Creating a binned lead and lag in R-CodePudding

I am trying to create a type of lead and lag. The dplyr::lead and dplyr::lag function almost get what I want, but it's missing a crucial step where it "fills" in the values I want. Take the following example:

treatment <- c(0,0,0,0,0,0,1,0,0,0,0,0,1,0,0)

df_treatment <- tibble(treatment)

df_treatment

I want a lead and lag column of the treatment column, but I want it to have 3 leading 1s for each treatment indicator. The dplyr::lead function can give me only 1 lead since it can't take a vector in it's n argument.

This is my desired output:

lead_2 <- c(1,1,1,0,0,0,1,1,1,0,0,0,0,0,0)
lead_1 <- c(0,0,0,1,1,1,0,0,0,1,1,1,0,0,0)

df_desired <- tibble(lead_2, lead_1, treatment)
df_desired

The purpose of this is to create 6 leads and lags columns similar to the df_desired.

CodePudding user response：

If your treatment is like that, define new function leead that can put vector instead of n.

leead <- function(x, v){
  xx <- rep(0, length(x))
  for(i in v){
    xx <- xx   lead(x, i)
  }
  xx[is.na(xx)] <- 0
  xx
}

tibble(treatment) %>%
  mutate(lead_1 = leead(treatment, c(1:3)),
         lead_2 = leead(treatment, c(4:6))) 

   treatment lead_1 lead_2
       <dbl>  <dbl>  <dbl>
 1         0      0      1
 2         0      0      1
 3         0      0      1
 4         0      1      0
 5         0      1      0
 6         0      1      0
 7         1      0      1
 8         0      0      1
 9         0      0      1
10         0      1      0
11         0      1      0
12         0      1      0
13         1      0      0
14         0      0      0
15         0      0      0