From a8e94ef8de55f818e94e380e6eca0db0a024d7bf Mon Sep 17 00:00:00 2001 From: Saran Ahluwalia Date: Wed, 12 Jan 2022 19:06:06 -0500 Subject: [PATCH] updates --- .../etl/sources/maryland_ejscreen/etl.py | 16 ++++++++++++---- .../data_pipeline/score/field_names.py | 4 ---- 2 files changed, 12 insertions(+), 8 deletions(-) diff --git a/data/data-pipeline/data_pipeline/etl/sources/maryland_ejscreen/etl.py b/data/data-pipeline/data_pipeline/etl/sources/maryland_ejscreen/etl.py index a08d6f59..25aad232 100644 --- a/data/data-pipeline/data_pipeline/etl/sources/maryland_ejscreen/etl.py +++ b/data/data-pipeline/data_pipeline/etl/sources/maryland_ejscreen/etl.py @@ -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 diff --git a/data/data-pipeline/data_pipeline/score/field_names.py b/data/data-pipeline/data_pipeline/score/field_names.py index 9ea159e3..08235b0f 100644 --- a/data/data-pipeline/data_pipeline/score/field_names.py +++ b/data/data-pipeline/data_pipeline/score/field_names.py @@ -233,10 +233,6 @@ MARYLAND_EJSCREEN_TRACT_90_PERCENTILE_FIELD: str = ( "Tract is >=90% all other Maryland Tracts" ) -MARYLAND_EJSCREEN_PERCENTILE_RANK_FIELD: str = ( - "Maryland EJSCREEN Percentile Rank for EJ Score" -) - MARYLAND_EJSCREEN_SCORE_FIELD: str = "Maryland Environmental Justice Score" # this references percentile ranks