Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion statvar_imports/brazil_sidra_ibge/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@

- Import Type: Fully Autorefresh

- Data Availability: 2022 to 2025
- Data Availability: Data is available from 2022-03 for every quarter and data is added every 3 months.

- Release Frequency: P3M, which means every 3 months (quarterly).

Expand Down
474 changes: 297 additions & 177 deletions statvar_imports/brazil_sidra_ibge/brazil_download_script.py

Large diffs are not rendered by default.

Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
"observationAbout"
"wikidataId/Q40780"
"wikidataId/Q40885"
"wikidataId/Q40130"
"wikidataId/Q40040"
"wikidataId/Q40430"
"country/BRA"
"wikidataId/Q40123"
"wikidataId/Q980175"
"wikidataId/Q119158"
"wikidataId/Q43233"
"wikidataId/Q41587"
"wikidataId/Q42362"
"wikidataId/Q42824"
"wikidataId/Q43319"
"wikidataId/Q39109"
"wikidataId/Q1136194"
"wikidataId/Q478465"
"wikidataId/Q39517"
"wikidataId/Q38088"
"wikidataId/Q15499"
"wikidataId/Q40942"
"wikidataId/Q42722"
"wikidataId/Q43255"
"wikidataId/Q40030"
"wikidataId/Q41428"
"wikidataId/Q43235"
"wikidataId/Q42508"
"wikidataId/Q175"
"wikidataId/Q41115"
"wikidataId/Q43783"
"wikidataId/Q1088815"
"wikidataId/Q1060042"
"wikidataId/Q43695"
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
"observationAbout"
"wikidataId/Q40780"
"wikidataId/Q40885"
"wikidataId/Q40130"
"wikidataId/Q40040"
"wikidataId/Q40430"
"country/BRA"
"wikidataId/Q40123"
"wikidataId/Q980175"
"wikidataId/Q119158"
"wikidataId/Q43233"
"wikidataId/Q41587"
"wikidataId/Q42362"
"wikidataId/Q42824"
"wikidataId/Q43319"
"wikidataId/Q39109"
"wikidataId/Q1136194"
"wikidataId/Q478465"
"wikidataId/Q39517"
"wikidataId/Q38088"
"wikidataId/Q15499"
"wikidataId/Q40942"
"wikidataId/Q42722"
"wikidataId/Q43255"
"wikidataId/Q40030"
"wikidataId/Q41428"
"wikidataId/Q43235"
"wikidataId/Q42508"
"wikidataId/Q175"
"wikidataId/Q41115"
"wikidataId/Q43783"
"wikidataId/Q1088815"
"wikidataId/Q1060042"
"wikidataId/Q43695"
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
"observationAbout"
"wikidataId/Q40780"
"wikidataId/Q40885"
"wikidataId/Q40130"
"wikidataId/Q40040"
"wikidataId/Q40430"
"country/BRA"
"wikidataId/Q40123"
"wikidataId/Q980175"
"wikidataId/Q119158"
"wikidataId/Q43233"
"wikidataId/Q41587"
"wikidataId/Q42362"
"wikidataId/Q42824"
"wikidataId/Q43319"
"wikidataId/Q39109"
"wikidataId/Q1136194"
"wikidataId/Q478465"
"wikidataId/Q39517"
"wikidataId/Q38088"
"wikidataId/Q15499"
"wikidataId/Q40942"
"wikidataId/Q42722"
"wikidataId/Q43255"
"wikidataId/Q40030"
"wikidataId/Q41428"
"wikidataId/Q43235"
"wikidataId/Q42508"
"wikidataId/Q175"
"wikidataId/Q41115"
"wikidataId/Q43783"
"wikidataId/Q1088815"
"wikidataId/Q1060042"
"wikidataId/Q43695"
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
"observationAbout"
"wikidataId/Q40780"
"wikidataId/Q40885"
"wikidataId/Q40130"
"wikidataId/Q40040"
"wikidataId/Q40430"
"country/BRA"
"wikidataId/Q40123"
"wikidataId/Q980175"
"wikidataId/Q119158"
"wikidataId/Q43233"
"wikidataId/Q41587"
"wikidataId/Q42362"
"wikidataId/Q42824"
"wikidataId/Q43319"
"wikidataId/Q39109"
"wikidataId/Q1136194"
"wikidataId/Q478465"
"wikidataId/Q39517"
"wikidataId/Q38088"
"wikidataId/Q15499"
"wikidataId/Q40942"
"wikidataId/Q42722"
"wikidataId/Q43255"
"wikidataId/Q40030"
"wikidataId/Q41428"
"wikidataId/Q43235"
"wikidataId/Q42508"
"wikidataId/Q175"
"wikidataId/Q41115"
"wikidataId/Q43783"
"wikidataId/Q1088815"
"wikidataId/Q1060042"
"wikidataId/Q43695"
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
"NumObservationsDates","MeasurementMethods","observationPeriods","MinDate","MinValue","MaxValue","NumObservations","Units","StatVar","NumPlaces","MaxDate","ScalingFactors"
"17","[]","[P3M]","2022-03","2.1","17.5","561","[Percent]","Count_Person_Years14Onwards_Unemployed_AsAFractionOf_Count_Person_Years14Onwards","33","2026-03","[100]"
"17","[]","[P3M]","2022-03","47.1","71.4","561","[Percent]","Count_Person_Years14Onwards_InLaborForce_AsAFractionOf_Count_Person_Years14Onwards","33","2026-03","[100]"
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
"Units","MinValue","MaxDate","NumObservationsDates","MeasurementMethods","observationPeriods","MinDate","MaxValue","NumObservations","ScalingFactors","StatVar","NumPlaces"
