publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-02-23 01:54:18 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'emma-nechamkin/release/score-narwhal' of github.com:usds/justice40-tool into emma-nechamkin/release/score-narwhal

Browse source
This commit is contained in:
Emma Nechamkin 2022-09-15 12:07:40 -04:00
commit fe4e8e52d2
1 changed files with 8 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
data/data-pipeline/data_pipeline/etl/score/etl_score.py
View file

@ -579,12 +579,17 @@ class ScoreETL(ExtractTransformLoad):
f"Dropping {len(drop_tracts)} tracts from Linguistic Isolation"
)
elif numeric_column == field_names.DOT_TRAVEL_BURDEN_FIELD:
elif numeric_column in [
field_names.DOT_TRAVEL_BURDEN_FIELD,
field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD,
]:
# Not having any people appears to be correlated with transit burden, but also doesn't represent
# on the ground need. For now, we remove these tracts from the percentile calculation. (To be QAed live)
# on the ground need. For now, we remove these tracts from the percentile calculation.ß
# Similarly, we want to exclude low population tracts from FEMA's index
low_population = 20
drop_tracts = df_copy[
df_copy[field_names.TOTAL_POP_FIELD] <= low_population
df_copy[field_names.TOTAL_POP_FIELD].fillna(0)
<= low_population
][field_names.GEOID_TRACT_FIELD].to_list()
logger.info(
f"Dropping {len(drop_tracts)} tracts from DOT traffic burden"