Closed mlsuh closed 1 year ago
Patch coverage: 98.02
% and project coverage change: -0.15
:warning:
Comparison is base (
d603f94
) 98.83% compared to head (84ae7df
) 98.68%.
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.
Please move the doe.jl
into the simulations
subfolder.
FractionalFactorial and BoxBehnken are now implemented. Can be tested by (un)commenting and manipulating the respective lines of code in ...demo/metamodels/responsesurface.jl
It turns out the mapping through standard normal space etc. is not the way to go. With the design of experiments we just want to cover the input space and don't care about the exact distributions. So we are going to do the following:
For finite bounds we just scale and shift the values between the bounds of the distribution. For example, for a Uniform(-1, 1)
the values [0.0, 0.5, 1.0]
would become[-1, 0.0, 1.0]
. For infinite bounds we add another property to all the designs σ::Integer=1
. In the transformation we will use +
or -
σ
times the standard deviation of the rv as the bounds.
This way, no mappings through the cdf
are performed and there is no risk of inf
or nan
values.
@mlsuh Can you adapt the sample
function to behave like this?
Nice work @mlsuh!
Adds a number of design of experiments to use with the
ResponseSurface
.The documentation and demo files include an example where the Himmelblau function is approximated.