**根据提供的答案更新了代码** 实施的解决方案不是对原始数据帧进行子集化。
In [1]: thresh_eval.head()
Out[1]:
WDIR WSPD GDR GST GTIME
TX_DTTM
2010-01-01 05:50:00 235 10.9 238 13.4 540
2010-01-02 00:20:00 329 10.6 NaN NaN NaN
2010-01-02 00:30:00 329 10.8 NaN NaN NaN
2010-01-02 00:40:00 329 12.1 NaN NaN NaN
2010-01-02 00:50:00 332 12.2 330 14.8 46
In [2]: len(thresh_eval)
Out[2]: 5503
In [3]: unique(thresh_eval.index.date)
Out[3]:
array([datetime.date(2010, 1, 1), datetime.date(2010, 1, 2),
datetime.date(2010, 1, 3), datetime.date(2010, 1, 4),
datetime.date(2010, 1, 6), datetime.date(2010, 1, 8),
datetime.date(2010, 1, 9), datetime.date(2010, 1, 12),
datetime.date(2010, 1, 16), datetime.date(2010, 1, 17),
datetime.date(2010, 1, 18), datetime.date(2010, 1, 21),
datetime.date(2010, 1, 22), datetime.date(2010, 1, 23),
datetime.date(2010, 1, 24), datetime.date(2010, 1, 25),
datetime.date(2010, 1, 26), datetime.date(2010, 1, 27),
datetime.date(2010, 1, 29), datetime.date(2010, 1, 30),
datetime.date(2010, 1, 31), datetime.date(2010, 2, 1),
datetime.date(2010, 2, 2), datetime.date(2010, 2, 3),
datetime.date(2010, 2, 4), datetime.date(2010, 2, 5),
datetime.date(2010, 2, 6), datetime.date(2010, 2, 7),
datetime.date(2010, 2, 9), datetime.date(2010, 2, 10),
datetime.date(2010, 2, 11), datetime.date(2010, 2, 12),
datetime.date(2010, 2, 13), datetime.date(2010, 2, 14),
datetime.date(2010, 2, 15), datetime.date(2010, 2, 16),
datetime.date(2010, 2, 17), datetime.date(2010, 2, 18),
datetime.date(2010, 2, 22), datetime.date(2010, 2, 25),
datetime.date(2010, 2, 26), datetime.date(2010, 2, 27),
datetime.date(2010, 2, 28), datetime.date(2010, 3, 2),
datetime.date(2010, 3, 3), datetime.date(2010, 3, 12),
datetime.date(2010, 3, 13), datetime.date(2010, 3, 14),
datetime.date(2010, 3, 15), datetime.date(2010, 3, 18),
datetime.date(2010, 3, 21), datetime.date(2010, 3, 22),
datetime.date(2010, 3, 23), datetime.date(2010, 3, 26),
datetime.date(2010, 3, 27), datetime.date(2010, 3, 28),
datetime.date(2010, 3, 29), datetime.date(2010, 3, 30),
datetime.date(2010, 4, 9), datetime.date(2010, 4, 17),
datetime.date(2010, 4, 18), datetime.date(2010, 4, 25),
datetime.date(2010, 4, 26), datetime.date(2010, 4, 27),
datetime.date(2010, 4, 28), datetime.date(2010, 5, 3),
datetime.date(2010, 5, 8), datetime.date(2010, 5, 9),
datetime.date(2010, 5, 17), datetime.date(2010, 5, 24),
datetime.date(2010, 5, 25), datetime.date(2010, 5, 26),
datetime.date(2010, 6, 2), datetime.date(2010, 6, 3),
datetime.date(2010, 6, 6), datetime.date(2010, 6, 7),
datetime.date(2010, 6, 16), datetime.date(2010, 6, 28),
datetime.date(2010, 7, 2), datetime.date(2010, 7, 3),
datetime.date(2010, 7, 10), datetime.date(2010, 7, 16),
datetime.date(2010, 7, 22), datetime.date(2010, 7, 26),
datetime.date(2010, 7, 28), datetime.date(2010, 7, 30),
datetime.date(2010, 8, 1), datetime.date(2010, 8, 7),
