Update app.py

app.py

@@ -11,7 +11,12 @@ from sklearn.decomposition import PCA
 
 # # Define the prediction function
 def predict(age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country):
-    features = np.array([age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country])
+    features = [age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country]
+    columns = [
+    "age", "workclass", "education", "marital_status", "occupation", 
+    "relationship", "race", "gender", "capital_gain", "capital_loss", 
+    "hours_per_week", "native_country"]
+    df = pd.DataFrame(features, columns=columns)
     fixed_features = cleaning_features(features)
     # prediction = model.predict(features)
     # prediction = 1
@@ -25,11 +30,13 @@ def cleaning_features(data):
     numeric_cols = ['age', 'educational-num', 'hours-per-week']
     columns_to_encode = ['race','marital-status','relationship']
     
+    
     # 1. Scale numerical features
     data[numeric_cols] = scaler.fit_transform(data[numeric_cols])
 
     # 2. Label encode gender and income
     data['gender'] = le.fit_transform(data['gender'])
+    data['education-num'] = le.fit_transform(data['education'])
     
     # 3. One-hot encode race
     for N in columns_to_encode: