Question

In a data management step of my analyses I incurred into the following problem.

In practice, each id is recorded up to 5 times, and I have a time-varying variable of interest, tv = 1, 2, 3, 4. Suppose my data are:

dat <- read.table(text = "

        id      tv    
        1       2
        1       2
        1       1
        1       4
        2       4
        2       1
        2       4
        3       1
        3       2
        3       3
        3       3
        3       2", 

    header=TRUE)  

What I need to do is to create two newly sets of variables starting from tv, in order to obtain:

   id     tv     tv1   tv2   tv3   tv4   tv5    dur1  dur2  dur3  dur4  dur5 
    1      2      2     1     4     0     0       2     1     1     0     0
    1      2      2     1     4     0     0       2     1     1     0     0
    1      1      2     1     4     0     0       2     1     1     0     0
    1      4      2     1     4     0     0       2     1     1     0     0
    2      4      4     1     4     0     0       1     1     1     0     0
    2      1      4     1     4     0     0       1     1     1     0     0
    2      4      4     1     4     0     0       1     1     1     0     0
    3      1      1     2     3     2     0       1     1     2     1     0
    3      2      1     2     3     2     0       1     1     2     1     0
    3      3      1     2     3     2     0       1     1     2     1     0
    3      3      1     2     3     2     0       1     1     2     1     0
    3      2      1     2     3     2     0       1     1     2     1     0

For each id, in tv1–tv5 we have the ordered sequence of distinct (non-repeated) records of tv, while in dur1–dur5 we have the number of times the respective distinct records are present in the original dataset dat.

I really don’t know how to proceed here.. Any help will be greatly appreciated.

Answer 1

This should do it:

require(plyr)
dat <- structure(list(id = c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 
         3L, 3L), tv = c(2L, 2L, 1L, 4L, 4L, 1L, 4L, 1L, 2L, 3L, 3L, 2L
         )), .Names = c("id", "tv"), class = "data.frame", row.names = c(NA, 
         -12L))

out <- ddply(dat, .(id), function(x) {
    this.rle <- rle(x$tv)

    val <- this.rle$values
    val <- c(val, rep(0, 5-length(val)))
    val <- matrix(rep(val,nrow(x)), byrow=T, nrow=nrow(x))
    val <- as.data.frame(val)
    names(val) <- paste("tv", 1:5, sep="")

    len <- this.rle$lengths
    len <- c(len, rep(0, 5-length(len)))
    len <- matrix(rep(len,nrow(x)), byrow=T, nrow=nrow(x))
    len <- as.data.frame(len)
    names(len) <- paste("dur", 1:5, sep="")
    cbind(data.frame(tv=x$tv), val, len)
})

> out
   id tv tv1 tv2 tv3 tv4 tv5 dur1 dur2 dur3 dur4 dur5
1   1  2   2   1   4   0   0    2    1    1    0    0
2   1  2   2   1   4   0   0    2    1    1    0    0
3   1  1   2   1   4   0   0    2    1    1    0    0
4   1  4   2   1   4   0   0    2    1    1    0    0
5   2  4   4   1   4   0   0    1    1    1    0    0
6   2  1   4   1   4   0   0    1    1    1    0    0
7   2  4   4   1   4   0   0    1    1    1    0    0
8   3  1   1   2   3   2   0    1    1    2    1    0
9   3  2   1   2   3   2   0    1    1    2    1    0
10  3  3   1   2   3   2   0    1    1    2    1    0
11  3  3   1   2   3   2   0    1    1    2    1    0
12  3  2   1   2   3   2   0    1    1    2    1    0