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

add epiweekly other forecast samples to standard pipeline #270

Merged
merged 36 commits into from
Jan 4, 2025

Conversation

dylanhmorris
Copy link
Contributor

@dylanhmorris dylanhmorris commented Jan 2, 2025

Key changes

  • Pipeline now outputs two kinds of epiweekly proportion forecasts:

    • Ones in which both the target disease and other ed visits are forecast daily and then aggregated to epiweekly
    • One in which only the target disease is forecast daily and aggregated; the other ed visits are forecast epiweekly
  • Pipeline automatically produces (and collates) plots of epiweekly aggregate predictions as well as daily-scale predictions, for better analysis of the actual forecast. For proportions, this includes both denominator options.

  • End to end test runs, and all plots are successfully collated.

  • to_epiweekly_quantile_table() in hewr now uses the pre-aggregated epiweekly trajectories rather than doing aggregation, and can be configured to use either of the two options (aggregated daily or directly forecast epiweekly) for the Other forecast.

Out of scope

Incorporation of epiweekly plots into diagnostic report (should be done, separate issue imo)

@dylanhmorris dylanhmorris changed the title Dhm epiweekly denom add epiweekly other forecast samples to standard pipeline Jan 2, 2025
Copy link

codecov bot commented Jan 2, 2025

Codecov Report

Attention: Patch coverage is 23.65591% with 142 lines in your changes missing coverage. Please review.

Project coverage is 16.54%. Comparing base (591b416) to head (6998961).
Report is 1 commits behind head on main.

Files with missing lines Patch % Lines
hewr/R/process_state_forecast.R 8.66% 137 Missing ⚠️
pipelines/postprocess_forecast_batches.py 0.00% 5 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main     #270      +/-   ##
==========================================
- Coverage   18.46%   16.54%   -1.93%     
==========================================
  Files          21       21              
  Lines        1446     1481      +35     
==========================================
- Hits          267      245      -22     
- Misses       1179     1236      +57     
Flag Coverage Δ
hewr 47.79% <24.30%> (-8.01%) ⬇️
pipelines 0.00% <0.00%> (ø)
pyrenew_hew 1.89% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@dylanhmorris dylanhmorris marked this pull request as ready for review January 3, 2025 19:35
@damonbayer damonbayer self-requested a review January 3, 2025 20:53
Copy link
Collaborator

@damonbayer damonbayer left a comment

Choose a reason for hiding this comment

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

Could be merged if needed, but I think some of my comments are clear and easy improvements.

@dylanhmorris dylanhmorris merged commit 9c9d86b into main Jan 4, 2025
15 checks passed
@dylanhmorris dylanhmorris deleted the dhm-epiweekly-denom branch January 4, 2025 16:32
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.

2 participants