r - 如何将当前行的负值传输到数据帧中的前一行？

Question

我想通过将当前行的负值添加到每组中的前一行来将它们传输到前一行。以下是我拥有的示例原始数据:

raw_data <- data.frame(GROUP = rep(c('A','B','C'),each = 6),
                   YEARMO = rep(c(201801:201806),3),
                   VALUE = c(100,-10,20,70,-50,30,20,60,40,-20,-10,50,0,10,-30,50,100,-100))
> raw_data
  GROUP YEARMO VALUE
1      A 201801   100  
2      A 201802   -10
3      A 201803    20
4      A 201804    70
5      A 201805   -50
6      A 201806    30
7      B 201801    20
8      B 201802    60
9      B 201803    40
10     B 201804   -20
11     B 201805   -10
12     B 201806    50
13     C 201801     0
14     C 201802    10
15     C 201803   -30
16     C 201804    50
17     C 201805   100
18     C 201806  -100

以下是我想要的输出:

final_data <- data.frame(GROUP = rep(c('A','B','C'),each = 6),
                   YEARMO = rep(c(201801:201806),3),
                   VALUE = c(90,0,20,20,0,30,20,60,10,0,0,50,-20,0,0,50,0,0))
> final_data
   GROUP YEARMO VALUE
1      A 201801    90
2      A 201802     0
3      A 201803    20
4      A 201804    20
5      A 201805     0
6      A 201806    30
7      B 201801    20
8      B 201802    60
9      B 201803    10
10     B 201804     0
11     B 201805     0
12     B 201806    50
13     C 201801   -20
14     C 201802     0
15     C 201803     0
16     C 201804    50
17     C 201805     0
18     C 201806     0

以下数据框将显示如何在每个组中进行转换:

Trans_GRP_A <- data.frame(GROUP = rep('A',each = 6),
                   YEARMO = c(201801:201806),
                   VALUE = c(100,-10,20,70,-50,30),
                   ITER_1 = c(100,-10,20,20,0,30),
                   ITER_2 = c(90,0,20,20,0,30))
> Trans_GRP_A
  GROUP YEARMO VALUE ITER_1 ITER_2
1     A 201801   100    100     90
2     A 201802   -10    -10      0
3     A 201803    20     20     20
4     A 201804    70     20     20
5     A 201805   -50      0      0
6     A 201806    30     30     30

> Trans_GRP_B <- data.frame(GROUP = rep('B',each = 6),
+                           YEARMO = c(201801:201806),
+                           VALUE = c(20,60,40,-20,-10,50),
+                           ITER_1 = c(20,60,40,-30,0,50),
+                           ITER_2 = c(20,60,10,0,0,50))
> Trans_GRP_B
  GROUP YEARMO VALUE ITER_1 ITER_2
1     B 201801    20     20     20
2     B 201802    60     60     60
3     B 201803    40     40     10
4     B 201804   -20    -30      0
5     B 201805   -10      0      0
6     B 201806    50     50     50

> Trans_GRP_C <- data.frame(GROUP = rep('C',each = 6),
+                           YEARMO = c(201801:201806),
+                           VALUE = c(0,10,-30,50,100,-100),
+                           ITER_1 = c(0,10,-30,50,0,0),
+                           ITER_2 = c(0,-20,0,50,0,0),
+                           ITER_3 = c(-20,0,0,50,0,0))
> Trans_GRP_C
  GROUP YEARMO VALUE ITER_1 ITER_2 ITER_3
1     C 201801     0      0      0    -20
2     C 201802    10     10    -20      0
3     C 201803   -30    -30      0      0
4     C 201804    50     50     50     50
5     C 201805   100      0      0      0
6     C 201806  -100      0      0      0

转账逻辑如下:

1. 将负值替换为 0。
2. 将当前行的负值与上一行的值相加。
3. 将负值转移到上一行，直到该值变为正值或 0。
4. 如果转移未产生正值，则转移直至在组内遇到第一行，此处每个组中的第一行是 YEARMO = 201801。

欢迎任何解决方案。我认为矢量化的解决方案可能执行得更快。

Answer 1

这里是另一种选择，将向量的正部分与向量的移位负部分递归地相加，直到不再有负值或已执行 .N 次(其中 .N 是行数)每个组)

setDT(raw_data)[, OUTPUT := {
        posVal <- replace(VALUE, VALUE<0, 0)
        negVal <- replace(VALUE, VALUE>0, 0)
        n <- 1L
        while (any(negVal < 0) && n < .N) {
            posVal <- replace(posVal, posVal<0, 0) + 
                shift(negVal, 1L, type="lead", fill=0) +
                c(negVal[1L], rep(0, .N-1L))
            negVal <- replace(posVal, posVal>0, 0)
            n <- n + 1L
        }
        posVal
    }, by=.(GROUP)]

输出:

    GROUP YEARMO VALUE OUTPUT
 1:     A 201801   100     90
 2:     A 201802   -10      0
 3:     A 201803    20     20
 4:     A 201804    70     20
 5:     A 201805   -50      0
 6:     A 201806    30     30
 7:     B 201801    20     20
 8:     B 201802    60     60
 9:     B 201803    40     10
10:     B 201804   -20      0
11:     B 201805   -10      0
12:     B 201806    50     50
13:     C 201801     0    -20
14:     C 201802    10      0
15:     C 201803   -30      0
16:     C 201804    50     50
17:     C 201805   100      0
18:     C 201806  -100      0