pandas-时序性数据创建和表示

第四课 Pandas时序型数据分析
第一节 时序型数据的创建和表示
import pandas as pd
通过日期型数据列表创建
from datetime import datetime

date_list1 = [datetime(2019, 1, 1), datetime(2019, 1, 2), datetime(2019, 1, 3)]
pd.Series(date_list1)
0   2019-01-01
1   2019-01-02
2   2019-01-03
dtype: datetime64[ns]

date_list2 = [pd.Timestamp('20190101'), pd.Timestamp('20190102'), pd.Timestamp('20190103')]
pd.Series(date_list2)
0   2019-01-01
1   2019-01-02
2   2019-01-03
dtype: datetime64[ns]

date_list3 = [pd.Timestamp('2019/01/01'), pd.Timestamp('2019/01/02'), pd.Timestamp('2019/01/03')]
pd.Series(date_list3)
0   2019-01-01
1   2019-01-02
2   2019-01-03
dtype: datetime64[ns]

date_range
pd.Series(pd.date_range(start='2019-01-01', end='2019-02-01'))
0    2019-01-01
1    2019-01-02
2    2019-01-03
3    2019-01-04
4    2019-01-05
5    2019-01-06
6    2019-01-07
7    2019-01-08
8    2019-01-09
9    2019-01-10
10   2019-01-11
11   2019-01-12
12   2019-01-13
13   2019-01-14
14   2019-01-15
15   2019-01-16
16   2019-01-17
17   2019-01-18
18   2019-01-19
19   2019-01-20
20   2019-01-21
21   2019-01-22
22   2019-01-23
23   2019-01-24
24   2019-01-25
25   2019-01-26
26   2019-01-27
27   2019-01-28
28   2019-01-29
29   2019-01-30
30   2019-01-31
31   2019-02-01
dtype: datetime64[ns]

pd.Series(pd.date_range(start='2019/01/01', periods=10))
0   2019-01-01
1   2019-01-02
2   2019-01-03
3   2019-01-04
4   2019-01-05
5   2019-01-06
6   2019-01-07
7   2019-01-08
8   2019-01-09
9   2019-01-10
dtype: datetime64[ns]

pd.Series(pd.date_range(start='20190101', periods=6, freq='M'))
0   2019-01-31
1   2019-02-28
2   2019-03-31
3   2019-04-30
4   2019-05-31
5   2019-06-30
dtype: datetime64[ns]

to_datetime()
# 转换日期字符串
date_val_list = ['2019-01-01', '20190102', None]
pd.Series(pd.to_datetime(date_val_list))
0   2019-01-01
1   2019-01-02
2          NaT
dtype: datetime64[ns]
# 合并转换日期
df = pd.read_csv('./datasets/BeijingPM20100101_20151231.csv')
df.head()
No	year	month	day	hour	season	PM_Dongsi	PM_Dongsihuan	PM_Nongzhanguan	PM_US Post	DEWP	HUMI	PRES	TEMP	cbwd	Iws	precipitation	Iprec
0	1	2010	1	1	0	4	NaN	NaN	NaN	NaN	-21.0	43.0	1021.0	-11.0	NW	1.79	0.0	0.0
1	2	2010	1	1	1	4	NaN	NaN	NaN	NaN	-21.0	47.0	1020.0	-12.0	NW	4.92	0.0	0.0
2	3	2010	1	1	2	4	NaN	NaN	NaN	NaN	-21.0	43.0	1019.0	-11.0	NW	6.71	0.0	0.0
3	4	2010	1	1	3	4	NaN	NaN	NaN	NaN	-21.0	55.0	1019.0	-14.0	NW	9.84	0.0	0.0
4	5	2010	1	1	4	4	NaN	NaN	NaN	NaN	-20.0	51.0	1018.0	-12.0	NW	12.97	0.0	0.0

pd.to_datetime(df[['year', 'month', 'day']])
0       2010-01-01
1       2010-01-01
2       2010-01-01
3       2010-01-01
4       2010-01-01
5       2010-01-01
6       2010-01-01
7       2010-01-01
8       2010-01-01
9       2010-01-01
10      2010-01-01
11      2010-01-01
12      2010-01-01
13      2010-01-01
14      2010-01-01
15      2010-01-01

           ...    

52567   2015-12-31
52568   2015-12-31
52569   2015-12-31
52570   2015-12-31
52571   2015-12-31
52572   2015-12-31
52573   2015-12-31
52574   2015-12-31
52575   2015-12-31
52576   2015-12-31
52577   2015-12-31
52578   2015-12-31
52579   2015-12-31
52580   2015-12-31
52581   2015-12-31
52582   2015-12-31
52583   2015-12-31
dtype: datetime64[ns]