def load_dataset(split="trn_set", limit=None, ignore_categorical=False):
    sql = """
    SELECT o.*, f1.*, f2.*, f3.*, f4.*,
    EXTRACT(MONTH FROM o.dt) AS month
    FROM %s AS t
    JOIN Online AS o
        ON t.index = o.index
    JOIN features_group_1 AS f1
        ON t.index = f1.index
    JOIN features_group_2 AS f2
        ON t.index = f2.index
    JOIN features_group_3 AS f3
        ON t.index = f3.index
    JOIN features_group_4 AS f4
        ON t.index = f4.index
    """%split
    if limit:
        sql += " LIMIT %i"%limit

    df = pd.read_sql_query(sql.replace('\n', " ").replace("\t", " "), engine)
    df.event1 = df.event1.fillna(0)
    X = df.drop(["index", "event2", "dt", "day", "session", "visitor", "custno"], axis=1)
    Y = df.event2
    return X, Y