Pandas-时间序列（二）-索引及切片：TimeSeries是Series的一个子类，所以Series索引及数据选取方面的方法基本一样【TimeSeries通过时间序列有更便捷的方法做索引和切片】

古城微笑少年丶 2023-09-29 09:37 27阅读 0赞

## 一、索引 ##

时间序列标签索引，支持各种时间字符串，以及datetime.datetime

*  时间序列由于按照时间先后排序，故不用考虑顺序问题
 *  索引方法同样适用于Dataframe

import numpy as np
    import pandas as pd
    from datetime import datetime
    
    # 索引
    
    rng = pd.date_range('2017/1', '2017/3')
    ts = pd.Series(np.random.rand(len(rng)), index=rng)
    print("ts = \n", ts)
    print("-" * 50)
    print("ts.head() = \n", ts.head())
    print("-" * 200)
    
    # 基本下标位置索引
    print("下标位置索引: ts[0] = ", ts[0])
    print("下标位置索引: ts[:2] = \n", ts[:2])
    print("-" * 200)
    
    # 时间序列标签索引，支持各种时间字符串，以及datetime.datetime
    # 时间序列由于按照时间先后排序，故不用考虑顺序问题
    # 索引方法同样适用于Dataframe
    print("ts['2017/1/2'] = ", ts['2017/1/2'])
    print("ts['20170103'] = ", ts['20170103'])
    print("ts['1/10/2017'] = ", ts['1/10/2017'])
    print("ts[datetime(2017, 1, 20)] = ", ts[datetime(2017, 1, 20)])
    print("-" * 200)

打印结果：

ts = 
    2017-01-01    0.551172
    2017-01-02    0.676984
    2017-01-03    0.449515
    2017-01-04    0.029888
    2017-01-05    0.760317
    2017-01-06    0.237550
    2017-01-07    0.447621
    2017-01-08    0.765687
    2017-01-09    0.594706
    2017-01-10    0.127133
    2017-01-11    0.585002
    2017-01-12    0.715092
    2017-01-13    0.452857
    2017-01-14    0.002166
    2017-01-15    0.919406
    2017-01-16    0.661433
    2017-01-17    0.816985
    2017-01-18    0.054109
    2017-01-19    0.941522
    2017-01-20    0.577710
    2017-01-21    0.896383
    2017-01-22    0.062862
    2017-01-23    0.765347
    2017-01-24    0.592148
    2017-01-25    0.278556
    2017-01-26    0.090711
    2017-01-27    0.772405
    2017-01-28    0.685413
    2017-01-29    0.564777
    2017-01-30    0.249494
    2017-01-31    0.353693
    2017-02-01    0.641812
    2017-02-02    0.744452
    2017-02-03    0.802991
    2017-02-04    0.286702
    2017-02-05    0.505531
    2017-02-06    0.147288
    2017-02-07    0.412554
    2017-02-08    0.690443
    2017-02-09    0.219935
    2017-02-10    0.631287
    2017-02-11    0.283691
    2017-02-12    0.637356
    2017-02-13    0.414368
    2017-02-14    0.670913
    2017-02-15    0.982919
    2017-02-16    0.787294
    2017-02-17    0.783862
    2017-02-18    0.110436
    2017-02-19    0.631306
    2017-02-20    0.857404
    2017-02-21    0.697764
    2017-02-22    0.990373
    2017-02-23    0.876479
    2017-02-24    0.617759
    2017-02-25    0.370738
    2017-02-26    0.523457
    2017-02-27    0.074906
    2017-02-28    0.875270
    2017-03-01    0.455254
    Freq: D, dtype: float64
    --------------------------------------------------
    ts.head() = 
     2017-01-01    0.551172
    2017-01-02    0.676984
    2017-01-03    0.449515
    2017-01-04    0.029888
    2017-01-05    0.760317
    Freq: D, dtype: float64
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    下标位置索引: ts[0] =  0.5511722618400913
    下标位置索引: ts[:2] = 
    2017-01-01    0.551172
    2017-01-02    0.676984
    Freq: D, dtype: float64
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    ts['2017/1/2'] =  0.6769837637858711
    ts['20170103'] =  0.4495150651749722
    ts['1/10/2017'] =  0.12713279349021678
    ts[datetime(2017, 1, 20)] =  0.5777095683188953
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    
    Process finished with exit code 0

