project.py

from sklearn import preprocessing
def encode_features(df_train, df_test):
    features = ['Fare', 'Cabin', 'Age', 'Sex', 'Lname', 'NamePrefix']
    df_combined = pd.concat([df_train[features], df_test[features]])
    
    for feature in features:
        le = preprocessing.LabelEncoder()
        le = le.fit(df_combined[feature])
        df_train[feature] = le.transform(df_train[feature])
        df_test[feature] = le.transform(df_test[feature])
    return df_train, df_test
    
data_train, data_test = encode_features(data_train, data_test)