datetime.date(2010, 8, 23), datetime.date(2010, 8, 24),
datetime.date(2010, 9, 2), datetime.date(2010, 9, 12),
datetime.date(2010, 9, 27), datetime.date(2010, 9, 29),
datetime.date(2010, 9, 30), datetime.date(2010, 10, 2),
datetime.date(2010, 10, 3), datetime.date(2010, 10, 15),
datetime.date(2010, 10, 16), datetime.date(2010, 10, 25),
datetime.date(2010, 10, 26), datetime.date(2010, 10, 27),
datetime.date(2010, 10, 29), datetime.date(2010, 11, 2),
datetime.date(2010, 11, 3), datetime.date(2010, 11, 4),
datetime.date(2010, 11, 5), datetime.date(2010, 11, 6),
datetime.date(2010, 11, 7), datetime.date(2010, 11, 9),
datetime.date(2010, 11, 12), datetime.date(2010, 11, 16),
datetime.date(2010, 11, 17), datetime.date(2010, 11, 26),
datetime.date(2010, 11, 27), datetime.date(2010, 11, 28),
datetime.date(2010, 11, 29), datetime.date(2010, 11, 30),
datetime.date(2010, 12, 1), datetime.date(2010, 12, 2),
datetime.date(2010, 12, 4), datetime.date(2010, 12, 5),
datetime.date(2010, 12, 6), datetime.date(2010, 12, 7),
datetime.date(2010, 12, 11), datetime.date(2010, 12, 12),
datetime.date(2010, 12, 13), datetime.date(2010, 12, 14),
datetime.date(2010, 12, 16), datetime.date(2010, 12, 17),
datetime.date(2010, 12, 18), datetime.date(2010, 12, 19),
datetime.date(2010, 12, 20), datetime.date(2010, 12, 22),
datetime.date(2010, 12, 23), datetime.date(2010, 12, 24),
datetime.date(2010, 12, 26), datetime.date(2010, 12, 27),
datetime.date(2010, 12, 28)], dtype=object)
In [4]: ais.head()
Out[4]:
MMSI LAT LON COURSE_OVER_GROUND NAV_STATUS POS_ACCURACY RATE_OF_TURN SPEED_OVER_GROUND HEADING
TX_DTTM
2010-01-01 00:00:19 12345678 32.834746 -79.929589 1820 0 0 128 71 NaN
2010-01-01 00:00:29 12345678 32.834384 -79.929602 1832 0 0 128 71 NaN
2010-01-01 00:00:40 12345678 32.834058 -79.929619 1836 0 0 128 70 NaN
2010-01-01 00:00:50 12345678 32.833703 -79.929647 1847 0 0 128 70 NaN
2010-01-01 00:01:00 12345678 32.833386 -79.929689 1897 0 0 128 69 NaN
In [5]: unique(ais.index.date)
Out[5]:
array([datetime.date(2010, 1, 1), datetime.date(2010, 1, 4),
datetime.date(2010, 1, 5), datetime.date(2010, 1, 6),
datetime.date(2010, 1, 7), datetime.date(2010, 1, 8),
datetime.date(2010, 1, 9), datetime.date(2010, 1, 10),
datetime.date(2010, 1, 11), datetime.date(2010, 1, 12),
datetime.date(2010, 1, 13), datetime.date(2010, 1, 14),
datetime.date(2010, 1, 15), datetime.date(2010, 1, 16),
datetime.date(2010, 1, 17), datetime.date(2010, 1, 18),
datetime.date(2010, 1, 19), datetime.date(2010, 1, 20),
datetime.date(2010, 1, 21), datetime.date(2010, 1, 22),
datetime.date(2010, 1, 23), datetime.date(2010, 1, 24),
datetime.date(2010, 1, 25), datetime.date(2010, 1, 26),
datetime.date(2010, 1, 27), datetime.date(2010, 1, 28),
datetime.date(2010, 1, 29), datetime.date(2010, 1, 30),
datetime.date(2010, 1, 31), datetime.date(2010, 2, 1)], dtype=object)
