Update helper.py

helper.py

@@ -11,24 +11,12 @@ import pandas as pd
 from sklearn.preprocessing import MinMaxScaler
 
 def assign_main_accounts(creators_file, chatter_files):
-    """
-    Process creators and chatter files to assign main accounts to chatters and prepare data for scheduling.
-    Returns the updated chatter files, processed creator file, and combined assignments for preview.
-    """
-    # Load and process creators data
     creators = pd.read_excel(creators_file)
     creators.columns = creators.columns.str.strip()
 
-    # Ensure required columns
-    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 rank creators
     creators["Total earnings"] = creators["Total earnings"].replace("[\$,]", "", regex=True).astype(float)
     creators["Subscription"] = creators["Subscription"].replace("[\$,]", "", regex=True).astype(float)
-    creators["Total active fans"] = creators["Total active fans"].fillna(0).astype(int)
+    creators["ActiveFans"] = pd.to_numeric(creators["ActiveFans"], errors="coerce").fillna(0)
 
     scaler = MinMaxScaler()
     creators[["Earnings_Normalized", "Subscriptions_Normalized"]] = scaler.fit_transform(
@@ -39,39 +27,20 @@ def assign_main_accounts(creators_file, chatter_files):
         0.7 * creators["Earnings_Normalized"] + 0.3 * creators["Subscriptions_Normalized"]
     ) * creators["Penalty Factor"]
     creators["Rank"] = creators["Score"].rank(ascending=False)
-
     creators = creators.sort_values(by="Rank").reset_index(drop=True)
 
-    # Save processed creator file
-    processed_creator_file = creators[["Creator", "Total active fans"]].rename(
-        columns={"Total active fans": "ActiveFans"}
-    )
+    processed_creator_file = creators[["Creator", "ActiveFans"]]
 
-    # Assign main accounts to chatters
     updated_chatter_files = []
-    combined_assignments = []
+    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}")
-
-        chatters = chatters.sort_values(by="Final Rating", ascending=False).reset_index(drop=True)
-        num_chatters = len(chatters)
-        top_creators = creators.iloc[:num_chatters]
-        chatters["Main Account"] = top_creators["Creator"].values
-        chatters["Shift"] = shift_name
-
+        chatters["Main Account"] = creators.iloc[:len(chatters)]["Creator"].values
         updated_chatter_files.append(chatters)
-        combined_assignments.append(chatters)
-
-    # Combine all assignments for display
-    combined_assignments_df = pd.concat(combined_assignments, ignore_index=True)
+        assignments.append(chatters)
 
-    return updated_chatter_files, processed_creator_file, combined_assignments_df
+    return updated_chatter_files, processed_creator_file, pd.concat(assignments)