Python数据分析与机器学习44-Python生成时间序列

文章目录

一. Python 生成时间序列
二.生成不同间隔的时间序列
三. 截断时间段
四. 时间戳及时间计算
五. 数据重采样
六. 移动窗口函数
参考：

一. Python 生成时间序列

时间序列

时间戳（timestamp）
固定周期（period）
时间间隔（interval）

date_range

可以指定开始时间与周期
H：小时
D：天
M：月

二.生成不同间隔的时间序列

代码:

import pandas as pd
import numpy as np
import datetime as dt

# 从2022-07-01开始，间隔3天，生成10条 时间数据
rng = pd.date_range('2022-07-01', periods = 10, freq = '3D')
print(rng)
print("#####################")

# 指定开始时间，结束时间  以及频率
data=pd.date_range('2022-01-01','2023-01-01',freq='M')
print(data)
print("#####################")

# 从2022-01-01开始，间隔1天，生成20条 时间数据
time=pd.Series(np.random.randn(20),
           index=pd.date_range(dt.datetime(2022,1,1),periods=20))
print(time)
print("#####################")

# 不规则的时间间隔
p1 = pd.period_range('2022-01-01 10:10', freq = '25H', periods = 10)
print(p1)
print("######################################")

# 指定索引
rng = pd.date_range('2022 Jul 1', periods = 10, freq = 'D')
print(pd.Series(range(len(rng)), index = rng))
print("######################################")
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29

测试记录:

DatetimeIndex(['2022-07-01', '2022-07-04', '2022-07-07', '2022-07-10',
               '2022-07-13', '2022-07-16', '2022-07-19', '2022-07-22',
               '2022-07-25', '2022-07-28'],
              dtype='datetime64[ns]', freq='3D')
#####################
DatetimeIndex(['2022-01-31', '2022-02-28', '2022-03-31', '2022-04-30',
               '2022-05-31', '2022-06-30', '2022-07-31', '2022-08-31',
               '2022-09-30', '2022-10-31', '2022-11-30', '2022-12-31'],
              dtype='datetime64[ns]', freq='M')
#####################
2022-01-01   -0.957412
2022-01-02   -0.333720
2022-01-03    1.079960
2022-01-04    0.050675
2022-01-05    0.270313
2022-01-06   -0.222715
2022-01-07   -0.560258
2022-01-08    1.009430
2022-01-09   -0.678157
2022-01-10    0.213557
2022-01-11   -0.720791
2022-01-12    0.332096
2022-01-13   -0.986449
2022-01-14   -0.357303
2022-01-15   -0.559618
2022-01-16    0.480281
2022-01-17   -0.443998
2022-01-18    1.541631
2022-01-19   -0.094559
2022-01-20    1.875012
Freq: D, dtype: float64
#####################
PeriodIndex(['2022-01-01 10:00', '2022-01-02 11:00', '2022-01-03 12:00',
             '2022-01-04 13:00', '2022-01-05 14:00', '2022-01-06 15:00',
             '2022-01-07 16:00', '2022-01-08 17:00', '2022-01-09 18:00',
             '2022-01-10 19:00'],
            dtype='period[25H]', freq='25H')
######################################
2022-07-01    0
2022-07-02    1
2022-07-03    2
2022-07-04    3
2022-07-05    4
2022-07-06    5
2022-07-07    6
2022-07-08    7
2022-07-09    8
2022-07-10    9
Freq: D, dtype: int64
######################################
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50

三. 截断时间段

代码:

import pandas as pd
import numpy as np
import datetime as dt

# 从2022-01-01开始，间隔1天，生成20条 时间数据
time=pd.Series(np.random.randn(20),
           index=pd.date_range(dt.datetime(2022,1,1),periods=20))
print(time)
print("#####################")

# 只输出2022-01-10 之后的数据
print(time.truncate(before='2022-1-10'))
print("#####################")

# 只输出2022-01-10 之后的数据
print(time.truncate(after='2022-1-10'))
print("#####################")

# 输出区间段
print(time['2022-01-15':'2022-01-20'])
print("#####################")
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21

测试记录:

