update script

etl/notebooks/economy_entity_domain.py

@@ -0,0 +1,25 @@
+"""a script to produce the data in economy_entity_domain.xlsx"""
+
+import pandas as pd
+import polars as pl
+
+input_file = "../source/CLASS.xlsx"
+
+
+data = pd.read_excel(input_file, sheet_name="Groups")
+
+data = pl.from_pandas(data)
+
+data.select(
+    pl.col(["GroupCode", "GroupName"]).unique()
+)
+
+groups = data.select(
+    pl.col(["GroupCode", "GroupName"]).unique(maintain_order=True)
+)
+
+groups.write_csv('./groups.csv')
+
+"""
+And then, copy the data into economy_entity_domain.xlsx, and use vlookup to update the data.
+"""

etl/scripts/etl.py

@@ -19,7 +19,7 @@
 source_dir = '../source/'
 output_dir = '../../'
 
-data_csv = os.path.join(source_dir, 'WDICSV.csv')
+data_csv = os.path.join(source_dir, 'WDIData.csv')
 country_csv = os.path.join(source_dir, 'WDICountry.csv')
 series_csv = os.path.join(source_dir, 'WDISeries.csv')
 groups_xls = os.path.join(source_dir, 'CLASS.xlsx')