forked from tesseract-ocr/tesseract
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcluster.cpp
2436 lines (2191 loc) · 93.9 KB
/
cluster.cpp
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/******************************************************************************
** Filename: cluster.cpp
** Purpose: Routines for clustering points in N-D space
** Author: Dan Johnson
**
** (c) Copyright Hewlett-Packard Company, 1988.
** Licensed under the Apache License, Version 2.0 (the "License");
** you may not use this file except in compliance with the License.
** You may obtain a copy of the License at
** http://www.apache.org/licenses/LICENSE-2.0
** Unless required by applicable law or agreed to in writing, software
** distributed under the License is distributed on an "AS IS" BASIS,
** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
** See the License for the specific language governing permissions and
** limitations under the License.
*****************************************************************************/
#include <cfloat> // for FLT_MAX
#include <cmath>
#include <vector> // for std::vector
#include "cluster.h"
#include "cutil.h" // for void_proc
#include "emalloc.h"
#include "genericheap.h"
#include "helpers.h"
#include "kdpair.h"
#include "matrix.h"
#include "tprintf.h"
#define HOTELLING 1 // If true use Hotelling's test to decide where to split.
#define FTABLE_X 10 // Size of FTable.
#define FTABLE_Y 100 // Size of FTable.
// Table of values approximating the cumulative F-distribution for a confidence of 1%.
const double FTable[FTABLE_Y][FTABLE_X] = {
{4052.19, 4999.52, 5403.34, 5624.62, 5763.65, 5858.97, 5928.33, 5981.10, 6022.50, 6055.85,},
{98.502, 99.000, 99.166, 99.249, 99.300, 99.333, 99.356, 99.374, 99.388, 99.399,},
{34.116, 30.816, 29.457, 28.710, 28.237, 27.911, 27.672, 27.489, 27.345, 27.229,},
{21.198, 18.000, 16.694, 15.977, 15.522, 15.207, 14.976, 14.799, 14.659, 14.546,},
{16.258, 13.274, 12.060, 11.392, 10.967, 10.672, 10.456, 10.289, 10.158, 10.051,},
{13.745, 10.925, 9.780, 9.148, 8.746, 8.466, 8.260, 8.102, 7.976, 7.874,},
{12.246, 9.547, 8.451, 7.847, 7.460, 7.191, 6.993, 6.840, 6.719, 6.620,},
{11.259, 8.649, 7.591, 7.006, 6.632, 6.371, 6.178, 6.029, 5.911, 5.814,},
{10.561, 8.022, 6.992, 6.422, 6.057, 5.802, 5.613, 5.467, 5.351, 5.257,},
{10.044, 7.559, 6.552, 5.994, 5.636, 5.386, 5.200, 5.057, 4.942, 4.849,},
{ 9.646, 7.206, 6.217, 5.668, 5.316, 5.069, 4.886, 4.744, 4.632, 4.539,},
{ 9.330, 6.927, 5.953, 5.412, 5.064, 4.821, 4.640, 4.499, 4.388, 4.296,},
