publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-02-23 10:04:18 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

Use tract instead of block group when calling census API (#901)

Browse source 
* Use tract instead of block group when calling census API

* fixing merge conflicts

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:
Shelby Switzer 2021-11-18 10:37:55 -05:00 • committed by lucasmbrown-usds
parent 0c8b32e679
commit 893758f1d4
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

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

@ -225,7 +225,6 @@ class ScoreETL(ExtractTransformLoad):
# Join all the data sources that use census block groups # Join all the data sources that use census block groups
census_block_group_dfs = [ census_block_group_dfs = [
self.ejscreen_df, self.ejscreen_df,
self.census_df,
self.census_acs_median_incomes_df, self.census_acs_median_incomes_df,
self.national_risk_index_df, self.national_risk_index_df,
] ]
@ -234,6 +233,7 @@ class ScoreETL(ExtractTransformLoad):
# Join all the data sources that use census tracts # Join all the data sources that use census tracts
census_tract_dfs = [ census_tract_dfs = [
self.census_df,
self.hud_housing_df, self.hud_housing_df,
self.cdc_places_df, self.cdc_places_df,
self.cdc_life_expectancy_df, self.cdc_life_expectancy_df,

6
data/data-pipeline/data_pipeline/etl/sources/census_acs/etl.py
View file

@ -77,7 +77,7 @@ class CensusACSETL(ExtractTransformLoad):
src="acs5", src="acs5",
year=self.ACS_YEAR, year=self.ACS_YEAR,
geo=censusdata.censusgeo( geo=censusdata.censusgeo(
[("state", fips), ("county", "*"), ("block group", "*")] [("state", fips), ("county", "*"), ("tract", "*")]
), ),
var=[ var=[
# Emploment fields # Emploment fields
@ -100,7 +100,7 @@ class CensusACSETL(ExtractTransformLoad):
self.df = pd.concat(dfs) self.df = pd.concat(dfs)
self.df[self.GEOID_FIELD_NAME] = self.df.index.to_series().apply( self.df[self.GEOID_TRACT_FIELD_NAME] = self.df.index.to_series().apply(
func=self._fips_from_censusdata_censusgeo func=self._fips_from_censusdata_censusgeo
) )
@ -179,7 +179,7 @@ class CensusACSETL(ExtractTransformLoad):
self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True) self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
columns_to_include = [ columns_to_include = [
self.GEOID_FIELD_NAME, self.GEOID_TRACT_FIELD_NAME,
self.UNEMPLOYED_FIELD_NAME, self.UNEMPLOYED_FIELD_NAME,
self.LINGUISTIC_ISOLATION_FIELD_NAME, self.LINGUISTIC_ISOLATION_FIELD_NAME,
self.MEDIAN_INCOME_FIELD_NAME, self.MEDIAN_INCOME_FIELD_NAME,