publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 14:11:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update Side Panel Tile Data (#866)

Browse source 
* Update Side Panel Tile Data

* Update Side Panel Tile Data

* Correct indicator names to match csv

* Replace Score with Rate

* Comment out FEMA Loss Rate to troubleshoot

* Removes all "FEMA Loss Rate" array elements

* Revert FEMA to Score

* Remove expected loss rate

* Remove RMP and NPL from BASIC array

* Attempt to make shape mismatch align

- update README typo

* Add Score L indicators to TILE_SCORE_FLOAT_COLUMNS

* removing cbg references

* completes the ticket

* Update side panel fields

* Update index file writing to create parent dir

* Updates from linting

* fixing missing field_names for island territories 90th percentile fields

* Update downloadable fields and fix field name

* Update file fields and tests

* Update ordering of fields and leave TODO

* Update pickle after re-ordering of file

* fixing bugs in etl_score_geo

* Repeating index for diesel fix

* passing tests

* adding pytest.ini

Co-authored-by: Vim USDS <vimal.k.shah@omb.eop.gov>
Co-authored-by: Shelby Switzer <shelby.switzer@cms.hhs.gov>
Co-authored-by: lucasmbrown-usds <lucas.m.brown@omb.eop.gov>
This commit is contained in:
Jorge Escobar 2021-12-13 14:53:50 -05:00 • committed by GitHub
commit 9709d08ca3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
13 changed files with 328 additions and 141 deletions
Download patch file Download diff file Expand all files Collapse all files

29
data/data-pipeline/data_pipeline/score/field_names.py
View file

@ -291,14 +291,27 @@ POVERTY_LOW_HS_EDUCATION_FIELD = (
" and has low HS education"
)
LOW_READING_LOW_HS_EDUCATION_FIELD = (
f"At or above the {PERCENTILE}th percentile for low 3rd grade reading proficiency"
" and has low HS education"
LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
f"At or above the {PERCENTILE}th percentile for low median household income as a "
f"percent of area median income and has low HS education"
)
LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
f"At or below the {PERCENTILE}th percentile for low median household income as a "
f"percent of area median income and has low HS education"
# Workforce for island areas
ISLAND_AREAS_SUFFIX = " in 2009 (island areas)"
ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
f"At or above the {PERCENTILE}th percentile for unemployment"
f" and has low HS education{ISLAND_AREAS_SUFFIX}"
)
ISLAND_AREAS_POVERTY_LOW_HS_EDUCATION_FIELD = (
f"At or above the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
f" and has low HS education{ISLAND_AREAS_SUFFIX}"
)
ISLAND_AREAS_LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
f"At or above 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}"
)
# Not currently used in a factor
@ -317,6 +330,10 @@ HEALTHY_FOOD_LOW_INCOME_FIELD = (
f"At or above the {PERCENTILE}th percentile for low "
f"access to healthy food and is low income"
)
LOW_READING_LOW_HS_EDUCATION_FIELD = (
f"At or above the {PERCENTILE}th percentile for low 3rd grade reading proficiency"
" and has low HS education"
)
THRESHOLD_COUNT = "Total threshold criteria exceeded"

55
data/data-pipeline/data_pipeline/score/score_l.py
View file

@ -117,7 +117,7 @@ class ScoreL(Score):
"""
self.df[field_names.THRESHOLD_COUNT] += self.df[columns_for_subset].sum(
axis=1
axis=1, skipna=True
)
def add_columns(self) -> pd.DataFrame:
@ -162,7 +162,7 @@ class ScoreL(Score):
non_workforce_factors
].any(axis=1)
self.df["Definition L (percentile)"] = self.df[
self.df[field_names.SCORE_L + field_names.PERCENTILE_FIELD_SUFFIX] = self.df[
field_names.SCORE_L_COMMUNITIES
].astype(int)
@ -586,12 +586,16 @@ class ScoreL(Score):
)
# Now, calculate workforce criteria for island territories.
island_areas_workforce_eligibility_columns = [
field_names.ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD,
field_names.ISLAND_AREAS_POVERTY_LOW_HS_EDUCATION_FIELD,
field_names.ISLAND_AREAS_LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD,
]
# F a couple of values, create a combined field and criteria field.
# First, combine unemployment.
(
self.df,
unemployment_island_areas_criteria_field_name,
island_areas_unemployment_criteria_field_name,
) = self._combine_island_areas_with_states_and_set_thresholds(
df=self.df,
column_from_island_areas=field_names.CENSUS_DECENNIAL_UNEMPLOYMENT_FIELD_2009,
@ -603,7 +607,7 @@ class ScoreL(Score):
# Next, combine poverty.
(
self.df,
poverty_island_areas_criteria_field_name,
island_areas_poverty_criteria_field_name,
) = self._combine_island_areas_with_states_and_set_thresholds(
df=self.df,
column_from_island_areas=field_names.CENSUS_DECENNIAL_POVERTY_LESS_THAN_100_FPL_FIELD_2009,
@ -614,12 +618,12 @@ class ScoreL(Score):
# Also check whether low area median income is 90th percentile or higher
# within the islands.
low_median_income_as_a_percent_of_ami_island_areas_criteria_field_name = (
island_areas_low_median_income_as_a_percent_of_ami_criteria_field_name = (
f"{field_names.LOW_CENSUS_DECENNIAL_AREA_MEDIAN_INCOME_PERCENT_FIELD_2009} exceeds "
f"{field_names.PERCENTILE}th percentile"
)
self.df[
low_median_income_as_a_percent_of_ami_island_areas_criteria_field_name
island_areas_low_median_income_as_a_percent_of_ami_criteria_field_name
] = (
self.df[
field_names.LOW_CENSUS_DECENNIAL_AREA_MEDIAN_INCOME_PERCENT_FIELD_2009
@ -628,17 +632,40 @@ class ScoreL(Score):
>= self.ENVIRONMENTAL_BURDEN_THRESHOLD
)
workforce_combined_criteria_for_island_areas = (
self.df[unemployment_island_areas_criteria_field_name]
| self.df[poverty_island_areas_criteria_field_name]
| self.df[
low_median_income_as_a_percent_of_ami_island_areas_criteria_field_name
]
) & (
island_areas_high_scool_achievement_rate_threshold = (
self.df[field_names.CENSUS_DECENNIAL_HIGH_SCHOOL_ED_FIELD_2009]
>= self.LACK_OF_HIGH_SCHOOL_MINIMUM_THRESHOLD
)
self.df[
field_names.ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD
] = (
self.df[island_areas_unemployment_criteria_field_name]
& island_areas_high_scool_achievement_rate_threshold
)
self.df[field_names.ISLAND_AREAS_POVERTY_LOW_HS_EDUCATION_FIELD] = (
self.df[island_areas_poverty_criteria_field_name]
& island_areas_high_scool_achievement_rate_threshold
)
self.df[
field_names.ISLAND_AREAS_LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD
] = (
self.df[
island_areas_low_median_income_as_a_percent_of_ami_criteria_field_name
]
& island_areas_high_scool_achievement_rate_threshold
)
workforce_combined_criteria_for_island_areas = self.df[
island_areas_workforce_eligibility_columns
].any(axis="columns")
self._increment_total_eligibility_exceeded(
island_areas_workforce_eligibility_columns
)
percent_of_island_tracts_highlighted = (
100
* workforce_combined_criteria_for_island_areas.sum()