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
Maybe out of scope for this project, but for TCGA data it would be useful to support PFS or OS being set to NaN. Right now, this gives an error because of the PFS <= OS assertion
The text was updated successfully, but these errors were encountered:
I think that's fair game. cohorts seems to support several random use cases; e.g. it's even useful for both genetic data and purely clinical data. Eventually, instead of None in a million places, it might be nice to clearly delineate some categories of use (and eventually split them out). But None in a lot of places seems fine for now.
This will actually be important for the RCC analysis, where we expect a subset of patients to have temporarily unknown survival status until time of unblinding
Maybe out of scope for this project, but for TCGA data it would be useful to support PFS or OS being set to NaN. Right now, this gives an error because of the PFS <= OS assertion
The text was updated successfully, but these errors were encountered: