Update app.py features

app.py

@@ -11,19 +11,45 @@ def preprocess_input(data_dict):
     """Preprocess input data to match the training format"""
     df = pd.DataFrame([data_dict])
     
-    # Numeric features
+    # Numeric features - add prefix 'num__'
     numeric_features = ['age', 'avg_glucose_level', 'bmi']
+    for feat in numeric_features:
+        df[f'num__{feat}'] = df[feat]
     
     # Scale numeric features
     scaler = StandardScaler()
-    df[numeric_features] = scaler.fit_transform(df[numeric_features])
+    for feat in numeric_features:
+        df[f'num__{feat}'] = scaler.fit_transform(df[[feat]])
     
-    # Create dummy variables for categorical features
-    df = pd.get_dummies(df, columns=['gender', 'hypertension', 'heart_disease', 
-                                    'ever_married', 'work_type', 'Residence_type', 
-                                    'smoking_status'])
+    # Create categorical features with proper prefixes
+    # gender
+    df['cat__gender_Male'] = (df['gender'] == 'Male').astype(float)
+    df['cat__gender_Other'] = 0.0  # Assuming no 'Other' gender in our interface
     
-    # Ensure all expected columns are present
+    # hypertension
+    df['cat__hypertension_1'] = df['hypertension'].astype(float)
+    
+    # heart_disease
+    df['cat__heart_disease_1'] = df['heart_disease'].astype(float)
+    
+    # ever_married
+    df['cat__ever_married_Yes'] = (df['ever_married'] == 'Yes').astype(float)
+    
+    # work_type
+    df['cat__work_type_Never_worked'] = (df['work_type'] == 'Never_worked').astype(float)
+    df['cat__work_type_Private'] = (df['work_type'] == 'Private').astype(float)
+    df['cat__work_type_Self-employed'] = (df['work_type'] == 'Self-employed').astype(float)
+    df['cat__work_type_children'] = (df['work_type'] == 'children').astype(float)
+    
+    # Residence_type
+    df['cat__Residence_type_Urban'] = (df['Residence_type'] == 'Urban').astype(float)
+    
+    # smoking_status
+    df['cat__smoking_status_formerly smoked'] = (df['smoking_status'] == 'formerly smoked').astype(float)
+    df['cat__smoking_status_never smoked'] = (df['smoking_status'] == 'never smoked').astype(float)
+    df['cat__smoking_status_smokes'] = (df['smoking_status'] == 'smokes').astype(float)
+    
+    # Select only the transformed columns in the correct order
     expected_columns = [
         'num__age', 'num__avg_glucose_level', 'num__bmi',
         'cat__gender_Male', 'cat__gender_Other', 'cat__hypertension_1',
@@ -34,10 +60,6 @@ def preprocess_input(data_dict):
         'cat__smoking_status_never smoked', 'cat__smoking_status_smokes'
     ]
     
-    for col in expected_columns:
-        if col not in df.columns:
-            df[col] = 0
-            
     return df[expected_columns]
 
 def predict(gender, age, hypertension, ever_married, work_type, heart_disease,