概述

>>df
      time  price_BRL     qt              time_dt
1312001297      23.49   1.00  2011-07-30 04:48:17
1312049148      23.40   1.00  2011-07-30 18:05:48
1312121523      23.49   2.00  2011-07-31 14:12:03
1312121523      23.50   6.50  2011-07-31 14:12:03
1312177622      23.40   2.00  2011-08-01 05:47:02
1312206416      23.25   1.00  2011-08-01 13:46:56
1312637929      18.95   1.50  2011-08-06 13:38:49
1312637929      18.95   4.00  2011-08-06 13:38:49
1312817114       0.80   0.01  2011-08-08 15:25:14
1312818289       0.10   0.01  2011-08-08 15:44:49
1312819795       6.00   0.09  2011-08-08 16:09:55
1312847064      16.00   0.86  2011-08-08 23:44:24
1312849282      16.00   6.14  2011-08-09 00:21:22
1312898146      19.90   1.00  2011-08-09 13:55:46
1312915666       6.00   0.01  2011-08-09 18:47:46
1312934897      19.90   1.00  2011-08-10 00:08:17
>>filter_by_last_day(df)
      time  price_BRL     qt              time_dt
1312049148      23.40   1.00  2011-07-30 18:05:48
1312121523      23.50   6.50  2011-07-31 14:12:03
1312206416      23.25   1.00  2011-08-01 13:46:56
1312637929      18.95   4.00  2011-08-06 13:38:49
1312847064      16.00   0.86  2011-08-08 23:44:24
1312915666       6.00   0.01  2011-08-09 18:47:46
1312934897      19.90   1.00  2011-08-10 00:08:17

#if necessery convert to datetime
df.time_dt = pd.to_datetime(df.time_dt)

df = df.groupby(df.time_dt.dt.date).last().reset_index(drop=True)
print (df)
         time  price_BRL    qt             time_dt
0  1312049148      23.40  1.00 2011-07-30 18:05:48
1  1312121523      23.50  6.50 2011-07-31 14:12:03
2  1312206416      23.25  1.00 2011-08-01 13:46:56
3  1312637929      18.95  4.00 2011-08-06 13:38:49
4  1312847064      16.00  0.86 2011-08-08 23:44:24
5  1312915666       6.00  0.01 2011-08-09 18:47:46
6  1312934897      19.90  1.00 2011-08-10 00:08:17

df = df.groupby(df.time_dt.dt.date,as_index=False).last()
print (df)
         time  price_BRL    qt             time_dt
0  1312049148      23.40  1.00 2011-07-30 18:05:48
1  1312121523      23.50  6.50 2011-07-31 14:12:03
2  1312206416      23.25  1.00 2011-08-01 13:46:56
3  1312637929      18.95  4.00 2011-08-06 13:38:49
4  1312847064      16.00  0.86 2011-08-08 23:44:24
5  1312915666       6.00  0.01 2011-08-09 18:47:46
6  1312934897      19.90  1.00 2011-08-10 00:08:17

df = df.resample('d',on='time_dt').last().dropna(how='all').reset_index(drop=True)
#cast column time to int
df.time = df.time.astype(int)
print (df)
         time  price_BRL    qt             time_dt
0  1312049148      23.40  1.00 2011-07-30 18:05:48
1  1312121523      23.50  6.50 2011-07-31 14:12:03
2  1312206416      23.25  1.00 2011-08-01 13:46:56
3  1312637929      18.95  4.00 2011-08-06 13:38:49
4  1312847064      16.00  0.86 2011-08-08 23:44:24
5  1312915666       6.00  0.01 2011-08-09 18:47:46
6  1312934897      19.90  1.00 2011-08-10 00:08:17

df = df.groupby(df.time_dt.dt.month).last().reset_index(drop=True)
print (df)
         time  price_BRL   qt             time_dt
0  1312121523       23.5  6.5 2011-07-31 14:12:03
1  1312934897       19.9  1.0 2011-08-10 00:08:17

hours = df.time_dt.values.astype('
  

总结

以上是编程之家为你收集整理的Pandas / Python – 按时间段分组数据全部内容，希望文章能够帮你解决Pandas / Python – 按时间段分组数据所遇到的程序开发问题。

如果您也喜欢它,动动您的小指点个赞吧