Update app.py

app.py

@@ -25,14 +25,39 @@ def predict(age, workclass, education, marital_status, occupation, relationship,
     return print(fixed_features)
 
 def cleaning_features(data):
-    le = LabelEncoder()
-    scaler = StandardScaler()
-    encoder = OneHotEncoder(sparse=False)
+    with open('race_onehot_encoder.pkl', 'rb') as enc_file:
+        encoder = pickle.load(enc_file)
+    
+    with open('label_encoder.pkl', 'rb') as le_file:
+        le = pickle.load(le_file)
+
+    with open('scaler.pkl', 'rb') as scaler_file:
+        scaler = pickle.load(scaler_file)
+        
+    education_num_mapping = {
+        "Preschool": 1,
+        "1st-4th": 2,
+        "5th-6th": 3,
+        "7th-8th": 4,
+        "9th": 5,
+        "10th": 6,
+        "11th": 7,
+        "12th": 8,
+        "HS-grad": 9,
+        "Some-college": 10,
+        "Assoc-voc": 11,
+        "Assoc-acdm": 12,
+        "Bachelors": 13,
+        "Masters": 14,
+        "Doctorate": 15,
+        "Prof-school": 16
+    }
+    
     numeric_cols = ['age', 'educational-num', 'hours-per-week']
     columns_to_encode = ['race','marital-status','relationship']
     
     data['gender'] = le.fit_transform(data['gender'])
-    data['educational-num'] = le.fit_transform(data['educational-num'])
+    data['educational-num'] = data['educational-num'].map(education_num_mapping)
     data['workclass'] = le.fit_transform(data['workclass'])
     data['occupation'] = le.fit_transform(data['occupation'])