You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Small documentation note: the guidance for importing the trees into fitted object x is to call invisible(x$fit$state). However, in the case of rbart_vi(), x$fit is itself a list-object, requiring an adjustment to make the technique work properly (e.g., invisible(x$fit[[1]]$state) in the use case I encountered, where the list at x$fit contained a single element).
It would be great if the docs could be updated to help users be aware of this nuance. Thanks for all your work building this great tool.
EDIT: even this doesn't produce fully equivalent results when working with a loaded model vs one that was fit in the current session. I'm at a loss for how to proceed here.
(on Windows 10 using dbarts 0.9-22. This is all with educational data on a secure server, so I don't have a ready example to show, sorry.)
The text was updated successfully, but these errors were encountered:
Small documentation note: the guidance for importing the trees into fitted object
x
is to callinvisible(x$fit$state)
. However, in the case ofrbart_vi()
,x$fit
is itself a list-object, requiring an adjustment to make the technique work properly (e.g.,invisible(x$fit[[1]]$state)
in the use case I encountered, where the list atx$fit
contained a single element).It would be great if the docs could be updated to help users be aware of this nuance. Thanks for all your work building this great tool.
EDIT: even this doesn't produce fully equivalent results when working with a loaded model vs one that was fit in the current session. I'm at a loss for how to proceed here.
(on Windows 10 using dbarts 0.9-22. This is all with educational data on a secure server, so I don't have a ready example to show, sorry.)
The text was updated successfully, but these errors were encountered: