cregouby

Anything I can help or modify to have this integrated (so I can move https://github.com/rstudio/vetiver-r/pull/124 to Ready-for-review)?

Hello @earowang, Sure *_gaps() don't know how to handle irregular temporal data, and this is the reason for my **feature request** here. And sorry for my mistake in using index2...

I fully agree of the missleading use of term interval here, so let's call it the `min_gap`, that could be the minimum time between end-time of event n and start-time...

Hello Ben, sorry for this miss. corrected. Hope you will b able to fix it. Best regards, C.R.

Hello @sametsoekel There is not such a possibility for now in the package. The easiest way to achieve it is to make a `tabnet_fit()` loop without split on your training-set,...

I'll do ! Thanks !

@dfalbel, I think I'm not mature enough on that task. Would you be kind enough to take over ?

Hello @parsifal9, I'm not from the single-cell genomic business, but I think tabnet cannot do that. This is because, by design, there is far too much degree of freedom in...

and to my knowledge, the Seurat methodology can not be challenged so easily ;-)

but in case you have a very large number of observations n without outcome, you can try to pre-train the tabnet model with them. That maybe could help the convergence...