Update app.py

app.py

@@ -15,27 +15,33 @@ day_choices = [col.replace('day_of_week_', '') for col in feature_names if col.s
 
 def predict_fall(movement_activity, location, day_of_week, hour_of_day, minute_of_day, time_since_last_event):
     try:
-        # Initialize all features to 0
+        # Initialize all features to 0 based on model's feature_names (which must be a list)
         data = {feat: 0 for feat in feature_names}
 
-        # Set one-hot encoded categorical variables
+        # Set categorical one-hot encoded features
         data[f'Movement Activity_{movement_activity}'] = 1
         data[f'Location_{location}'] = 1
         data[f'day_of_week_{day_of_week}'] = 1
 
-        # Set numerical features
+        # Set numeric features
         data['hour_of_day'] = hour_of_day
         data['minute_of_day'] = minute_of_day
         data['time_since_last_event'] = time_since_last_event
 
-        # Build DataFrame in the exact order of feature_names (very important)
+        # Create input DataFrame in the order of feature_names
         input_df = pd.DataFrame([data], columns=feature_names)
 
-        # Pass columns in correct order to scaler
-        scaled_features = scaler.transform(input_df[feature_names])
+        print("Scaler expects:", scaler.feature_names_in_)
+        print("Input columns:", input_df.columns.tolist())
 
-        # Replace numerical values with scaled values (or all if scaler scales all)
-        input_df.loc[:, feature_names] = scaled_features
+        # Select columns in scaler's expected order
+        input_for_scaler = input_df[scaler.feature_names_in_]
+
+        # Transform
+        scaled_features = scaler.transform(input_for_scaler)
+
+        # Replace original columns with scaled data in scaler's order
+        input_df.loc[:, scaler.feature_names_in_] = scaled_features
 
         # Predict probability
         pred_proba = model.predict_proba(input_df)[0, 1]
@@ -47,7 +53,7 @@ def predict_fall(movement_activity, location, day_of_week, hour_of_day, minute_o
     except Exception as e:
         import traceback
         traceback.print_exc()
-        return f"Error: {str(e)}. Check logs for details."
+        return f"Error: {str(e)}. Check logs."
 
 
 # Gradio interface setup