publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-08-03 23:54:19 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Changing LHE in tiles to a boolean (#1767)

Browse source 
also includes merging / clean up of the release
This commit is contained in:
Emma Nechamkin 2022-08-03 13:55:58 -04:00 • committed by Emma Nechamkin
commit 0d90ae563a
5 changed files with 18 additions and 89 deletions
Download patch file Download diff file Expand all files Collapse all files

1
data/data-pipeline/data_pipeline/score/field_names.py
View file

@ -432,7 +432,6 @@ HAZARDOUS_WASTE_LOW_INCOME_FIELD = (
WASTEWATER_DISCHARGE_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for wastewater discharge and is low income?"
UST_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for leaky underground storage tanks and is low income?"
# Health Burdens
DIABETES_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for diabetes and is low income?"
ASTHMA_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for asthma and is low income?"

26
data/data-pipeline/data_pipeline/score/score_narwhal.py
View file

@ -435,6 +435,11 @@ class ScoreNarwhal(Score):
# poverty level and has a low percent of higher ed students
# Source: Census's American Community Survey
eligibility_columns = [
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD,
field_names.UST_LOW_INCOME_FIELD,
]
self.df[field_names.WASTEWATER_PCTILE_THRESHOLD] = (
self.df[
field_names.WASTEWATER_FIELD
@ -457,28 +462,17 @@ class ScoreNarwhal(Score):
& self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED]
)
self.df[field_names.WATER_THRESHOLD_EXCEEDED] = self.df[
[
field_names.WASTEWATER_PCTILE_THRESHOLD,
field_names.UST_PCTILE_THRESHOLD,
]
].max(axis=1)
self._increment_total_eligibility_exceeded(
[
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD,
field_names.UST_LOW_INCOME_FIELD,
],
eligibility_columns,
skip_fips=constants.DROP_FIPS_FROM_NON_WTD_THRESHOLDS,
)
return self.df[
[
field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD,
field_names.UST_LOW_INCOME_FIELD,
]
self.df[field_names.WATER_THRESHOLD_EXCEEDED] = self.df[
eligibility_columns
].any(axis=1)
return self.df[field_names.WATER_THRESHOLD_EXCEEDED]
def _health_factor(self) -> bool:
# In Xth percentile or above for diabetes (Source: CDC Places)
# or

30
data/data-pipeline/data_pipeline/score/score_runner.py
View file

@ -28,7 +28,6 @@ class ScoreRunner:
self.df = ScoreA(df=self.df).add_columns()
self.df = ScoreB(df=self.df).add_columns()
self.df = ScoreC(df=self.df).add_columns()
self.df = ScoreD(df=self.df).add_columns()
self.df = ScoreF(df=self.df).add_columns()
self.df = ScoreG(df=self.df).add_columns()
self.df = ScoreH(df=self.df).add_columns()
@ -38,33 +37,4 @@ class ScoreRunner:
self.df = ScoreM(df=self.df).add_columns()
self.df = ScoreNarwhal(df=self.df).add_columns()
# TODO do this with each score instead of in a bundle
# Create percentiles for these index scores
self.df = self._add_score_percentiles()
return self.df
def _add_score_percentiles(self) -> pd.DataFrame:
logger.info("Adding Score Percentiles")
for score_field in [
field_names.SCORE_A,
field_names.SCORE_B,
field_names.SCORE_C,
field_names.SCORE_D,
field_names.SCORE_E,
]:
self.df[
f"{score_field}{field_names.PERCENTILE_FIELD_SUFFIX}"
] = self.df[score_field].rank(pct=True)
for threshold in [0.25, 0.3, 0.35, 0.4]:
fraction_converted_to_percent = int(100 * threshold)
self.df[
f"{score_field} (top {fraction_converted_to_percent}th percentile)"
] = (
self.df[
f"{score_field}{field_names.PERCENTILE_FIELD_SUFFIX}"
]
>= 1 - threshold
)
return self.df