运行 HoltWinters 时发生意外的日期更改

问题描述

我正在运行时间序列数据，但在运行 HoltWinters 函数时遇到了意外的日期更改。原始数据的日期范围为 2013 - 2017 年，但运行 HoltWinters 会将日期转换为 2014-2018 年。

代码如下：

fs<- HoltWinters(ts(tss$Average_sales,start = as.yearmon(tss$date[1]),freq = 12))

这是可重现的 tss 数据：

structure(list(year = c(2013,2013,2014,2015,2016,2017,2017),date = structure(c(15706,15737,15765,15796,15826,15857,15887,15918,15949,15979,16010,16040,16071,16102,16130,16161,16191,16222,16252,16283,16314,16344,16375,16405,16436,16467,16495,16526,16556,16587,16617,16648,16679,16709,16740,16770,16801,16832,16861,16892,16922,16953,16983,17014,17045,17075,17106,17136,17167,17198,17226,17257,17287,17318,17348,17379,17410,17440,17471,17501),class = "Date"),Average_sales = c(29.3486451612903,32.8155,39.8310967741935,45.4849333333333,49.2414193548387,53.0398,55.2207741935484,49.4684516129032,45.9938,42.3604516129032,46.1762,32.6843225806452,33.9346451612903,37.7940714285714,45.4387741935484,52.5942666666667,56.9598064516129,60.4561333333333,63.8070967741935,57.1352258064516,52.3416,48.9601935483871,53.3855333333333,37.2934193548387,35.646,39.3797857142857,47.1581290322581,54.9644666666667,59.8001290322581,62.4789333333333,66.9258064516129,59.3807096774194,54.8888,51.4356774193548,55.1763333333333,39.1981935483871,38.8670322580645,42.4108275862069,51.0245806451613,60.13,63.7890322580645,68.1776,73.4656774193548,63.3221935483871,59.7887333333333,55.7185161290323,59.4298666666667,42.8007096774194,39.8261935483871,44.3835,53.0752903225806,62.5908,65.8507096774194,70.9749333333333,75.5737419354839,66.2195483870968,62.3508666666667,57.4941935483871,61.9224666666667,44.8496774193548)),row.names = c(NA,-60L),groups = structure(list(
    year = c(2013,.rows = structure(list(
        1:12,13:24,25:36,37:48,49:60),ptype = integer(0),class = c("vctrs_list_of","vctrs_vctr","list"))),-5L),class = c("tbl_df","tbl","data.frame"),.drop = TRUE),class = c("grouped_df","tbl_df","data.frame"))

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）