publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-29 02:31:17 -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

8
data/data-pipeline/data_pipeline/tests/sources/national_risk_index/test_etl.py
View file

@ -98,7 +98,9 @@ class TestNationalRiskIndexETL(TestETL):
# setup
etl = NationalRiskIndexETL()
data_path, tmp_path = mock_paths
input_csv = tmp_path / "NRI_Table_CensusTracts.csv"
input_csv = (
tmp_path / "NationalRiskIndexETL" / "NRI_Table_CensusTracts.csv"
)
# validation
assert etl.INPUT_CSV == input_csv
@ -141,7 +143,9 @@ class TestNationalRiskIndexETL(TestETL):
)
# Assert that the extracted file exists
extracted_file_path = tmp_path / "NRI_Table_CensusTracts.csv"
extracted_file_path = (
tmp_path / "NationalRiskIndexETL" / "NRI_Table_CensusTracts.csv"
)
assert extracted_file_path.is_file()
input_csv_path = (