X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=find_best_caesar_break_parameters.py;h=7a8ddc9dc0a4dd3340a84c3fb021d44131d1ab87;hb=f420062910c850658815504763c8ca77067bac82;hp=ed8bbaac3f278f122b97612875ff3d614bc5c442;hpb=afc6b4e900c2215e205ea97d191dd5b78619d250;p=cipher-tools.git diff --git a/find_best_caesar_break_parameters.py b/find_best_caesar_break_parameters.py index ed8bbaa..7a8ddc9 100644 --- a/find_best_caesar_break_parameters.py +++ b/find_best_caesar_break_parameters.py @@ -1,60 +1,80 @@ import random +import collections from cipher import * +from cipherbreak import * +import itertools +import csv - -corpus = sanitise(''.join([open('shakespeare.txt', 'r').read(), open('sherlock-holmes.txt', 'r').read(), open('war-and-peace.txt', 'r').read()])) +corpus = sanitise(''.join([open('shakespeare.txt', 'r').read(), + open('sherlock-holmes.txt', 'r').read(), + open('war-and-peace.txt', 'r').read()])) corpus_length = len(corpus) -scaled_english_counts = norms.scale(english_counts) +euclidean_scaled_english_counts = norms.euclidean_scale(english_counts) + +metrics = [{'func': norms.l1, 'invert': True, 'name': 'l1'}, + {'func': norms.l2, 'invert': True, 'name': 'l2'}, + {'func': norms.l3, 'invert': True, 'name': 'l3'}, + {'func': norms.cosine_similarity, 'invert': False, 'name': 'cosine_similarity'}] + # {'func': norms.harmonic_mean, 'invert': True, 'name': 'harmonic_mean'}, + # {'func': norms.geometric_mean, 'invert': True, 'name': 'geometric_mean'}] +scalings = [{'corpus_frequency': normalised_english_counts, + 'scaling': norms.normalise, + 'name': 'normalised'}, + {'corpus_frequency': euclidean_scaled_english_counts, + 'scaling': norms.euclidean_scale, + 'name': 'euclidean_scaled'}] +message_lengths = [100, 50, 30, 20, 10, 5] +trials = 5000 -metrics = [norms.l1, norms.l2, norms.l3, norms.cosine_distance, norms.harmonic_mean, norms.geometric_mean] -corpus_frequencies = [normalised_english_counts, scaled_english_counts] -scalings = [norms.normalise, norms.scale] -message_lengths = [300, 100, 50, 30, 20, 10, 5] +scores = {} -metric_names = ['l1', 'l2', 'l3', 'cosine_distance', 'harmonic_mean', 'geometric_mean'] -corpus_frequency_names = ['normalised_english_counts', 'scaled_english_counts'] -scaling_names = ['normalise', 'scale'] -trials = 5000 +def make_frequency_compare_function(target_frequency, frequency_scaling, metric, invert): + def frequency_compare(text): + counts = frequency_scaling(frequencies(text)) + if invert: + score = -1 * metric(target_frequency, counts) + else: + score = metric(target_frequency, counts) + return score + return frequency_compare + +def scoring_functions(): + return [{'func': make_frequency_compare_function(s['corpus_frequency'], + s['scaling'], m['func'], m['invert']), + 'name': '{} + {}'.format(m['name'], s['name'])} + for m in metrics + for s in scalings] + [{'func': Pletters, 'name': 'Pletters'}] + +def eval_scores(): + [eval_one_score(f, l) + for f in scoring_functions() + for l in message_lengths] + +def eval_one_score(scoring_function, message_length): + print(scoring_function['name'], message_length) + if scoring_function['name'] not in scores: + scores[scoring_function['name']] = collections.defaultdict(int) + for _ in range(trials): + sample_start = random.randint(0, corpus_length - message_length) + sample = corpus[sample_start:(sample_start + message_length)] + key = random.randint(1, 25) + ciphertext = caesar_encipher(sample, key) + found_key, _ = caesar_break(ciphertext, scoring_function['func']) + if found_key == key: + scores[scoring_function['name']][message_length] += 1 + return scores[scoring_function['name']][message_length] + +def show_results(): + with open('caesar_break_parameter_trials.csv', 'w') as f: + writer = csv.DictWriter(f, ['name'] + message_lengths, + quoting=csv.QUOTE_NONNUMERIC) + writer.writeheader() + for scoring in sorted(scores): + scores[scoring]['name'] = scoring + writer.writerow(scores[scoring]) -scores = collections.defaultdict(int) -for metric in range(len(metrics)): - scores[metric_names[metric]] = collections.defaultdict(int) - for corpus_freqency in range(len(corpus_frequencies)): - scores[metric_names[metric]][corpus_frequency_names[corpus_freqency]] = collections.defaultdict(int) - for scaling in range(len(scalings)): - scores[metric_names[metric]][corpus_frequency_names[corpus_freqency]][scaling_names[scaling]] = collections.defaultdict(int) - for message_length in message_lengths: - for i in range(trials): - sample_start = random.randint(0, corpus_length - message_length) - sample = corpus[sample_start:(sample_start + message_length)] - key = random.randint(1, 25) - sample_ciphertext = caesar_encipher(sample, key) - (found_key, score) = caesar_break(sample_ciphertext, - metric=metrics[metric], - target_frequencies=corpus_frequencies[corpus_freqency], - message_frequency_scaling=scalings[scaling]) - if found_key == key: - scores[metric_names[metric]][corpus_frequency_names[corpus_freqency]][scaling_names[scaling]][message_length] += 1 - print(', '.join([metric_names[metric], - corpus_frequency_names[corpus_freqency], - scaling_names[scaling], - str(message_length), - str(scores[metric_names[metric]][corpus_frequency_names[corpus_freqency]][scaling_names[scaling]][message_length] / trials) ])) - - -with open('caesar_break_parameter_trials.csv', 'w') as f: - for metric in range(len(metrics)): - for corpus_freqency in range(len(corpus_frequencies)): - for scaling in range(len(scalings)): - for message_length in message_lengths: - print(', '.join([metric_names[metric], - corpus_frequency_names[corpus_freqency], - scaling_names[scaling], - str(message_length), - str(scores[metric_names[metric]][corpus_frequency_names[corpus_freqency]][scaling_names[scaling]][message_length] / trials) ]), - file=f) - - \ No newline at end of file +eval_scores() +show_results()