"[BRL]","6.48E8","2026-03","17","[]","[P3M]","2022-03","4.06112E11","561","[]","Monthly_Income_Person_Years14Onwards_Employed_IncomeActuallyReceived","33"
"[BRL]","6.33E8","2026-03","17","[]","[P3M]","2022-03","3.74819E11","561","[]","Monthly_Income_Person_Years14Onwards_Employed","33"
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
"NumPlaces","NumObservations","Units","StatVar","observationPeriods","MaxValue","MinValue","ScalingFactors","MeasurementMethods","NumObservationsDates","MinDate","MaxDate"
"33","561","[]","Count_Person_Years14Onwards_PublicSector_Employed","[P3M]","1.3004E7","53000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_Employer_Employed","[P3M]","4270000.0","6000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person","[P3M]","2.13328E8","583000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_AdminSocialServiceEducation_Employed","[P3M]","1.9362E7","59000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_AgricultureForestFishingSector_Employed","[P3M]","8700000.0","12000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_AuxiliaryFamilyWorker_Employed","[P3M]","1923000.0","1000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards","[P3M]","1.7508E8","435000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_SelfEmployed_Employed","[P3M]","2.6109E7","61000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_PrivateSectorNoFormalContract_Employed","[P3M]","1.4067E7","26000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_DomesticServicesSector_Employed","[P3M]","6020000.0","10000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_TransportStorageSector_Employed","[P3M]","5992000.0","9000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_IBGEOtherServicesSector_Employed","[P3M]","5540000.0","10000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_VehicleTradeRepair_Employed","[P3M]","1.9505E7","43000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_GeneralIndustry_Employed","[P3M]","1.3287E7","10000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_Employed","[P3M]","1.02998E8","232000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_CommunicationFinanceSector_Employed","[P3M]","1.3229E7","20000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_AccommodationFoodSector_Employed","[P3M]","5636000.0","12000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_ConstructionSector_Employed","[P3M]","7688000.0","15000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_InLaborForce","[P3M]","1.08569E8","255000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_Unemployed","[P3M]","1.1725E7","12000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_DomesticWorker_Employed","[P3M]","5978000.0","10000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_PrivateSectorFormalContract_Employed","[P3M]","3.9409E7","55000.0","[]","[]","17","2022-03","2026-03"
"33","561","[]","Count_Person_Years14Onwards_NotInLaborForce","[P3M]","6.6525E7","165000.0","[]","[]","17","2022-03","2026-03"
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
"MaxValue","NumObservationsDates","MinValue","MinDate","NumObservations","observationPeriods","MeasurementMethods","ScalingFactors","NumPlaces","Units","MaxDate","StatVar"
"5474.0","17","1257.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_IBGEOtherServicesSector_Employed_MainJob"
"5875.0","17","1497.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_GeneralIndustry_Employed_MainJob"
"7585.0","17","1827.0","2022-03","561","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_Employed_AllJobs_IncomeActuallyReceived"
"10441.0","17","2962.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_AdminSocialServiceEducation_Employed_MainJob"
"5440.0","17","1571.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_TransportStorageSector_Employed_MainJob"
"5631.0","17","611.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_AgricultureForestFishingSector_Employed_MainJob"
"3956.0","17","1926.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_PrivateSectorFormalContract_Employed_MainJob"
"3939.0","17","1650.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_VehicleCommerceRepair_Employed_MainJob"
"6464.0","17","1769.0","2022-03","561","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_Employed_MainJob"
