我想创建一个索引列，该索引列会查找诸如“开始”和“结束”之类的某些关键字以分配唯一的ID，并具有一个计数器/循环以在映射下一个“开始”时分配序列中的下一个数字< / p>
library(data.table)
in.data <- data.table(colA=c("random", "random", "random", "random", "random", "start", "random", "random",
"end", "start", "random", "end", "start", "end", "random", "random", "random",
"start","end","random","random", "start","start", "end", "end"))
in.data$wanted.column <- c(NA, NA, NA, NA, NA, 1, 1, 1,
1, 2, 2, 2, 3, 3, NA, NA, NA,
4, 4, NA, NA, 5, 6, 6, 6)
in.data$wanted.column2 = NA
IND <- min(which(in.data$colA %in% "start")):max(which(in.data$colA %in% "end"))
in.data$wanted.column2[IND] = cumsum(in.data$colA %in% "start")[IND]
in.data$wanted.column3 = NA
IND <- min(which(in.data$colA =="start")):max(which(in.data$colA == "end"))
in.data$wanted.column3[IND] = cumsum(in.data$colA == "start")[IND]
in.data
colA wanted.column wanted.column2 wanted.column3
1: random NA NA NA
2: random NA NA NA
3: random NA NA NA
4: random NA NA NA
5: random NA NA NA
6: start 1 1 1
7: random 1 1 1
8: random 1 1 1
9: end 1 1 1
10: start 2 2 2
11: random 2 2 2
12: end 2 2 2
13: start 3 3 3
14: end 3 3 3
15: random NA 3 3
16: random NA 3 3
17: random NA 3 3
18: start 4 4 4
19: end 4 4 4
20: random NA 4 4
21: random NA 4 4
22: start 5 5 5
23: start 6 6 6
24: end 6 6 6
25: end 6 6 6
colA wanted.column wanted.column2 wanted.column3