publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-25 18:10:16 -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

15
data/data-pipeline/data_pipeline/etl/base.py
View file

@ -98,6 +98,17 @@ class ExtractTransformLoad:
)
return output_file_path
def get_tmp_path(self) -> pathlib.Path:
"""Returns the temporary path associated with this ETL class."""
# Note: the temporary path will be defined on `init`, because it uses the class
# of the instance which is often a child class.
tmp_path = self.DATA_PATH / "tmp" / str(self.__class__.__name__)
# Create directory if it doesn't exist
tmp_path.mkdir(parents=True, exist_ok=True)
return tmp_path
def extract(
self,
source_url: str = None,
@ -112,7 +123,7 @@ class ExtractTransformLoad:
if source_url and extract_path:
unzip_file_from_url(
file_url=source_url,
download_path=self.TMP_PATH,
download_path=self.get_tmp_path(),
unzipped_file_path=extract_path,
verify=verify,
)
@ -265,4 +276,4 @@ class ExtractTransformLoad:
def cleanup(self) -> None:
"""Clears out any files stored in the TMP folder"""
remove_all_from_dir(self.TMP_PATH)
remove_all_from_dir(self.get_tmp_path())