publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 19:11:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updating field names to match score M definitions (#1190)

Browse source 
When implementing definition M for the score, the variable names were not yet updated. For example:

This legacy field naming: 
```
UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
    f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
    " and has low HS education"
)
``` 

Should actually be renamed something like this:
```
UNEMPLOYMENT_LOW_HS_LOW_HIGHER_ED_FIELD = (
    f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
    " and has low HS education and low higher ed attendance"
)
``` 

This PR is for the backend updates for this -- keeping the old fields, and adding new, Score M specific fields as listed below: 
- [x] `field_names`: add new fields to capture low_higher_ed
- [x] `score_m`: replace old fields with new fields 
- [x] `DOWNLOADABLE_SCORE_COLUMNS`: replace old fields with new fields
- [x] `TILES_SCORE_COLUMNS`: replace old fields with new fields
This commit is contained in:
Emma Nechamkin 2022-02-01 18:54:43 -05:00 • committed by GitHub
commit 49868401be
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 250 additions and 152 deletions
Download patch file Download diff file Expand all files Collapse all files

88
data/data-pipeline/data_pipeline/etl/score/constants.py
View file

@ -138,28 +138,28 @@ TILES_SCORE_COLUMNS = {
field_names.M_HEALTH: "M_HLTH",
field_names.SCORE_M_COMMUNITIES: "SM_C",
field_names.SCORE_M + field_names.PERCENTILE_FIELD_SUFFIX: "SM_PFS",
field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD: "EPLRLI",
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD: "EALRLI",
field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD: "EBLRLI",
field_names.PM25_EXPOSURE_LOW_INCOME_FIELD: "PM25LI",
field_names.ENERGY_BURDEN_LOW_INCOME_FIELD: "EBLI",
field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD: "DPMLI",
field_names.TRAFFIC_PROXIMITY_LOW_INCOME_FIELD: "TPLI",
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD: "LPMHVLI",
field_names.HOUSING_BURDEN_LOW_INCOME_FIELD: "HBLI",
field_names.RMP_LOW_INCOME_FIELD: "RMPLI",
field_names.SUPERFUND_LOW_INCOME_FIELD: "SFLI",
field_names.HAZARDOUS_WASTE_LOW_INCOME_FIELD: "HWLI",
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD: "WDLI",
field_names.DIABETES_LOW_INCOME_FIELD: "DLI",
field_names.ASTHMA_LOW_INCOME_FIELD: "ALI",
field_names.HEART_DISEASE_LOW_INCOME_FIELD: "HDLI",
field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_FIELD: "LLELI",
field_names.LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD: "LILHSE",
field_names.POVERTY_LOW_HS_EDUCATION_FIELD: "PLHSE",
field_names.LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD: "LMILHSE",
field_names.UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD: "ULHSE",
field_names.LOW_HS_EDUCATION_LOW_COLLEGE_ATTENDANCE_FIELD: "LHE",
field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "EPLRLI",
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "EALRLI",
field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "EBLRLI",
field_names.PM25_EXPOSURE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "PM25LI",
field_names.ENERGY_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD: "EBLI",
field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_LOW_HIGHER_ED_FIELD: "DPMLI",
field_names.TRAFFIC_PROXIMITY_LOW_INCOME_LOW_HIGHER_ED_FIELD: "TPLI",
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "LPMHVLI",
field_names.HOUSING_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD: "HBLI",
field_names.RMP_LOW_INCOME_LOW_HIGHER_ED_FIELD: "RMPLI",
field_names.SUPERFUND_LOW_INCOME_LOW_HIGHER_ED_FIELD: "SFLI",
field_names.HAZARDOUS_WASTE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "HWLI",
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "WDLI",
field_names.DIABETES_LOW_INCOME_LOW_HIGHER_ED_FIELD: "DLI",
field_names.ASTHMA_LOW_INCOME_LOW_HIGHER_ED_FIELD: "ALI",
field_names.HEART_DISEASE_LOW_INCOME_LOW_HIGHER_ED_FIELD: "HDLI",
field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_LOW_HIGHER_ED_FIELD: "LLELI",
field_names.LINGUISTIC_ISOLATION_LOW_HS_LOW_HIGHER_ED_FIELD: "LILHSE",
field_names.POVERTY_LOW_HS_LOW_HIGHER_ED_FIELD: "PLHSE",
field_names.LOW_MEDIAN_INCOME_LOW_HS_LOW_HIGHER_ED_FIELD: "LMILHSE",
field_names.UNEMPLOYMENT_LOW_HS_LOW_HIGHER_ED_FIELD: "ULHSE",
field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD: "LHE",
field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES: "FPL200S",
field_names.THRESHOLD_COUNT: "TC",
field_names.ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD: "IAULHSE",
@ -199,7 +199,7 @@ TILES_SCORE_FLOAT_COLUMNS = [
field_names.TSDF_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.TRAFFIC_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.UNEMPLOYMENT_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.LOW_HS_EDUCATION_LOW_COLLEGE_ATTENDANCE_FIELD,
field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD,
field_names.ISLAND_AREAS_LOW_HS_EDUCATION_FIELD,
field_names.WASTEWATER_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.SCORE_M + field_names.PERCENTILE_FIELD_SUFFIX,
@ -214,73 +214,73 @@ DOWNLOADABLE_SCORE_COLUMNS = [
field_names.SCORE_M_COMMUNITIES,
field_names.TOTAL_POP_FIELD,
field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES,
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD,
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX,
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD,
field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD,
field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX,
field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD,
field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD,
field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX,
field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD,
field_names.ENERGY_BURDEN_LOW_INCOME_FIELD,
field_names.ENERGY_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.ENERGY_BURDEN_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.ENERGY_BURDEN_FIELD,
field_names.PM25_EXPOSURE_LOW_INCOME_FIELD,
field_names.PM25_EXPOSURE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.PM25_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.PM25_FIELD,
field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD,
field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.DIESEL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.DIESEL_FIELD,
field_names.TRAFFIC_PROXIMITY_LOW_INCOME_FIELD,
field_names.TRAFFIC_PROXIMITY_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.TRAFFIC_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.TRAFFIC_FIELD,
field_names.HOUSING_BURDEN_LOW_INCOME_FIELD,
field_names.HOUSING_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.HOUSING_BURDEN_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.HOUSING_BURDEN_FIELD,
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD,
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.LEAD_PAINT_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.LEAD_PAINT_FIELD,
field_names.MEDIAN_HOUSE_VALUE_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.MEDIAN_HOUSE_VALUE_FIELD,
field_names.HAZARDOUS_WASTE_LOW_INCOME_FIELD,
field_names.HAZARDOUS_WASTE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.TSDF_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.TSDF_FIELD,
field_names.SUPERFUND_LOW_INCOME_FIELD,
field_names.SUPERFUND_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.NPL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.NPL_FIELD,
field_names.RMP_LOW_INCOME_FIELD,
field_names.RMP_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.RMP_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.RMP_FIELD,
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD,
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.WASTEWATER_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.WASTEWATER_FIELD,
field_names.ASTHMA_LOW_INCOME_FIELD,
field_names.ASTHMA_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.ASTHMA_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.ASTHMA_FIELD,
field_names.DIABETES_LOW_INCOME_FIELD,
field_names.DIABETES_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.DIABETES_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.DIABETES_FIELD,
field_names.HEART_DISEASE_LOW_INCOME_FIELD,
field_names.HEART_DISEASE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.HEART_DISEASE_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.HEART_DISEASE_FIELD,
field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_FIELD,
field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.LOW_LIFE_EXPECTANCY_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.LIFE_EXPECTANCY_FIELD,
field_names.LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD,
field_names.LOW_MEDIAN_INCOME_LOW_HS_LOW_HIGHER_ED_FIELD,
field_names.LOW_MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX,
field_names.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD,
field_names.LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD,
field_names.LINGUISTIC_ISOLATION_LOW_HS_LOW_HIGHER_ED_FIELD,
field_names.LINGUISTIC_ISO_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.LINGUISTIC_ISO_FIELD,
field_names.UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD,
field_names.UNEMPLOYMENT_LOW_HS_LOW_HIGHER_ED_FIELD,
field_names.UNEMPLOYMENT_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
field_names.UNEMPLOYMENT_FIELD,
field_names.POVERTY_LOW_HS_EDUCATION_FIELD,
field_names.POVERTY_LOW_HS_LOW_HIGHER_ED_FIELD,
field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX,
field_names.POVERTY_LESS_THAN_100_FPL_FIELD

6
data/data-pipeline/data_pipeline/etl/score/tests/sample_data/score_data_initial.csv
View file

File diff suppressed because one or more lines are too long

BIN
data/data-pipeline/data_pipeline/etl/score/tests/snapshots/downloadable_data_expected.pkl
View file

Binary file not shown.