2022-01-01   -0.203552
2022-01-02   -1.035483
2022-01-03    0.252587
2022-01-04   -1.046993
2022-01-05    0.152435
2022-01-06   -0.534518
2022-01-07    0.770170
2022-01-08   -0.038129
2022-01-09    0.531485
2022-01-10    0.499937
2022-01-11    0.815295
2022-01-12    2.315740
2022-01-13   -0.443379
2022-01-14   -0.689247
2022-01-15    0.667250
2022-01-16   -2.067246
2022-01-17   -0.105151
2022-01-18   -0.420562
2022-01-19    1.012943
2022-01-20    0.509710
Freq: D, dtype: float64
#####################
2022-01-10    0.499937
2022-01-11    0.815295
2022-01-12    2.315740
2022-01-13   -0.443379
2022-01-14   -0.689247
2022-01-15    0.667250
2022-01-16   -2.067246
2022-01-17   -0.105151
2022-01-18   -0.420562
2022-01-19    1.012943
2022-01-20    0.509710
Freq: D, dtype: float64
#####################
2022-01-01   -0.203552
2022-01-02   -1.035483
2022-01-03    0.252587
2022-01-04   -1.046993
2022-01-05    0.152435
2022-01-06   -0.534518
2022-01-07    0.770170
2022-01-08   -0.038129
2022-01-09    0.531485
2022-01-10    0.499937
Freq: D, dtype: float64
#####################
2022-01-15    0.667250
2022-01-16   -2.067246
2022-01-17   -0.105151
2022-01-18   -0.420562
2022-01-19    1.012943
2022-01-20    0.509710
Freq: D, dtype: float64
#####################
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55

四. 时间戳及时间计算

代码:

import pandas as pd
import numpy as np
import datetime as dt

#时间戳
print(pd.Timestamp('2022-07-25'))
print(pd.Timestamp('2022-07-25 10'))
print(pd.Timestamp('2022-07-25 10:15'))
print("######################################")

#时间区间
print(pd.Period('2022-01'))
print(pd.Period('2022-01-01'))
print("######################################")

#时间计算
#help(pd.Timedelta)
print(pd.Period('2022-01-01 10:10') + pd.Timedelta('1 day'))
print(pd.Period('2022-01-01 10:10:10') + pd.Timedelta('1 s'))
print("######################################")
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20

测试记录:

2022-07-25 00:00:00
2022-07-25 10:00:00
2022-07-25 10:15:00
######################################
2022-01
2022-01-01
######################################
2022-01-02 10:10
2022-01-01 10:10:11
######################################
1
2
3
4
5
6
7
8
9
10

五. 数据重采样

数据重采样

时间数据由一个频率转换到另一个频率
降采样
升采样

代码:

import pandas as pd
import numpy as np
import datetime as dt

# 生成时间序列
rng = pd.date_range('1/1/2022', periods=90, freq='D')
ts = pd.Series(np.random.randn(len(rng)), index=rng)
#print(ts.head())

# 按月进行汇总
print(ts.resample('M').sum())
print("######################################")
# 按3天进行汇总
print(ts.resample('3D').sum())
print("######################################")
#  求3天的平均值
day3Ts = ts.resample('3D').mean()
print(day3Ts)
print("######################################")
# 将3天的时间序列转为1天的，结果发现很多空值
# 插值方法：
# 1. ffill 空值取前面的值
# 2. bfill 空值取后面的值
# 3. interpolate 线性取值
print(day3Ts.resample('D').asfreq())
print("######################################")
print(day3Ts.resample('D').ffill(1))
print("######################################")
print(day3Ts.resample('D').bfill(1))
print("######################################")
print(day3Ts.resample('D').interpolate('linear'))
print("######################################")
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

测试记录:

