Update helper.py

helper.py

@@ -8,62 +8,60 @@ import pandas as pd
 from sklearn.preprocessing import MinMaxScaler
 
 def assign_main_accounts(creators_file, chatter_files):
-
+    # Load and process creators data
     creators = pd.read_excel(creators_file)
-    creators.columns = creators.columns.str.strip()
-
-    column_mapping = {
-        "Creator": "Creator",
-        "Total earnings": "Total earnings",
-        "Subscription": "Subscription",
-        "Active Fans": "ActiveFans",
-        "Total active fans": "ActiveFans",
-    }
-    creators.rename(columns={k: v for k, v in column_mapping.items() if k in creators.columns}, inplace=True)
-
-    required_columns = ["Creator", "Total earnings", "Subscription", "ActiveFans"]
+    creators.columns = creators.columns.str.strip()  # Clean up column names
+
+    # Ensure required columns are present
+    required_columns = ["Creator", "Total earnings", "Subscription", "Total active fans"]
     missing_columns = [col for col in required_columns if col not in creators.columns]
     if missing_columns:
         raise KeyError(f"Missing required columns in creators file: {missing_columns}")
 
-
+    # Normalize and calculate scores for creators
     creators["Total earnings"] = creators["Total earnings"].replace("[\$,]", "", regex=True).astype(float)
     creators["Subscription"] = creators["Subscription"].replace("[\$,]", "", regex=True).astype(float)
-    creators["ActiveFans"] = pd.to_numeric(creators["ActiveFans"], errors="coerce").fillna(0)
-
+    creators["Total active fans"] = creators["Total active fans"].fillna(0).astype(int)
 
+    # Scale data for ranking
     scaler = MinMaxScaler()
     creators[["Earnings_Normalized", "Subscriptions_Normalized"]] = scaler.fit_transform(
         creators[["Total earnings", "Subscription"]]
+    )
+    creators["Penalty Factor"] = 1 - abs(creators["Earnings_Normalized"] - creators["Subscriptions_Normalized"])
+    creators["Score"] = (
         0.7 * creators["Earnings_Normalized"] + 0.3 * creators["Subscriptions_Normalized"]
     ) * creators["Penalty Factor"]
     creators["Rank"] = creators["Score"].rank(ascending=False)
 
-
+    # Sort creators by rank
     creators = creators.sort_values(by="Rank").reset_index(drop=True)
 
-
+    # Assign main accounts to chatters
     assignments = {}
     for idx, chatter_file in enumerate(chatter_files):
         shift_name = ["overnight", "day", "prime"][idx]
+        chatters = pd.read_excel(chatter_file)
+        chatters.columns = chatters.columns.str.strip()
+
         if "Final Rating" not in chatters.columns:
             raise KeyError(f"'Final Rating' column is missing in {chatter_file}")
 
-
+        # Sort chatters by performance
         chatters = chatters.sort_values(by="Final Rating", ascending=False).reset_index(drop=True)
 
-
+        # Match top creators with top chatters
         num_chatters = len(chatters)
-        creators_to_assign = creators.iloc[:num_chatters]
-        chatters["Main Account"] = creators_to_assign["Creator"].values
-
+        top_creators = creators.iloc[:num_chatters]
+        chatters["Main Account"] = top_creators["Creator"].values
 
+        # Save assignment
         assignments[shift_name] = chatters.to_dict(orient="records")
 
-    assignments["creator_names"] = creators["Creator"].tolist()
-    print("DEBUG: Chatter Data with Main Account Assignments:")
-    print(chatters.head())
-
+    # Add processed creators for schedule generation
+    assignments["creators"] = creators[["Creator", "Total active fans"]].rename(
+        columns={"Total active fans": "ActiveFans"}
+    ).to_dict(orient="records")
 
     return assignments
 
@@ -72,6 +70,7 @@ def assign_main_accounts(creators_file, chatter_files):
 
 
 
+
 def save_processed_files(assignments, output_dir):
     """
     Save processed files for main assignments, ensuring chatter names and main accounts are preserved correctly.