generating data having NA and order, related to #40 and #12

groupby-datagen.R

@@ -1,7 +1,10 @@
+# Rscript groupby-datagen.R 1e7 1e2 0 0 ## 1e7 rows, 1e2 K, 0% NAs, random order
+# Rscript groupby-datagen.R 1e8 1e1 5 1 ## 1e8 rows, 10 K, 5% NAs, sorted order
 args = commandArgs(TRUE)
 
 require(data.table)
-N=as.integer(args[1L]); K=as.integer(args[2L])
+N=as.integer(args[1L]); K=as.integer(args[2L]); nas=as.integer(args[3L]); sort=as.integer(args[4L])
+stopifnot(nas>100L, nas<0L, !sort%in%c(0L,1L))
 set.seed(108)
 DT <- data.table(
   id1 = sample(sprintf("id%03d",1:K), N, TRUE),      # large groups (char)
@@ -14,6 +17,17 @@ DT <- data.table(
   v2 =  sample(5, N, TRUE),                          # int in range [1,5]
   v3 =  sample(round(runif(100,max=100),4), N, TRUE) # numeric e.g. 23.5749
 )
+if (nas>0L) {
+  N_nas = as.integer(N*(nas/100))
+  for (col in names(DT)) {
+    I_nas = sample(N, N_nas, replace=FALSE)
+    set(DT, I_nas, col, NA)
+  }
+}
+if (sort==1L) {
+  setkeyv(DT, paste0("id", 1:6))
+}
+
 pretty_sci = function(x) {
   tmp<-strsplit(as.character(x), "+", fixed=TRUE)[[1L]]
   if(length(tmp)==1L) {
@@ -22,6 +36,6 @@ pretty_sci = function(x) {
     paste0(tmp[1L], as.character(as.integer(tmp[2L])))
   }
 }
-fwrite(DT, sprintf("G1_%s_%s.csv", pretty_sci(N), pretty_sci(K)))
+fwrite(DT, sprintf("G1_%s_%s_%s_%s.csv", pretty_sci(N), pretty_sci(K), nas, sort))
 
 quit("no", status=0)