publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 23:11:16 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

updated doe enerygy link and changed fieldnames - removed computation step as BURDEN is already ratio (#963)

Browse source 
Co-authored-by: Saran Ahluwalia <sarahluw@cisco.com>
This commit is contained in:
Saran Ahluwalia 2021-12-03 13:33:19 -05:00 • committed by GitHub
commit 8cb9d197df
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

11
data/data-pipeline/data_pipeline/etl/sources/doe_energy_burden/etl.py
View file

@ -12,15 +12,15 @@ class DOEEnergyBurden(ExtractTransformLoad):
def __init__(self): def __init__(self):
self.DOE_FILE_URL = ( self.DOE_FILE_URL = (
settings.AWS_JUSTICE40_DATASOURCES_URL settings.AWS_JUSTICE40_DATASOURCES_URL
+ "/DOE_LEAD_with_EJSCREEN.csv.zip" + "/DOE_LEAD_AMI_TRACT_2018_ALL.csv.zip"
) )
self.OUTPUT_PATH: Path = ( self.OUTPUT_PATH: Path = (
self.DATA_PATH / "dataset" / "doe_energy_burden" self.DATA_PATH / "dataset" / "doe_energy_burden"
) )
self.TRACT_INPUT_COLUMN_NAME = "GEOID" self.TRACT_INPUT_COLUMN_NAME = "FIP"
self.ENERGY_BURDEN_FIELD_NAME = "Energy burden" self.ENERGY_BURDEN_FIELD_NAME = "BURDEN"
# Constants for output # Constants for output
self.COLUMNS_TO_KEEP = [ self.COLUMNS_TO_KEEP = [
@ -61,11 +61,6 @@ class DOEEnergyBurden(ExtractTransformLoad):
} }
) )
# Convert energy burden to a fraction, since we represent all other percentages as fractions.
output_df[self.ENERGY_BURDEN_FIELD_NAME] = (
output_df[self.ENERGY_BURDEN_FIELD_NAME] / 100
)
# Left-pad the tracts with 0s # Left-pad the tracts with 0s
expected_length_of_census_tract_field = 11 expected_length_of_census_tract_field = 11
output_df[self.GEOID_TRACT_FIELD_NAME] = ( output_df[self.GEOID_TRACT_FIELD_NAME] = (