Question

我有以下两个数据帧：

df1 <- data.frame(ID = c("A","A","B","B","C","D","D","D","E"),
             Date = as.POSIXct(c("2018-04-12 08:56:00","2018-04-13 11:03:00","2018-04-14 14:30:00","2018-04-15 03:10:00","2018-04-16 07:28:00","2018-04-17 11:17:00","2018-04-17 14:21:00","2018-04-18 09:56:00","2018-05-02 07:49:00")))

df2 <- data.frame(ID = c("A","A","A","B","C","D","D","D","D","D","E"),
              Date = as.POSIXct(c("2018-04-10 07:11:00","2018-04-11 18:59:00","2018-04-12 12:37:00","2018-04-15 01:43:00","2018-04-21 09:52:00","2018-04-15 20:25:00","2018-04-17 12:33:00","2018-04-17 14:21:00","2018-04-18 10:59:00","2018-04-20 14:11:00","2018-05-01 09:50:00")))

对于df1，我想做两件事：首先，我想通过df2通过ID查找最近的日期。其次，我想再次从df2中找到ID以后的最近日期，而无需重复值。在这两种情况下，我都不希望在df1中重复来自df2的日期。

使用data.table包中的roll = Inf功能，我可以在前面的日期中按ID合并。

setDT(df1)
setDT(df2)

setkey(df1, ID, Date)
setkey(df2, ID, Date)[, PrecedingDate:=Date]

result <- df2[df1, roll=Inf]

我不确定如何将最近的日期从df2拉入df1，以及如何确保不重复日期。

结果应如下：

result <- data.frame(ID = c("A","A","B","B","C","D","D","D","E"),
                     Date = as.POSIXct(c("2018-04-12 08:56:00","2018-04-13 11:03:00","2018-04-14 14:30:00","2018-04-15 03:10:00","2018-04-16 07:28:00","2018-04-17 11:17:00","2018-04-17 14:21:00","2018-04-18 09:56:00","2018-05-02 07:49:00")),
                     PrecedingDate = as.POSIXct(c("2018-04-11 18:59:00","2018-04-12 02:37:00",NA,"2018-04-15 01:43:00",NA,"2018-04-15 20:25:00","2018-04-17 14:21:00",NA,"2018-05-01 09:50:00")),
                     FollowingDate = as.POSIXct(c("2018-04-12 02:37:00",NA,"2018-04-15 01:43:00",NA,"2018-04-21 09:52:00","2018-04-17 12:33:00","2018-04-17 14:21:00","2018-04-18 10:59:00",NA)))

在这里的任何帮助将不胜感激。

Answer 1

这是使用dplyr的解决方案。您可能会收到有关min max函数的一些警告，但可以放心地忽略或取消它们。

library(dplyr)

closest_to_zero <- function(x) {
  neg <- which(x == max(x[x < 0]))
  pos <- which(x == min(x[x > 0]))
  c(previous = neg, following = pos)
}

result <- left_join(df1, df2, by = "ID") %>%
  group_by(ID, Date.x) %>%
  mutate(
    time_diff = Date.y - Date.x,
    Preceding = Date.y[closest_to_zero(time_diff)["previous"]],
    Following = Date.y[closest_to_zero(time_diff)["following"]]
  ) %>%
  distinct(ID, Date.x, Preceding, Following)

# A tibble: 9 x 4
# Groups:   ID, Date.x [9]
  ID    Date.x              Preceding           Following          
  <fct> <dttm>              <dttm>              <dttm>             
1 A     2018-04-12 08:56:00 2018-04-11 18:59:00 2018-04-12 12:37:00
2 A     2018-04-13 11:03:00 2018-04-12 12:37:00 NA                 
3 B     2018-04-14 14:30:00 NA                  2018-04-15 01:43:00
4 B     2018-04-15 03:10:00 2018-04-15 01:43:00 NA                 
5 C     2018-04-16 07:28:00 NA                  2018-04-21 09:52:00
6 D     2018-04-17 11:17:00 2018-04-15 20:25:00 2018-04-17 12:33:00
7 D     2018-04-17 14:21:00 2018-04-17 12:33:00 2018-04-18 10:59:00
8 D     2018-04-18 09:56:00 2018-04-17 14:21:00 2018-04-18 10:59:00
9 E     2018-05-02 07:49:00 2018-05-01 09:50:00 NA