BIN
data/data-pipeline/data_pipeline/etl/score/tests/snapshots/score_data_expected.pkl
View file

Binary file not shown.

BIN
data/data-pipeline/data_pipeline/etl/score/tests/snapshots/score_transformed_expected.pkl
View file

Binary file not shown.

139
data/data-pipeline/data_pipeline/score/field_names.py
View file

@ -313,8 +313,7 @@ TRANSPORTATION_COSTS = "Transportation Costs"
#####
# Names for individual factors being exceeded
# TODO: for Definition M, create new output field names (different than those used by
# Definition L) and change all output fields to say low income and low college
# Climate Change
EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile"
@ -369,50 +368,156 @@ LOW_LIFE_EXPECTANCY_LOW_INCOME_FIELD = (
f"for low life expectancy and is low income?"
)
# Score M Low Income Change
SCORE_M_LOW_INCOME_SUFFIX = (
", is low income, and has a low percent of higher ed students"
)
# Climate Change
EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile"
f" for expected population loss rate{SCORE_M_LOW_INCOME_SUFFIX}?"
)
EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile"
f" for expected agriculture loss rate{SCORE_M_LOW_INCOME_SUFFIX}?"
)
EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile"
f" for expected building loss rate{SCORE_M_LOW_INCOME_SUFFIX}?"
)
# Clean Energy and Efficiency
PM25_EXPOSURE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile "
f"for PM2.5 exposure{SCORE_M_LOW_INCOME_SUFFIX}?"
)
ENERGY_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile "
f"for energy burden{SCORE_M_LOW_INCOME_SUFFIX}?"
)
# Clean Transportation
DIESEL_PARTICULATE_MATTER_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for "
f"diesel particulate matter{SCORE_M_LOW_INCOME_SUFFIX}?"
)
TRAFFIC_PROXIMITY_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for "
f"traffic proximity{SCORE_M_LOW_INCOME_SUFFIX}?"
)
# Affordable and Sustainable Housing
LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for lead paint,"
f" the median house value is less than {MEDIAN_HOUSE_VALUE_PERCENTILE}th "
f"percentile{SCORE_M_LOW_INCOME_SUFFIX}?"
)
HOUSING_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile "
f"for housing burden{SCORE_M_LOW_INCOME_SUFFIX}?"
)
# Remediation and Reduction of Legacy Pollution
RMP_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for "
f"proximity to RMP sites{SCORE_M_LOW_INCOME_SUFFIX}?"
)
SUPERFUND_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for proximity to "
f"superfund sites{SCORE_M_LOW_INCOME_SUFFIX}?"
)
HAZARDOUS_WASTE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile"
f" for proximity to hazardous waste facilities{SCORE_M_LOW_INCOME_SUFFIX}?"
)
# Critical Clean Water and Waste Infrastructure
WASTEWATER_DISCHARGE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for"
f" wastewater discharge{SCORE_M_LOW_INCOME_SUFFIX}?"
)
# Health Burdens
DIABETES_LOW_INCOME_LOW_HIGHER_ED_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for diabetes{SCORE_M_LOW_INCOME_SUFFIX}?"
ASTHMA_LOW_INCOME_LOW_HIGHER_ED_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for asthma{SCORE_M_LOW_INCOME_SUFFIX}?"
HEART_DISEASE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile "
f"for heart disease{SCORE_M_LOW_INCOME_SUFFIX}?"
)
LOW_LIFE_EXPECTANCY_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile "
f"for low life expectancy{SCORE_M_LOW_INCOME_SUFFIX}?"
)
# Workforce
# TODO: for Definition M, create new output field names (different than those used by
# Definition L) and change all output fields to say low HS and low college
UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
