publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-26 01:01:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

updates

Browse source
This commit is contained in:
Saran Ahluwalia 2022-01-12 19:06:06 -05:00
commit a8e94ef8de
2 changed files with 12 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

16
data/data-pipeline/data_pipeline/etl/sources/maryland_ejscreen/etl.py
View file

@ -32,7 +32,8 @@ class MarylandEJScreenETL(ExtractTransformLoad):
field_names.MARYLAND_EJSCREEN_TRACT_90_PERCENTILE_FIELD,
field_names.MARYLAND_EJSCREEN_SCORE_FIELD,
field_names.MARYLAND_EJSCREEN_BURDENED_THRESHOLD_FIELD,
field_names.MARYLAND_EJSCREEN_SCORE_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
field_names.MARYLAND_EJSCREEN_SCORE_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX,
]
self.df: pd.DataFrame
@ -94,13 +95,20 @@ class MarylandEJScreenETL(ExtractTransformLoad):
# 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_SCORE_FIELD + field_names.PERCENTILE_FIELD_SUFFIX] = self.df[
self.df[
field_names.MARYLAND_EJSCREEN_SCORE_FIELD
].rank(pct=True, ascending=True)
+ field_names.PERCENTILE_FIELD_SUFFIX
] = self.df[field_names.MARYLAND_EJSCREEN_SCORE_FIELD].rank(
pct=True, ascending=True
)
# 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_SCORE_FIELD + field_names.PERCENTILE_FIELD_SUFFIX] > 0.75
self.df[
field_names.MARYLAND_EJSCREEN_SCORE_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX
]
> 0.75
)
# Baseline Comparisons with some quartiles and the 90th percent OF EJ Score