publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 14:21:16 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

details on ranked percentiles

Browse source
This commit is contained in:
Saran Ahluwalia 2022-01-01 14:49:43 -05:00
commit c1e35fb2f5
2 changed files with 8 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

9
data/data-pipeline/data_pipeline/etl/sources/maryland_ejscreen/etl.py
View file

@ -92,14 +92,13 @@ class MarylandEJScreenETL(ExtractTransformLoad):
inplace=True, inplace=True,
) )
# Interpretation: An EJ score (reported as a percentile)
# has a percentile rank of N for some N between 0 - 100"
self.df[field_names.MARYLAND_EJSCREEN_PERCENTILE_FIELD] = self.df[ self.df[field_names.MARYLAND_EJSCREEN_PERCENTILE_FIELD] = self.df[
field_names.MARYLAND_EJSCREEN_SCORE_FIELD field_names.MARYLAND_EJSCREEN_SCORE_FIELD
].rank( ].rank(pct=True, ascending=True)
pct=True,
ascending=True
)
# An arbitrarily chosen percentile is used in the comparison tool output # An arbitrarily chosen threshold is used in the comparison tool output
self.df[field_names.MARYLAND_EJSCREEN_BURDENED_THRESHOLD_FIELD] = ( self.df[field_names.MARYLAND_EJSCREEN_BURDENED_THRESHOLD_FIELD] = (
self.df[field_names.MARYLAND_EJSCREEN_PERCENTILE_FIELD] > 0.75 self.df[field_names.MARYLAND_EJSCREEN_PERCENTILE_FIELD] > 0.75
) )

5
data/data-pipeline/data_pipeline/score/field_names.py
View file

@ -239,8 +239,11 @@ MARYLAND_EJSCREEN_PERCENTILE_FIELD: str = (
MARYLAND_EJSCREEN_SCORE_FIELD: str = "Maryland Environmental Justice Score" MARYLAND_EJSCREEN_SCORE_FIELD: str = "Maryland Environmental Justice Score"
# this references ranked percentiles
# please see here for interpretation: https://github.com/usds/justice40-tool/issues/239#issuecomment-1003567593
# and here: https://github.com/usds/justice40-tool/issues/239#issuecomment-1003448074
MARYLAND_EJSCREEN_BURDENED_THRESHOLD_FIELD: str = ( MARYLAND_EJSCREEN_BURDENED_THRESHOLD_FIELD: str = (
"Tract is greater than 75th percentile for Maryland EJ Score" "Tract has an EJ Score greater than 75"
) )
# Child Opportunity Index data # Child Opportunity Index data