File byte distribution comparison

compare.py

"""
compares the byte value distribution of the first argument with all the files in victims/
"""

from distr import calc_distribution
import os
import pickle
import sys

def dot(d1, d2):
   return sum([a*b for a,b in zip(d1, d2)]) 


distr = {}
datafile = "data.filee"
if os.path.isfile(datafile):
    with open(datafile, "rb") as f:
        distr = pickle.load(f)
    print "loaded distr from " + datafile


victimpath = "victims"

for path in os.listdir(victimpath):
    if path in distr:
        continue
    print path + ""
    distr[path] = calc_distribution(victimpath + "/" + path)

with open(datafile, "wb") as f:
    pickle.dump(distr, f)

mystery = calc_distribution(sys.argv[1])
scores = [(name, dot(d, mystery)) for name, d in distr.iteritems()]
scores = sorted(scores, key=lambda x: -x[1])
for score in scores[0:15]:
    print  "{:.<30}{:0.2f}".format(score[0], score[1])

distr.py

import sys

def calc_distribution(path):
    hits = [0]*256

    with open(path, "rb") as f:
        byte = f.read(1)
        while byte != "":
            # Do stuff with byte.
            byte = f.read(1)
            if byte == "":
                break
            hits[ord(byte[0])] += 1

    total = sum(hits)
    return [x/float(total) for x in hits]

if __name__ == "__main__":
    path = sys.argv[1]
    d = calc_distribution(path)
    print(str(d))