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 backfill alerting system for CHNG Outpatient Data #1383

Open
wants to merge 3 commits into
base: main
Choose a base branch
from

Conversation

jingjtang
Copy link
Contributor

Description

Add backfill alerting system for CHNG Outpatient Data. The pipeline is compatible for the following magnitude:

  • Count type: Covid outpatient count or total outpatient count
  • Geo level: state level (ignore as, mp, gu) and county level (200 most populated counties)
  • Backfill Variable:
    • backfill fraction (training and testing monthly, anchor_lag = 60 days)
    • change rates (training and testing daily, ref_lag = 1 / 7 days)
  • Using Gamma GLM for model training
  • Using generalized prediction residues for evaluation, taking weighted average of the residues considering how large the lags are
  • Residues generated in testing data (most recent data) are compared with residues in training data to see whether they are surprisingly large or small
  • Generalized residues for specific report dates or location-report date pairs with extremely large/small quantiles are reported

Changelog

  • Add supporting code to delphi_backfill_alerting
  • Add unit tests to tests

TO-DOs

  • Work with Brian to test the elast alert while under review
  • Communicate with Brian whether to delete the input cache folder which share the downloaded chng data with changhc indicator pipeline

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.

None yet

1 participant