import_build_points_file
File containing points you wish to use to build a surrogate
Specification
Alias: import_points_file samples_file
Arguments: STRING
Default: no point import from a file
Child Keywords:
Required/Optional |
Description of Group |
Dakota Keyword |
Dakota Keyword Description |
---|---|---|---|
Optional (Choose One) |
Tabular Format |
Selects custom-annotated tabular file format |
|
Selects annotated tabular file format |
|||
Selects freeform file format |
|||
Optional |
Import only active variables from tabular data file |
Description
The import_build_points_file
allows the user to specify a file that
contains a list of points and truth model responses used to construct
a surrogate model. These can be used by all methods that (explicitly,
e.g. surrogate-based optimization, or implicitly, e.g. efficient
global optimization) operate on a surrogate. In particular, these
points and responses are used in place of truth model evaluations to
construct the initial surrogate. When used to construct surrogate
models or emulators these are often called build points or training
data.
Default Behavior
By default, methods do not import points from a file.
Usage Tips
Dakota parses input files without regard to whitespace, but the import_build_points_file must be in one of three formats:
annotated
(default)custom_annotated
freeform
Examples
method
polynomial_chaos
expansion_order = 4
import_build_points_file = 'dakota_uq_rosenbrock_pce_import.annot.pts.dat'