How can I revise my code to improve my processing speed

Question

I have to run a similar code across columns in a large matrix.

set.seed(1)

my_vector <- runif( 10000 )

my_sums <- NULL

for ( l in 1:length( my_vector ) ) {

  current_result <- my_vector[ my_vector < runif( 1 ) ]

  my_sums[l] <- sum( current_result )

}

head(my_sums)
# [1]   21.45613 2248.31463 2650.46104   62.82708   11.11391   86.21950

Sys.time results:

   user  system elapsed 
   1.14    0.00    1.14

Any ideas on how to improve performance?

Answer 1

Matt Dowle's excellent data.table approach in base R

system.time({
  set.seed(1)
  my_vector <- runif(10000)
  x <- runif(10000)
  sorted <- sort(my_vector)
  ind <- findInterval(x, sorted) + 1
  my_sums <- c(0, cumsum(sorted))[ind]
})

#   user  system elapsed 
#      0       0       0 

head(my_sums)
#[1]   21.45613 2248.31463 2650.46104   62.82708   11.11391   86.21950

Answer 2

require(data.table)

system.time({
  set.seed(1)
  my_vector = runif(10000)
  DT = data.table(my_vector)
  setkey(DT, my_vector)
  DT[,cumsum:=cumsum(my_vector)]
  my_sums = DT[.(runif(10000)), cumsum, roll=TRUE]
  my_sums[is.na(my_sums)] = 0
})

head(my_sums)
# [1]   21.45613 2248.31463 2650.46104   62.82708   11.11391   86.21950

#   user  system elapsed 
#  0.004   0.000   0.004

Answer 3

What about sapply?

temp <- sapply(seq_along(my_vector), function(l){

  current_result <- my_vector[ my_vector < runif( 1 ) ]
  my_sums[l] <- sum( current_result )

})

Gives this some performance improvements?