" and has low HS education"
" and has low HS education?"
)
LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for households in linguistic isolation"
" and has low HS education"
" and has low HS education?"
)
POVERTY_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
" and has low HS education"
" and has low HS education?"
)
LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for low median household income as a "
f"percent of area median income and has low HS education"
f"percent of area median income and has low HS education?"
)
# Score M Workforce Variables
SCORE_M_LOW_EDUCATION_SUFFIX = (
", has low HS attainment, and has a low percent of higher ed students"
)
UNEMPLOYMENT_LOW_HS_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
f"{SCORE_M_LOW_EDUCATION_SUFFIX}?"
)
LINGUISTIC_ISOLATION_LOW_HS_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for households in linguistic isolation"
f"{SCORE_M_LOW_EDUCATION_SUFFIX}?"
)
POVERTY_LOW_HS_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
f"{SCORE_M_LOW_EDUCATION_SUFFIX}?"
)
LOW_MEDIAN_INCOME_LOW_HS_LOW_HIGHER_ED_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for low median household income as a "
f"percent of area median income{SCORE_M_LOW_EDUCATION_SUFFIX}?"
)
LOW_HS_EDUCATION_FIELD = "Low high school education"
LOW_HS_EDUCATION_LOW_COLLEGE_ATTENDANCE_FIELD = (
"Low high school education and low college attendance"
LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD = (
"Low high school education and low percent of higher ed students"
)
# Workforce for island areas
ISLAND_AREAS_SUFFIX = " in 2009 (island areas)"
ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
f" and has low HS education{ISLAND_AREAS_SUFFIX}"
f" and has low HS education{ISLAND_AREAS_SUFFIX}?"
)
ISLAND_AREAS_POVERTY_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
f" and has low HS education{ISLAND_AREAS_SUFFIX}"
f" and has low HS education{ISLAND_AREAS_SUFFIX}?"
)
ISLAND_AREAS_LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for low median household income as a "
f"percent of area median income"
f" and has low HS education{ISLAND_AREAS_SUFFIX}"
f" and has low HS education{ISLAND_AREAS_SUFFIX}?"
)
ISLAND_AREAS_LOW_HS_EDUCATION_FIELD = (
@ -425,9 +530,10 @@ EXTREME_HEAT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD = (
f"the median house value is less than {MEDIAN_HOUSE_VALUE_PERCENTILE}th "
f"percentile and is low income?"
)
IMPENETRABLE_SURFACES_LOW_INCOME_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for impenetrable surfaces and is low "
f"income"
f"income?"
)
AIR_TOXICS_CANCER_RISK_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for air toxics cancer risk and is low income?"
RESPIRATORY_HAZARD_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for respiratory hazard index and is low income?"
@ -435,16 +541,17 @@ HEALTHY_FOOD_LOW_INCOME_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for low "
f"access to healthy food and is low income?"
)
LOW_READING_LOW_HS_EDUCATION_FIELD = (
f"Greater than or equal to the {PERCENTILE}th percentile for low 3rd grade reading proficiency"
" and has low HS education"
" and has low HS education?"
)
THRESHOLD_COUNT = "Total threshold criteria exceeded"
FPL_200_SERIES = "Is low income?"
FPL_200_AND_COLLEGE_ATTENDANCE_SERIES = (
"Is low income and low college attendance?"
"Is low income and has a low percent of higher ed students?"
)
# End of names for individual factors being exceeded
####

169
data/data-pipeline/data_pipeline/score/score_m.py
View file

@ -143,13 +143,13 @@ class ScoreM(Score):
# AND
# Low income: In Nth percentile or above for percent of block group population
# of households where household income is less than or equal to twice the federal
# poverty level. Source: Census's American Community Survey]
# poverty level and there is low higher ed attendance
# Source: Census's American Community Survey
climate_eligibility_columns = [
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,
field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
]
expected_population_loss_threshold = (
@ -176,39 +176,24 @@ class ScoreM(Score):
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
extreme_heat_and_median_house_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] = (
self.df[
field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD
] = (
expected_population_loss_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD] = (
self.df[
field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD
] = (
expected_agriculture_loss_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD] = (
expected_building_loss_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[
field_names.EXTREME_HEAT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD
field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD
] = (
extreme_heat_and_median_house_value_threshold
expected_building_loss_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
@ -221,11 +206,12 @@ class ScoreM(Score):
# AND
# Low income: In Nth percentile or above for percent of block group population
# of households where household income is less than or equal to twice the federal
# poverty level. Source: Census's American Community Survey]
# poverty level and has low higher ed attendance.
# Source: Census's American Community Survey
energy_eligibility_columns = [
field_names.PM25_EXPOSURE_LOW_INCOME_FIELD,
field_names.ENERGY_BURDEN_LOW_INCOME_FIELD,
field_names.PM25_EXPOSURE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.ENERGY_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD,
]
energy_burden_threshold = (
@ -243,12 +229,12 @@ class ScoreM(Score):
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
self.df[field_names.PM25_EXPOSURE_LOW_INCOME_FIELD] = (
self.df[field_names.PM25_EXPOSURE_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
pm25_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.ENERGY_BURDEN_LOW_INCOME_FIELD] = (
self.df[field_names.ENERGY_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
energy_burden_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
@ -266,11 +252,12 @@ class ScoreM(Score):
# AND
# Low income: In Nth percentile or above for percent of block group population
# of households where household income is less than or equal to twice the federal
# poverty level. Source: Census's American Community Survey]
# poverty level and has a low percent of higher ed students.
# Source: Census's American Community Survey
transportion_eligibility_columns = [
field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD,
field_names.TRAFFIC_PROXIMITY_LOW_INCOME_FIELD,
field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.TRAFFIC_PROXIMITY_LOW_INCOME_LOW_HIGHER_ED_FIELD,
]
diesel_threshold = (
@ -287,12 +274,16 @@ class ScoreM(Score):
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
self.df[field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD] = (
self.df[
field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_LOW_HIGHER_ED_FIELD
] = (
diesel_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.TRAFFIC_PROXIMITY_LOW_INCOME_FIELD] = (
self.df[
field_names.TRAFFIC_PROXIMITY_LOW_INCOME_LOW_HIGHER_ED_FIELD
] = (
traffic_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
@ -315,11 +306,12 @@ class ScoreM(Score):
# AND
# Low income: In Nth percentile or above for percent of block group population
# of households where household income is less than or equal to twice the federal
# poverty level. Source: Census's American Community Survey]
# poverty level and has a low percent of higher ed students.
# Source: Census's American Community Survey
housing_eligibility_columns = [
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD,
field_names.HOUSING_BURDEN_LOW_INCOME_FIELD,
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.HOUSING_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD,
]
lead_paint_median_home_value_threshold = (
@ -345,12 +337,14 @@ class ScoreM(Score):
)
# series by series indicators
self.df[field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD] = (
self.df[
field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_LOW_HIGHER_ED_FIELD
] = (
lead_paint_median_home_value_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.HOUSING_BURDEN_LOW_INCOME_FIELD] = (
self.df[field_names.HOUSING_BURDEN_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
housing_burden_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
@ -364,12 +358,13 @@ class ScoreM(Score):
# AND
# Low income: In Nth percentile or above for percent of block group population
# of households where household income is less than or equal to twice the federal
# poverty level. Source: Census's American Community Survey]
# poverty level and has a low percent of higher ed students.
# Source: Census's American Community Survey
pollution_eligibility_columns = [
field_names.RMP_LOW_INCOME_FIELD,
field_names.SUPERFUND_LOW_INCOME_FIELD,
field_names.HAZARDOUS_WASTE_LOW_INCOME_FIELD,
field_names.RMP_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.SUPERFUND_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.HAZARDOUS_WASTE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
]
rmp_sites_threshold = (
@ -390,15 +385,15 @@ class ScoreM(Score):
)
# individual series-by-series
self.df[field_names.RMP_LOW_INCOME_FIELD] = (
self.df[field_names.RMP_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
rmp_sites_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.SUPERFUND_LOW_INCOME_FIELD] = (