{ 9.074, 6.701, 5.739, 5.205, 4.862, 4.620, 4.441, 4.302, 4.191, 4.100,},
{ 8.862, 6.515, 5.564, 5.035, 4.695, 4.456, 4.278, 4.140, 4.030, 3.939,},
{ 8.683, 6.359, 5.417, 4.893, 4.556, 4.318, 4.142, 4.004, 3.895, 3.805,},
{ 8.531, 6.226, 5.292, 4.773, 4.437, 4.202, 4.026, 3.890, 3.780, 3.691,},
{ 8.400, 6.112, 5.185, 4.669, 4.336, 4.102, 3.927, 3.791, 3.682, 3.593,},
{ 8.285, 6.013, 5.092, 4.579, 4.248, 4.015, 3.841, 3.705, 3.597, 3.508,},
{ 8.185, 5.926, 5.010, 4.500, 4.171, 3.939, 3.765, 3.631, 3.523, 3.434,},
{ 8.096, 5.849, 4.938, 4.431, 4.103, 3.871, 3.699, 3.564, 3.457, 3.368,},
{ 8.017, 5.780, 4.874, 4.369, 4.042, 3.812, 3.640, 3.506, 3.398, 3.310,},
{ 7.945, 5.719, 4.817, 4.313, 3.988, 3.758, 3.587, 3.453, 3.346, 3.258,},
{ 7.881, 5.664, 4.765, 4.264, 3.939, 3.710, 3.539, 3.406, 3.299, 3.211,},
{ 7.823, 5.614, 4.718, 4.218, 3.895, 3.667, 3.496, 3.363, 3.256, 3.168,},
{ 7.770, 5.568, 4.675, 4.177, 3.855, 3.627, 3.457, 3.324, 3.217, 3.129,},
{ 7.721, 5.526, 4.637, 4.140, 3.818, 3.591, 3.421, 3.288, 3.182, 3.094,},
{ 7.677, 5.488, 4.601, 4.106, 3.785, 3.558, 3.388, 3.256, 3.149, 3.062,},
{ 7.636, 5.453, 4.568, 4.074, 3.754, 3.528, 3.358, 3.226, 3.120, 3.032,},
{ 7.598, 5.420, 4.538, 4.045, 3.725, 3.499, 3.330, 3.198, 3.092, 3.005,},
{ 7.562, 5.390, 4.510, 4.018, 3.699, 3.473, 3.305, 3.173, 3.067, 2.979,},
{ 7.530, 5.362, 4.484, 3.993, 3.675, 3.449, 3.281, 3.149, 3.043, 2.955,},
{ 7.499, 5.336, 4.459, 3.969, 3.652, 3.427, 3.258, 3.127, 3.021, 2.934,},
{ 7.471, 5.312, 4.437, 3.948, 3.630, 3.406, 3.238, 3.106, 3.000, 2.913,},
{ 7.444, 5.289, 4.416, 3.927, 3.611, 3.386, 3.218, 3.087, 2.981, 2.894,},
{ 7.419, 5.268, 4.396, 3.908, 3.592, 3.368, 3.200, 3.069, 2.963, 2.876,},
{ 7.396, 5.248, 4.377, 3.890, 3.574, 3.351, 3.183, 3.052, 2.946, 2.859,},
{ 7.373, 5.229, 4.360, 3.873, 3.558, 3.334, 3.167, 3.036, 2.930, 2.843,},
{ 7.353, 5.211, 4.343, 3.858, 3.542, 3.319, 3.152, 3.021, 2.915, 2.828,},
{ 7.333, 5.194, 4.327, 3.843, 3.528, 3.305, 3.137, 3.006, 2.901, 2.814,},
{ 7.314, 5.179, 4.313, 3.828, 3.514, 3.291, 3.124, 2.993, 2.888, 2.801,},
{ 7.296, 5.163, 4.299, 3.815, 3.501, 3.278, 3.111, 2.980, 2.875, 2.788,},
{ 7.280, 5.149, 4.285, 3.802, 3.488, 3.266, 3.099, 2.968, 2.863, 2.776,},
{ 7.264, 5.136, 4.273, 3.790, 3.476, 3.254, 3.087, 2.957, 2.851, 2.764,},
{ 7.248, 5.123, 4.261, 3.778, 3.465, 3.243, 3.076, 2.946, 2.840, 2.754,},
{ 7.234, 5.110, 4.249, 3.767, 3.454, 3.232, 3.066, 2.935, 2.830, 2.743,},
{ 7.220, 5.099, 4.238, 3.757, 3.444, 3.222, 3.056, 2.925, 2.820, 2.733,},
