-
-
Notifications
You must be signed in to change notification settings - Fork 6
Conversation
…/nowcasting_dataset into jack/update-nwpdatasource
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
I'm pretty sure that, once the NWP shape issue is also fixed, then we should be all set to produce NWP batches (although NWP batches will be output pretty slowly until #311 is done). |
# If there are any duplicated init_times then drop the duplicated init_times: | ||
init_time = pd.DatetimeIndex(ukv["init_time"]) | ||
if not init_time.is_unique: | ||
_LOG.warning("NWP Zarr has duplicated init_times. Fixing...") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
good warning
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I like it where it says how many duplicates were dropped too. nice to have thought
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good idea - I'll add that! Thanks!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
great work - good comments and I like the TODOs with issue numbers
Pull Request
Description
Change
nowcasting_dataset
to use new NWP Zarr.Fixes #371
How Has This Been Tested?
prepare_ml_data.py
runs.Checklist: