Develop vm 20240224

README.md

@@ -157,6 +157,10 @@ Use `docker-compose build --no-cache` to force a rebuild of the Docker image.
     # Clone this repo through https to avoid need for an SSH key
     git clone https://github.com/RMI-PACTA/workflow.data.preparation.git ~/workflow.data.preparation
 
+    cd ~/workflow.data.preparation
+    git checkout develop-vm-20240224
+    cd ~
+
     # Install az cli
     sudo apt update
     # See https://aka.ms/installcli for alternate instructions

config.yml

@@ -106,7 +106,6 @@ docker:
 
 
 2022Q4:
-  inherits: docker
   masterdata_ownership_filename: "2023-06-18_AI_RMI Bespoke_Company Data Products_masterdata_ownership_2022Q4.csv"
   masterdata_debt_filename: "2023-06-18_AI_RMI Bespoke_Company Data Products_masterdata_debt_2022Q4.csv"
   ar_company_id__factset_entity_id_filename: "2023-02-15_AI_RMI_Bespoke_Company_Data_Products_Company_ID_List_2022Q4.csv"
@@ -143,3 +142,38 @@ docker:
   masterdata_ownership_filename: "2023-06-18/2023-06-18_AI_RMI Bespoke_Company Data Products_masterdata_ownership_2022Q4.csv"
   masterdata_debt_filename: "2023-06-18/2023-06-18_AI_RMI Bespoke_Company Data Products_masterdata_debt_2022Q4.csv"
   ar_company_id__factset_entity_id_filename: "2023-02-15/2023-02-15_AI_RMI_Bespoke_Company_Data_Products_Company_ID_List_2022Q4.csv"
+
+
+2023Q4:
+  masterdata_ownership_filename: "2024-02-14_AI_RMI Bespoke_Company Data Products_masterdata_ownership_2023Q4.csv"
+  masterdata_debt_filename: "2024-02-14_AI_RMI Bespoke_Company Data Products_masterdata_debt_2023Q4.csv"
+  ar_company_id__factset_entity_id_filename: "2024-02-14_AI_RMI_Bespoke_Company_Data_Products_Company_ID_List_2023Q4.csv"
+  factset_financial_data_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_financial_data.rds"
+  factset_entity_info_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_entity_info.rds"
+  factset_entity_financing_data_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_entity_financing_data.rds"
+  factset_fund_data_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_fund_data.rds"
+  factset_isin_to_fund_table_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_isin_to_fund_table.rds"
+  factset_iss_emissions_data_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_iss_emissions.rds"
+  factset_issue_code_bridge_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_issue_code_bridge.rds"
+  factset_industry_map_bridge_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_industry_map_bridge.rds"
+  factset_manual_pacta_sector_override_filename: "timestamp-20231231T000000Z_pulled-20240217T135833Z_factset_manual_sector_override.rds"
+  imf_quarter_timestamp: "2023-Q4"
+  pacta_financial_timestamp: "2023Q4"
+  market_share_target_reference_year: 2023
+  time_horizon: 5
+  scenario_sources_list: ["GECO2022", "ISF2023", "WEO2022"]
+  sector_list: ["Automotive", "Power", "Oil&Gas", "Coal"]
+  other_sector_list: ["Steel", "Aviation", "Cement"]
+  zero_emission_factor_techs: ["Electric", "HydroCap", "NuclearCap", "RenewablesCap"]
+  green_techs: ["FuelCell", "Electric", "Hybrid", "RenewablesCap", "HydroCap", "NuclearCap", "FuelCell_HDV", "Electric_HDV", "Hybrid_HDV"]
+  scenario_raw_data_to_include: ["geco_2022", "isf_2023", "weo_2022"]
+  tech_exclude: ["OtherCap", "OtherFF", "Coking Plant", "Sintering Plant", "Direct Or Smelting Reduction Plant", "Pelletizing Plant", "Grinding Plant", "Passenger / Freight"]
+  scenario_geographies_list: ["Global", "NonOECD", "OECD"]
+  global_aggregate_scenario_sources_list: ["WEO2022"]
+  global_aggregate_sector_list: ["Power"]
+
+2023Q4_azure:
+  inherits: 2023Q4
+  data_prep_outputs_path: "/mnt/outputs"
+  asset_impact_data_path: "/mnt/asset-impact/2024-02-15_AI_RMI_2023Q4"
+  factset_data_path: "/mnt/factset-extracted/factset-pacta_timestamp-20231231T000000Z_pulled-20240217T135833Z"