## 二、切片 ##

和Series按照index索引原理一样，也是末端包含。

import numpy as np
    import pandas as pd
    
    # 切片
    
    rng = pd.date_range('2017/1', '2017/3', freq='12H')
    ts = pd.Series(np.random.rand(len(rng)), index=rng)
    print("ts = \n", ts)
    print('-' * 200)
    
    # 和Series按照index索引原理一样，也是末端包含
    data1 = ts['2017/1/5':'2017/1/10']
    print("data1 = ts['2017/1/5':'2017/1/10'] = \n", data1)
    print('-' * 200)
    
    # 传入月，直接得到一个切片
    data2 = ts['2017/2']
    data3 = data2.head()
    print("data2 = ts['2017/2'] = \n", data2)
    print('-' * 50)
    print("data3 = ts['2017/2'].head() = \n", data3)
    print('-' * 200)

打印结果：

ts = 
    2017-01-01 00:00:00    0.494033
    2017-01-01 12:00:00    0.820702
    2017-01-02 00:00:00    0.616621
    2017-01-02 12:00:00    0.011143
    2017-01-03 00:00:00    0.940433
                             ...   
    2017-02-27 00:00:00    0.978302
    2017-02-27 12:00:00    0.414231
    2017-02-28 00:00:00    0.218717
    2017-02-28 12:00:00    0.580957
    2017-03-01 00:00:00    0.090996
    Freq: 12H, Length: 119, dtype: float64
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    data1 = ts['2017/1/5':'2017/1/10'] = 
    2017-01-05 00:00:00    0.652041
    2017-01-05 12:00:00    0.773052
    2017-01-06 00:00:00    0.463288
    2017-01-06 12:00:00    0.335351
    2017-01-07 00:00:00    0.099362
    2017-01-07 12:00:00    0.883344
    2017-01-08 00:00:00    0.426475
    2017-01-08 12:00:00    0.580315
    2017-01-09 00:00:00    0.863783
    2017-01-09 12:00:00    0.494119
    2017-01-10 00:00:00    0.577613
    2017-01-10 12:00:00    0.168280
    Freq: 12H, dtype: float64
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    data2 = ts['2017/2'] = 
    2017-02-01 00:00:00    0.906511
    2017-02-01 12:00:00    0.208719
    2017-02-02 00:00:00    0.831267
    2017-02-02 12:00:00    0.496934
    2017-02-03 00:00:00    0.882586
    2017-02-03 12:00:00    0.269308
    2017-02-04 00:00:00    0.767492
    2017-02-04 12:00:00    0.928533
    2017-02-05 00:00:00    0.404165
    2017-02-05 12:00:00    0.573177
    2017-02-06 00:00:00    0.298927
    2017-02-06 12:00:00    0.987986
    2017-02-07 00:00:00    0.097949
    2017-02-07 12:00:00    0.971335
    2017-02-08 00:00:00    0.194750
    2017-02-08 12:00:00    0.224471
    2017-02-09 00:00:00    0.628354
    2017-02-09 12:00:00    0.487055
    2017-02-10 00:00:00    0.166684
    2017-02-10 12:00:00    0.644644
    2017-02-11 00:00:00    0.479011
    2017-02-11 12:00:00    0.035003
    2017-02-12 00:00:00    0.694782
    2017-02-12 12:00:00    0.784163
    2017-02-13 00:00:00    0.740384
    2017-02-13 12:00:00    0.983730
    2017-02-14 00:00:00    0.010376
    2017-02-14 12:00:00    0.026971
    2017-02-15 00:00:00    0.012298
    2017-02-15 12:00:00    0.679321
    2017-02-16 00:00:00    0.594517
    2017-02-16 12:00:00    0.260168
    2017-02-17 00:00:00    0.405923
    2017-02-17 12:00:00    0.856798
    2017-02-18 00:00:00    0.615552
    2017-02-18 12:00:00    0.261799
    2017-02-19 00:00:00    0.786273
    2017-02-19 12:00:00    0.316262
    2017-02-20 00:00:00    0.457370
    2017-02-20 12:00:00    0.975753
    2017-02-21 00:00:00    0.232189
    2017-02-21 12:00:00    0.373186
    2017-02-22 00:00:00    0.506089
    2017-02-22 12:00:00    0.849335
    2017-02-23 00:00:00    0.623559
    2017-02-23 12:00:00    0.215287
    2017-02-24 00:00:00    0.985915
    2017-02-24 12:00:00    0.998497
    2017-02-25 00:00:00    0.294932
    2017-02-25 12:00:00    0.993772
    2017-02-26 00:00:00    0.852245
    2017-02-26 12:00:00    0.957576
    2017-02-27 00:00:00    0.978302
    2017-02-27 12:00:00    0.414231
    2017-02-28 00:00:00    0.218717
    2017-02-28 12:00:00    0.580957
    Freq: 12H, dtype: float64
    --------------------------------------------------
    data3 = ts['2017/2'].head() = 
    2017-02-01 00:00:00    0.906511
    2017-02-01 12:00:00    0.208719
    2017-02-02 00:00:00    0.831267
    2017-02-02 12:00:00    0.496934
    2017-02-03 00:00:00    0.882586
    Freq: 12H, dtype: float64
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    
    Process finished with exit code 0

