Skip to content

Conversation

@dshemetov
Copy link

Update:

  • Environment variables
  • Directory structure

Add:

  • An overview of the pipeline structure
  • A guide to adding a forecaster with information about the interface and expected arguments
  • Information about utilities

Drive-by edit to location of some utility functions that better belong in utils rather than aux data utils.

@dshemetov dshemetov requested a review from dsweber2 April 18, 2025 22:35
README.md Outdated
Comment on lines 185 to 189
- `filter_source`: a string of the source to filter to. This is often empty, but
sometimes it's a string like "nhsn". This allows us to create one large
dataset (such as `joined_archive_data`) that contains all the data for all
sources, which we can feed uniformly to every forecaster and have them select
which data they want to use.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this ends up being required if you want to run it on flu.

In general, it might be easier to point to a template forecaster to some degree that's what scaled_pop is for, though we could probably go more minimal.

@dshemetov dshemetov merged commit 6934a1e into main Apr 19, 2025
1 check failed
@dshemetov dshemetov deleted the ds/readme branch April 19, 2025 00:31
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants