Update app.py

app.py

@@ -13,12 +13,18 @@ from sklearn.preprocessing import LabelEncoder
 model = joblib.load('lgbm_model.pkl')  # Replace with actual path
 scaler = joblib.load('minmax_scaler.pkl')  # Replace with actual path
 
-# Get expected feature names from the model
-expected_features = model.feature_name_  # Extracts trained feature names
+# Define the expected feature names manually
+expected_features = ['meanr', 'meang', 'meanb', 'HHR', 'Ent', 'B', 
+                     'g1', 'g2', 'g3', 'g4', 'g5', 'Age']  # No 'Hgb'
+
+# Include 'Gender' if it was used during training
+use_gender = True  # Set to False if your model was not trained with 'Gender'
+if use_gender:
+    expected_features.append('Gender')
 
 # Initialize LabelEncoder for gender encoding (if used in training)
 gender_encoder = LabelEncoder()
-gender_encoder.fit(['Female', 'Male'])  # Ensure correct mapping
+gender_encoder.fit(['Female', 'Male'])
 
 # Function to extract features
 def extract_features(image):
@@ -68,18 +74,22 @@ def predict_hemoglobin(age, gender, image):
 
         # Extract features
         features = extract_features(image)
-        
-        # Encode gender only if the model was trained with it
-        if "Gender" in expected_features:
+
+        # Encode gender only if used in training
+        if use_gender:
             features["Gender"] = gender_encoder.transform([gender])[0]
-        
+
         features["Age"] = age
 
         # Convert to DataFrame
         features_df = pd.DataFrame([features])
 
         # Ensure only model-expected features are used
-        features_df = features_df[expected_features]  # Select only required columns
+        for col in expected_features:
+            if col not in features_df:
+                features_df[col] = 0  # Add missing columns with default value
+
+        features_df = features_df[expected_features]  # Ensure correct column order
 
         # Apply scaling
         features_scaled = scaler.transform(features_df)