## 三、重复索引的时间序列 ##

import numpy as np
    import pandas as pd
    
    # index有重复，is_unique检查 → values唯一，index不唯一
    dates = pd.DatetimeIndex(['1/1/2015', '1/2/2015', '1/3/2015', '1/4/2015', '1/1/2015', '1/2/2015'])
    ts = pd.Series(np.random.rand(6), index=dates)
    print("ts = \n", ts)
    print('-' * 50)
    print("ts.is_unique = {0}, ts.index.is_unique = {1}".format(ts.is_unique, ts.index.is_unique))
    print('-' * 200)
    
    # index有重复的将返回多个值
    data1 = ts['20150101']
    print("data1 = \n{0} \ntype(data1) = {1}".format(data1, type(data1)))
    print('-' * 50)
    data2 = ts['20150104']
    print("data2 = \n{0} \ntype(data2) = {1}".format(data2, type(data2)))
    print('-' * 200)
    
    # 通过groupby做分组，重复的值这里用平均值处理
    data3 = ts.groupby(level=0).mean()
    print("data3 = \n{0} \ntype(data3) = {1}".format(data3, type(data3)))
    print('-' * 200)

打印结果：

ts = 
    2015-01-01    0.488589
    2015-01-02    0.621012
    2015-01-03    0.657300
    2015-01-04    0.164756
    2015-01-01    0.078192
    2015-01-02    0.899275
    dtype: float64
    --------------------------------------------------
    ts.is_unique = True, ts.index.is_unique = False
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    data1 = 
    2015-01-01    0.488589
    2015-01-01    0.078192
    dtype: float64 
    type(data1) = <class 'pandas.core.series.Series'>
    --------------------------------------------------
    data2 = 
    2015-01-04    0.164756
    dtype: float64 
    type(data2) = <class 'pandas.core.series.Series'>
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    data3 = 
    2015-01-01    0.283390
    2015-01-02    0.760143
    2015-01-03    0.657300
    2015-01-04    0.164756
    dtype: float64 
    type(data3) = <class 'pandas.core.series.Series'>
    --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    
    Process finished with exit code 0