features_generator.py 文件源码

def load_user_act_cnt_with_timeZone(start_date = '2016-02-01 00:00:00', end_date = '2016-04-16 00:00:00'):
    '''
    ????????????
    '''
    dump_path = './cache/user_act_cnt_with_timeZone_{0}_{1}.pkl'.format(start_date[:10], end_date[:10])
    if os.path.exists(dump_path):
        with open(dump_path, 'rb') as f:
            df = pickle.load(f)
    else:
        df = get_action_data(start_date = start_date, end_date = end_date, field=['user_id', 'time_zone'])
        timeZone_dummies = pd.get_dummies(df.time_zone, prefix='time_zone_cnt')
        df = pd.concat([df, timeZone_dummies], axis=1)
        df.drop(['time_zone'], axis=1, inplace=True)
        df = df.groupby(['user_id'], as_index=False).sum()

        with open(dump_path, 'wb') as f:
            pickle.dump(df, f)

    return df