Tweaks, and record of a run

diff --git a/caesar_break_parameter_trials.csv b/caesar_break_parameter_trials.csv
index ae1b8415f1b65f23a0c263e744cd61ccce40d486..37e60fb26903064644413deaa65da8d7d8b91102 100644 (file)
--- a/caesar_break_parameter_trials.csv
+++ b/caesar_break_parameter_trials.csv
@@ -1,148 +1,127 @@
 metric,scaling,message_length,score
-l1, normalised, 300, 0.9996
-l1, normalised, 100, 1.0
-l1, normalised, 50, 0.9988
-l1, normalised, 30, 0.99
-l1, normalised, 20, 0.952
-l1, normalised, 10, 0.7144
-l1, normalised, 5, 0.4368
-l1, euclidean_scaled, 300, 0.999
-l1, euclidean_scaled, 100, 0.9994
-l1, euclidean_scaled, 50, 0.9984
-l1, euclidean_scaled, 30, 0.9912
-l1, euclidean_scaled, 20, 0.9526
-l1, euclidean_scaled, 10, 0.7478
-l1, euclidean_scaled, 5, 0.439
-l1, normalised_with_identity, 300, 0.9652
-l1, normalised_with_identity, 100, 0.9898
-l1, normalised_with_identity, 50, 0.9862
-l1, normalised_with_identity, 30, 0.9622
-l1, normalised_with_identity, 20, 0.9084
-l1, normalised_with_identity, 10, 0.7134
-l1, normalised_with_identity, 5, 0.4376
-l2, normalised, 300, 0.9994
-l2, normalised, 100, 0.9994
-l2, normalised, 50, 0.999
-l2, normalised, 30, 0.9808
-l2, normalised, 20, 0.9364
-l2, normalised, 10, 0.7062
-l2, normalised, 5, 0.4304
-l2, euclidean_scaled, 300, 0.9994
-l2, euclidean_scaled, 100, 0.9996
-l2, euclidean_scaled, 50, 0.9978
-l2, euclidean_scaled, 30, 0.9842
-l2, euclidean_scaled, 20, 0.9372
-l2, euclidean_scaled, 10, 0.7214
-l2, euclidean_scaled, 5, 0.4402
-l2, normalised_with_identity, 300, 0.9992
-l2, normalised_with_identity, 100, 0.9992
-l2, normalised_with_identity, 50, 0.9966
-l2, normalised_with_identity, 30, 0.9848
-l2, normalised_with_identity, 20, 0.9346
-l2, normalised_with_identity, 10, 0.719
-l2, normalised_with_identity, 5, 0.428
-l2, normalised, 300, 0.9994
-l2, normalised, 100, 0.9994
-l2, normalised, 50, 0.9928
-l2, normalised, 30, 0.9554
-l2, normalised, 20, 0.8642
-l2, normalised, 10, 0.5982
-l2, normalised, 5, 0.3996
-l2, euclidean_scaled, 300, 0.9998
-l2, euclidean_scaled, 100, 0.9998
-l2, euclidean_scaled, 50, 0.994
-l2, euclidean_scaled, 30, 0.9692
-l2, euclidean_scaled, 20, 0.8902
-l2, euclidean_scaled, 10, 0.6312
-l2, euclidean_scaled, 5, 0.3964
-l2, normalised_with_identity, 300, 0.9996
-l2, normalised_with_identity, 100, 0.9976
-l2, normalised_with_identity, 50, 0.9702
-l2, normalised_with_identity, 30, 0.8988
-l2, normalised_with_identity, 20, 0.7732
-l2, normalised_with_identity, 10, 0.5536
-l2, normalised_with_identity, 5, 0.3958
-cosine_distance, normalised, 300, 1.0
-cosine_distance, normalised, 100, 0.9992
-cosine_distance, normalised, 50, 0.9978
-cosine_distance, normalised, 30, 0.9862
-cosine_distance, normalised, 20, 0.938
-cosine_distance, normalised, 10, 0.7216
-cosine_distance, normalised, 5, 0.4358
-cosine_distance, euclidean_scaled, 300, 1.0
-cosine_distance, euclidean_scaled, 100, 0.9996
-cosine_distance, euclidean_scaled, 50, 0.9986
-cosine_distance, euclidean_scaled, 30, 0.9856
-cosine_distance, euclidean_scaled, 20, 0.9348
-cosine_distance, euclidean_scaled, 10, 0.7036
-cosine_distance, euclidean_scaled, 5, 0.4402
-cosine_distance, normalised_with_identity, 300, 0.999
-cosine_distance, normalised_with_identity, 100, 0.9994
-cosine_distance, normalised_with_identity, 50, 0.9984
-cosine_distance, normalised_with_identity, 30, 0.9844
-cosine_distance, normalised_with_identity, 20, 0.9376
-cosine_distance, normalised_with_identity, 10, 0.7184
-cosine_distance, normalised_with_identity, 5, 0.442
-harminic_mean, normalised, 300, 0.8082
-harminic_mean, normalised, 100, 0.8386
-harminic_mean, normalised, 50, 0.7576
-harminic_mean, normalised, 30, 0.2696
-harminic_mean, normalised, 20, 0.8576
-harminic_mean, normalised, 10, 0.6748
-harminic_mean, normalised, 5, 0.4498
-harminic_mean, euclidean_scaled, 300, 0.4754
-harminic_mean, euclidean_scaled, 100, 0.5136
-harminic_mean, euclidean_scaled, 50, 0.6756
-harminic_mean, euclidean_scaled, 30, 0.596
-harminic_mean, euclidean_scaled, 20, 0.538
-harminic_mean, euclidean_scaled, 10, 0.4296