"12900.0","17","2946.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_PublicSector_Employed_MainJob"
"14912.0","17","3527.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_Employer_Employed_MainJob"
"4364.0","17","1093.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_PrivateSectorNoFormalContract_Employed_MainJob"
"7351.0","17","1779.0","2022-03","561","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_Employed_MainJob_IncomeActuallyReceived"
"2020.0","17","722.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_DomesticWorker_Employed_MainJob"
"4883.0","17","1242.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_SelfEmployed_Employed_MainJob"
"3369.0","17","1227.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_AccommodationFoodSector_Employed_MainJob"
"6720.0","17","1813.0","2022-03","561","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_Employed_AllJobs"
"7364.0","17","2224.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_CommunicationFinanceSector_Employed_MainJob"
"2020.0","17","722.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_DomesticServicesSector_Employed_MainJob"
"5150.0","17","1339.0","2022-03","529","[]","[]","[]","33","[BRL]","2026-03","Monthly_Mean_Income_Person_Years14Onwards_ConstructionSector_Employed_MainJob"
15 changes: 9 additions & 6 deletions statvar_imports/brazil_sidra_ibge/manifest.json
Original file line number Diff line number Diff line change
Expand Up @@ -9,10 +9,10 @@
"provenance_description": "Population Census on Economy Statistics for Brazil at country and state level.",
"scripts": [
"brazil_download_script.py",
"../../tools/statvar_importer/stat_var_processor.py --existing_statvar_mcf=gs://unresolved_mcf/scripts/statvar/stat_vars.mcf --input_data=input_files/Average_Real_Income/*.xlsx --pv_map=config_files/average_real_income_pvmap.csv,config_files/place_pvmap.csv --config_file=config_files/brazil_sidra_metadata.csv --output_path=output/average_real_income_output",
"../../tools/statvar_importer/stat_var_processor.py --existing_statvar_mcf=gs://unresolved_mcf/scripts/statvar/stat_vars.mcf --input_data=input_files/Mass_Income/*.xlsx --pv_map=config_files/mass_income_pvmap.csv,config_files/place_pvmap.csv --config_file=config_files/brazil_sidra_metadata.csv --output_path=output/mass_income_output",
"../../tools/statvar_importer/stat_var_processor.py --existing_statvar_mcf=gs://unresolved_mcf/scripts/statvar/stat_vars.mcf --input_data=input_files/Population_Economic_sector/*.xlsx --pv_map=config_files/population_pvmap.csv,config_files/place_pvmap.csv --config_file=config_files/brazil_sidra_metadata.csv --output_path=output/population_economic_sector_output",
"../../tools/statvar_importer/stat_var_processor.py --existing_statvar_mcf=gs://unresolved_mcf/scripts/statvar/stat_vars.mcf --input_data=input_files/Employment_And_Unemployment_Labor_Force/*.xlsx --pv_map=config_files/employment_and_unemployment_labor_force_pvmap.csv,config_files/place_pvmap.csv --config_file=config_files/brazil_sidra_metadata.csv --output_path=output/employment_and_unemployment_labor_force_output"
"../../tools/statvar_importer/stat_var_processor.py --existing_statvar_mcf=gs://unresolved_mcf/scripts/statvar/stat_vars.mcf --input_data=input_files/Average_Real_Income/*.xlsx --pv_map=config_files/average_real_income_pvmap.csv,config_files/place_pvmap.csv --config_file=config_files/brazil_sidra_metadata.csv --output_path=output/average_real_income_output --output_counters=counters/average_real_income_counters.csv",
"../../tools/statvar_importer/stat_var_processor.py --existing_statvar_mcf=gs://unresolved_mcf/scripts/statvar/stat_vars.mcf --input_data=input_files/Mass_Income/*.xlsx --pv_map=config_files/mass_income_pvmap.csv,config_files/place_pvmap.csv --config_file=config_files/brazil_sidra_metadata.csv --output_path=output/mass_income_output --output_counters=counters/mass_income_counters.csv",
"../../tools/statvar_importer/stat_var_processor.py --existing_statvar_mcf=gs://unresolved_mcf/scripts/statvar/stat_vars.mcf --input_data=input_files/Population_Economic_sector/*.xlsx --pv_map=config_files/population_pvmap.csv,config_files/place_pvmap.csv --config_file=config_files/brazil_sidra_metadata.csv --output_path=output/population_economic_sector_output --output_counters=counters/population_economic_sector_counters.csv",
