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

updating field_names, adding extreme heat

Browse source
This commit is contained in:
lucasmbrown-usds 2021-12-05 20:52:50 -05:00
parent e52b99542b
commit 3b5ea59b53
3 changed files with 36 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
data/data-pipeline/data_pipeline/etl/score/etl_score.py
View file

@ -168,14 +168,10 @@ class ScoreETL(ExtractTransformLoad):
# Load COI data
child_opportunity_index_csv = (
<<<<<<< HEAD
constants.DATA_PATH
/ "dataset"
/ "child_opportunity_index"
/ "usa.csv"
=======
constants.DATA_PATH / "dataset" / "child_opportunity_index" / "usa.csv"
>>>>>>> 050a5c30 (added fields to score_etl)
)
self.child_opportunity_index_df = pd.read_csv(
child_opportunity_index_csv,
@ -364,11 +360,7 @@ class ScoreETL(ExtractTransformLoad):
self.census_acs_median_incomes_df,
self.census_decennial_df,
self.census_2010_df,
<<<<<<< HEAD
self.child_opportunity_index_df,
=======
self.child_opportunity_index_df
>>>>>>> 050a5c30 (added fields to score_etl)
]
# Sanity check each data frame before merging.

14
data/data-pipeline/data_pipeline/score/field_names.py
View file

@ -236,6 +236,11 @@ LOW_READING_FIELD = "Low third grade reading proficiency"
EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for expected population loss rate and is low income"
EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for expected agriculture loss rate and is low income"
EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for expected building loss rate and is low income"
EXTREME_HEAT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD = (
f"At or above the {PERCENTILE}th percentile for summer days above 90F and "
f"the median house value is less than {MEDIAN_HOUSE_VALUE_PERCENTILE}th "
f"percentile and is low income"
)
# Clean energy and efficiency
PM25_EXPOSURE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for PM2.5 exposure and is low income"
@ -275,6 +280,11 @@ LOW_LIFE_EXPECTANCY_LOW_INCOME_FIELD = (
f"for low life expectancy and is low income"
)
HEALTHY_FOOD_LOW_INCOME_FIELD = (
f"At or above the {PERCENTILE}th percentile for low "
f"access to healthy food and is low income"
)
# Workforce
UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
f"At or above the {PERCENTILE}th percentile for unemployment"
@ -317,6 +327,10 @@ HEALTHY_FOOD_LOW_INCOME_FIELD = (
f"At or above the {PERCENTILE}th percentile for low "
f"access to healthy food and is low income"
)
READING_LOW_HS_EDUCATION_FIELD = (
f"At or above the {PERCENTILE}th percentile for 3rd grade reading proficiency"
" and has low HS education"
)
THRESHOLD_COUNT = "Total threshold criteria exceeded"

22
data/data-pipeline/data_pipeline/score/score_l.py
View file

@ -179,6 +179,7 @@ class ScoreL(Score):
field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD,
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD,
field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD,
field_names.EXTREME_HEAT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD,
]
expected_population_loss_threshold = (
@ -205,6 +206,20 @@ class ScoreL(Score):
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
extreme_heat_median_home_value_threshold = (
self.df[
field_names.EXTREME_HEAT_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX
]
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) & (
self.df[
field_names.MEDIAN_HOUSE_VALUE_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX
]
<= self.MEDIAN_HOUSE_VALUE_THRESHOLD
)
self.df[field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD] = (
expected_population_loss_threshold
& self.df[field_names.FPL_200_SERIES]
@ -220,6 +235,13 @@ class ScoreL(Score):
& self.df[field_names.FPL_200_SERIES]
)
self.df[
field_names.EXTREME_HEAT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD
] = (
extreme_heat_median_home_value_threshold
& self.df[field_names.FPL_200_SERIES]
)
self._increment_total_eligibility_exceeded(climate_eligibility_columns)
return self.df[climate_eligibility_columns].any(axis="columns")