Skip to content

Conversation

@anth-volk
Copy link
Collaborator

Fixes #207.

This PR introduces a very naïve means of preventing downsampling when constructing the Pooled 3-Year CPS dataset, which we use by default for states due to states' limited number of observations in any given single year CPS set. This PR creates three new datasets - essentially the old un-downsampled 2021, '22, and '23 CPS - then uses those to construct the Pooled 3-Year while maintaining the default downsampled versions of these, as well.

This code should be improved separately, and if this code is still here, unchanged, on July 1, 2025, someone should open a ticket.

@anth-volk anth-volk requested a review from MaxGhenis April 11, 2025 22:10
@anth-volk
Copy link
Collaborator Author

Tests not running due to expiry of GitHub PAT

Copy link
Contributor

@MaxGhenis MaxGhenis left a comment

Choose a reason for hiding this comment

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

sure why not

@anth-volk
Copy link
Collaborator Author

Tests now failing due to some sort of county FIPS error; unclear what's going on

@anth-volk
Copy link
Collaborator Author

Attempting to fix in most recent push

Copy link
Contributor

@nikhilwoodruff nikhilwoodruff left a comment

Choose a reason for hiding this comment

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

Just a few minor fixes, then LGTM

@anth-volk anth-volk merged commit e409ead into main Apr 22, 2025
2 checks passed
@anth-volk anth-volk deleted the fix/dont-downsample-pooled-cps branch April 22, 2025 18:27
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.

Stop downsampling pooled 3-year CPS

4 participants