-harminic_mean, euclidean_scaled, 5, 0.357
-harminic_mean, normalised_with_identity, 300, 0.9544
-harminic_mean, normalised_with_identity, 100, 0.9738
-harminic_mean, normalised_with_identity, 50, 0.952
-harminic_mean, normalised_with_identity, 30, 0.9252
-harminic_mean, normalised_with_identity, 20, 0.8956
-harminic_mean, normalised_with_identity, 10, 0.747
-harminic_mean, normalised_with_identity, 5, 0.4582
-geometric_mean, normalised, 300, 0.9996
-geometric_mean, normalised, 100, 0.9996
-geometric_mean, normalised, 50, 0.989
-geometric_mean, normalised, 30, 0.9218
-geometric_mean, normalised, 20, 0.9434
-geometric_mean, normalised, 10, 0.7138
-geometric_mean, normalised, 5, 0.4626
-geometric_mean, euclidean_scaled, 300, 0.9998
-geometric_mean, euclidean_scaled, 100, 0.9986
-geometric_mean, euclidean_scaled, 50, 0.993
-geometric_mean, euclidean_scaled, 30, 0.9538
-geometric_mean, euclidean_scaled, 20, 0.8868
-geometric_mean, euclidean_scaled, 10, 0.6452
-geometric_mean, euclidean_scaled, 5, 0.4466
-geometric_mean, normalised_with_identity, 300, 0.9416
-geometric_mean, normalised_with_identity, 100, 0.9894
-geometric_mean, normalised_with_identity, 50, 0.9854
-geometric_mean, normalised_with_identity, 30, 0.9758
-geometric_mean, normalised_with_identity, 20, 0.9336
-geometric_mean, normalised_with_identity, 10, 0.7704
-geometric_mean, normalised_with_identity, 5, 0.4742
-inverse_log_pl, normalised, 300, 0.9994
-inverse_log_pl, normalised, 100, 0.9992
-inverse_log_pl, normalised, 50, 0.9998
-inverse_log_pl, normalised, 30, 0.9974
-inverse_log_pl, normalised, 20, 0.9804
-inverse_log_pl, normalised, 10, 0.8164
-inverse_log_pl, normalised, 5, 0.4832
-inverse_log_pl, euclidean_scaled, 300, 0.9996
-inverse_log_pl, euclidean_scaled, 100, 0.9994
-inverse_log_pl, euclidean_scaled, 50, 0.9998
-inverse_log_pl, euclidean_scaled, 30, 0.9968
-inverse_log_pl, euclidean_scaled, 20, 0.98
-inverse_log_pl, euclidean_scaled, 10, 0.8116
-inverse_log_pl, euclidean_scaled, 5, 0.4824
-inverse_log_pl, normalised_with_identity, 300, 0.9994
-inverse_log_pl, normalised_with_identity, 100, 0.9996
-inverse_log_pl, normalised_with_identity, 50, 0.9994
-inverse_log_pl, normalised_with_identity, 30, 0.996
-inverse_log_pl, normalised_with_identity, 20, 0.9796
-inverse_log_pl, normalised_with_identity, 10, 0.8148
-inverse_log_pl, normalised_with_identity, 5, 0.477
+'l2', 'normalised_with_identity', 50,1.969
+'l2', 'euclidean_scaled', 10,1.3528
+'l2', 'euclidean_scaled', 100,1.998
+'inverse_log_pl', 'normalised_with_identity', 100,0.9994
+'l1', 'normalised', 100,1.0
+'inverse_log_pl', 'normalised', 20,0.9814
+'l2', 'normalised_with_identity', 20,1.7306
+'l2', 'euclidean_scaled', 300,1.9984
+'cosine_distance', 'normalised', 5,0.4382
+'l2', 'normalised', 5,0.8352
+'l1', 'normalised', 300,0.9998
+'cosine_distance', 'normalised', 50,0.9968
+'inverse_log_pl', 'normalised', 5,0.4866
+'harmonic_mean', 'normalised', 5,0.4616
+'l2', 'normalised_with_identity', 10,1.2578
+'geometric_mean', 'normalised', 10,0.726
+'harmonic_mean', 'normalised_with_identity', 10,0.7482
+'harmonic_mean', 'euclidean_scaled', 50,0.6858
+'inverse_log_pl', 'normalised', 10,0.813
+'l1', 'normalised_with_identity', 5,0.4436
+'inverse_log_pl', 'euclidean_scaled', 50,0.9996
+'inverse_log_pl', 'normalised', 50,0.9992
+'l1', 'euclidean_scaled', 20,0.9532
+'geometric_mean', 'normalised_with_identity', 10,0.7706
+'l2', 'normalised', 300,1.9992
+'l1', 'normalised', 5,0.4384
+'cosine_distance', 'normalised_with_identity', 5,0.4398
+'l1', 'normalised_with_identity', 300,0.9578
+'inverse_log_pl', 'normalised_with_identity', 20,0.9826
+'inverse_log_pl', 'euclidean_scaled', 20,0.9786
+'harmonic_mean', 'normalised', 100,0.8316
+'l2', 'normalised', 10,1.2958
+'geometric_mean', 'normalised_with_identity', 5,0.464
+'l1', 'normalised_with_identity', 30,0.9562
+'cosine_distance', 'normalised', 20,0.9338
+'l1', 'normalised_with_identity', 10,0.7094
+'harmonic_mean', 'normalised_with_identity', 5,0.4542
+'geometric_mean', 'euclidean_scaled', 100,0.9992
+'inverse_log_pl', 'normalised', 30,0.995
