aboutsummaryrefslogtreecommitdiff
path: root/generate_test_data.sh
diff options
context:
space:
mode:
Diffstat (limited to 'generate_test_data.sh')
-rwxr-xr-xgenerate_test_data.sh22
1 files changed, 22 insertions, 0 deletions
diff --git a/generate_test_data.sh b/generate_test_data.sh
new file mode 100755
index 0000000..1cc6c9f
--- /dev/null
+++ b/generate_test_data.sh
@@ -0,0 +1,22 @@
+#!/bin/sh
+# Note generating test data
+# may take a while
+
+mkdir -p data
+sizes=(10000 50000 100000 500000 1000000 5000000)
+
+for size in "${sizes[@]}"; do
+ for run in {1..3}; do
+ outfile="data/random_${size}_run${run}.tsv" # '.tsv' stands for
+ echo "Generating $outfile ..." # tab seperaed values
+ {
+ for ((i=1; i<=size; i++)); do
+ # using 'printf' instead of 'echo'
+ # due to performance issues
+ printf "%d\t%d\n" $((1 + RANDOM % 32767)) $((1 + RANDOM % 10000))
+ done
+ } > "$outfile"
+ done
+done
+
+echo "All random data files gernated in ./data/"