python 分析字母出现频率

代码 :

#!/usr/bin/env python
# coding:utf-8

import string

with open("data.txt", "r") as f:
    data = f.read()

letters = [0 for x in range(0, 26)]
frequency = "EARIOTNSLCUDPMHGBFYWKVXZJQ".lower()

print frequency

for i in data:
    if i.isalpha():
        i = i.lower()
        index = ord(i) - ord('a')
        letters[index] += 1

temp_letters = [{} for x in range(0, 26)]

counter = 0
for i in letters:
    temp_letters[counter] = {chr(ord('a') + counter): i}
    counter += 1


def compare(a, b):
    return a.values()[0] - b.values()[0]


target = ''


for i in sorted(temp_letters, compare, None, True):
    target += target.join(i.keys())


print "[+] Freque : %s" % frequency
print "[+] Target : %s" % target

table = string.maketrans(frequency, target)

print data
print string.translate(data, table)