publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-24 01:10:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Score Indicators (#690)

Browse source 
* Score Indicators

* roudning issue with housing burden column

* switching out score g

* final list of columns

* removing duplicate housing burden percentile fields

* removing duplicate

Co-authored-by: lucasmbrown-usds <lucas.m.brown@omb.eop.gov>
This commit is contained in:
Jorge Escobar 2021-09-16 10:53:05 -04:00 • committed by GitHub
commit 487f6a8e04
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 51 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

32
data/data-pipeline/data_pipeline/etl/score/constants.py
View file

@ -64,6 +64,20 @@ TILES_SCORE_COLUMNS = [
"Linguistic isolation (percent) (percentile)",
"Unemployed civilians (percent) (percentile)",
"Housing burden (percent) (percentile)",
"Diagnosed diabetes among adults aged >=18 years (percentile)",
"Current asthma among adults aged >=18 years (percentile)",
"Coronary heart disease among adults aged >=18 years (percentile)",
"Life expectancy (years) (percentile)",
"Traffic proximity and volume (percentile)",
"FEMA Risk Index Expected Annual Loss Score (percentile)",
"Energy burden (percentile)",
"Wastewater discharge (percentile)",
"Percent pre-1960s housing (lead paint indicator) (percentile)",
"Diesel particulate matter (percentile)",
"Particulate matter (PM2.5) (percentile)",
"Median household income (% of AMI) (percentile)",
"Percent of individuals < 200% Federal Poverty Line (percentile)",
"Percent individuals age 25 or over with less than high school degree (percentile)",
]
# columns to round floats to 2 decimals
@ -77,6 +91,24 @@ TILES_SCORE_FLOAT_COLUMNS = [
"Linguistic isolation (percent)",
"Unemployed civilians (percent)",
"Housing burden (percent)",
"Poverty (Less than 200% of federal poverty line) (percentile)",
"Percent individuals age 25 or over with less than high school degree (percentile)",
"Linguistic isolation (percent) (percentile)",
"Unemployed civilians (percent) (percentile)",
"Housing burden (percent) (percentile)",
"Diagnosed diabetes among adults aged >=18 years (percentile)",
"Current asthma among adults aged >=18 years (percentile)",
"Coronary heart disease among adults aged >=18 years (percentile)",
"Life expectancy (years) (percentile)",
"Traffic proximity and volume (percentile)",
"FEMA Risk Index Expected Annual Loss Score (percentile)",
"Energy burden (percentile)",
"Wastewater discharge (percentile)",
"Percent pre-1960s housing (lead paint indicator) (percentile)",
"Diesel particulate matter (percentile)",
"Particulate matter (PM2.5) (percentile)",
"Median household income (% of AMI) (percentile)",
"Percent of individuals < 200% Federal Poverty Line (percentile)",
]
TILES_ROUND_NUM_DECIMALS = 2

22
data/data-pipeline/data_pipeline/etl/score/etl_score.py
View file

@ -608,15 +608,26 @@ class ScoreETL(ExtractTransformLoad):
high_school_cutoff_threshold = 0.05
high_school_cutoff_threshold_2 = 0.06
# Score G is now modified NMTC
df["Score G (communities)"] = (
(df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.8)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold)
) | (
(df[self.POVERTY_LESS_THAN_100_FPL_FIELD_NAME] > 0.20)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold)
)
df["Score G"] = df["Score G (communities)"].astype(int)
df["Score G (percentile)"] = df["Score G"]
df["Score I (communities)"] = (
(df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.7)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold)
) | (
(df[self.POVERTY_LESS_THAN_200_FPL_FIELD_NAME] > 0.50)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold)
)
df["Score G"] = df["Score G (communities)"].astype(int)
df["Score G (percentile)"] = df["Score G"]
df["Score I"] = df["Score I (communities)"].astype(int)
df["Score I (percentile)"] = df["Score I"]
df["Score H (communities)"] = (
(df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.8)
@ -631,12 +642,13 @@ class ScoreETL(ExtractTransformLoad):
(df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.8)
) | (df[self.POVERTY_LESS_THAN_100_FPL_FIELD_NAME] > 0.20)
df["NMTC modified (communities)"] = (
df["Score K (communities)"] = (
(df[self.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD_NAME] < 0.8)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold_2)
) | (
(df[self.POVERTY_LESS_THAN_100_FPL_FIELD_NAME] > 0.20)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold)
& (df[self.HIGH_SCHOOL_FIELD_NAME] > high_school_cutoff_threshold_2)
)
return df

2
data/data-pipeline/data_pipeline/etl/score/etl_score_post.py
View file

@ -183,6 +183,7 @@ class PostScoreETL(ExtractTransformLoad):
def _create_tile_data(
self, score_county_state_merged_df: pd.DataFrame
) -> pd.DataFrame:
logger.info("Rounding Decimals")
score_tiles = score_county_state_merged_df[
constants.TILES_SCORE_COLUMNS
]
@ -191,6 +192,7 @@ class PostScoreETL(ExtractTransformLoad):
* len(constants.TILES_SCORE_FLOAT_COLUMNS),
index=constants.TILES_SCORE_FLOAT_COLUMNS,
)
return score_tiles.round(decimals)
def _create_downloadable_data(