2022-01-31    0.904974
2022-02-28   -1.930083
2022-03-31    7.617911
Freq: M, dtype: float64
######################################
2022-01-01    0.104413
2022-01-04    2.255400
2022-01-07   -0.993552
2022-01-10    1.234344
2022-01-13   -0.621381
2022-01-16   -0.072830
2022-01-19   -0.215890
2022-01-22    0.050444
2022-01-25   -1.794619
2022-01-28    0.030952
2022-01-31   -1.022843
2022-02-03   -1.035522
2022-02-06   -1.124857
2022-02-09    1.915781
2022-02-12    0.263875
2022-02-15    0.927552
2022-02-18    0.760483
2022-02-21   -2.771669
2022-02-24    2.157336
2022-02-27    0.107964
2022-03-02   -0.852413
2022-03-05    1.252628
2022-03-08   -0.529793
2022-03-11    2.110139
2022-03-14    1.624062
2022-03-17   -0.241604
2022-03-20   -2.165326
2022-03-23    2.975993
2022-03-26    1.389412
2022-03-29    0.874324
dtype: float64
######################################
2022-01-01    0.034804
2022-01-04    0.751800
2022-01-07   -0.331184
2022-01-10    0.411448
2022-01-13   -0.207127
2022-01-16   -0.024277
2022-01-19   -0.071963
2022-01-22    0.016815
2022-01-25   -0.598206
2022-01-28    0.010317
2022-01-31   -0.340948
2022-02-03   -0.345174
2022-02-06   -0.374952
2022-02-09    0.638594
2022-02-12    0.087958
2022-02-15    0.309184
2022-02-18    0.253494
2022-02-21   -0.923890
2022-02-24    0.719112
2022-02-27    0.035988
2022-03-02   -0.284138
2022-03-05    0.417543
2022-03-08   -0.176598
2022-03-11    0.703380
2022-03-14    0.541354
2022-03-17   -0.080535
2022-03-20   -0.721775
2022-03-23    0.991998
2022-03-26    0.463137
2022-03-29    0.291441
dtype: float64
######################################
2022-01-01    0.034804
2022-01-02         NaN
2022-01-03         NaN
2022-01-04    0.751800
2022-01-05         NaN
2022-01-06         NaN
2022-01-07   -0.331184
2022-01-08         NaN
2022-01-09         NaN
2022-01-10    0.411448
2022-01-11         NaN
2022-01-12         NaN
2022-01-13   -0.207127
2022-01-14         NaN
2022-01-15         NaN
2022-01-16   -0.024277
2022-01-17         NaN
2022-01-18         NaN
2022-01-19   -0.071963
2022-01-20         NaN
2022-01-21         NaN
2022-01-22    0.016815
2022-01-23         NaN
2022-01-24         NaN
2022-01-25   -0.598206
2022-01-26         NaN
2022-01-27         NaN
2022-01-28    0.010317
2022-01-29         NaN
2022-01-30         NaN
                ...   
2022-02-28         NaN
2022-03-01         NaN
2022-03-02   -0.284138
2022-03-03         NaN
2022-03-04         NaN
2022-03-05    0.417543
2022-03-06         NaN
2022-03-07         NaN
2022-03-08   -0.176598
2022-03-09         NaN
2022-03-10         NaN
2022-03-11    0.703380
2022-03-12         NaN
2022-03-13         NaN
2022-03-14    0.541354
2022-03-15         NaN
2022-03-16         NaN
2022-03-17   -0.080535
2022-03-18         NaN
2022-03-19         NaN
2022-03-20   -0.721775
2022-03-21         NaN
2022-03-22         NaN
2022-03-23    0.991998
2022-03-24         NaN
2022-03-25         NaN
2022-03-26    0.463137
2022-03-27         NaN
2022-03-28         NaN
2022-03-29    0.291441
Freq: D, Length: 88, dtype: float64
######################################
2022-01-01    0.034804
2022-01-02    0.034804
2022-01-03         NaN
2022-01-04    0.751800
2022-01-05    0.751800
2022-01-06         NaN
2022-01-07   -0.331184
2022-01-08   -0.331184
2022-01-09         NaN
2022-01-10    0.411448
2022-01-11    0.411448
2022-01-12         NaN
2022-01-13   -0.207127
2022-01-14   -0.207127
2022-01-15         NaN
2022-01-16   -0.024277
2022-01-17   -0.024277
2022-01-18         NaN
2022-01-19   -0.071963
2022-01-20   -0.071963
2022-01-21         NaN
2022-01-22    0.016815
2022-01-23    0.016815
2022-01-24         NaN
2022-01-25   -0.598206
2022-01-26   -0.598206
2022-01-27         NaN
2022-01-28    0.010317
2022-01-29    0.010317
2022-01-30         NaN
                ...   
2022-02-28    0.035988
2022-03-01         NaN
2022-03-02   -0.284138
2022-03-03   -0.284138
2022-03-04         NaN
2022-03-05    0.417543
2022-03-06    0.417543
2022-03-07         NaN
2022-03-08   -0.176598
2022-03-09   -0.176598
2022-03-10         NaN
2022-03-11    0.703380
2022-03-12    0.703380
2022-03-13         NaN
2022-03-14    0.541354
2022-03-15    0.541354
2022-03-16         NaN