In [6]: len(ais)
Out[6]: 2750499
In [7]: ais[Index(ais.index.date).isin(Index(thresh_eval.index.date))]
Out[7]:
MMSI LAT LON COURSE_OVER_GROUND NAV_STATUS POS_ACCURACY RATE_OF_TURN SPEED_OVER_GROUND HEADING
TX_DTTM
2010-01-01 00:00:19 12345678 32.834746 -79.929589 1820 0 0 128 71 NaN
2010-01-01 00:00:29 12345678 32.834384 -79.929602 1832 0 0 128 71 NaN
2010-01-01 00:00:40 12345678 32.834058 -79.929619 1836 0 0 128 70 NaN
2010-01-01 00:00:50 12345678 32.833703 -79.929647 1847 0 0 128 70 NaN
2010-01-01 00:01:00 12345678 32.833386 -79.929689 1897 0 0 128 69 NaN
2010-01-01 00:01:06 12345678 32.833106 -79.929757 1934 0 0 128 69 NaN
2010-01-01 00:01:16 12345678 32.832830 -79.929850 1978 0 0 128 69 NaN
2010-01-01 00:01:26 12345678 32.832495 -79.929990 2010 0 0 128 69 NaN
In [8]: len(ais)
Out[8]: 2750499
In [9]: unique(ais.index.date)
Out[9]:
array([datetime.date(2010, 1, 1), datetime.date(2010, 1, 4),
datetime.date(2010, 1, 5), datetime.date(2010, 1, 6),
datetime.date(2010, 1, 7), datetime.date(2010, 1, 8),
datetime.date(2010, 1, 9), datetime.date(2010, 1, 10),
datetime.date(2010, 1, 11), datetime.date(2010, 1, 12),
datetime.date(2010, 1, 13), datetime.date(2010, 1, 14),
datetime.date(2010, 1, 15), datetime.date(2010, 1, 16),
datetime.date(2010, 1, 17), datetime.date(2010, 1, 18),
datetime.date(2010, 1, 19), datetime.date(2010, 1, 20),
datetime.date(2010, 1, 21), datetime.date(2010, 1, 22),
datetime.date(2010, 1, 23), datetime.date(2010, 1, 24),
datetime.date(2010, 1, 25), datetime.date(2010, 1, 26),
datetime.date(2010, 1, 27), datetime.date(2010, 1, 28),
datetime.date(2010, 1, 29), datetime.date(2010, 1, 30),
datetime.date(2010, 1, 31), datetime.date(2010, 2, 1)], dtype=object)
**原始问题：** 我正在尝试基于其日期时间索引与另一个数据帧的日期时间索引之间的比较来对数据帧进行子集化。 df1是用作过滤器的下采样时间序列的数据帧。 df2是要过滤的记录的数据帧，具有更高的时间分辨率，并且每个日期的多个记录出现在df1中：
In [1]: df1
Out[1]:
WSPD cd
date
2010-07-10 11.325645 0.000019
2010-08-23 12.258462 0.000019
2010-11-09 10.771429 0.000019
2010-11-12 10.650000 0.000019
2010-11-16 11.939535 0.000019
...
In [2]: df2
Out[2]:
ID Latitude Longitude Course RateOfTurn
TimeStamp
2010-06-26 22:36:11 311425000 32.832500 -79.929000 3 0
2010-06-26 22:36:21 311425000 32.832845 -79.929037 3 0
2010-06-26 22:36:32 311425000 32.833333 -79.929000 3 0
2010-06-26 22:36:42 311425000 32.833666 -79.929000 3 0
2010-07-10 07:37:21 548723000 32.832333 -79.929000 1.0 0
2010-07-10 07:37:31 548723000 32.832666 -79.929000 1.0 0
2010-07-10 07:37:40 548723000 32.833000 -79.929000 2.0 0
2010-07-10 07:37:51 548723000 32.833333 -79.929000 1.0 0
2010-07-10 07:38:04 548723000 32.833666 -79.929000 0.0 0
2010-08-23 09:29:48 311425000 32.832590 -79.928985 0.0 0
2010-08-23 09:30:00 311425000 32.833053 -79.928970 1.0 0
2010-08-23 09:30:10 311425000 32.833443 -79.928957 1.0 0
2010-08-23 09:30:18 311425000 32.833746 -79.928944 2.0 0
...
