identify whenever values repeat in r

April 22, 2022

I have a dataframe like this.

data <- data.frame(Condition = c(1,1,2,3,1,1,2,2,2,3,1,1,2,3,3))

I want to populate a new variable Sequence which identifies whenever Condition starts again from 1.

So the new dataframe would look like this.

Thanks in advance for the help!

data <- data.frame(Condition = c(1,1,2,3,1,1,2,2,2,3,1,1,2,3,3),
                   Sequence = c(1,1,1,1,2,2,2,2,2,2,3,3,3,3,3))

>Solution :

base R

data$Sequence2 <- cumsum(c(TRUE, data$Condition[-1] == 1 & data$Condition[-nrow(data)] != 1))
data
#    Condition Sequence Sequence2
# 1          1        1         1
# 2          1        1         1
# 3          2        1         1
# 4          3        1         1
# 5          1        2         2
# 6          1        2         2
# 7          2        2         2
# 8          2        2         2
# 9          2        2         2
# 10         3        2         2
# 11         1        3         3
# 12         1        3         3
# 13         2        3         3
# 14         3        3         3
# 15         3        3         3

dplyr

library(dplyr)
data %>%
  mutate(
    Sequence2 = cumsum(Condition == 1 & lag(Condition != 1, default = TRUE))
  )
#    Condition Sequence Sequence2
# 1          1        1         1
# 2          1        1         1
# 3          2        1         1
# 4          3        1         1
# 5          1        2         2
# 6          1        2         2
# 7          2        2         2
# 8          2        2         2
# 9          2        2         2
# 10         3        2         2
# 11         1        3         3
# 12         1        3         3
# 13         2        3         3
# 14         3        3         3
# 15         3        3         3