堆栈内存溢出
  繁体   English   中英

使用一个分组变量在 R 中进行预测

[英]Forecasting in R using one grouping variable

 原文  2022-01-04 12:28:40  0   1    r/ dplyr/ forecasting/ arima/ fable-r

问题描述

我正在尝试使用一个分组变量“实际交付位置”来预测年月数据。 我正在使用来自 Fable package 的 ARIMA 进行预测，但是当我运行 model 时出现以下错误

错误消息：ARIMA(Sales.Units, stepwise = F, approximation = F) [3] 遇到 3 个错误（1 个唯一）。数据包含隐含的时间间隔。 如果需要，您应该检查您的数据并使用tsibble::fill_gaps()将隐式间隙转换为显式缺失值。

我已将缺失值替换为零，并使用实际交付位置变量执行 group_by。

你能帮忙解决这个问题吗？

library(tidyverse)
library(tibbletime)
library(lubridate)
library(norm)
library(tibble)
library(tsibble)
library(fpp3)

Global.df<-structure(list(Actual.Delivery.Location = c("A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A324", "A324", "A324", 
"A324", "A324", "A324", "A324", "A324", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A482", "A482", "A482", 
"A482", "A482", "A482", "A482", "A482", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999", "A999", "A999", "A999", 
"A999", "A999", "A999", "A999", "A999"), YearMonth = c("Jan 2016", 
"Feb 2016", "Mar 2016", "Apr 2016", "May 2016", "Jun 2016", "Jul 2016", 
"Aug 2016", "Sep 2016", "Oct 2016", "Nov 2016", "Dec 2016", "Jan 2017", 
"Feb 2017", "Mar 2017", "Apr 2017", "May 2017", "Jun 2017", "Jul 2017", 
"Aug 2017", "Sep 2017", "Oct 2017", "Nov 2017", "Dec 2017", "Jan 2018", 
"Feb 2018", "Mar 2018", "Apr 2018", "May 2018", "Jun 2018", "Jul 2018", 
"Aug 2018", "Sep 2018", "Oct 2018", "Nov 2018", "Dec 2018", "Jan 2019", 
"Feb 2019", "Mar 2019", "Apr 2019", "May 2019", "Jun 2019", "Jul 2019", 
"Aug 2019", "Sep 2019", "Oct 2019", "Nov 2019", "Dec 2019", "Jan 2020", 
"Feb 2020", "Mar 2020", "Apr 2020", "May 2020", "Jun 2020", "Jul 2020", 
"Aug 2020", "Sep 2020", "Oct 2020", "Nov 2020", "Dec 2020", "Jan 2021", 
"Feb 2021", "Mar 2021", "Apr 2021", "May 2021", "Jun 2021", "Jul 2021", 
"Aug 2021", "Sep 2021", "Oct 2021", "Nov 2021", "Dec 2021", "Jan 2016", 
"Feb 2016", "Mar 2016", "Apr 2016", "May 2016", "Jun 2016", "Jul 2016", 
"Aug 2016", "Sep 2016", "Oct 2016", "Nov 2016", "Dec 2016", "Jan 2017", 
"Feb 2017", "Mar 2017", "Apr 2017", "May 2017", "Jun 2017", "Jul 2017", 
"Aug 2017", "Sep 2017", "Oct 2017", "Nov 2017", "Dec 2017", "Jan 2018", 
"Feb 2018", "Mar 2018", "Apr 2018", "May 2018", "Jun 2018", "Jul 2018", 
"Aug 2018", "Sep 2018", "Oct 2018", "Nov 2018", "Dec 2018", "Jan 2019", 
"Feb 2019", "Mar 2019", "Apr 2019", "May 2019", "Jun 2019", "Jul 2019", 
"Aug 2019", "Sep 2019", "Oct 2019", "Nov 2019", "Dec 2019", "Jan 2020", 
"Feb 2020", "Mar 2020", "Apr 2020", "May 2020", "Jun 2020", "Jul 2020", 
"Aug 2020", "Sep 2020", "Oct 2020", "Nov 2020", "Dec 2020", "Jan 2021", 
"Feb 2021", "Mar 2021", "Apr 2021", "May 2021", "Jun 2021", "Jul 2021", 
"Aug 2021", "Sep 2021", "Oct 2021", "Nov 2021", "Dec 2021", "Jan 2016", 
"Feb 2016", "Mar 2016", "Apr 2016", "May 2016", "Jun 2016", "Jul 2016", 
"Aug 2016", "Sep 2016", "Oct 2016", "Nov 2016", "Dec 2016", "Jan 2017", 
"Feb 2017", "Mar 2017", "Apr 2017", "May 2017", "Jun 2017", "Jul 2017", 
