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:
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

View file

@ -1,8 +1,18 @@
DATASET_LIST = [
{
"name": "mapping_for_ej",
"module_dir": "mapping_for_ej",
"class_name": "MappingForEJETL",
"name": "cdc_places",
"module_dir": "cdc_places",
"class_name": "CDCPlacesETL",
},
{
"name": "national_risk_index",
"module_dir": "national_risk_index",
"class_name": "NationalRiskIndexETL",
},
{
"name": "tree_equity_score",
"module_dir": "tree_equity_score",
"class_name": "TreeEquityScoreETL",
},
{
"name": "census_acs",
@ -14,6 +24,21 @@ DATASET_LIST = [
"module_dir": "census_acs_2010",
"class_name": "CensusACS2010ETL",
},
{
"name": "census_decennial",
"module_dir": "census_decennial",
"class_name": "CensusDecennialETL",
},
{
"name": "housing_and_transportation",
"module_dir": "housing_and_transportation",
"class_name": "HousingTransportationETL",
},
{
"name": "mapping_for_ej",
"module_dir": "mapping_for_ej",
"class_name": "MappingForEJETL",
},
{
"name": "ejscreen",
"module_dir": "ejscreen",
@ -24,16 +49,6 @@ DATASET_LIST = [
"module_dir": "hud_housing",
"class_name": "HudHousingETL",
},
{
"name": "cdc_places",
"module_dir": "cdc_places",
"class_name": "CDCPlacesETL",
},
{
"name": "national_risk_index",
"module_dir": "national_risk_index",
"class_name": "NationalRiskIndexETL",
},
{
"name": "census_acs_median_income",
"module_dir": "census_acs_median_income",
@ -74,16 +89,6 @@ DATASET_LIST = [
"module_dir": "ejscreen_areas_of_concern",
"class_name": "EJSCREENAreasOfConcernETL",
},
{
"name": "census_decennial",
"module_dir": "census_decennial",
"class_name": "CensusDecennialETL",
},
{
"name": "housing_and_transportation",
"module_dir": "housing_and_transportation",
"class_name": "HousingTransportationETL",
},
{
"name": "calenviroscreen",
"module_dir": "calenviroscreen",
@ -104,11 +109,6 @@ DATASET_LIST = [
"module_dir": "energy_definition_alternative_draft",
"class_name": "EnergyDefinitionAlternativeDraft",
},
{
"name": "tree_equity_score",
"module_dir": "tree_equity_score",
"class_name": "TreeEquityScoreETL",
},
{
"name": "michigan_ejscreen",
"module_dir": "michigan_ejscreen",