publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-08-04 01:14:18 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Run ETL processes in parallel (#1253)

Browse source 
* WIP on parallelizing

* switching to get_tmp_path for nri

* switching to get_tmp_path everywhere necessary

* fixing linter errors

* moving heavy ETLs to front of line

* add hold

* moving cdc places up

* removing unnecessary print

* moving h&t up

* adding parallel to geo post

* better census labels

* switching to concurrent futures

* fixing output
This commit is contained in:
Lucas Merrill Brown 2022-02-11 14:04:53 -05:00 • committed by GitHub
commit a0d6e55f0a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
30 changed files with 286 additions and 160 deletions
Download patch file Download diff file Expand all files Collapse all files

4
data/data-pipeline/data_pipeline/etl/sources/national_risk_index/etl.py
View file

@ -20,7 +20,7 @@ class NationalRiskIndexETL(ExtractTransformLoad):
GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
def __init__(self):
self.INPUT_CSV = self.TMP_PATH / "NRI_Table_CensusTracts.csv"
self.INPUT_CSV = self.get_tmp_path() / "NRI_Table_CensusTracts.csv"
self.RISK_INDEX_EXPECTED_ANNUAL_LOSS_SCORE_INPUT_FIELD_NAME = (
"EAL_SCORE"
@ -68,7 +68,7 @@ class NationalRiskIndexETL(ExtractTransformLoad):
logger.info("Downloading 405MB National Risk Index Data")
super().extract(
source_url=self.SOURCE_URL,
extract_path=self.TMP_PATH,
extract_path=self.get_tmp_path(),
)
def transform(self) -> None: