned short adaptedBasisAdvancements
 initial grid level for the ADAPTED_BASIS_EXPANDING_FRONT approach to defining the candidate basis for sparse recovery (compressed sensing)
 
bool normalizedCoeffs
 flag indicating the output of PCE coefficients corresponding to normalized basis polynomials
 
String pointReuse
 allows PCE construction to reuse points from previous sample sets or data import using the reuse_points specification in MethodNonDPCE
 
bool tensorGridFlag
 flag for usage of a sub-sampled set of tensor-product grid points within regression PCE; based on the tensor_grid specification in MethodNonDPCE
 
UShortArray tensorGridOrder
 order of tensor-product grid points that are sub-sampled within orthogonal least interpolation PCE; based on the tensor_grid specification in MethodNonDPCE
 
String importExpansionFile
 the import_expansion_file specification in MethodNonDPCE
 
String exportExpansionFile
 the export_expansion_file specification in MethodNonDPCE
 
unsigned short sampleType
 the sample_type specification in MethodNonDMC, MethodNonDPCE, and MethodNonDSC
 
bool dOptimal
 whether to generate D-optimal designs
 
size_t numCandidateDesigns
 number of candidate designss in D-optimal design selection
 
String reliabilityIntegration
 the first_order or second_order integration selection in MethodNonDLocalRel
 
unsigned short integrationRefine
 the import, adapt_import, or mm_adapt_import integration refinement selection in MethodNonDLocalRel, MethodNonDPCE, and MethodNonDSC
 
IntVector refineSamples
 Sequence of refinement samples, e.g., the size of the batch (e.g. number of supplemental points added) to be added to be added to the build points for an emulator at each iteration.
 
unsigned short optSubProbSolver
 the method used for solving an optimization sub-problem (e.g., pre-solve for the MAP point)
 
unsigned short numericalSolveMode
 approach for overriding an analytic solution based on simplifying assumptions that might be violated, suggesting a fallback approach, or lacking robustness, suggesting an optional override replacement
 
SizetArray pilotSamples
 the pilot_samples selection in ML/MF methods
 
short ensemblePilotSolnMode
 the solution_mode selection for ML/MF sampling methods
 
short pilotGroupSampling
 the group sampling approach for pilot sampling in ML BLUE: independent or shared
 
short groupThrottleType
 approach to restricting the total number of groups in group estimators
 
unsigned short groupSizeThrottle
 restricting the number of group combinations in group estimators by enforcing a maximum size in terms of the number of models per group
 
bool truthPilotConstraint
 the truth_fixed_by_pilot flag for ACV methods
 
short dagRecursionType
 option specified for extent of DAG enumeration within search_model_graphs for generalized ACV methods
 
unsigned short dagDepthLimit
 option specified for depth_limit in generalized ACV methods with partial graph recursion
 
short modelSelectType
 option specified for model_selection within search_model_graphs for generalized ACV methods
 
RealVector relaxFactorSequence
 sequence of (under-)relaxation factors that are applied to sample increments computed in the latest ML/MF allocation solution: f_i = f_seq[i] for iter <= len, f_seq[last_i] for iter > len
 
Real relaxFixedFactor
 fixed (under-)relaxation factor applied to sample increments computed in the latest ML/MF allocation solution: f_i = f_fixed for all iter
 
Real relaxRecursiveFactor
 (under-)relaxation factor that is applied to sample increments computed in the latest ML/MF allocation solution. The relaxation factor for each iteration (f_i) is defined from recursive application of the user specification (f_recur) to the remaining partition of unity: f_{i+1} = f_i + f_recur (1 - f_i), where f_0 = 0 gives f_1 = f_recur. E.g., f_recur = 0.5 gives f_i = 0.5, .75, .875, .9375, ...
 
short allocationTarget
 the allocationTarget selection in MethodMultilevelMC
 
bool useTargetVarianceOptimizationFlag
 the allocation_target selection in MethodMultilevelMC
 
short qoiAggregation
 the qoi_aggregation_norm selection in MethodMultilevelMC
 
RealVector scalarizationRespCoeffs
 the scalarization_response_mapping for defining the statistical goal in multilevel UQ methods
 
short convergenceToleranceType
 the convergence_tolerance_type selection in MethodMultilevelMC
 
short convergenceToleranceTarget
 the convergence_tolerance_target selection in MethodMultilevelMC
 
short multilevAllocControl
 the allocation_control selection in MethodMultilevelPCE
 
Real multilevEstimatorRate
 the estimator_rate selection in MethodMultilevelPCE
 
short multilevDiscrepEmulation
 type of discrepancy emulation in multilevel methods: distinct or recursive
 
short finalStatsType
 specification of the type of final statistics in MethodNonD
 
short finalMomentsType
 the final_moments specification in MethodNonD, subordinate to the type of final statistics
 
short distributionType
 the distribution cumulative or complementary specification in MethodNonD
 
short responseLevelTarget
 the compute probabilities, reliabilities, or gen_reliabilities specification in MethodNonD
 
short responseLevelTargetReduce
 the system series or parallel specification in MethodNonD
 
