r-将随机数转换为一组有序数

Question

我有一个数据帧"df"，它有三列。第三列包含一系列随机分配的数字(1到X(，这些数字经常重复多次。即使该列包含一组随机分配的数字，它们也会从小到大排序，以使这更容易。此外，Site和Date有多个条目，其中Site和Date的每个组合都有随机选择的数字(1到X(。df目前看起来是这样的(出于太空目的而缩短(：

分钟44[/tr>4[/tr>4[/tr>4[/tr>[/tr>[/tr>[/tr>[/tr>[/tr>[/tr>[/tr>[/tr>

站点	日期
BMA	44648
BMA	44648
BMA	44648
BMA	44648
BMA	44648
BMA	44648	13
BMA	44648	13
BMA	44648	13
BMA	44648	27
BMA	44648	27
BMA	44648	27
BMA	44648	27
BMA	44648	27
BMA	44773	2
BMA	44773	2
BMA	44773	2
BMA	44773	2
BMA	44773	2
BMA	44773	12
BMA	44773	12
BMA	44773	12
BMC	44648	3
BMC	44648	3
BMC	44648	3
BMC	44648	3
BMC	44648	3
BMC	44648	3
BMC	44648	44
BMC	44648	44
BMC	44648	44
BMC	44648	44
BMC	44648	60
BMC	44648	60
BMC	44648	60
BMC	44648	60

基R

ave(dat$Minute, dat[c("Site","Date")], FUN = function(z) match(z, sort(unique(z))))
#  [1] 1 1 1 1 1 2 2 2 3 3 3 3 3 1 1 1 1 1 2 2 2 1 1 1 1 1 1 2 2 2 2 3 3 3 3
dat$NewMinute <- ave(dat$Minute, dat[c("Site","Date")], FUN = function(z) match(z, sort(unique(z))))
identical(dat, dat2) # dat2 is expected output from the OP
# [1] TRUE

dplyr

library(dplyr)
dat %>%
group_by(Site, Date) %>%
mutate(NewMinute = match(Minute, sort(unique(Minute)))) %>%
ungroup()
# # A tibble: 35 x 4
#    Site   Date Minute NewMinute
#    <chr> <int>  <int>     <int>
#  1 BMA   44648      4         1
#  2 BMA   44648      4         1
#  3 BMA   44648      4         1
#  4 BMA   44648      4         1
#  5 BMA   44648      4         1
#  6 BMA   44648     13         2
#  7 BMA   44648     13         2
#  8 BMA   44648     13         2
#  9 BMA   44648     27         3
# 10 BMA   44648     27         3
# # ... with 25 more rows

---

数据

dat <- structure(list(Site = c("BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC"), Date = c(44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44773L, 44773L, 44773L, 44773L, 44773L, 44773L, 44773L, 44773L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L,  44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L), Minute = c(4L, 4L, 4L, 4L, 4L, 13L, 13L, 13L, 27L, 27L, 27L, 27L, 27L, 2L, 2L, 2L, 2L, 2L, 12L, 12L, 12L, 3L, 3L, 3L, 3L, 3L, 3L, 44L, 44L, 44L, 44L, 60L, 60L, 60L, 60L)), row.names = c(NA, -35L), class = "data.frame")
dat2 <- structure(list(Site = c("BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMA", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC", "BMC"), Date = c(44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44773L, 44773L, 44773L, 44773L, 44773L, 44773L, 44773L, 44773L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L,  44648L, 44648L, 44648L, 44648L, 44648L, 44648L, 44648L), Minute = c(4L, 4L, 4L, 4L, 4L, 13L, 13L, 13L, 27L, 27L, 27L, 27L, 27L, 2L, 2L, 2L, 2L, 2L, 12L, 12L, 12L, 3L, 3L, 3L, 3L, 3L, 3L, 44L, 44L, 44L, 44L, 60L, 60L, 60L, 60L), NewMinute = c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L)), class = "data.frame", row.names = c(NA, -35L))