simple_preprocessing_titanic.py

def simple_preprocessing(dataframe, train=True):
    le = LabelEncoder()
    X = dataframe.drop(['PassengerId', 'Cabin', 'Name', 'Ticket'], axis=1)
    X['Age'] = X['Age'].fillna(value=X['Age'].mode()[0])
    X['Embarked'] = le.fit_transform(X['Embarked'].fillna(value=X['Embarked'].mode()[0]))
    X['Sex'] = np.where(X['Sex'] == 'male', 1, 0)
    
    if train:
        X = X.drop(['Survived'], axis=1)
        y = np.where(dataframe['Survived'] == 1, 'Alive', 'Dead')
        y = pd.get_dummies(y, columns=['Survived'])
        return X, y
    else:
        return X