find_best_caesar_break_parameters.py

   1 import random
   2 import collections
   3 from cipher import *
   4 from cipherbreak import *
   5 import itertools
   6 import csv
   7
   8 corpus = sanitise(''.join([open('shakespeare.txt', 'r').read(),
   9     open('sherlock-holmes.txt', 'r').read(),
  10     open('war-and-peace.txt', 'r').read()]))
  11 corpus_length = len(corpus)
  12
  13 euclidean_scaled_english_counts = norms.euclidean_scale(english_counts)
  14
  15 metrics = [{'func': norms.l1, 'invert': True, 'name': 'l1'},
  16     {'func': norms.l2, 'invert': True, 'name': 'l2'},
  17     {'func': norms.l3, 'invert': True, 'name': 'l3'},
  18     {'func': norms.cosine_similarity, 'invert': False, 'name': 'cosine_similarity'}]
  19     # {'func': norms.harmonic_mean, 'invert': True, 'name': 'harmonic_mean'},
  20     # {'func': norms.geometric_mean, 'invert': True, 'name': 'geometric_mean'}]
  21 scalings = [{'corpus_frequency': normalised_english_counts,
  22          'scaling': norms.normalise,
  23          'name': 'normalised'},
  24         {'corpus_frequency': euclidean_scaled_english_counts,
  25          'scaling': norms.euclidean_scale,
  26          'name': 'euclidean_scaled'}]
  27 message_lengths = [100, 50, 30, 20, 10, 5]
  28
  29 trials = 5000
  30
  31 scores = {}
  32
  33
  34 def make_frequency_compare_function(target_frequency, frequency_scaling, metric, invert):
  35     def frequency_compare(text):
  36         counts = frequency_scaling(frequencies(text))
  37         if invert:
  38             score = -1 * metric(target_frequency, counts)
  39         else:
  40             score = metric(target_frequency, counts)
  41         return score
  42     return frequency_compare
  43
  44 def scoring_functions():
  45     return [{'func': make_frequency_compare_function(s['corpus_frequency'],
  46                 s['scaling'], m['func'], m['invert']),
  47             'name': '{} + {}'.format(m['name'], s['name'])}
  48         for m in metrics
  49         for s in scalings] + [{'func': Pletters, 'name': 'Pletters'}]
  50
  51 def eval_scores():
  52     [eval_one_score(f, l)
  53         for f in scoring_functions()
  54         for l in message_lengths]
  55
  56 def eval_one_score(scoring_function, message_length):
  57     print(scoring_function['name'], message_length)
  58     if scoring_function['name'] not in scores:
  59         scores[scoring_function['name']] = collections.defaultdict(int)
  60     for _ in range(trials):
  61         sample_start = random.randint(0, corpus_length - message_length)
  62         sample = corpus[sample_start:(sample_start + message_length)]
  63         key = random.randint(1, 25)
  64         ciphertext = caesar_encipher(sample, key)
  65         found_key, _ = caesar_break(ciphertext, scoring_function['func'])
  66         if found_key == key:
  67             scores[scoring_function['name']][message_length] += 1
  68     return scores[scoring_function['name']][message_length]
  69
  70 def show_results():
  71     with open('caesar_break_parameter_trials.csv', 'w') as f:
  72         writer = csv.DictWriter(f, ['name'] + message_lengths,
  73             quoting=csv.QUOTE_NONNUMERIC)
  74         writer.writeheader()
  75         for scoring in sorted(scores.keys()):
  76             scores[scoring]['name'] = scoring
  77             writer.writerow(scores[scoring])
  78
  79 eval_scores()
  80 show_results()