{ 7.207, 5.087, 4.228, 3.747, 3.434, 3.213, 3.046, 2.916, 2.811, 2.724,},
{ 7.194, 5.077, 4.218, 3.737, 3.425, 3.204, 3.037, 2.907, 2.802, 2.715,},
{ 7.182, 5.066, 4.208, 3.728, 3.416, 3.195, 3.028, 2.898, 2.793, 2.706,},
{ 7.171, 5.057, 4.199, 3.720, 3.408, 3.186, 3.020, 2.890, 2.785, 2.698,},
{ 7.159, 5.047, 4.191, 3.711, 3.400, 3.178, 3.012, 2.882, 2.777, 2.690,},
{ 7.149, 5.038, 4.182, 3.703, 3.392, 3.171, 3.005, 2.874, 2.769, 2.683,},
{ 7.139, 5.030, 4.174, 3.695, 3.384, 3.163, 2.997, 2.867, 2.762, 2.675,},
{ 7.129, 5.021, 4.167, 3.688, 3.377, 3.156, 2.990, 2.860, 2.755, 2.668,},
{ 7.119, 5.013, 4.159, 3.681, 3.370, 3.149, 2.983, 2.853, 2.748, 2.662,},
{ 7.110, 5.006, 4.152, 3.674, 3.363, 3.143, 2.977, 2.847, 2.742, 2.655,},
{ 7.102, 4.998, 4.145, 3.667, 3.357, 3.136, 2.971, 2.841, 2.736, 2.649,},
{ 7.093, 4.991, 4.138, 3.661, 3.351, 3.130, 2.965, 2.835, 2.730, 2.643,},
{ 7.085, 4.984, 4.132, 3.655, 3.345, 3.124, 2.959, 2.829, 2.724, 2.637,},
{ 7.077, 4.977, 4.126, 3.649, 3.339, 3.119, 2.953, 2.823, 2.718, 2.632,},
{ 7.070, 4.971, 4.120, 3.643, 3.333, 3.113, 2.948, 2.818, 2.713, 2.626,},
{ 7.062, 4.965, 4.114, 3.638, 3.328, 3.108, 2.942, 2.813, 2.708, 2.621,},
{ 7.055, 4.959, 4.109, 3.632, 3.323, 3.103, 2.937, 2.808, 2.703, 2.616,},
{ 7.048, 4.953, 4.103, 3.627, 3.318, 3.098, 2.932, 2.803, 2.698, 2.611,},
{ 7.042, 4.947, 4.098, 3.622, 3.313, 3.093, 2.928, 2.798, 2.693, 2.607,},
{ 7.035, 4.942, 4.093, 3.618, 3.308, 3.088, 2.923, 2.793, 2.689, 2.602,},
{ 7.029, 4.937, 4.088, 3.613, 3.304, 3.084, 2.919, 2.789, 2.684, 2.598,},
{ 7.023, 4.932, 4.083, 3.608, 3.299, 3.080, 2.914, 2.785, 2.680, 2.593,},
{ 7.017, 4.927, 4.079, 3.604, 3.295, 3.075, 2.910, 2.781, 2.676, 2.589,},
{ 7.011, 4.922, 4.074, 3.600, 3.291, 3.071, 2.906, 2.777, 2.672, 2.585,},
{ 7.006, 4.917, 4.070, 3.596, 3.287, 3.067, 2.902, 2.773, 2.668, 2.581,},
{ 7.001, 4.913, 4.066, 3.591, 3.283, 3.063, 2.898, 2.769, 2.664, 2.578,},
{ 6.995, 4.908, 4.062, 3.588, 3.279, 3.060, 2.895, 2.765, 2.660, 2.574,},
{ 6.990, 4.904, 4.058, 3.584, 3.275, 3.056, 2.891, 2.762, 2.657, 2.570,},
{ 6.985, 4.900, 4.054, 3.580, 3.272, 3.052, 2.887, 2.758, 2.653, 2.567,},
{ 6.981, 4.896, 4.050, 3.577, 3.268, 3.049, 2.884, 2.755, 2.650, 2.563,},
{ 6.976, 4.892, 4.047, 3.573, 3.265, 3.046, 2.881, 2.751, 2.647, 2.560,},
{ 6.971, 4.888, 4.043, 3.570, 3.261, 3.042, 2.877, 2.748, 2.644, 2.557,},
{ 6.967, 4.884, 4.040, 3.566, 3.258, 3.039, 2.874, 2.745, 2.640, 2.554,},
{ 6.963, 4.881, 4.036, 3.563, 3.255, 3.036, 2.871, 2.742, 2.637, 2.551,},