+'l1', 'normalised', 30,0.9916
+'l2', 'normalised_with_identity', 300,1.9984
+'l2', 'euclidean_scaled', 30,1.9528
+'geometric_mean', 'euclidean_scaled', 50,0.9938
+'cosine_distance', 'euclidean_scaled', 10,0.7118
+'harmonic_mean', 'normalised', 50,0.7522
+'l1', 'normalised_with_identity', 50,0.9884
+'inverse_log_pl', 'normalised_with_identity', 30,0.9964
+'harmonic_mean', 'normalised', 30,0.2622
+'geometric_mean', 'normalised', 300,0.9986
+'inverse_log_pl', 'normalised_with_identity', 50,0.9994
+'inverse_log_pl', 'euclidean_scaled', 100,0.9998
+'cosine_distance', 'normalised', 10,0.7008
+'harmonic_mean', 'euclidean_scaled', 20,0.5326
+'l1', 'euclidean_scaled', 30,0.9896
+'inverse_log_pl', 'euclidean_scaled', 300,0.9994
+'inverse_log_pl', 'normalised_with_identity', 10,0.8118
+'geometric_mean', 'normalised', 50,0.9902
+'l1', 'euclidean_scaled', 50,0.9984
+'l2', 'normalised_with_identity', 5,0.8336
+'geometric_mean', 'normalised', 5,0.4578
+'l2', 'normalised', 50,1.9936
+'harmonic_mean', 'normalised_with_identity', 50,0.9532
+'cosine_distance', 'euclidean_scaled', 5,0.4254
+'geometric_mean', 'normalised', 20,0.9404
+'cosine_distance', 'normalised_with_identity', 10,0.7152
+'geometric_mean', 'normalised_with_identity', 30,0.9718
+'cosine_distance', 'euclidean_scaled', 30,0.9826
+'harmonic_mean', 'normalised_with_identity', 20,0.8938
+'l2', 'euclidean_scaled', 50,1.9918
+'l2', 'euclidean_scaled', 5,0.8332
+'harmonic_mean', 'normalised', 20,0.86
+'l1', 'normalised_with_identity', 20,0.9032
+'cosine_distance', 'normalised_with_identity', 300,0.9994
+'inverse_log_pl', 'normalised', 300,0.9996
+'l1', 'euclidean_scaled', 5,0.4422
+'harmonic_mean', 'euclidean_scaled', 30,0.5952
+'cosine_distance', 'normalised_with_identity', 100,0.999
+'l1', 'normalised', 20,0.9504
+'inverse_log_pl', 'euclidean_scaled', 10,0.8132
+'l2', 'normalised_with_identity', 30,1.8724
+'inverse_log_pl', 'normalised_with_identity', 5,0.4792
+'l2', 'normalised', 20,1.811
+'geometric_mean', 'normalised', 30,0.9208
+'cosine_distance', 'normalised_with_identity', 20,0.9368
+'cosine_distance', 'normalised', 100,0.9994
+'geometric_mean', 'normalised_with_identity', 20,0.9394
+'harmonic_mean', 'normalised_with_identity', 30,0.9188
+'geometric_mean', 'euclidean_scaled', 30,0.9554
+'geometric_mean', 'normalised_with_identity', 50,0.989
+'l2', 'normalised', 100,1.9992
+'cosine_distance', 'euclidean_scaled', 50,0.998
+'inverse_log_pl', 'normalised_with_identity', 300,0.9998
+'harmonic_mean', 'normalised_with_identity', 300,0.9526
+'inverse_log_pl', 'normalised', 100,0.9998
+'l1', 'normalised_with_identity', 100,0.9934
+'cosine_distance', 'normalised', 30,0.9816
+'harmonic_mean', 'normalised', 300,0.815
+'l1', 'normalised', 50,0.9986
+'cosine_distance', 'normalised', 300,0.9994
+'cosine_distance', 'euclidean_scaled', 20,0.9322
+'inverse_log_pl', 'euclidean_scaled', 5,0.4754
+'cosine_distance', 'normalised_with_identity', 30,0.9832
+'l2', 'euclidean_scaled', 20,1.8416
+'cosine_distance', 'normalised_with_identity', 50,0.9982
+'harmonic_mean', 'normalised', 10,0.6732
+'cosine_distance', 'euclidean_scaled', 100,0.9996
+'geometric_mean', 'normalised_with_identity', 100,0.9894
+'l2', 'normalised_with_identity', 100,1.9958
+'cosine_distance', 'euclidean_scaled', 300,0.9992
+'geometric_mean', 'normalised_with_identity', 300,0.9442
+'harmonic_mean', 'euclidean_scaled', 5,0.3516
+'geometric_mean', 'euclidean_scaled', 5,0.4426
+'harmonic_mean', 'euclidean_scaled', 10,0.4234
+'l2', 'normalised', 30,1.9426
+'geometric_mean', 'normalised', 100,0.999
+'geometric_mean', 'euclidean_scaled', 10,0.6498
+'geometric_mean', 'euclidean_scaled', 20,0.889
+'l1', 'euclidean_scaled', 300,0.9996
+'inverse_log_pl', 'euclidean_scaled', 30,0.9972
+'harmonic_mean', 'normalised_with_identity', 100,0.9694
+'harmonic_mean', 'euclidean_scaled', 300,0.4752
+'l1', 'euclidean_scaled', 100,1.0
+'l1', 'euclidean_scaled', 10,0.7564
+'harmonic_mean', 'euclidean_scaled', 100,0.5166
+'l1', 'normalised', 10,0.7374
+'geometric_mean', 'euclidean_scaled', 300,0.9996