In [3]: list = []
for i,item in enumerate(df2.index.date):
if item in df1.index.date:
list.append(item)
In [4]: list
out[4]: [datetime.date(2010, 8, 23),
datetime.date(2010, 8, 23),
datetime.date(2010, 8, 23),
datetime.date(2010, 8, 23),
datetime.date(2010, 7, 10),
datetime.date(2010, 7, 10),
datetime.date(2010, 7, 10),
datetime.date(2010, 7, 10),
datetime.date(2010, 7, 10)]
我正在丢失索引之外的内容。我真的很喜欢来自df2的记录子集，包括所有数据，其日期时间与日间频率的df1相匹配，如：
2010-07-10 07:37:21 548723000 32.832333 -79.929000 1.0 0
2010-07-10 07:37:31 548723000 32.832666 -79.929000 1.0 0
2010-07-10 07:37:40 548723000 32.833000 -79.929000 2.0 0
2010-07-10 07:37:51 548723000 32.833333 -79.929000 1.0 0
2010-07-10 07:38:04 548723000 32.833666 -79.929000 0.0 0
2010-08-23 09:29:48 311425000 32.832590 -79.928985 0.0 0
2010-08-23 09:30:00 311425000 32.833053 -79.928970 1.0 0
2010-08-23 09:30:10 311425000 32.833443 -79.928957 1.0 0
2010-08-23 09:30:18 311425000 32.833746 -79.928944 2.0 0
任何帮助将不胜感激！
答案 0 :(得分：2)
使用isin方法：
In [33]: import datetime
In [34]: import pandas as pd
In [35]: from pandas import DataFrame, Index
In [36]: from numpy.random import randn, unique, array
In [37]: df1 = DataFrame({'lat': randn(48), 'long': randn(48)}, index=pd.date_range('2013-01-02',periods=4
8,freq='H'))
In [38]: df2 = DataFrame({'lat': randn(72), 'long': randn(72)}, index=pd.date_range('2013-01-02',periods=7
2,freq='H'))
In [39]: df1.head()
Out[39]:
lat long
2013-01-02 00:00:00 0.7310 0.3083
2013-01-02 01:00:00 1.8540 0.7355
2013-01-02 02:00:00 0.3097 -0.1834
2013-01-02 03:00:00 0.8455 0.8350
2013-01-02 04:00:00 0.4017 0.0559
[5 rows x 2 columns]
In [40]: df2.head()
Out[40]:
lat long
2013-01-02 00:00:00 1.4248 0.2289
2013-01-02 01:00:00 -0.5055 0.1072
2013-01-02 02:00:00 -1.8265 -1.0651
2013-01-02 03:00:00 0.5888 0.3992
2013-01-02 04:00:00 -1.5210 0.0710
[5 rows x 2 columns]
In [41]: df2[Index(df2.index.date).isin(Index(df1.index.date))]
Out[41]:
lat long
2013-01-02 00:00:00 1.4248 0.2289
2013-01-02 01:00:00 -0.5055 0.1072
2013-01-02 02:00:00 -1.8265 -1.0651
2013-01-02 03:00:00 0.5888 0.3992
2013-01-02 04:00:00 -1.5210 0.0710
2013-01-02 05:00:00 0.8382 -1.5569
2013-01-02 06:00:00 -0.7878 0.9253
2013-01-02 07:00:00 -0.1686 -1.0128
2013-01-02 08:00:00 -0.2481 -0.4247
2013-01-02 09:00:00 0.0794 -0.1947
2013-01-02 10:00:00 -0.5046 -0.1535
2013-01-02 11:00:00 0.0696 -1.5125
2013-01-02 12:00:00 1.1984 -0.1880
2013-01-02 13:00:00 0.8251 -0.2588
2013-01-02 14:00:00 1.5858 -1.2998
2013-01-02 15:00:00 0.2727 -0.3030
2013-01-02 16:00:00 0.9459 -0.8018
2013-01-02 17:00:00 -1.5055 -1.1344
2013-01-02 18:00:00 0.3970 0.7449
2013-01-02 19:00:00 -1.0256 0.2245
2013-01-02 20:00:00 0.8322 0.6473
2013-01-02 21:00:00 0.2759 1.4096
2013-01-02 22:00:00 -0.5167 1.5676
2013-01-02 23:00:00 0.4620 0.4936
2013-01-03 00:00:00 1.4400 0.5696
... ...
[48 rows x 2 columns]
您可以通过比较
来检查结果是否仅包含它们在日间频率上重叠的日期索引In [42]: unique(df2[Index(df2.index.date).isin(Index(df1.index.date))].index.date)
Out[42]: array([datetime.date(2013, 1, 2), datetime.date(2013, 1, 3)], dtype=object)
In [43]: unique(df1.index.date)
Out[43]: array([datetime.date(2013, 1, 2), datetime.date(2013, 1, 3)], dtype=object)