R 查找日期差异

我有以下数据：

ID GROUP     DATE 
A   GR1   12/01/2013
A   GR1   09/04/2014
A   GR1   01/03/2015
A   GR2   04/04/2015
A   GR2   08/21/2015
A   GR1   01/05/2016
A   GR1   06/28/2016
B   GR2   11/01/2013
B   GR2   06/04/2014
B   GR2   04/15/2015
B   GR3   11/04/2015
B   GR2   03/21/2016
B   GR2   07/05/2016
B   GR1   06/28/2016
C   GR2   01/16/2014
C   GR2   06/04/2014
C   GR2   04/15/2015
C   GR3   11/04/2015
C   GR2   03/21/2016
C   GR2   06/05/2016
C   GR1   06/28/2016

我想得到每个组中的人的差异。因此，新表将如下所示：

ID GROUP     DATE      Diff
A   GR1   12/01/2013
A   GR1   09/04/2014
A   GR1   01/03/2015    398
A   GR2   04/04/2015
A   GR2   08/21/2015    139
A   GR1   01/05/2016
A   GR1   06/28/2016    175
B   GR2   11/01/2013
B   GR2   06/04/2014
B   GR2   04/15/2015    530
B   GR3   11/04/2015
B   GR2   03/21/2016
B   GR2   07/05/2016    106
B   GR1   06/28/2016
C   GR2   01/16/2014
C   GR2   06/04/2014    
C   GR2   04/15/2015    454
C   GR3   11/04/2015
C   GR2   03/21/2016
C   GR2   01/05/2016    76
C   GR1   06/28/2016

“Diff”398列中的值取“01/03/2015”-“12/1/2013”之间的差值。同样，所有其他的差异

现在我的问题是如何获得这种差异？我不能在每个组中取max（date）-min（date），因为组在不同的时间重复。类似地，我不能像SAS中那样使用第一个点和最后一个点

如果有人帮我解决这个问题，我将不胜感激。我更喜欢SAS中的解决方案，因为数据量非常大。所以不会保存在记忆中

---

在这方面，

使用SAS完成这项工作是微不足道的。使用“保留”保留组的第一条记录的开始日期。您的数据似乎没有排序，因此您可以先对其排序，或者如果您想保持当前顺序（并且组中的记录已按日期排序），则可以使用

by

语句中的

NOTSORTED

选项

library(dplyr)
library(data.table)
df$xxx = rleidv(df[, c("ID","GROUP"),with = FALSE ])
df$DATE = as.Date(df$DATE, format = "%m/%d/%Y")
df %>% group_by(xxx) %>% mutate(diff = max(DATE) - min(DATE)) %>%
       ungroup(xxx) %>% mutate(xxx = NULL)
#     ID GROUP       DATE     diff
#   <chr> <chr>     <date>   <time>
#1      A   GR1 2013-12-01 398 days
#2      A   GR1 2014-09-04 398 days
#3      A   GR1 2015-01-03 398 days
#4      A   GR2 2015-04-04 139 days
#5      A   GR2 2015-08-21 139 days
#6      A   GR1 2016-01-05 175 days
#7      A   GR1 2016-06-28 175 days
#8      B   GR2 2013-11-01 530 days
#9      B   GR2 2014-06-04 530 days
#10     B   GR2 2015-04-15 530 days

data want ;
  set have ;
  by id group notsorted;
  if first.group then start = date ;
  else if last.group then diff = date - start ;
  retain start;
  drop start;
run;

如果您需要保持当前顺序，但日期未在组中排序，那么要在组中查找最小和最大日期，您需要添加另一个变量和更多的逻辑

data want ;
  set have ;
  by id group notsorted;
  if first.group then start = date ;
  if first.group then stop = date ;
  start = min(start,date);
  stop = max(stop,date);
  if last.group and not first.group then diff = stop - start ;
  retain start stop;
  drop start stop;
run;

data want ;
  set have ;
  by id group notsorted;
  if first.group then start = date ;
  else if last.group then diff = date - start ;
  retain start;
  drop start;
run;

data want ;
  set have ;
  by id group notsorted;
  if first.group then start = date ;
  if first.group then stop = date ;
  start = min(start,date);
  stop = max(stop,date);
  if last.group and not first.group then diff = stop - start ;
  retain start stop;
  drop start stop;
run;