Hacky script to convert an apache benchmark data file into a CDF

convert_to_cdf.py

#!/usr/bin/python
# Usage
# ./convert_to_cdf.py ab_output.dat ab_output_cdf.dat
import csv
import sys

times = []
just_times = []
infile = sys.argv[1]
outfile = sys.argv[2]

with open(infile, 'r') as f:
    next(f)
    reader = csv.reader(f, delimiter='\t')
    for st, s, ctime, dtime, ttime, wait in reader:
        times.append((s, ttime))
        just_times.append(ttime)

with open(outfile, 'w') as f:
    writer = csv.writer(f, delimiter='\t')
    writer.writerow(('ms', 'percent'))
    num = float(len(times))
    seen = {}
    rows = []
    for s, ttime in times:
        if ttime in seen:
            continue
        rows.append((ttime, '{:.6f}'.format(just_times.count(ttime) / num)))
        seen[ttime] = True
    writer.writerows(rows)