Refactor code structure for improved readability and maintainability

preprocessor/main.py

@@ -13,7 +13,8 @@ logger = logging.getLogger(__name__)
 # Import the schema
 init_database()
 
-#===================== Ingesting Original Data =====================#
+
+# ===================== Ingesting Original Data =====================#
 def parse_investor_names(investor_names_str):
     """Parse comma-separated investor names and return a list"""
     if pd.isna(investor_names_str) or investor_names_str == "":
@@ -21,7 +22,9 @@ def parse_investor_names(investor_names_str):
 
     # Split by comma and clean whitespace
     # investors = [name.strip() for name in str(investor_names_str).split(",")]
-    investors = [clean_name(name.strip()) for name in str(investor_names_str).split(",")]
+    investors = [
+        clean_name(name.strip()) for name in str(investor_names_str).split(",")
+    ]
     return [investor for investor in investors if investor]
 
 
@@ -165,8 +168,8 @@ def ingest_data():
                 if not existing_investor:
                     investor = InvestorTable(
                         name=investor_name,
-                        # description=clean_string(row.get("Business model", "")),
-                        # geographic_focus=clean_string(row.get("HQ", "")),
+                        description=clean_string(row.get("Business model", "")),
+                        headquarters=clean_string(row.get("HQ", "")),
                         website=parse_website(str(row.get("Website", "")).strip()),
                         number_of_investments=clean_integer(
                             row.get("Number of investments")
@@ -305,8 +308,6 @@ def ingest_data():
     session.close()
 
 
-
-
 if __name__ == "__main__":
     ingest_data()
     # print(clean_name("A... Energi"))