{ 6.958, 4.877, 4.033, 3.560, 3.252, 3.033, 2.868, 2.739, 2.634, 2.548,},
{ 6.954, 4.874, 4.030, 3.557, 3.249, 3.030, 2.865, 2.736, 2.632, 2.545,},
{ 6.950, 4.870, 4.027, 3.554, 3.246, 3.027, 2.863, 2.733, 2.629, 2.542,},
{ 6.947, 4.867, 4.024, 3.551, 3.243, 3.025, 2.860, 2.731, 2.626, 2.539,},
{ 6.943, 4.864, 4.021, 3.548, 3.240, 3.022, 2.857, 2.728, 2.623, 2.537,},
{ 6.939, 4.861, 4.018, 3.545, 3.238, 3.019, 2.854, 2.725, 2.621, 2.534,},
{ 6.935, 4.858, 4.015, 3.543, 3.235, 3.017, 2.852, 2.723, 2.618, 2.532,},
{ 6.932, 4.855, 4.012, 3.540, 3.233, 3.014, 2.849, 2.720, 2.616, 2.529,},
{ 6.928, 4.852, 4.010, 3.538, 3.230, 3.012, 2.847, 2.718, 2.613, 2.527,},
{ 6.925, 4.849, 4.007, 3.535, 3.228, 3.009, 2.845, 2.715, 2.611, 2.524,},
{ 6.922, 4.846, 4.004, 3.533, 3.225, 3.007, 2.842, 2.713, 2.609, 2.522,},
{ 6.919, 4.844, 4.002, 3.530, 3.223, 3.004, 2.840, 2.711, 2.606, 2.520,},
{ 6.915, 4.841, 3.999, 3.528, 3.221, 3.002, 2.838, 2.709, 2.604, 2.518,},
{ 6.912, 4.838, 3.997, 3.525, 3.218, 3.000, 2.835, 2.706, 2.602, 2.515,},
{ 6.909, 4.836, 3.995, 3.523, 3.216, 2.998, 2.833, 2.704, 2.600, 2.513,},
{ 6.906, 4.833, 3.992, 3.521, 3.214, 2.996, 2.831, 2.702, 2.598, 2.511,},
{ 6.904, 4.831, 3.990, 3.519, 3.212, 2.994, 2.829, 2.700, 2.596, 2.509,},
{ 6.901, 4.829, 3.988, 3.517, 3.210, 2.992, 2.827, 2.698, 2.594, 2.507,},
{ 6.898, 4.826, 3.986, 3.515, 3.208, 2.990, 2.825, 2.696, 2.592, 2.505,},
{ 6.895, 4.824, 3.984, 3.513, 3.206, 2.988, 2.823, 2.694, 2.590, 2.503}
};
/** define the variance which will be used as a minimum variance for any
dimension of any feature. Since most features are calculated from numbers
with a precision no better than 1 in 128, the variance should never be
less than the square of this number for parameters whose range is 1. */
#define MINVARIANCE 0.0004
/** define the absolute minimum number of samples which must be present in
order to accurately test hypotheses about underlying probability
distributions. Define separately the minimum samples that are needed
before a statistical analysis is attempted; this number should be
equal to MINSAMPLES but can be set to a lower number for early testing
when very few samples are available. */
#define MINSAMPLESPERBUCKET 5
#define MINSAMPLES (MINBUCKETS * MINSAMPLESPERBUCKET)
#define MINSAMPLESNEEDED 1
/** define the size of the table which maps normalized samples to
histogram buckets. Also define the number of standard deviations
in a normal distribution which are considered to be significant.
