Update app.py

app.py

@@ -17,7 +17,7 @@ def predict(age, workclass, education, marital_status, occupation, relationship,
     "relationship", "race", "gender", "capital_gain", "capital_loss", 
     "hours_per_week", "native_country"]
     df = pd.DataFrame(index=features, columns=columns)
-    fixed_features = cleaning_features(features)
+    fixed_features = cleaning_features(df)
     # prediction = model.predict(features)
     # prediction = 1
     # return "Income >50K" if prediction == 1 else "Income <=50K"
@@ -63,6 +63,16 @@ def pca(data):
     data = pd.concat([data, pca_df], axis=1)
     return data
 
+def hbdscan_tranform(df_transformed):
+    df_transformed['capital-gain'] = np.log1p(df_transformed['capital-gain'])
+    df_transformed['capital-loss'] = np.log1p(df_transformed['capital-loss'])
+    
+    # Apply RobustScaler to all numerical features
+    numerical_features = ['age', 'capital-gain', 'capital-loss', 'hours-per-week']
+    scaler = RobustScaler()
+    df_transformed[numerical_features] = scaler.fit_transform(df_transformed[numerical_features])
+    return df_transformed
+
 
 # Create the Gradio interface
 interface = gr.Interface(