R Optimizing double for loop, matrix manipulation

Question

I am trying to manipulate column data in a two column matrix and output it as a data.frame.

The matrix that I have is in this format where both the values in the sta

Answer 1

You could use Rcpp:

start_end <- matrix(c(1, 6, 2, 9, 3, 15, 7, NA, 8, NA, 11, NA, 12, NA, 14, NA), 
                    nrow=8, 
                    ncol=2, byrow = TRUE)

library(Rcpp)
cppFunction('
            DataFrame fun(const IntegerMatrix& Mat) {
              IntegerVector start = na_omit(Mat(_, 0)); // remove NAs from starts
              std::sort(start.begin(), start.end()); // sort starts
              IntegerVector end = na_omit(Mat(_, 1)); // remove NAs from ends
              std::sort(end.begin(), end.end()); // sort ends
              IntegerVector res = clone(start); // initialize vector for matching ends
              int j = 0;
              for (int i = 0; i < start.length(); i++) { // loop over starts
                while (end(j) < start(i) && j < (end.length() - 1)) { // find corresponding end
                  j++;
                }
                if (end(j) >= start(i)) res(i) = end(j); // assign end
                else res(i) = NA_INTEGER; // assign NA if no end >= start exists
              }
              return DataFrame::create(_["start"]= start, _["end"]= res); // return a data.frame
            }
            ')

Res <- fun(start_end)

library(data.table)
setDT(Res)
Res[, .(start = paste(start, collapse = ",")), by = end]
#   end    start
#1:   6    1,2,3
#2:   9      7,8
#3:  15 11,12,14