Question

在我的数据集中

 mydat=structure(list(code = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 1L, 
1L, 1L, 1L, 1L, 1L), .Label = c("25480МСК", "25481МСК"), class = "factor"), 
    item = c(13163L, 13163L, 13163L, 13163L, 13163L, 13163L, 
    13164L, 13164L, 13164L, 13164L, 13164L, 13164L), sales = c(1L, 
    2L, 15L, 1L, 4L, 3L, 3L, 3L, 15L, 4L, 4L, 4L), action = c(0L, 
    0L, 1L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L)), .Names = c("code", 
"item", "sales", "action"), class = "data.frame", row.names = c(NA, 
-12L))

我有2个小组vars代码和项目。这是两组：

25481МСК    13163
25480МСК    13164

我也有行动专栏。它只能有两个值零（0）或一（1）。我需要通过action = 0计算销售的中位数，然后用该中位数替换所有的（1）。必须分别为每个组完成该操作。

I.E。所需的输出

code    item    sales   action  output
25481МСК    13163   1   0        1
25481МСК    13163   2   0        2
25481МСК    13163   15  1        2
25481МСК    13163   1   0        1
25481МСК    13163   4   0        4
25481МСК    13163   3   0        3
25480МСК    13164   3   0        3
25480МСК    13164   3   0        3
25480МСК    13164   15  1        4
25480МСК    13164   4   0        4
25480МСК    13164   4   0        4
25480МСК    13164   4   0        4

25481МСК 13163组中销售活动的零值中位数= 2，而活动1 = 15，因此我们替换了2上的活动1 = 15。

请注意，action = 0的sales列的值也应该在输出列中。如何执行？

Answer 1

librar(dplyr)
mydat %>% group_by(code,item) %>% 
          mutate(output=ifelse(action==0,sales,median(sales[action==0],na.rm = TRUE))) 


# A tibble: 12 x 5
  # Groups:   code, item [2]
  code      item sales action output
  <fct>    <int> <int>  <int>  <int>
  1 25481МСК 13163     1      0      1
  2 25481МСК 13163     2      0      2
  3 25481МСК 13163    15      1      2
  4 25481МСК 13163     1      0      1
  5 25481МСК 13163     4      0      4
  6 25481МСК 13163     3      0      3
  7 25480МСК 13164     3      0      3
  8 25480МСК 13164     3      0      3
  9 25480МСК 13164    15      1      4
  10 25480МСК 13164     4      0      4
  11 25480МСК 13164     4      0      4
  12 25480МСК 13164     4      0      4

Answer 2

library(data.table)
setDT(mydat)
mydat[, 
      output := ifelse(action, median(sales[!action]), sales), 
      by = .(code, item)]

        code  item sales action output
 1: 25481MCK 13163     1      0      1
 2: 25481MCK 13163     2      0      2
 3: 25481MCK 13163    15      1      2
 4: 25481MCK 13163     1      0      1
 5: 25481MCK 13163     4      0      4
 6: 25481MCK 13163     3      0      3
 7: 25480MCK 13164     3      0      3
 8: 25480MCK 13164     3      0      3
 9: 25480MCK 13164    15      1      4
10: 25480MCK 13164     4      0      4
11: 25480MCK 13164     4      0      4
12: 25480MCK 13164     4      0      4

Answer 3

为了完整起见，这是使用 update join 的另一种方法：

library(data.table)
# compute medians for each group
med <- setDT(mydat)[action == 0L, median(sales), by = .(code, item)][
  # append column to pick only rows with action == 1L in join
  , action := 1L]
mydat[
  # copy sales to output column, thereby coercing to double to match value of median()
  , output := as.numeric(sales)][
    # join and update selectively
    med, on = .(code, item, action), output := V1]
mydat[]

        code  item sales action output
 1: 25481MCK 13163     1      0      1
 2: 25481MCK 13163     2      0      2
 3: 25481MCK 13163    15      1      2
 4: 25481MCK 13163     1      0      1
 5: 25481MCK 13163     4      0      4
 6: 25481MCK 13163     3      0      3
 7: 25480MCK 13164     3      0      3
 8: 25480MCK 13164     3      0      3
 9: 25480MCK 13164    15      1      4
10: 25480MCK 13164     4      0      4
11: 25480MCK 13164     4      0      4
12: 25480MCK 13164     4      0      4

用R

3 个答案: