X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=find_best_caesar_break_parameters-2.py;fp=find_best_caesar_break_parameters-2.py;h=88ca06c3f806288a0352c605c62650e4f00d3396;hb=c71e96eb2f7ee215802f30b60dc4c136a60d701d;hp=0000000000000000000000000000000000000000;hpb=36820d02361529d5327ad040432d0198b72baed2;p=cipher-tools.git

diff --git a/find_best_caesar_break_parameters-2.py b/find_best_caesar_break_parameters-2.py
new file mode 100644
index 0000000..88ca06c
--- /dev/null
+++ b/find_best_caesar_break_parameters-2.py
@@ -0,0 +1,62 @@
+import random
+import collections
+from cipher import *
+from cipherbreak import *
+import itertools
+
+print('Loading...')
+
+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)
+
+euclidean_scaled_english_counts = norms.euclidean_scale(english_counts)
+
+metrics = [{'func': norms.l1, 'name': 'l1'}, 
+    {'func': norms.l2, 'name': 'l2'},
+    {'func': norms.l3, 'name': 'l2'},
+    {'func': norms.cosine_distance, 'name': 'cosine_distance'},
+    {'func': norms.harmonic_mean, 'name': 'harminic_mean'},
+    {'func': norms.geometric_mean, 'name': 'geometric_mean'},
+    {'func': norms.inverse_log_pl, 'name': 'inverse_log_pl'}]
+scalings = [{'corpus_frequency': normalised_english_counts, 
+         'scaling': norms.normalise,
+         'name': 'normalised'},
+        {'corpus_frequency': euclidean_scaled_english_counts, 
+         'scaling': norms.euclidean_scale,
+         'name': 'euclidean_scaled'},
+         {'corpus_frequency': normalised_english_counts,
+         'scaling': norms.identity_scale,
+         'name': 'normalised_with_identity'}]
+message_lengths = [300, 100, 50, 30, 20, 10, 5]
+
+trials = 5000
+
+scores = collections.defaultdict(int)
+
+def eval_all():
+    list(itertools.starmap(eval_one_parameter_set,
+        itertools.product(metrics, scalings, message_lengths)))
+
+def eval_one_parameter_set(metric, scaling, message_length):
+    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=metric['func'], 
+                                          target_counts=scaling['corpus_frequency'], 
+                                          message_frequency_scaling=scaling['scaling'])
+        if found_key == key:
+            scores[(metric['name'], scaling['name'], message_length)] += 1 
+    return scores[(metric['name'], scaling['name'], message_length)]
+
+def show_results():
+    with open('caesar_break_parameter_trials.csv', 'w') as f:
+        for (k, v) in scores.items():
+            print(str(k)[1:-1], v, sep=",", file=f)
+
+eval_all()
+show_results()