R Holt Winters 分解错误 'no or less than 2 periods'

Question

我有一个每周级别的 R 时间序列，从 2013 年 1 月 7 日开始到 2016 年 5 月 23 日结束。

我使用以下代码创建了时间序列:

    start_date <- min(Orders_All_weekly$Week_Start)

    Orders_Weekly.ts <- ts(Orders_All_weekly$Sales, start = decimal_date(ymd(start_date)), freq = (365.25/7))

    Orders_Weekly.stl <- stl(Orders_Weekly.ts, s.window = 'periodic')

我正在尝试对这些数据运行 Holt Winters 时间序列，但收到错误

Orders_Weekly.hw <- HoltWinters(Orders_Weekly.stl)


Error in decompose(ts(x[1L:wind], start = start(x), frequency = f), seasonal) : 
  time series has no or less than 2 periods

我看到好几个人发布了这个错误，普遍的 react 是数据实际上并没有至少两个周期......这对于这个过程是必要的。除非我完全误解了这个的意思(这是可能的)，否则我有超过要求的两个时期。我的数据是每周级别的，我有 3 年以上的观察。

我设置不正确吗？或者错误本质上是说没有季节性？

ID   Week_Start     Sales
1   2013-04-08  932662.9
3   2013-05-13 1021574.4
4   2013-05-20  913812.9
5   2013-06-17 1086239.1
7   2013-08-26  762829.3
8   2013-11-18 1085033.0
9   2013-12-02  897158.4
10  2013-12-09  776733.7
11  2013-12-23  867362.8
12  2013-02-04  666362.0
13  2013-02-18  748603.2
15  2013-07-22 1005986.7
16  2013-09-02  896582.8
17  2013-10-28  868364.8
18  2014-01-06  814648.7
19  2014-02-10  847342.4
20  2014-02-17  869374.3
21  2014-03-17  827677.6
22  2014-03-24  897462.3
23  2014-03-31  850542.4
24  2014-04-21 1139619.4
25  2014-07-28  889043.3
26  2014-08-04 1097560.6
27  2014-09-08 1029379.4
28  2014-10-13  998094.8
29  2014-11-10 1238445.9
30  2014-12-15 1204006.6
31  2014-07-14 1106800.6
32  2014-09-01  730030.8
33  2014-10-06 1085331.8
34  2014-05-05 1072926.8
35  2014-05-19  863283.7
36  2015-01-19 1095186.1
37  2015-02-02  866258.2
38  2015-02-16 1006247.0
39  2015-03-23 1214339.7
40  2015-04-20 1181482.9
41  2015-05-18 1112542.4
42  2015-06-01 1188714.7
43  2015-07-20 1216050.4
45  2015-08-17  848302.8
46  2015-08-24 1081198.9
47  2015-09-14  916539.8
48  2015-09-28  957177.8
49  2015-10-26  964467.1
50  2015-11-02 1063949.1
51  2015-01-12  879343.9
53  2015-03-09 1245047.9
55  2015-11-16  913514.4
56  2015-02-09 1108247.6
57  2015-12-28 1014929.2
58  2016-01-25  946786.3
59  2016-02-01  891230.8
60  2016-02-29 1274039.8
61  2016-03-07  847501.8
62  2016-04-04 1057844.1
64  2016-04-11 1207347.4
65  2016-04-18 1159690.4
66  2016-05-02 1394727.6
67  2016-05-23 1044129.3
68  2013-03-04 1040017.1
69  2013-03-11  984574.2
70  2013-04-15 1054174.1
72  2013-04-29  952720.1
73  2013-05-06 1000977.1
74  2013-06-03 1091743.6
75  2013-07-01  955164.8
76  2013-08-12  808803.7
77  2013-09-23  960096.4
78  2013-09-30  814014.4
79  2013-10-14  743264.9
81  2013-01-28  956396.4
84  2013-10-21  959058.5
85  2013-11-11  915108.6
90  2013-01-14  867140.6
91  2014-01-27  910063.7
92  2014-03-10  963144.2
93  2014-04-07  975789.6
95  2014-04-28 1030313.7
97  2014-05-26 1139089.3
99  2014-06-09 1077980.6
100 2014-06-30 1019326.6
101 2014-09-15  666787.6
103 2014-11-03 1059089.4