"Aug 2017", "Sep 2017", "Oct 2017", "Nov 2017", "Dec 2017", "Jan 2018", 
"Feb 2018", "Mar 2018", "Apr 2018", "May 2018", "Jun 2018", "Jul 2018", 
"Aug 2018", "Sep 2018", "Oct 2018", "Nov 2018", "Dec 2018", "Jan 2019", 
"Feb 2019", "Mar 2019", "Apr 2019", "May 2019", "Jun 2019", "Jul 2019", 
"Aug 2019", "Sep 2019", "Oct 2019", "Nov 2019", "Dec 2019", "Jan 2020", 
"Feb 2020", "Mar 2020", "Apr 2020", "May 2020", "Jun 2020", "Jul 2020", 
"Aug 2020", "Sep 2020", "Oct 2020", "Nov 2020", "Dec 2020", "Jan 2021", 
"Feb 2021", "Mar 2021", "Apr 2021", "May 2021", "Jun 2021", "Jul 2021", 
"Aug 2021", "Sep 2021", "Oct 2021", "Nov 2021", "Dec 2021"), 
    Sales.Units = c(2422, 1176, 2398, 2540, 3608, 4915, 3267, 
    4315, 2112, 3106, 1868, 2867, 2884, 555, 3208, 1732, 1180, 
    5911, 4082, 2992, 2173, 1974, 1665, 1997, 1989, 1382, 2074, 
    1433, 2537, 1869, 2106, 1923, 3410, 2035, 1174, 1462, 2372, 
    982, 4115, 2370, 3332, 983, 816, 2008, 3107, 4657, 1208, 
    1569, 1459, 1835, 1952, 337, 677, 4876, 2966, 2718, 6459, 
    1384, 1082, 2533, 1568, 1055, 1948, 1332, 2324, 3935, 2340, 
    1153, 1136, 491, 736, 802, 1303, 917, 683, 47, 847, 876, 
    196, 124, 620, 334, 114, 363, 592, 348, 842, 139, 747, 2242, 
    1653, 831, 105, 832, 400, 1026, 1053, 932, 998, 188, 334, 
    1418, 609, 300, 1097, 135, 549, 339, 1506, 1293, 76, 261, 
    97, 92, 678, 44, 697, 535, 203, 21, 135, 132, 259, 48, NA, 
    NA, 986, 985, 1340, 541, 211, 1018, 1810, 1028, 443, 1960, 
    114, 1342, 740, 73, 1512, 137, 169, 2308, 8324, 9000, 10006, 
    11553, 13637, 21684, 17027, 14328, 13915, 3828, 7620, 9405, 
    12086, 5963, 28456, 7933, 10039, 19783, 13488, 14828, 18563, 
    8864, 9995, 12951, 11156, 13203, 19383, 15198, 18466, 24225, 
    12761, 13580, 10387, 7638, 5584, 11093, 10959, 5781, 22894, 
    19559, 11428, 19135, 14153, 13864, 10961, 13355, 9454, 16976, 
    4837, 1077, 13443, 23364, 3667, 7469, 9465, 14030, 25455, 
    21555, 12228, 21354, 11829, 11518, 29550, 20653, 8949, 35923, 
    9466, 22290, 18310, 11170, 10732, 17269)), row.names = c(NA, 
216L), class = "data.frame")

Global.df[is.na(Global.df)]<-0
Global.df$YearMonth<-lubridate::my(Global.df$YearMonth)
Global.df <- as_tibble(Global.df)

Global.df<- Global.df %>%
  group_by(Actual.Delivery.Location) %>%
  as_tsibble(key = Actual.Delivery.Location,
             index = YearMonth)

Fit.Global.df<- Global.df %>%
  group_by(Actual.Delivery.Location) %>%
  model(ARIMA(Sales.Units,stepwise = F, approximation = F))

1 个解决方案

解决方案1
 0  2022-01-04 13:28:48

我已经想通了。我必须使用 yearmonth function 转换年份月份，而不是将其转换为日期。

Global.df <- Global.df %>% 
  mutate(Month = yearmonth(YearMonth))

暂无
暂无

声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 使用 R 进行分层预测 在 R 中使用 Prophet 进行预测 R中的领先一步预测 是否有 R function 用于按一个变量（列）对数据进行分组？ 使用预测包在R中进行预测 时间序列预测（使用R） 在R中使用GARCH模型进行预测 在R中使用ets（）进行预测的准确性 使用两个分组指定来创建一个“组合”分组变量 预测R中的多个可变时间序列
相关标签
 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM