Update app.py

app.py

@@ -3,7 +3,7 @@ import joblib
 import numpy as np
 import pandas as pd
 from huggingface_hub import hf_hub_download
-from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder
+from sklearn.preprocessing import LabelEncoder
 
 # Load the trained model and scaler objects from file
 REPO_ID = "Hemg/modelxxx"  # hugging face repo ID
@@ -30,6 +30,7 @@ def encode_categorical_columns(df):
     df = pd.get_dummies(df, columns=nominal_columns, drop_first=True)
 
     return df
+
 def predict_performance(Location, Course, College, Faculty, Source, Event, Presenter, Visited_Parent, Visited_College_for_Inquiry, Attended_Any_Event, College_Fee, GPA, Year):
     input_data = [Location, Course, College, Faculty, Source, Event, Presenter, Visited_Parent, Visited_College_for_Inquiry, Attended_Any_Event, College_Fee, GPA, Year]
 
@@ -41,32 +42,45 @@ def predict_performance(Location, Course, College, Faculty, Source, Event, Prese
     
     input_df = pd.DataFrame([input_data], columns=feature_names)
 
-    
-    # Debug print 2: Show DataFrame before encoding
+    # Debug print: Show DataFrame before encoding
     print("\nDataFrame before encoding:")
     print(input_df)
     
     # Encode categorical columns
     df = encode_categorical_columns(input_df)
     
-    # Debug print 3: Show DataFrame after encoding
+    # Debug print: Show DataFrame after encoding
     print("\nDataFrame after encoding:")
     print(df)
     
+    # Ensure the DataFrame has the same columns as the scaler was trained on
+    expected_columns = scaler.feature_names_in_
+    for col in expected_columns:
+        if col not in df.columns:
+            df[col] = 0  # Add missing columns with default value 0
+
+    df = df[expected_columns]  # Reorder columns to match the scaler's training data
+
+    # Debug print: Show DataFrame after aligning columns
+    print("\nDataFrame after aligning columns:")
+    print(df)
+    
     # Scale input data using the loaded scaler
     scaled_input = scaler.transform(df)
     
+    # Debug print: Show scaled input
+    print("\nScaled input:")
+    print(scaled_input)
+    
     # Make the prediction
     prediction = model.predict(scaled_input)[0]
     
     # Clip the prediction to be between 0 and 1
     prediction = np.clip(prediction, 0, 1)
     
-    
-    # Debug print
+    # Debug print: Show prediction details
     print("\nPrediction details:")
     print(f"Raw prediction: {prediction}")
-   
     
     return f"Chance of Admission: {prediction:.1f}"