The mapping table will be defined in such a way that it covers
the specified number of standard deviations on either side of
the mean. BUCKETTABLESIZE should always be even. */
#define BUCKETTABLESIZE 1024
#define NORMALEXTENT 3.0
struct TEMPCLUSTER {
CLUSTER *Cluster;
CLUSTER *Neighbor;
};
using ClusterPair = tesseract::KDPairInc<float, TEMPCLUSTER*>;
using ClusterHeap = tesseract::GenericHeap<ClusterPair>;
struct STATISTICS {
float AvgVariance;
float *CoVariance;
float *Min; // largest negative distance from the mean
float *Max; // largest positive distance from the mean
};
struct BUCKETS {
DISTRIBUTION Distribution; // distribution being tested for
uint32_t SampleCount; // # of samples in histogram
double Confidence; // confidence level of test
double ChiSquared; // test threshold
uint16_t NumberOfBuckets; // number of cells in histogram
uint16_t Bucket[BUCKETTABLESIZE]; // mapping to histogram buckets
uint32_t *Count; // frequency of occurrence histogram
float *ExpectedCount; // expected histogram
};
struct CHISTRUCT{
uint16_t DegreesOfFreedom;
double Alpha;
double ChiSquared;
};
// For use with KDWalk / MakePotentialClusters
struct ClusteringContext {
ClusterHeap *heap; // heap used to hold temp clusters, "best" on top
TEMPCLUSTER *candidates; // array of potential clusters
KDTREE *tree; // kd-tree to be searched for neighbors
int32_t next; // next candidate to be used
};
typedef double (*DENSITYFUNC) (int32_t);
typedef double (*SOLVEFUNC) (CHISTRUCT *, double);
#define Odd(N) ((N)%2)
#define Mirror(N,R) ((R) - (N) - 1)
#define Abs(N) (((N) < 0) ? (-(N)) : (N))
//--------------Global Data Definitions and Declarations----------------------
/** the following variables describe a discrete normal distribution
which is used by NormalDensity() and NormalBucket(). The
constant NORMALEXTENT determines how many standard
deviations of the distribution are mapped onto the fixed
discrete range of x. x=0 is mapped to -NORMALEXTENT standard
deviations and x=BUCKETTABLESIZE is mapped to
+NORMALEXTENT standard deviations. */
#define SqrtOf2Pi 2.506628275
static const double kNormalStdDev = BUCKETTABLESIZE / (2.0 * NORMALEXTENT);
static const double kNormalVariance =
(BUCKETTABLESIZE * BUCKETTABLESIZE) / (4.0 * NORMALEXTENT * NORMALEXTENT);
static const double kNormalMagnitude =
(2.0 * NORMALEXTENT) / (SqrtOf2Pi * BUCKETTABLESIZE);
static const double kNormalMean = BUCKETTABLESIZE / 2;
/** define lookup tables used to compute the number of histogram buckets
that should be used for a given number of samples. */
#define LOOKUPTABLESIZE 8
#define MAXDEGREESOFFREEDOM MAXBUCKETS
static const uint32_t kCountTable[LOOKUPTABLESIZE] = {
MINSAMPLES, 200, 400, 600, 800, 1000, 1500, 2000
}; // number of samples
static const uint16_t kBucketsTable[LOOKUPTABLESIZE] = {
MINBUCKETS, 16, 20, 24, 27, 30, 35, MAXBUCKETS
}; // number of buckets
/*-------------------------------------------------------------------------
Private Function Prototypes
--------------------------------------------------------------------------*/
static void CreateClusterTree(CLUSTERER* Clusterer);
static void MakePotentialClusters(ClusteringContext* context, CLUSTER* Cluster,
int32_t Level);
static CLUSTER* FindNearestNeighbor(KDTREE*Tree, CLUSTER* Cluster,
float* Distance);
static CLUSTER* MakeNewCluster(CLUSTERER* Clusterer, TEMPCLUSTER* TempCluster);
