R data.table条件求和

Question

> tempDT <- data.table(colA = c("E","E","A","C","E","C","E","C","E"), colB = c(20,30,40,30,30,40,30,20,10), group = c(1,1,1,1,2,2,2,2,2), want = c(NA, 30, 40, 70,NA,40,70,20,30))
> tempDT
   colA colB group want
1:    E   20     1   NA
2:    E   30     1   30
3:    A   40     1   40
4:    C   30     1   70
5:    E   30     2   NA
6:    C   40     2   40
7:    E   30     2   70
8:    C   20     2   20
9:    E   10     2   30

I have columns 'colA' 'colB' 'group': within each 'group', I would like to sum up 'colB' from bottom up until 'colA' is 'E'.

Answer 1

Based on the expected 'want', we create a run-length-id column 'grp' by checking if the value is 'E' in 'colA', then create 'want1' as the cumulative sum of 'colB' after grouping by 'grp' and 'group', get the row index ('i1') of elements that are duplicated in 'colA' and also is 'E' and assign the 'colB' values to 'want1'

tempDT[, grp:= rleid(colA=="E") * (colA != "E")
        ][grp!= 0, want1 := cumsum(colB), .(grp, group)]
i1 <- tempDT[, .I[colA=="E" & duplicated(colA)], group]$V1
tempDT[i1, want1 := colB][, grp := NULL][]
#    colA colB group want want1
#1:    E   20     1   NA    NA
#2:    E   30     1   30    30
#3:    A   40     1   40    40
#4:    C   30     1   70    70
#5:    E   30     2   NA    NA
#6:    C   30     2   30    30

Answer 2

Hope this helps!

library(dplyr)

df %>%
  group_by(group) %>%
  mutate(row_num = n():1) %>%
  group_by(group) %>%
  mutate(sum_colB = sum(colB[row_num < row_num[which(colA=='E')]]),
         flag = ifelse(row_num >= row_num[which(colA=='E')], 0, 1),) %>%
  mutate(sum_colB = ifelse(flag==1 & row_num==1, sum_colB, ifelse(flag==0, NA, colB))) %>%
  select(-flag, -row_num) %>%
  data.frame()

Output is:

  colA colB group want sum_colB
1    E   20     1   NA       NA
2    E   30     1   30       NA
3    A   40     1   40       40
4    C   30     1   70       70
5    E   30     2   NA       NA
6    C   30     2   30       30

Sample data:

df <- structure(list(colA = structure(c(3L, 3L, 1L, 2L, 3L, 2L), .Label = c("A", 
"C", "E"), class = "factor"), colB = c(20, 30, 40, 30, 30, 30
), group = c(1, 1, 1, 1, 2, 2), want = c(NA, 30, 40, 70, NA, 
30)), .Names = c("colA", "colB", "group", "want"), row.names = c(NA, 
-6L), class = "data.frame")

Answer 3

There's one approach: row reference + sums

# input data
tempDT <- data.table(colA = c("E","E","A","C","E","C","E","C","E"), colB = c(20,30,40,30,30,40,30,20,10), group = c(1,1,1,1,2,2,2,2,2), want = c(NA, 30, 40, 70,NA,40,70,20,30))
tempDT

# find row reference previous row where colA is "E"
lastEpos <- function(i) tail(which(tempDT$colA[1:(i-1)] == "E"), 1)
tempDT[, rowRef := sapply(.I, lastEpos), by = "group"]

# sum up
sumEpos <- function(i) {
  valTEMP <- tempDT$rowRef[i]
  outputTEMP <- sum(tempDT$colB[(valTEMP+1):i])  # sum
  return(outputTEMP)
}
tempDT[, want1 := sapply(.I, sumEpos), by = "group"]

# deal with first row in every group
tempDT[, want1 := c(NA, want1[-1]), by = "group"]

# clean output
tempDT[, rowRef := NULL]
tempDT