Update app.py

app.py

@@ -11,7 +11,7 @@ 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 = [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])
     fixed_features = cleaning_features(features)
     # prediction = model.predict(features)
     # prediction = 1
@@ -24,8 +24,6 @@ def cleaning_features(data):
     encoder = OneHotEncoder(sparse_output=False)
     numeric_cols = ['age', 'educational-num', 'hours-per-week']
     columns_to_encode = ['race','marital-status','relationship']
-
-    data.replace({'?': np.nan, 99999: np.nan}, inplace=True)
     
     # 1. Scale numerical features
     data[numeric_cols] = scaler.fit_transform(data[numeric_cols])