self.df[field_names.SUPERFUND_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
npl_sites_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.HAZARDOUS_WASTE_LOW_INCOME_FIELD] = (
self.df[field_names.HAZARDOUS_WASTE_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
tsdf_sites_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
@ -414,7 +409,8 @@ class ScoreM(Score):
# AND
# Low income: In Nth percentile or above for percent of block group population
# of households where household income is less than or equal to twice the federal
# poverty level. Source: Census's American Community Survey]
# poverty level and has a low percent of higher ed students
# Source: Census's American Community Survey
wastewater_threshold = (
self.df[
@ -424,16 +420,20 @@ class ScoreM(Score):
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
self.df[field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD] = (
self.df[
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_LOW_HIGHER_ED_FIELD
] = (
wastewater_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self._increment_total_eligibility_exceeded(
[field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD]
[field_names.WASTEWATER_DISCHARGE_LOW_INCOME_LOW_HIGHER_ED_FIELD]
)
return self.df[field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD]
return self.df[
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_LOW_HIGHER_ED_FIELD
]
def _health_factor(self) -> bool:
# In Xth percentile or above for diabetes (Source: CDC Places)
@ -446,14 +446,14 @@ class ScoreM(Score):
# AND
# Low income: In Nth percentile or above for percent of block group population
# of households where household income is less than or equal to twice the federal
# poverty level. Source: Census's American Community Survey]
# poverty level and has a low percent of higher ed students
# Source: Census's American Community Survey
health_eligibility_columns = [
field_names.DIABETES_LOW_INCOME_FIELD,
field_names.ASTHMA_LOW_INCOME_FIELD,
field_names.HEART_DISEASE_LOW_INCOME_FIELD,
field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_FIELD,
# field_names.HEALTHY_FOOD_LOW_INCOME_FIELD,
field_names.DIABETES_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.ASTHMA_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.HEART_DISEASE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_LOW_HIGHER_ED_FIELD,
]
diabetes_threshold = (
@ -486,34 +486,24 @@ class ScoreM(Score):
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
healthy_food_threshold = (
self.df[
field_names.HEALTHY_FOOD_FIELD
+ field_names.PERCENTILE_FIELD_SUFFIX
]
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
self.df[field_names.DIABETES_LOW_INCOME_FIELD] = (
self.df[field_names.DIABETES_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
diabetes_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.ASTHMA_LOW_INCOME_FIELD] = (
self.df[field_names.ASTHMA_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
asthma_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.HEART_DISEASE_LOW_INCOME_FIELD] = (
self.df[field_names.HEART_DISEASE_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
heart_disease_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_FIELD] = (
self.df[
field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_LOW_HIGHER_ED_FIELD
] = (
low_life_expectancy_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self.df[field_names.HEALTHY_FOOD_LOW_INCOME_FIELD] = (
healthy_food_threshold
& self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
)
self._increment_total_eligibility_exceeded(health_eligibility_columns)
@ -531,17 +521,18 @@ class ScoreM(Score):
# AND
# Where the high school degree achievement rates for adults 25 years and older
# is less than Y%
# AND the higher ed attendance rates are under Z%
# (necessary to screen out university tracts)
# Workforce criteria for states fields.
workforce_eligibility_columns = [
field_names.UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD,
field_names.POVERTY_LOW_HS_EDUCATION_FIELD,
field_names.LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD,
field_names.LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD,
field_names.UNEMPLOYMENT_LOW_HS_LOW_HIGHER_ED_FIELD,
field_names.POVERTY_LOW_HS_LOW_HIGHER_ED_FIELD,
field_names.LINGUISTIC_ISOLATION_LOW_HS_LOW_HIGHER_ED_FIELD,
field_names.LOW_MEDIAN_INCOME_LOW_HS_LOW_HIGHER_ED_FIELD,
]
self.df[field_names.LOW_HS_EDUCATION_LOW_COLLEGE_ATTENDANCE_FIELD] = (
self.df[field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD] = (
self.df[field_names.HIGH_SCHOOL_ED_FIELD]
>= self.LACK_OF_HIGH_SCHOOL_MINIMUM_THRESHOLD
) & (
@ -588,24 +579,24 @@ class ScoreM(Score):
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
self.df[field_names.LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD] = (
self.df[field_names.LINGUISTIC_ISOLATION_LOW_HS_LOW_HIGHER_ED_FIELD] = (
linguistic_isolation_threshold
& self.df[field_names.LOW_HS_EDUCATION_LOW_COLLEGE_ATTENDANCE_FIELD]
& self.df[field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD]
)
self.df[field_names.POVERTY_LOW_HS_EDUCATION_FIELD] = (
self.df[field_names.POVERTY_LOW_HS_LOW_HIGHER_ED_FIELD] = (
poverty_threshold
& self.df[field_names.LOW_HS_EDUCATION_LOW_COLLEGE_ATTENDANCE_FIELD]
& self.df[field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD]
)
self.df[field_names.LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD] = (
self.df[field_names.LOW_MEDIAN_INCOME_LOW_HS_LOW_HIGHER_ED_FIELD] = (
low_median_income_threshold
& self.df[field_names.LOW_HS_EDUCATION_LOW_COLLEGE_ATTENDANCE_FIELD]
& self.df[field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD]
)
self.df[field_names.UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD] = (
self.df[field_names.UNEMPLOYMENT_LOW_HS_LOW_HIGHER_ED_FIELD] = (
unemployment_threshold
& self.df[field_names.LOW_HS_EDUCATION_LOW_COLLEGE_ATTENDANCE_FIELD]
& self.df[field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD]
)
workforce_combined_criteria_for_states = self.df[