X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=find_best_caesar_break_parameters.py;h=edab90fcc2c55bfe5dc6b74b425413837030f1cd;hb=3906e8a686e3d1943e22746b65c394a4def34fc0;hp=246400ff65a6628b433e57c237fbf0f493f2f593;hpb=36820d02361529d5327ad040432d0198b72baed2;p=cipher-tools.git

diff --git a/find_best_caesar_break_parameters.py b/find_best_caesar_break_parameters.py
index 246400f..edab90f 100644
--- a/find_best_caesar_break_parameters.py
+++ b/find_best_caesar_break_parameters.py
@@ -2,8 +2,7 @@ import random
 import collections
 from cipher import *
 from cipherbreak import *
-
-print('Loading...')
+import itertools
 
 corpus = sanitise(''.join([open('shakespeare.txt', 'r').read(), 
     open('sherlock-holmes.txt', 'r').read(), 
@@ -14,9 +13,9 @@ 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.l3, 'name': 'l3'},
     {'func': norms.cosine_distance, 'name': 'cosine_distance'},
-    {'func': norms.harmonic_mean, 'name': 'harminic_mean'},
+    {'func': norms.harmonic_mean, 'name': 'harmonic_mean'},
     {'func': norms.geometric_mean, 'name': 'geometric_mean'},
     {'func': norms.inverse_log_pl, 'name': 'inverse_log_pl'}]
 scalings = [{'corpus_frequency': normalised_english_counts, 
@@ -32,34 +31,35 @@ message_lengths = [300, 100, 50, 30, 20, 10, 5]
 
 trials = 5000
 
-# rebuild with itertools.product and itertools.starmap
-# e.g. results = starmap(one_trial, product(metrics, scalings, message_lengths))
-# ... which would then be easy parallelise.
+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 _ 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, _ = 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:
+        print(',message_length', file = f)
+        print('metric+scaling,', ','.join([str(l) for l in message_lengths]), file = f)
+        for (metric, scaling) in itertools.product(metrics, scalings):
+            print('{}:{}'.format(metric['name'], scaling['name']), end='', file=f)
+            for l in message_lengths:
+                print(',', scores[(metric['name'], scaling['name'], l)] / trials, end='', file=f)
+            print('', file = f)
 
-print('Starting:', end='', flush=True)
-with open('caesar_break_parameter_trials.csv', 'w') as f:
-    print('metric,scaling,message_length,score', file = f)
-    scores = collections.defaultdict(int)
-    for metric in metrics:
-        scores[metric['name']] = collections.defaultdict(int)
-        for scaling in scalings:
-            scores[metric['name']][scaling['name']] = 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=metric['func'], 
-                                                      target_counts=scaling['corpus_frequency'], 
-                                                      message_frequency_scaling=scaling['scaling'])
-                    if found_key == key:
-                        scores[metric['name']][scaling['name']][message_length] += 1 
-                print('.', end='', flush=True)
-                print(', '.join([metric['name'], 
-                                 scaling['name'], 
-                                 str(message_length), 
-                                 str(scores[metric['name']][scaling['name']][message_length] / trials) ]),
-                    file = f)
-print()
+eval_all()
+show_results()