publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-09-14 19:48:18 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add EJSCREEN Areas of Concern (#843)

Browse source 
* Adding ej screen areas of concern

* Uses it where user has local files, but not otherwise

Co-authored-by: VincentLaUSDS <vincent.la@omb.eop.gov>
This commit is contained in:
Lucas Merrill Brown 2021-11-02 15:38:42 -04:00 • committed by GitHub
commit 1d541be447
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
10 changed files with 2546 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

43
data/data-pipeline/data_pipeline/score/field_names.py
View file

@ -56,7 +56,9 @@ POVERTY_LESS_THAN_100_FPL_PERCENTILE_FIELD = (
"Percent of individuals < 100% Federal Poverty Line (percentile)"
)
MEDIAN_INCOME_PERCENT_AMI_FIELD = "Median household income (% of AMI)"
MEDIAN_INCOME_PERCENT_AMI_PERCENTILE_FIELD = "Median household income (% of AMI) (percentile)"
MEDIAN_INCOME_PERCENT_AMI_PERCENTILE_FIELD = (
"Median household income (% of AMI) (percentile)"
)
STATE_MEDIAN_INCOME_FIELD = (
"Median household income (State; 2019 inflation-adjusted dollars)"
)
@ -153,3 +155,42 @@ OVER_64_FIELD = "Individuals over 64 years old"
# Urban Rural Map
URBAN_HERUISTIC_FIELD = "Urban Heuristic Flag"
# EJSCREEN Areas of Concern
EJSCREEN_AREAS_OF_CONCERN_NATIONAL_70TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, National, 70th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_NATIONAL_75TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, National, 75th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_NATIONAL_80TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, National, 80th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_NATIONAL_85TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, National, 85th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_NATIONAL_90TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, National, 90th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_NATIONAL_95TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, National, 95th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_STATE_70TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, State, 70th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_STATE_75TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, State, 75th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_STATE_80TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, State, 80th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_STATE_85TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, State, 85th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_STATE_90TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, State, 90th percentile (communities)"
)
EJSCREEN_AREAS_OF_CONCERN_STATE_95TH_PERCENTILE_COMMUNITIES_FIELD_NAME = (
"EJSCREEN Areas of Concern, State, 95th percentile (communities)"
)

12
data/data-pipeline/data_pipeline/score/score_c.py
View file

@ -10,7 +10,7 @@ logger = get_module_logger(__name__)
class ScoreC(Score):
def __init__(self, df: pd.DataFrame) -> None:
Bucket = namedtuple('Bucket', ['name', 'fields'])
Bucket = namedtuple(typename="Bucket", field_names=["name", "fields"])
self.BUCKET_SOCIOECONOMIC = Bucket(
field_names.C_SOCIOECONOMIC,
@ -20,15 +20,15 @@ class ScoreC(Score):
field_names.HIGH_SCHOOL_ED_FIELD,
field_names.UNEMPLOYMENT_FIELD,
field_names.HT_INDEX_FIELD,
]
)
],
)
self.BUCKET_SENSITIVE = Bucket(
field_names.C_SENSITIVE,
[
field_names.UNDER_5_FIELD,
field_names.OVER_64_FIELD,
field_names.LINGUISTIC_ISO_FIELD,
]
],
)
self.BUCKET_ENVIRONMENTAL = Bucket(
field_names.C_ENVIRONMENTAL,
@ -38,7 +38,7 @@ class ScoreC(Score):
field_names.NPL_FIELD,
field_names.WASTEWATER_FIELD,
field_names.LEAD_PAINT_FIELD,
]
],
)
self.BUCKET_EXPOSURES = Bucket(
field_names.C_EXPOSURES,
@ -63,7 +63,7 @@ class ScoreC(Score):
def add_columns(self) -> pd.DataFrame:
logger.info("Adding Score C")
# Average all the percentile values in each bucket into a single score for each of the four buckets.
# TODO just use the percentile fields in the list instead
for bucket in self.BUCKETS:
fields_to_average = []