features_generator.py 文件源码

 复制代码def load_base_user_feat(end_date='2016-04-16'):
    '''
    ????????
    '''
    dump_path = './cache/base_user_feat_{0}.pkl'.format(end_date[:10])
    if os.path.exists(dump_path):
        with open(dump_path, 'rb') as f:
            df = pickle.load(f)
    else:
        df = pd.read_csv(USER_FILE, encoding='gbk')
        # sex_dummies = pd.get_dummies(df.sex, prefix='sex')
        df.user_reg_tm.fillna('2016-02-01', inplace=True)
        df.user_reg_tm = pd.to_datetime(df.user_reg_tm).apply(lambda t: pd.to_datetime('2016-02-01') if t > pd.to_datetime('2016-04-15') else t)
        df['reg_tm_dist'] = df.user_reg_tm.apply(lambda t: (pd.to_datetime(end_date) - t).days)
        df = df[['user_id', 'user_lv_cd', 'reg_tm_dist']]
        # df = pd.concat([df, sex_dummies], axis=1)
        # age_dummies = pd.get_dummies(df.age, prefix='age')
        # N = age_dummies.shape[1]
        # age_dummies.columns = ['age_{0}'.format(i) for i in range(N)]
        # df = pd.concat([df, age_dummies], axis=1)
        with open(dump_path, 'wb') as f:
            pickle.dump(df, f)
    return df