Update app.py

app.py

@@ -8,14 +8,16 @@ model = joblib.load("best_model.pkl")
 le_operation_type = joblib.load("le_operation_type.pkl")
 le_operator_id = joblib.load("le_operator_id.pkl")
 
-def predict_end_date(start_date, quantity, operation_code, operator_code, day_of_week):
-    # Convert inputs to correct types
+def predict_end_date(start_date, quantity, operation_type, operator_id, day_of_week):
+    # Convert input types
     quantity = float(quantity)
-    operation_code = int(operation_code)
-    operator_code = int(operator_code)
     day_of_week = int(day_of_week)
 
-    # Log transform and feature engineering
+    # Use label encoders to convert strings to codes
+    operation_code = le_op.transform([operation_type])[0]
+    operator_code = le_opr.transform([operator_id])[0]
+
+    # Feature engineering
     quantity_log = np.log1p(quantity)
     quantity_log_squared = quantity_log ** 2
     quantity_log_cubed = quantity_log ** 3
@@ -24,7 +26,6 @@ def predict_end_date(start_date, quantity, operation_code, operator_code, day_of
     quantity_operator_interaction_squared = quantity_operator_interaction ** 2
     operation_operator_interaction = operation_code * operator_code
 
-    # Match the model's training feature order
     X = pd.DataFrame([[
         quantity_log,
         quantity_log_squared,
@@ -49,10 +50,9 @@ def predict_end_date(start_date, quantity, operation_code, operator_code, day_of
         'DayOfWeek'
     ])
 
-    # Predict
     pred_days = model.predict(X)[0]
 
-    # Convert to date and readable duration
+    # Convert predicted days to readable date + time
     from datetime import datetime, timedelta
     start_dt = datetime.strptime(start_date, "%d-%m-%Y")
     end_dt = start_dt + timedelta(days=pred_days)