nassimhaddad

# Set up some example data
year <-    sample(1970:2008, 1e6, rep=T)
state <-   sample(1:50, 1e6, rep=T)
group1 <-  sample(1:6, 1e6, rep=T)
group2 <-  sample(1:3, 1e6, rep=T)
myFact <-  rnorm(100, 15, 1e6)
weights <- rnorm(1e6)
myDF <- data.frame(year, state, group1, group2, myFact, weights)

system.time({

nassimhaddad

pb <- txtProgressBar(style = 3, min = 0, max = length(files_list))
i <- 0

for (file in files_list){
  i <- i+1
  setTxtProgressBar(pb, i)

  do_computations()
}

nassimhaddad

Routine:

1. When an error occurs, the first thing that I usually do is look at the stack trace by calling traceback(): that shows you where the error occurred, which is especially useful if you have several nested functions.
2. Next I will set options(error=recover); this immediately switches into browser mode where the error occurs, so you can browse the workspace from there.
3. If I still don't have enough information, I usually use the debug() function and step through

nassimhaddad

# downloads a gist
# usage: download_gist("4539629", "4539629.R")
#
# see also: source_gist {devtools}
download_gist <- function (entry, destfile, ...) 
{
  if (is.numeric(entry) || grepl("^[[:digit:]]+$", entry)) {
    entry <- paste("https://raw.github.com/gist/", entry, 
                   sep = "")
  }

nassimhaddad

nrow <- 100000
ncol <- 100
big_matrix <- matrix(sample(c(0,1,2), nrow * ncol, replace = TRUE), ncol = ncol)
print(object.size(big_matrix), units = "Mb")
# 76.3 Mb

nassimhaddad

# generate example:
prob <- c(2, rep(1,9))
v <- vector()
for (i in 1:10000){
  v <- c(v, sample(1:10, 1, prob = prob))
}

# print the output:
print(table(v))