Answer 2

使用data.table的可能解决方案：

df1[, PrecedingDate := df2[df1
                           , on = .(ID, Date <= Date)
                           , .(ID, Date = i.Date, pd = x.Date)
                           ][, .SD[.N], by = .(ID, Date)
                             ][shift(pd) == pd, pd := NA][, pd]
    ][, FollowingDate := df2[df1
                             , on = .(ID, Date >= Date)
                             , .(ID, Date = i.Date, fd = x.Date)
                             ][, .SD[1], by = .(ID, Date)][, fd]][]

给出：

> df1
   ID                Date       PrecedingDate       FollowingDate
1:  A 2018-04-12 08:56:00 2018-04-11 18:59:00 2018-04-12 12:37:00
2:  A 2018-04-13 11:03:00 2018-04-12 12:37:00                <NA>
3:  B 2018-04-14 14:30:00                <NA> 2018-04-15 01:43:00
4:  B 2018-04-15 03:10:00 2018-04-15 01:43:00                <NA>
5:  C 2018-04-16 07:28:00                <NA> 2018-04-21 09:52:00
6:  D 2018-04-17 11:17:00 2018-04-15 20:25:00 2018-04-17 12:33:00
7:  D 2018-04-17 14:21:00 2018-04-17 14:21:00 2018-04-17 14:21:00
8:  D 2018-04-18 09:56:00                <NA> 2018-04-18 10:59:00
9:  E 2018-05-02 07:49:00 2018-05-01 09:50:00                <NA>

这等于期望的结果：

> all.equal(df1, as.data.table(result))
[1] TRUE

使用的数据：

df1 <- data.frame(ID = c("A","A","B","B","C","D","D","D","E"),
                  Date = as.POSIXct(c("2018-04-12 08:56:00","2018-04-13 11:03:00","2018-04-14 14:30:00","2018-04-15 03:10:00","2018-04-16 07:28:00","2018-04-17 11:17:00","2018-04-17 14:21:00","2018-04-18 09:56:00","2018-05-02 07:49:00")))
df2 <- data.frame(ID = c("A","A","A","B","C","D","D","D","D","D","E"),
                  Date = as.POSIXct(c("2018-04-10 07:11:00","2018-04-11 18:59:00","2018-04-12 12:37:00","2018-04-15 01:43:00","2018-04-21 09:52:00","2018-04-15 20:25:00","2018-04-17 12:33:00","2018-04-17 14:21:00","2018-04-18 10:59:00","2018-04-20 14:11:00","2018-05-01 09:50:00")))
result <- data.frame(ID = c("A","A","B","B","C","D","D","D","E"),
                     Date = as.POSIXct(c("2018-04-12 08:56:00","2018-04-13 11:03:00","2018-04-14 14:30:00","2018-04-15 03:10:00","2018-04-16 07:28:00","2018-04-17 11:17:00","2018-04-17 14:21:00","2018-04-18 09:56:00","2018-05-02 07:49:00")),
                     PrecedingDate = as.POSIXct(c("2018-04-11 18:59:00","2018-04-12 12:37:00",NA,"2018-04-15 01:43:00",NA,"2018-04-15 20:25:00","2018-04-17 14:21:00",NA,"2018-05-01 09:50:00")),
                     FollowingDate = as.POSIXct(c("2018-04-12 12:37:00",NA,"2018-04-15 01:43:00",NA,"2018-04-21 09:52:00","2018-04-17 12:33:00","2018-04-17 14:21:00","2018-04-18 10:59:00",NA)))

查找数据框之间的最近的前后日期

2 个答案: