X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=find_best_caesar_break_parameters.py;h=7a550aaacc3cfade2fe06b9b6f6b81675fa8f6b6;hb=2def5210d568279bb38890c2de282e171f4ff7dd;hp=9ed53488dde8161ea13b1b6caa35b8aa60eb0fa0;hpb=3e8d2bd8cd7c623116fa3d2b77db954f51b191e4;p=cipher-training.git

diff --git a/find_best_caesar_break_parameters.py b/find_best_caesar_break_parameters.py
index 9ed5348..7a550aa 100644
--- a/find_best_caesar_break_parameters.py
+++ b/find_best_caesar_break_parameters.py
@@ -3,6 +3,7 @@ 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(), 
@@ -11,27 +12,19 @@ corpus_length = len(corpus)
 
 euclidean_scaled_english_counts = norms.euclidean_scale(english_counts)
 
-# def frequency_compare(text, target_frequency, frequency_scaling, metric):
-#     counts = frequency_scaling(frequencies(text))
-#     return -1 * metric(target_frequency, counts)
-
-# def euclidean_compare(text):
-#     return frequency_compare(text, norms.euclidean_scale(english_counts),
-#             norms.euclidean_scale, norms.euclidean_distance)
-
 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_distance, 'invert': False, 'name': 'cosine_distance'},
-    {'func': norms.harmonic_mean, 'invert': True, 'name': 'harmonic_mean'},
-    {'func': norms.geometric_mean, 'invert': True, 'name': 'geometric_mean'}]
+    {'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 = [300, 100, 50, 30, 20, 10, 5]
+message_lengths = [100, 50, 30, 20, 10, 5]
 
 trials = 5000
 
@@ -48,7 +41,6 @@ def make_frequency_compare_function(target_frequency, frequency_scaling, metric,
         return score
     return frequency_compare
 
-
 def scoring_functions():
     return [{'func': make_frequency_compare_function(s['corpus_frequency'], 
                 s['scaling'], m['func'], m['invert']),
@@ -77,14 +69,12 @@ def eval_one_score(scoring_function, message_length):
 
 def show_results():
     with open('caesar_break_parameter_trials.csv', 'w') as f:
-        print(',message_length', file = f)
-        print('scoring,', ', '.join([str(l) for l in message_lengths]), file = f)
+        writer = csv.DictWriter(f, ['name'] + message_lengths, 
+            quoting=csv.QUOTE_NONNUMERIC)
+        writer.writeheader()
         for scoring in sorted(scores.keys()):
-            for length in message_lengths:
-                print(scoring, end='', sep='', file=f)
-                for l in message_lengths:
-                    print(',', scores[scoring][l] / trials, end='', file=f)
-                print('', file = f)
+            scores[scoring]['name'] = scoring
+            writer.writerow(scores[scoring])
 
 eval_scores()
 show_results()