105 2014-11-24  705428.6
106 2014-12-22  889368.8
108 2014-06-23 1046989.4
110 2015-02-23 1327066.4
112 2015-04-13 1110673.9
115 2015-06-08 1177799.1
116 2015-07-06 1314697.7
118 2015-07-27 1094805.6
119 2015-08-03  882394.2
120 2015-09-21 1159233.2
121 2015-10-19 1171636.9
122 2015-11-23 1036050.9
125 2015-12-21  984050.8
128 2016-01-04 1371348.3
129 2016-01-11 1086225.4
131 2016-02-22 1077692.4
137 2013-03-18  854699.1
141 2013-05-27 1011870.1
142 2013-08-05  893878.4
143 2013-12-16  801215.2
148 2013-10-07  805962.8
150 2013-11-04  801729.8
152 2013-08-19  726361.0
155 2014-02-24  979288.7
158 2014-04-14 1006729.5
161 2014-07-07 1102600.4
162 2014-08-11  979494.5
164 2014-10-20  901047.1
166 2014-10-27 1260062.0
169 2014-12-29 1022656.2
171 2014-08-18  976136.5
175 2015-03-02  897352.6
177 2015-03-30 1059103.8
178 2015-05-11 1033694.4
179 2015-06-29 1037959.4
182 2015-09-07 1230050.6
183 2015-10-12  975898.2
185 2015-12-07 1057603.4
186 2015-12-14  953718.2
189 2015-04-06 1233091.9
190 2015-04-27 1176994.2
192 2015-01-26 1256182.6
196 2016-01-18  955919.5
197 2016-02-15  954623.5
198 2016-03-14  740724.2
199 2013-01-07  924205.2
201 2013-02-11  672150.0
202 2013-03-25  769391.5
205 2013-06-10  870971.1
206 2013-06-24 1043166.2
208 2013-07-15 1106379.4
210 2013-09-09  916382.0
215 2013-04-22  934307.5
217 2013-12-30  974004.0
219 2014-01-13  972211.2
220 2014-01-20  952294.8
221 2014-02-03  946820.6
225 2014-06-02 1182837.6
228 2014-08-25  912550.8
234 2014-03-03 1013797.0
245 2015-06-15  946565.2
246 2015-07-13 1139633.6
248 2015-08-10 1080701.8
249 2015-08-31 1052796.2
253 2015-11-30  980493.4
259 2016-03-28 1105384.2
264 2016-02-08  897832.2
267 2013-02-25  766646.8
269 2013-04-01  954419.8
281 2013-11-25  852430.6
286 2013-09-16  997656.1
290 2014-07-21 1171519.8
294 2014-09-29  804772.4
298 2014-12-01  813872.0
299 2014-12-08 1005479.1
304 2014-06-16  981782.5
312 2015-03-16 1009182.7
315 2015-05-25 1166947.6
329 2015-01-05  903062.3
337 2016-03-21 1299648.7
338 2016-04-25 1132090.1
341 2013-01-21  818799.7
364 2014-05-12 1035870.7
367 2014-09-22 1234683.8
381 2015-06-22  990619.5
383 2015-10-05 1175100.6
385 2015-11-09 1095345.9
395 2016-05-16 1121192.5
399 2016-05-09 1175343.4
407 2013-07-08 1035513.8
430 2014-11-17 1024473.3
443 2015-05-04 1063411.6
476 2013-07-29  809045.3

Answer 1

我不确定这是否完全回答了问题，但我能够通过下面稍微修改的代码从您的数据中得到结果。

希望这对您有所帮助!

有一点，我首先按日期对数据进行排序，假设这是您意图的一部分。

Orders_Sorted <- Orders_Weekly[order(Orders_Weekly$Week_Start),] # Sort by date (unless you want to keep the data out of date order for some reason)
Orders_Weekly.ts <- ts(Orders_Sorted$Sales, frequency = (365.25/7)) # Convert df to time series
Orders_Weekly.hw <- HoltWinters(x=Orders_Weekly.ts, beta = FALSE, gamma = FALSE) # Run HW
plot(Orders_Weekly.hw) # Show plot of HW output

这会产生下图。

Plot of Holt-Winters exponential smoothing of data