static void ComputePrototypes(CLUSTERER* Clusterer, CLUSTERCONFIG* Config);
static PROTOTYPE* MakePrototype(CLUSTERER* Clusterer, CLUSTERCONFIG* Config,
CLUSTER* Cluster);
static PROTOTYPE* MakeDegenerateProto(uint16_t N,
CLUSTER* Cluster, STATISTICS* Statistics,
PROTOSTYLE Style, int32_t MinSamples);
static PROTOTYPE* TestEllipticalProto(CLUSTERER* Clusterer,
CLUSTERCONFIG* Config, CLUSTER* Cluster,
STATISTICS* Statistics);
static PROTOTYPE* MakeSphericalProto(CLUSTERER* Clusterer,
CLUSTER* Cluster, STATISTICS* Statistics,
BUCKETS* Buckets);
static PROTOTYPE* MakeEllipticalProto(CLUSTERER* Clusterer,
CLUSTER* Cluster, STATISTICS* Statistics,
BUCKETS* Buckets);
static PROTOTYPE* MakeMixedProto(CLUSTERER* Clusterer,
CLUSTER* Cluster, STATISTICS* Statistics,
BUCKETS* NormalBuckets, double Confidence);
static void MakeDimRandom(uint16_t i, PROTOTYPE* Proto, PARAM_DESC* ParamDesc);
static void MakeDimUniform(uint16_t i, PROTOTYPE* Proto, STATISTICS* Statistics);
static STATISTICS* ComputeStatistics(int16_t N, PARAM_DESC ParamDesc[],
CLUSTER* Cluster);
static PROTOTYPE* NewSphericalProto(uint16_t N, CLUSTER* Cluster,
STATISTICS* Statistics);
static PROTOTYPE* NewEllipticalProto(int16_t N, CLUSTER* Cluster,
STATISTICS* Statistics);
static PROTOTYPE* NewMixedProto(int16_t N, CLUSTER *Cluster, STATISTICS *Statistics);
static PROTOTYPE* NewSimpleProto(int16_t N, CLUSTER *Cluster);
static bool Independent(PARAM_DESC* ParamDesc,
int16_t N, float* CoVariance, float Independence);
static BUCKETS *GetBuckets(CLUSTERER* clusterer,
DISTRIBUTION Distribution,
uint32_t SampleCount,
double Confidence);
static BUCKETS *MakeBuckets(DISTRIBUTION Distribution,
uint32_t SampleCount,
double Confidence);
static uint16_t OptimumNumberOfBuckets(uint32_t SampleCount);
static double ComputeChiSquared(uint16_t DegreesOfFreedom, double Alpha);
static double NormalDensity(int32_t x);
static double UniformDensity(int32_t x);
static double Integral(double f1, double f2, double Dx);
static void FillBuckets(BUCKETS *Buckets,
CLUSTER *Cluster,
uint16_t Dim,
PARAM_DESC *ParamDesc,
float Mean,
float StdDev);
static uint16_t NormalBucket(PARAM_DESC *ParamDesc,
float x,
float Mean,
float StdDev);
static uint16_t UniformBucket(PARAM_DESC *ParamDesc,
float x,
float Mean,
float StdDev);
static bool DistributionOK(BUCKETS* Buckets);
static void FreeStatistics(STATISTICS *Statistics);
static void FreeBuckets(BUCKETS *Buckets);
static void FreeCluster(CLUSTER *Cluster);
static uint16_t DegreesOfFreedom(DISTRIBUTION Distribution, uint16_t HistogramBuckets);
static void AdjustBuckets(BUCKETS *Buckets, uint32_t NewSampleCount);
static void InitBuckets(BUCKETS *Buckets);
static int AlphaMatch(void *arg1, // CHISTRUCT *ChiStruct,
void *arg2); // CHISTRUCT *SearchKey);
static CHISTRUCT *NewChiStruct(uint16_t DegreesOfFreedom, double Alpha);
static double Solve(SOLVEFUNC Function,
void *FunctionParams,
double InitialGuess,
double Accuracy);
static double ChiArea(CHISTRUCT *ChiParams, double x);
static bool MultipleCharSamples(CLUSTERER* Clusterer,
CLUSTER* Cluster,
float MaxIllegal);
static double InvertMatrix(const float* input, int size, float* inv);
//--------------------------Public Code--------------------------------------
/**
* This routine creates a new clusterer data structure,
* initializes it, and returns a pointer to it.
