Print percentiles for list of data points

percentiles.sh

#!/bin/sh

# Exit immediately on error
set -e
# set -x

# Create temporary file
FILE=$(mktemp /tmp/$(basename $0).XXXXX) || exit 1

# Sort entries
sort -n $* > $FILE

# Count number of data points
N=$(wc -l $FILE | awk '{print $1}')
echo "Percentiles at 50, 90, 95 and 99 % for $N data points:"

# Calculate line numbers for each percentile we're interested in
P50=$(dc -e "$N 2 / p")
P90=$(dc -e "$N 9 * 10 / p")
P95=$(dc -e "$N 95 * 100 / p")
P99=$(dc -e "$N 99 * 100 / p")
awk "FNR==$P50 || FNR==$P90 || FNR==$P95 || FNR==$P99" $FILE
echo "Std. dev:"
awk '{x+=$0;y+=$0^2}END{print sqrt(y/NR-(x/NR)^2)}' $FILE

Super-superseded by istats