diff --git a/find_best_caesar_break_parameters-2.py b/find_best_caesar_break_parameters-2.py
index 88ca06c3f806288a0352c605c62650e4f00d3396..fce55f6f94d1644ec25f15f9bd7b92bc5b02bbca 100644 (file)
--- a/find_best_caesar_break_parameters-2.py
+++ b/find_best_caesar_break_parameters-2.py
@@ -4,8 +4,6 @@ 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()]))
@@ -17,7 +15,7 @@ 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.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, 
@@ -55,8 +53,9 @@ def eval_one_parameter_set(metric, scaling, message_length):
 
 def show_results():
     with open('caesar_break_parameter_trials.csv', 'w') as f:
+        print('metric,scaling,message_length,score', file = f)
         for (k, v) in scores.items():
-            print(str(k)[1:-1], v, sep=",", file=f)
+            print(str(k)[1:-1], v / trials, sep=",", file=f)
 
 eval_all()
 show_results()

diff --git a/find_best_caesar_break_parameters.py b/find_best_caesar_break_parameters.py
index 246400ff65a6628b433e57c237fbf0f493f2f593..a07f30f096684ac3f282be95fb3ecfe1f7eba45a 100644 (file)
--- a/find_best_caesar_break_parameters.py
+++ b/find_best_caesar_break_parameters.py
@@ -3,8 +3,6 @@ import collections
 from cipher import *
 from cipherbreak import *
 
-print('Loading...')
-
 corpus = sanitise(''.join([open('shakespeare.txt', 'r').read(), 
     open('sherlock-holmes.txt', 'r').read(), 
     open('war-and-peace.txt', 'r').read()]))
@@ -16,7 +14,7 @@ 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.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, 
@@ -32,18 +30,12 @@ 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)
 
-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)
@@ -55,11 +47,10 @@ with open('caesar_break_parameter_trials.csv', 'w') as f:
                                                       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)
+                        scores[(metric['name'], scaling['name'], message_length)] += 1 
                 print(', '.join([metric['name'], 
                                  scaling['name'], 
                                  str(message_length), 
-                                 str(scores[metric['name']][scaling['name']][message_length] / trials) ]),
+                                 str(scores[(metric['name'], scaling['name'], message_length)] / trials) ]),
                     file = f)
 print()