Substract last N values from rle() object

Question

The following function is used to create a path overview for the following dataset:

tc <- textConnection('
path           touchpoint  time
abc             A           1        
abc             A           2        
abc             B           3        
abc             C           4         
def             A           2       
def             B           3       
def             D           4        
def             C           5        
def             D           6 
ghi             A           1
ghi             A           2
ghi             A           3
ghi             C           4
jkl             A           5        
jkl             A           6        
jkl             B           7        
jkl             C           8     
mno             B           1        
mno             A           2        
mno             A           3       
mno             C           4 
pqr             A           1
pqr             C           2
')

paths <- read.table(tc, header=TRUE)

--

library(plyr)

foo <- function(x){
  r <- rle(as.character(x))
  short <- paste0(r$values, collapse="_")
  long  <- paste0(r$values, "(", r$lengths, ")", collapse="_")
  data.frame(short, long)
}

ddply(paths, .(path), function(x)foo(x$touchpoint))

  path                     short                            long
1  abc                     A_B_C                  A(2)_B(1)_C(1)
2  def                 A_B_D_C_D        A(1)_B(1)_D(1)_C(1)_D(1)
3  ghi                       A_C                       A(3)_C(1)
4  jkl                     A_B_C                  A(2)_B(1)_C(1)
5  mno                     B_A_C                  B(1)_A(2)_C(1)
6  pqr                       A_C                       A(1)_C(1)

Thus this function creates two forms of 'paths':

• Short provides the sequence of touchpoints per path from least recent to most recent.
• Long provides the sequence of touchpoints per path from least recent to most recent including the number of times a touchpoint was involved.

Since the number of touchpoints can be quite large for some paths, I would like to incorporate the following constraint: only select the n most recent values from short and long. Since the paths are constructed from an rle() object, my question is:

How can I get N values and their corresponding lengths from an rle() object? Since the paths are saved from least recent touchpoint to most recent touchpoint, the last N values and corresponding lengths need to be selected. rle() documentation does not provide a solution for this issue.

Expected outcome if N=2 will be:

  path                     short                            long
1  abc                     B_C                          B(1)_C(1)
2  def                     C_D                          C(1)_D(1)
3  ghi                     A_C                          A(3)_C(1)
4  jkl                     B_C                          B(1)_C(1)
5  mno                     A_C                          A(2)_C(1)
6  pqr                     A_C                          A(1)_C(1)

Answer 1

Take only the last N values from r$values and r$lengths:

foo <- function(x,N){
  r <- rle(as.character(x))
  lastN<-max(1,(length(r$lengths) - N + 1)):length(r$lengths)
  short <- paste0(r$values[lastN], collapse="_")
  long  <- paste0(r$values[lastN], "(", r$lengths[lastN], ")", collapse="_")
  data.frame(short, long)
}


ddply(paths, .(path), function(x) foo(x$touchpoint,N=2))

  path short      long
1  abc   B_C B(1)_C(1)
2  def   C_D C(1)_D(1)
3  ghi   A_C A(3)_C(1)
4  jkl   B_C B(1)_C(1)
5  mno   A_C A(2)_C(1)
6  pqr   A_C A(1)_C(1)

 ddply(paths, .(path), function(x) foo(x$touchpoint,N=4))
  path   short                long
1  abc   A_B_C      A(2)_B(1)_C(1)
2  def B_D_C_D B(1)_D(1)_C(1)_D(1)
3  ghi     A_C           A(3)_C(1)
4  jkl   A_B_C      A(2)_B(1)_C(1)
5  mno   B_A_C      B(1)_A(2)_C(1)
6  pqr     A_C           A(1)_C(1)

EDIT: Edited the function to take last N values, not the first.