RealVectorArray responseLevels
 the response_levels specification in MethodNonD
 
RealVectorArray probabilityLevels
 the probability_levels specification in MethodNonD
 
RealVectorArray reliabilityLevels
 the reliability_levels specification in MethodNonD
 
RealVectorArray genReliabilityLevels
 the gen_reliability_levels specification in MethodNonD
 
int chainSamples
 the number of MCMC chain samples
 
int buildSamples
 the number of samples to construct an emulator, e.g., for Bayesian calibration methods
 
int samplesOnEmulator
 number of samples to perform on emulator
 
int emulatorOrder
 The total order to be used in construction of a VPS surrogate.
 
short emulatorType
 the emulator specification in MethodNonDBayesCalib
 
String mcmcType
 the mcmc type specification in MethodNonDBayesCalib
 
bool standardizedSpace
 use of standardized probability spaces for MCMC within Bayesian inference
 
bool adaptPosteriorRefine
 flag indicating adaptive refinement of the emulator in regions of high posterior probability
 
bool logitTransform
 flag indicating user activation of logit transform option within QUESO
 
bool gpmsaNormalize
 whether to apply GPMSA-internal normalization
 
bool posteriorStatsKL
 flag indicating the calculation of KL divergence between prior and posterior in Bayesian methods
 
bool posteriorStatsMutual
 flag indicating the calculation of mutual information between prior and posterior in Bayesian methods
 
bool posteriorStatsKDE
 flag indicating calculation of kernel density estimate of posterior distributions
 
bool chainDiagnostics
 flag indicating calculation of chain diagnostics
 
bool chainDiagnosticsCI
 flag indicating calculation of confidence intervals as a chain diagnositc
 
bool modelEvidence
 flag indicating calculation of the evidence of the model
 
bool modelEvidMC
 flag indicating use of Monte Carlo approximation for evidence calc.
 
int evidenceSamples
 number of prior samples to use in model evidence calculation
 
bool modelEvidLaplace
 flag indicating use of Laplace approximation for evidence calc.
 
String proposalCovType
 the type of proposal covariance: user, derivatives, or prior
 
Real priorPropCovMult
 optional multiplier for prior-based proposal covariance
 
int proposalCovUpdatePeriod
 number of samples after which to update the proposal covariance from misfit Hessian (using residual values and derivatives)
 
String proposalCovInputType
 the format of proposal covariance input: diagonal or matrix
 
RealVector proposalCovData
 raw list of real data for the proposal covariance
 
String proposalCovFile
 file from which to read proposal covariance in diagonal or matrix format
 
String advancedOptionsFilename
 file containing advanced ROL option overrides
 
String quesoOptionsFilename
 file containing advanced QUESO option overrides
 
String fitnessMetricType
 the fitness metric type specification in MethodNonDAdaptive
 
String batchSelectionType
 the batch selection type specification in MethodNonDAdaptive
 
String lipschitzType
 the Lipschitz type specification in MethodNonDPOFDarts (e.g. either local or global estimation)
 
unsigned short calibrateErrorMode
 calibration mode for observation error multipliers (CALIBRATE_*)
 
RealVector hyperPriorAlphas
 hyperparameters inverse gamma prior alphas
 
RealVector hyperPriorBetas
 hyperparameters inverse gamma prior alphas
 
int burnInSamples
 number of MCMC samples to discard from acceptance chain
 
int subSamplingPeriod
 period or skip in post-processing the acceptance chain
 
bool calModelDiscrepancy
 flag to calculate model discrepancy
 
size_t numPredConfigs
 number of prediction configurations at which to calculate model discrepancy
 
RealVector predictionConfigList
 list of prediction configurations at which to calculate model discrepancy
 
String importPredConfigs
 whether to import prediction configurations at which to calculate model discrepancy
 
unsigned short importPredConfigFormat
 tabular format for prediction configurations import file
 
String modelDiscrepancyType
 type of model discrepancy emulation
 
short polynomialOrder
 polynomial order for model discrepancy calculations: either gaussian process trend order or polynomial basis order
 
String exportCorrModelFile
 specify the name of file to which corrected model (model+discrepancy) calculations are output
 
unsigned short exportCorrModelFormat
 tabular format for corrected model (model+discrepancy) export file
 
String exportCorrVarFile
 specify the name of file to which corrected model variance calculations are output
 
unsigned short exportCorrVarFormat
 tabular format for corrected model variance export file
 
String exportDiscrepFile
 specify the name of file to which discrepancy calculations are output
 
unsigned short exportDiscrepFormat
 tabular format for model discrepancy export file
 
bool adaptExpDesign
 whether to perform adaptive Bayesian design of experiments
 
String importCandPtsFile
 whether to import candidate design points for adaptive Bayesian experimental design
 
unsigned short importCandFormat
 tabular format for the candidate design points import file
 
size_t numCandidates
 number of candidate designs for adaptive Bayesian experimental design
 
int maxHifiEvals
 maximum number of highfidelity model runs to be used for adaptive Bayesian experimental design
 
int batchSize
 number of optimal designs selected per iteration of experimental design algorithm; also number of concurrent GP refinement points for EGO
 
int batchSizeExplore
 portion of batchSize earmarked for exploration rather than acquisition
 
bool mutualInfoKSG2
 indicate that the KSG2 algorithm is to be employed in the calculation of the mutual information
 
int numChains
 number of concurrent chains
 
int numCR
 number of CR-factors
 
int crossoverChainPairs
 number of crossover chain pairs
 
Real grThreshold
 threshold for the Gelmin-Rubin statistic
 
int jumpStep
 how often to perform a long jump in generations
 
int numPushforwardSamples
 Number of samples from the prior that is pushed forward through the model to obtain the initial set of pushforward samples.
 
String dataDistType
 the type of data distribution: kde, or gaussian
 
String dataDistCovInputType
 the format of data distribution gaussian covariance input: diagonal or matrix
 
RealVector dataDistMeans
 raw list of real data for the data distribution gaussian means
 
RealVector dataDistCovariance
 raw list of real data for the data distribution gaussian covariance
 
String dataDistFile
 file from which to read data distribution data (covariance or samples )
 
String posteriorDensityExportFilename
 The filename of the export file containing an arbitrary set of samples and their corresponding density values.
 
String posteriorSamplesExportFilename
 The filename of the export file containing samples from the posterior and their corresponding density values.
 
String posteriorSamplesImportFilename
 The filename of the import file containing samples at which the posterior will be evaluated.
 
bool generatePosteriorSamples
 Flag specifying whether to generate random samples from the posterior.
 
bool evaluatePosteriorDensity
 Flag specifying whether to evaluate the posterior density at a set of samples.
 
int drNumStages
 DR num stages.
 
String drScaleType
 DR scale type.
 
Real drScale
 DR scale.
 
int amPeriodNumSteps
 AM period num steps.
 
int amStartingStep
 AM staring step.
 
Real amScale
 AM scale.
 
Real malaStepSize
 MALA step size.
 
RealVector finalPoint
 the final_point specification in MethodPSVPS
 
RealVector stepVector
 the step_vector specification in MethodPSVPS and MethodPSCPS
 
int numSteps
 the num_steps specification in MethodPSVPS
 
IntVector stepsPerVariable
 the deltas_per_variable specification in MethodPSCPS
 
RealVector listOfPoints
 the list_of_points specification in MethodPSLPS
 
String pstudyFilename
 the import_points_file spec for a file-based parameter study
 
unsigned short pstudyFileFormat
 tabular format for the parameter study points file
 
bool pstudyFileActive
 whether to import active variables only
 
UShortArray varPartitions
 the partitions specification for PStudy method in MethodPSMPS
 
Real refinementRate
 rate of mesh refinement in Richardson extrapolation
 
String importBuildPtsFile
 the file name from the import_build_points_file specification
 
unsigned short importBuildFormat
 tabular format for the build point import file
 
bool importBuildActive
 whether to import active variables only
 
String importApproxPtsFile
 the file name from the import_approx_points_file specification
 
unsigned short importApproxFormat
 tabular format for the approx point import file
 
bool importApproxActive
 whether to import active variables only
 
String exportApproxPtsFile
 the file name from the export_approx_points_file specification
 
unsigned short exportApproxFormat
 tabular format for the approx point export file
 
String exportMCMCPtsFile
 the file name from the export_mcmc_points_file specification
 
bool exportSampleSeqFlag
 flag for exporting the sequence of sample increments within multilevel sampling from the export_sample_sequence specification
 
unsigned short exportSamplesFormat
 tabular format for the MCMC chain and MLMC sample sequence exports
 
bool exportSurrogate
 Option to turn on surrogate model export (export_model)
 
String modelExportPrefix
 the filename prefix for export_model
 
unsigned short modelExportFormat
 Format selection for export_model.
 

Private Member Functions

 DataMethodRep ()
 constructor
 
void write (std::ostream &s) const
 write a DataInterfaceRep object to an std::ostream
 
void read (MPIUnpackBuffer &s)
 read a DataInterfaceRep object from a packed MPI buffer
 
void write (MPIPackBuffer &s) const
 write a DataInterfaceRep object to a packed MPI buffer
 

Friends

class DataMethod
 the handle class can access attributes of the body class directly
 

Detailed Description

Body class for method specification data.

The DataMethodRep class is used to contain the data from a method keyword specification. Default values are managed in the DataMethodRep constructor. Data is public to avoid maintaining set/get functions, but is still encapsulated within ProblemDescDB since ProblemDescDB::dataMethodList is private.


The documentation for this class was generated from the following files: