-
Notifications
You must be signed in to change notification settings - Fork 14
Multiple train/test splits result in discontinuous batches #127
Comments
Interesting. It's been a while since I wrote this (or thought about this ... or used this 😄). Have you confirmed that this is what happens? |
Using the existing If you apply |
I think this issue has been addressed from #218 |
river-dl/river_dl/preproc_utils.py
Lines 112 to 117 in a7629eb
Here, if we have discontinuous training and testing groups (i.e. two sets of date ranges for both), and batches are set to anything other than 365, then I think this results in one batch that starts in the first date range and ends in the second. I think we should first group by water year, then split into batches and just pad and/or drop the last one. What do you all think?
The text was updated successfully, but these errors were encountered: