Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Syncing lineages between model and eval data #49

Open
afmagee42 opened this issue Aug 29, 2024 · 0 comments · May be fixed by #51
Open

Syncing lineages between model and eval data #49

afmagee42 opened this issue Aug 29, 2024 · 0 comments · May be fixed by #51
Labels
architecture Pipeline engineering, class structures, etc.

Comments

@afmagee42
Copy link
Collaborator

I'm looking at the pair of model.csv and eval.csv for a 2022-01-01 forecast date, and the evaluation data has one more lineage than the model data, namely 22C. We need to make sure that the set of lineages is consistent across modeling and evaluation.

Part of the awkwardness here is hindsight, in that we have said 22C is a lineage we want to model for all three of the forecast dates in retrospective-forecasting/config even though it emerges after the first calibration period.

I think the generally correct thing to do is to make sure such lineages get labeled as "other" but there may be the possibility that we know we want to model a lineage but just don't happen to see it? (Something which has attracted attention elsewhere, but not been imported yet, for instance.)

@thanasibakis thanasibakis linked a pull request Sep 10, 2024 that will close this issue
@afmagee42 afmagee42 added the architecture Pipeline engineering, class structures, etc. label Dec 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
architecture Pipeline engineering, class structures, etc.
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant