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

Integrate proximity to waste sites into pollution factors (#959)

Browse source 
* add tsdf proximity into predicate to determine thresholds

* strict inequality --> inclusive

Co-authored-by: Saran Ahluwalia <sarahluw@cisco.com>
This commit is contained in:
Saran Ahluwalia 2021-12-03 12:43:48 -05:00 • committed by GitHub
parent fdba1eb171
commit 8cb1070d1e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 32 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

61
data/data-pipeline/data_pipeline/score/score_l.py
View file

@ -70,21 +70,21 @@ class ScoreL(Score):
field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD_NAME field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD_NAME
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
| ( | (
self.df[ self.df[
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD_NAME field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD_NAME
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
| ( | (
self.df[ self.df[
field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD_NAME field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD_NAME
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
) )
@ -93,7 +93,7 @@ class ScoreL(Score):
field_names.POVERTY_LESS_THAN_200_FPL_FIELD field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.LOW_INCOME_THRESHOLD >= self.LOW_INCOME_THRESHOLD
) & climate_criteria ) & climate_criteria
def _energy_factor(self) -> bool: def _energy_factor(self) -> bool:
@ -107,12 +107,12 @@ class ScoreL(Score):
field_names.ENERGY_BURDEN_FIELD field_names.ENERGY_BURDEN_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) | ( ) | (
self.df[ self.df[
field_names.PM25_FIELD + field_names.PERCENTILE_FIELD_SUFFIX field_names.PM25_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
return ( return (
@ -120,7 +120,7 @@ class ScoreL(Score):
field_names.POVERTY_LESS_THAN_200_FPL_FIELD field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.LOW_INCOME_THRESHOLD >= self.LOW_INCOME_THRESHOLD
) & energy_criteria ) & energy_criteria
def _transportation_factor(self) -> bool: def _transportation_factor(self) -> bool:
@ -137,12 +137,12 @@ class ScoreL(Score):
self.df[ self.df[
field_names.DIESEL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX field_names.DIESEL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) | ( ) | (
self.df[ self.df[
field_names.TRAFFIC_FIELD + field_names.PERCENTILE_FIELD_SUFFIX field_names.TRAFFIC_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
return ( return (
@ -150,7 +150,7 @@ class ScoreL(Score):
field_names.POVERTY_LESS_THAN_200_FPL_FIELD field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.LOW_INCOME_THRESHOLD >= self.LOW_INCOME_THRESHOLD
) & transportation_criteria ) & transportation_criteria
def _housing_factor(self) -> bool: def _housing_factor(self) -> bool:
@ -172,28 +172,28 @@ class ScoreL(Score):
field_names.LEAD_PAINT_FIELD field_names.LEAD_PAINT_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
& ( & (
self.df[ self.df[
field_names.MEDIAN_HOUSE_VALUE_FIELD field_names.MEDIAN_HOUSE_VALUE_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
< self.MEDIAN_HOUSE_VALUE_THRESHOLD <= self.MEDIAN_HOUSE_VALUE_THRESHOLD
) )
) | ( ) | (
self.df[ self.df[
field_names.HOUSING_BURDEN_FIELD field_names.HOUSING_BURDEN_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
return ( return (
self.df[ self.df[
field_names.POVERTY_LESS_THAN_200_FPL_FIELD field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.LOW_INCOME_THRESHOLD >= self.LOW_INCOME_THRESHOLD
) & housing_criteria ) & housing_criteria
def _pollution_factor(self) -> bool: def _pollution_factor(self) -> bool:
@ -205,10 +205,13 @@ class ScoreL(Score):
pollution_criteria = ( pollution_criteria = (
self.df[field_names.RMP_FIELD + field_names.PERCENTILE_FIELD_SUFFIX] self.df[field_names.RMP_FIELD + field_names.PERCENTILE_FIELD_SUFFIX]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) | ( ) | (
self.df[field_names.NPL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX] self.df[field_names.NPL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) | (
self.df[field_names.TSDF_FIELD + field_names.PERCENTILE_FIELD_SUFFIX]
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
return pollution_criteria & ( return pollution_criteria & (
@ -216,7 +219,7 @@ class ScoreL(Score):
field_names.POVERTY_LESS_THAN_200_FPL_FIELD field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.LOW_INCOME_THRESHOLD >= self.LOW_INCOME_THRESHOLD
) )
def _water_factor(self) -> bool: def _water_factor(self) -> bool:
@ -230,13 +233,13 @@ class ScoreL(Score):
field_names.POVERTY_LESS_THAN_200_FPL_FIELD field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.LOW_INCOME_THRESHOLD >= self.LOW_INCOME_THRESHOLD
) & ( ) & (
self.df[ self.df[
field_names.WASTEWATER_FIELD field_names.WASTEWATER_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
def _health_factor(self) -> bool: def _health_factor(self) -> bool:
@ -258,21 +261,21 @@ class ScoreL(Score):
field_names.DIABETES_FIELD field_names.DIABETES_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
| ( | (
self.df[ self.df[
field_names.ASTHMA_FIELD field_names.ASTHMA_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
| ( | (
self.df[ self.df[
field_names.HEART_DISEASE_FIELD field_names.HEART_DISEASE_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
| ( | (
self.df[ self.df[
@ -281,7 +284,7 @@ class ScoreL(Score):
] ]
# Note: a high life expectancy is good, so take 1 minus the threshold to invert it, # Note: a high life expectancy is good, so take 1 minus the threshold to invert it,
# and then look for life expenctancies lower than that (not greater than). # and then look for life expenctancies lower than that (not greater than).
< 1 - self.ENVIRONMENTAL_BURDEN_THRESHOLD <= 1 - self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
) )
return ( return (
@ -289,7 +292,7 @@ class ScoreL(Score):
field_names.POVERTY_LESS_THAN_200_FPL_FIELD field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.LOW_INCOME_THRESHOLD >= self.LOW_INCOME_THRESHOLD
) & health_criteria ) & health_criteria
def _workforce_factor(self) -> bool: def _workforce_factor(self) -> bool:
@ -309,7 +312,7 @@ class ScoreL(Score):
field_names.UNEMPLOYMENT_FIELD field_names.UNEMPLOYMENT_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
| ( | (
self.df[ self.df[
@ -318,23 +321,23 @@ class ScoreL(Score):
] ]
# Note: a high median income as a % of AMI is good, so take 1 minus the threshold to invert it. # Note: a high median income as a % of AMI is good, so take 1 minus the threshold to invert it.
# and then look for median income lower than that (not greater than). # and then look for median income lower than that (not greater than).
< 1 - self.ENVIRONMENTAL_BURDEN_THRESHOLD <= 1 - self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
| ( | (
self.df[ self.df[
field_names.POVERTY_LESS_THAN_100_FPL_FIELD field_names.POVERTY_LESS_THAN_100_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
| ( | (
self.df[ self.df[
field_names.LINGUISTIC_ISO_FIELD field_names.LINGUISTIC_ISO_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX + field_names.PERCENTILE_FIELD_SUFFIX
] ]
> self.ENVIRONMENTAL_BURDEN_THRESHOLD >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
) )
) )
return ( return (
self.df[field_names.HIGH_SCHOOL_ED_FIELD] > 0.10 self.df[field_names.HIGH_SCHOOL_ED_FIELD] >= 0.10
) & workforce_criteria ) & workforce_criteria