mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-07-28 20:41:18 -07:00
Run ETL processes in parallel (#1253)
* 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:
parent
389eb59ac4
commit
a0d6e55f0a
30 changed files with 286 additions and 160 deletions
|
@ -37,12 +37,12 @@ class DOEEnergyBurden(ExtractTransformLoad):
|
|||
|
||||
unzip_file_from_url(
|
||||
file_url=self.DOE_FILE_URL,
|
||||
download_path=self.TMP_PATH,
|
||||
unzipped_file_path=self.TMP_PATH / "doe_energy_burden",
|
||||
download_path=self.get_tmp_path(),
|
||||
unzipped_file_path=self.get_tmp_path() / "doe_energy_burden",
|
||||
)
|
||||
|
||||
self.raw_df = pd.read_csv(
|
||||
filepath_or_buffer=self.TMP_PATH
|
||||
filepath_or_buffer=self.get_tmp_path()
|
||||
/ "doe_energy_burden"
|
||||
/ "DOE_LEAD_AMI_TRACT_2018_ALL.csv",
|
||||
# The following need to remain as strings for all of their digits, not get converted to numbers.
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue