![]() |
Dakota Reference Manual
Version 6.13
Explore and Predict with Confidence
|
Enable exporting output sample sequences on files
Alias: none
Argument(s): none
Child Keywords:
Required/Optional | Description of Group | Dakota Keyword | Dakota Keyword Description | |
---|---|---|---|---|
Optional (Choose One) | Tabular Format (Group 1) | custom_annotated | Export sample sequences enabling file format customization | |
annotated | Export sample sequences with descriptors | |||
freeform | Export sample sequences without heading descriptors |
If present, separate output files are written for each model form and discretization level. For the multilevel technique, separate files are written for the samples used at each iteration (pilot samples are denoted by iteration 0).
Default Behavior
If not specified, the annotated
format is assumed.
Expected Output
Separate output files are generated according to the following format: {ml/cv}_{interface_id}_{iteration_number}_{level_number}_{number_of_samples}
.dat.
If one single model form is present the first field of the file name is ml_
, otherwise ml_
is used for the HF model and cv_
is used for the LF one.
The following method block
method, model_pointer = 'HIERARCH' multilevel_sampling pilot_samples = 20 seed = 1237 convergence_tolerance = .01 output silent export_sample_sequence
results in enabling the sample output on file with the defaults annotated
format.
The following variables block
variables, id_variables = 'LF_VARS' uniform_uncertain = 7 lower_bounds = 7*-1. upper_bounds = 7* 1. discrete_state_set integer = 2 num_set_values = 4 1 set_values = 5 15 30 60 # number of spatial coords 3 # number of Fourier solution modes initial_state = 5 3 descriptors 'N_x' 'N_mod'
illustrates how to define descriptors for a model form. For instance, in this case the descriptors N_x
and N_mod
are reported in the sample sequences files for all the format.