publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 19:41:17 -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/maryland_ejscreen/etl.py
View file

@ -21,7 +21,7 @@ class MarylandEJScreenETL(ExtractTransformLoad):
settings.AWS_JUSTICE40_DATASOURCES_URL + "/MD_EJScreen.zip"
)
self.SHAPE_FILES_PATH = self.TMP_PATH / "mdejscreen"
self.SHAPE_FILES_PATH = self.get_tmp_path() / "mdejscreen"
self.OUTPUT_CSV_PATH = self.DATA_PATH / "dataset" / "maryland_ejscreen"
self.COLUMNS_TO_KEEP = [
@ -36,7 +36,7 @@ class MarylandEJScreenETL(ExtractTransformLoad):
logger.info("Downloading 207MB Maryland EJSCREEN Data")
super().extract(
self.MARYLAND_EJSCREEN_URL,
self.TMP_PATH,
self.get_tmp_path(),
)
def transform(self) -> None: