-
Notifications
You must be signed in to change notification settings - Fork 199
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Kriging based surrogates are not pickable #153
Comments
user-defined correlation or regression functions is not supported by SMT. In the current version of SMT, if the user wants to add a defined function, he has to declare it manually. I agree to make these options an enumerate |
My point is that currently the user could declare his own function and give it to the |
Current Kriging based surrogates are not pickable because of options related to regression or correlation functions which are actual functions which results in the following error message
Actually the declaration of those options (
poly
,corr
) is a bit hacky as such option allows to specify a callable while acceptable values are documented to be an enumerate.This implementation has the benefit to allow the user to specify is own functions for correlation and regression but it prevents from pickling.
I would like to propose a pull request to modify the code to have the current Krigings implementation pickable (hence make these options an enumerate). I am not sure at the moment on what is the best way to keep the "user-defined correlation or regression functions" capability. Is it used? Do we have to keep it? Plugin mechanism? Any thoughts?
The text was updated successfully, but these errors were encountered: