search

kosukeimai / wru

Who Are You? Bayesian Prediction of Racial Category Using Surname and Geolocation
129 stars 30 forks source link

Add support for ZCTAs and 2020 age and sex data #123

Closed rossellhayes closed 10 months ago

rossellhayes commented 10 months ago

This PR adds support for using ZCTAs as the geographic unit for predictions. It also adds support for making predictions including 2020 age and sex data. Previously, only 2010 data could be used to make predictions with age and sex.

In order to accomplish this, this PR pulls 2020 data from the Demographic and Housing Characteristics File (DHC) rather than Redistricting Data (PL 94-171). PL 94-171 does not report age and sex data and does not report any data at the ZCTA level. I made an effort to ensure that data that was saved with the previous version of get_census_data() can still be used to make predictions.

This PR is branched from #120.

1beb commented 10 months ago

Closing this one because it was against main. PR'd these into dev branch.