David Nicholson

Just updating that I asked a question in the dask forum here: https://dask.discourse.group/t/how-to-troubleshoot-optimize-n-partitions-partition-size-for-dask-bag/1216/2

Hi again @kalleknast just checking back -- I never got a reply on the `dask` forum. Any chance you'd be willing to share data so I could replicate and test...

Awesome, thank you @kalleknast! I will download this weekend to verify I can access, and see if I can replicate the issue on my machine. I'm catching up on the...

Confirming I was able to download the files and replicate this issue, thank you @kalleknast -- I've got this on the to-do list for features/enhancements now

try re-creating the .csv but without an `annot_format` argument in the `toml` config file -- i.e. as if it was not annotated this should cause `annot_format` to be `none` for...

The simplest way to be able to run `predict` on any dataset `csv` would be to just remove the logic that checks for what split to use. But then we...

Changed title to reflect > The second simplest way would be to add a config option that says "predict on this split" We'd still need to work around core issue...

Thank you @vivinastase -- you are completely right, as you suggested on #135 https://github.com/NickleDave/vak/issues/135#issuecomment-1063048286 > Because you asked how you could make the process better -- it would be good...

Note that #537 blocks this. Should also address #471 at the same time

Hmm. Yes, this would be a good place for the error message to tell you which files are generating the error. Can you try the following and see what it...