Update app.py

app.py

@@ -15,12 +15,18 @@ scaler = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=SCALER_FILENAME))
 
 def encode_categorical_columns(df):
     label_encoder = LabelEncoder()
+    
+    # Identify categorical columns
     ordinal_columns = df.select_dtypes(include=['object']).columns
-
+    
+    # Encode ordinal columns using LabelEncoder
     for col in ordinal_columns:
         df[col] = label_encoder.fit_transform(df[col])
 
+    # Get nominal columns for one-hot encoding
     nominal_columns = df.select_dtypes(include=['object']).columns.difference(ordinal_columns)
+    
+    # Apply one-hot encoding to nominal columns (drop the first column to avoid multicollinearity)
     df = pd.get_dummies(df, columns=nominal_columns, drop_first=True)
 
     return df
@@ -44,7 +50,10 @@ def predict_performance(Location, Course, College, Faculty, Source, Event, Prese
 
     input_data = [Location, Course, College, Faculty, Source, Event, Presenter, Visited_Parent, Visited_College_for_Inquiry, Attended_Any_Event, College_Fee, GPA, Year]
 
-    feature_names = ["Location", "Course", "College", "Faculty", "Source", "Event", "Presenter", "Visited_Parent", "Visited_College_for_Inquiry", "Attended_Any_Event", "College_Fee", "GPA", "Year"]
+    feature_names = [
+        "Location", "Course", "College", "Faculty", "Source", "Event", "Presenter", 
+        "Visited_Parent", "Visited_College_for_Inquiry", "Attended_Any_Event", "College_Fee", "GPA", "Year"
+    ]
     
     input_df = pd.DataFrame([input_data], columns=feature_names)
     
@@ -52,12 +61,14 @@ def predict_performance(Location, Course, College, Faculty, Source, Event, Prese
     print("\nDataFrame before encoding:")
     print(input_df)
     
+    # Encode categorical columns
     df = encode_categorical_columns(input_df)
     
     # Debug print 3: Show DataFrame after encoding
     print("\nDataFrame after encoding:")
     print(df)
     
+    # Scale input data using the loaded scaler
     scaled_input = scaler.transform(df)
     
     # Make the prediction