"../../tools/statvar_importer/stat_var_processor.py --existing_statvar_mcf=gs://unresolved_mcf/scripts/statvar/stat_vars.mcf --input_data=input_files/Employment_And_Unemployment_Labor_Force/*.xlsx --pv_map=config_files/employment_and_unemployment_labor_force_pvmap.csv,config_files/place_pvmap.csv --config_file=config_files/brazil_sidra_metadata.csv --output_path=output/employment_and_unemployment_labor_force_output --output_counters=counters/employment_and_unemployment_labor_force_counters.csv"
],
"import_inputs": [
{
Expand All @@ -36,9 +36,12 @@
"input_files/Average_Real_Income/*.xlsx",
"input_files/Mass_Income/*.xlsx",
"input_files/Population_Economic_sector/*.xlsx",
"input_files/Employment_And_Unemployment_Labor_Force/*.xlsx"
"input_files/Employment_And_Unemployment_Labor_Force/*.xlsx",
"golden_data/*.csv",
"counters/*.csv"
],
"cron_schedule": "30 09 25 * *"
"cron_schedule": "30 09 25 * *",
"validation_config_file": "validation_config.json"
}
]
}
85 changes: 85 additions & 0 deletions statvar_imports/brazil_sidra_ibge/validation_config.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,85 @@
{
"schema_version": "1.0",
"rules": [
{
"rule_id": "check_deleted_records_percent",
"description": "Checks that the percentage of deleted records for the entire import is within threshold.",
"validator": "DELETED_RECORDS_PERCENT",
"params": {
"threshold": 0.1
}
},
{
"rule_id": "check_goldens_average_real_income",
"description": "Validates average real income data against its golden summary report.",
"validator": "GOLDENS_CHECK",
"params": {
"golden_files": "../../../../golden_data/golden_summary_report_average_real_income.csv",
"input_files": "../../input0/genmcf/summary_report.csv"
}
},
{
"rule_id": "check_goldens_mass_income",
"description": "Validates mass income data against its golden summary report.",
"validator": "GOLDENS_CHECK",
"params": {
"golden_files": "../../../../golden_data/golden_summary_mass_income.csv",
"input_files": "../../input1/genmcf/summary_report.csv"
}
},
{
"rule_id": "check_goldens_population_economic",
"description": "Validates population economic sector data against its golden summary report.",
"validator": "GOLDENS_CHECK",
"params": {
"golden_files": "../../../../golden_data/golden_summary_population_economic.csv",
"input_files": "../../input2/genmcf/summary_report.csv"
}
},
{
"rule_id": "check_goldens_employment_unemployment",
"description": "Validates employment and unemployment data against its golden summary report.",
"validator": "GOLDENS_CHECK",
"params": {
"golden_files": "../../../../golden_data/golden_summary_employment_unemployment.csv",
"input_files": "../../input3/genmcf/summary_report.csv"
}
},
{
"rule_id": "Check_goldens_output_csv_average_real_income",
"description": "Verifies the generated output CSV data matches established critical golden records",
"validator": "GOLDENS_CHECK",
"params": {
"golden_files": "../../../../golden_data/golden_observations_average_real_income.csv",
"input_files": "../../../../output/average_real_income_output.csv"
}
},
{
"rule_id": "Check_goldens_output_csv_mass_income",
"description": "Verifies the generated output CSV data matches established critical golden records",
"validator": "GOLDENS_CHECK",
"params": {
"golden_files": "../../../../golden_data/golden_observations_mass_income.csv",
"input_files": "../../../../output/mass_income_output.csv"
}
},
{
"rule_id": "Check_goldens_output_csv_population_economic",
"description": "Verifies the generated output CSV data matches established critical golden records",
"validator": "GOLDENS_CHECK",
"params": {
"golden_files": "../../../../golden_data/golden_observations_population_economic.csv",
"input_files": "../../../../output/population_economic_sector_output.csv"
}
},
{
"rule_id": "Check_goldens_output_csv_employment_unemployment",
"description": "Verifies the generated output CSV data matches established critical golden records",
"validator": "GOLDENS_CHECK",
"params": {
"golden_files": "../../../../golden_data/golden_observations_employment_unemployment.csv",
"input_files": "../../../../output/employment_and_unemployment_labor_force_output.csv"
}
}
]
}
Loading