2022-03-17   -0.080535
2022-03-18   -0.080535
2022-03-19         NaN
2022-03-20   -0.721775
2022-03-21   -0.721775
2022-03-22         NaN
2022-03-23    0.991998
2022-03-24    0.991998
2022-03-25         NaN
2022-03-26    0.463137
2022-03-27    0.463137
2022-03-28         NaN
2022-03-29    0.291441
Freq: D, Length: 88, dtype: float64
######################################
2022-01-01    0.034804
2022-01-02         NaN
2022-01-03    0.751800
2022-01-04    0.751800
2022-01-05         NaN
2022-01-06   -0.331184
2022-01-07   -0.331184
2022-01-08         NaN
2022-01-09    0.411448
2022-01-10    0.411448
2022-01-11         NaN
2022-01-12   -0.207127
2022-01-13   -0.207127
2022-01-14         NaN
2022-01-15   -0.024277
2022-01-16   -0.024277
2022-01-17         NaN
2022-01-18   -0.071963
2022-01-19   -0.071963
2022-01-20         NaN
2022-01-21    0.016815
2022-01-22    0.016815
2022-01-23         NaN
2022-01-24   -0.598206
2022-01-25   -0.598206
2022-01-26         NaN
2022-01-27    0.010317
2022-01-28    0.010317
2022-01-29         NaN
2022-01-30   -0.340948
                ...   
2022-02-28         NaN
2022-03-01   -0.284138
2022-03-02   -0.284138
2022-03-03         NaN
2022-03-04    0.417543
2022-03-05    0.417543
2022-03-06         NaN
2022-03-07   -0.176598
2022-03-08   -0.176598
2022-03-09         NaN
2022-03-10    0.703380
2022-03-11    0.703380
2022-03-12         NaN
2022-03-13    0.541354
2022-03-14    0.541354
2022-03-15         NaN
2022-03-16   -0.080535
2022-03-17   -0.080535
2022-03-18         NaN
2022-03-19   -0.721775
2022-03-20   -0.721775
2022-03-21         NaN
2022-03-22    0.991998
2022-03-23    0.991998
2022-03-24         NaN
2022-03-25    0.463137
2022-03-26    0.463137
2022-03-27         NaN
2022-03-28    0.291441
2022-03-29    0.291441
Freq: D, Length: 88, dtype: float64
######################################
2022-01-01    0.034804
2022-01-02    0.273803
2022-01-03    0.512801
2022-01-04    0.751800
2022-01-05    0.390805
2022-01-06    0.029811
2022-01-07   -0.331184
2022-01-08   -0.083640
2022-01-09    0.163904
2022-01-10    0.411448
2022-01-11    0.205256
2022-01-12   -0.000935
2022-01-13   -0.207127
2022-01-14   -0.146177
2022-01-15   -0.085227
2022-01-16   -0.024277
2022-01-17   -0.040172
2022-01-18   -0.056068
2022-01-19   -0.071963
2022-01-20   -0.042371
2022-01-21   -0.012778
2022-01-22    0.016815
2022-01-23   -0.188192
2022-01-24   -0.393199
2022-01-25   -0.598206
2022-01-26   -0.395365
2022-01-27   -0.192524
2022-01-28    0.010317
2022-01-29   -0.106771
2022-01-30   -0.223859
                ...   
2022-02-28   -0.070721
2022-03-01   -0.177429
2022-03-02   -0.284138
2022-03-03   -0.050244
2022-03-04    0.183649
2022-03-05    0.417543
2022-03-06    0.219496
2022-03-07    0.021449
2022-03-08   -0.176598
2022-03-09    0.116728
2022-03-10    0.410054
2022-03-11    0.703380
2022-03-12    0.649371
2022-03-13    0.595363
2022-03-14    0.541354
2022-03-15    0.334058
2022-03-16    0.126762
2022-03-17   -0.080535
2022-03-18   -0.294281
2022-03-19   -0.508028
2022-03-20   -0.721775
2022-03-21   -0.150518
2022-03-22    0.420740
2022-03-23    0.991998
2022-03-24    0.815711
2022-03-25    0.639424
2022-03-26    0.463137
2022-03-27    0.405905
2022-03-28    0.348673
2022-03-29    0.291441
Freq: D, Length: 88, dtype: float64
######################################
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321

六. 移动窗口函数

代码:

import matplotlib.pylab as plt
import numpy as np
import pandas as pd

# 生成时间序列
df = pd.Series(np.random.randn(600), index = pd.date_range('7/1/2022', freq = 'D', periods = 600))

# 使用window函数
r = df.rolling(window = 10)
# 输出最近10个值的平均值
print(print(r.mean()))


# 画图
plt.figure(figsize=(15, 5))

df.plot(style='r')
df.rolling(window=10).mean().plot(style='b')

plt.show()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20

测试记录:

参考：

https://study.163.com/course/introduction.htm?courseId=1003590004#/courseDetail?tab=1

相关阅读:
IntelliJ IDEA 简介
 Gin 自定义控制器
 Linux：把进程/线程绑定到特定cpu核上运行
 Ai-WB2模组基于TCP的MQTT连接服务器使用示例
 vue2.x和vue3.x 环境相关配置
 关于深度学习一些疑惑的总结
 【数据结构】树与二叉树（九）：二叉树的后序遍历（非递归算法NPO）
textarea 让多行输入框高度随内容变化
 package-info.java
计网个人作业02
原文地址：https://blog.csdn.net/u010520724/article/details/126135039