*
* @param SampleSize number of dimensions in feature space
* @param ParamDesc description of each dimension
* @return pointer to the new clusterer data structure
*/
CLUSTERER *
MakeClusterer (int16_t SampleSize, const PARAM_DESC ParamDesc[]) {
CLUSTERER *Clusterer;
int i;
// allocate main clusterer data structure and init simple fields
Clusterer = (CLUSTERER *) Emalloc (sizeof (CLUSTERER));
Clusterer->SampleSize = SampleSize;
Clusterer->NumberOfSamples = 0;
Clusterer->NumChar = 0;
// init fields which will not be used initially
Clusterer->Root = nullptr;
Clusterer->ProtoList = NIL_LIST;
// maintain a copy of param descriptors in the clusterer data structure
Clusterer->ParamDesc =
(PARAM_DESC *) Emalloc (SampleSize * sizeof (PARAM_DESC));
for (i = 0; i < SampleSize; i++) {
Clusterer->ParamDesc[i].Circular = ParamDesc[i].Circular;
Clusterer->ParamDesc[i].NonEssential = ParamDesc[i].NonEssential;
Clusterer->ParamDesc[i].Min = ParamDesc[i].Min;
Clusterer->ParamDesc[i].Max = ParamDesc[i].Max;
Clusterer->ParamDesc[i].Range = ParamDesc[i].Max - ParamDesc[i].Min;
Clusterer->ParamDesc[i].HalfRange = Clusterer->ParamDesc[i].Range / 2;
Clusterer->ParamDesc[i].MidRange =
(ParamDesc[i].Max + ParamDesc[i].Min) / 2;
}
// allocate a kd tree to hold the samples
Clusterer->KDTree = MakeKDTree (SampleSize, ParamDesc);
// Initialize cache of histogram buckets to minimize recomputing them.
for (int d = 0; d < DISTRIBUTION_COUNT; ++d) {
for (int c = 0; c < MAXBUCKETS + 1 - MINBUCKETS; ++c)
Clusterer->bucket_cache[d][c] = nullptr;
}
return Clusterer;
} // MakeClusterer
/**
* This routine creates a new sample data structure to hold
* the specified feature. This sample is added to the clusterer
* data structure (so that it knows which samples are to be
* clustered later), and a pointer to the sample is returned to
* the caller.
*
* @param Clusterer clusterer data structure to add sample to
* @param Feature feature to be added to clusterer
* @param CharID unique ident. of char that sample came from
*
* @return Pointer to the new sample data structure
*/
SAMPLE* MakeSample(CLUSTERER * Clusterer, const float* Feature,
int32_t CharID) {
SAMPLE *Sample;
int i;
// see if the samples have already been clustered - if so trap an error
// Can't add samples after they have been clustered.
ASSERT_HOST(Clusterer->Root == nullptr);
// allocate the new sample and initialize it
Sample = (SAMPLE *) Emalloc (sizeof (SAMPLE) +
(Clusterer->SampleSize -
1) * sizeof (float));
Sample->Clustered = FALSE;
Sample->Prototype = FALSE;
Sample->SampleCount = 1;
Sample->Left = nullptr;
Sample->Right = nullptr;
Sample->CharID = CharID;
for (i = 0; i < Clusterer->SampleSize; i++)
Sample->Mean[i] = Feature[i];
// add the sample to the KD tree - keep track of the total # of samples
Clusterer->NumberOfSamples++;
KDStore(Clusterer->KDTree, Sample->Mean, Sample);
if (CharID >= Clusterer->NumChar)
Clusterer->NumChar = CharID + 1;
// execute hook for monitoring clustering operation
// (*SampleCreationHook)(Sample);
return (Sample);
} // MakeSample
/**
* This routine first checks to see if the samples in this
* clusterer have already been clustered before; if so, it does
* not bother to recreate the cluster tree. It simply recomputes
* the prototypes based on the new Config info.
*
* If the samples have not been clustered before, the
* samples in the KD tree are formed into a cluster tree and then
* the prototypes are computed from the cluster tree.
*
* In either case this routine returns a pointer to a
* list of prototypes that best represent the samples given
* the constraints specified in Config.
*
* @param Clusterer data struct containing samples to be clustered
* @param Config parameters which control clustering process
*
* @return Pointer to a list of prototypes
*/
LIST ClusterSamples(CLUSTERER *Clusterer, CLUSTERCONFIG *Config) {
//only create cluster tree if samples have never been clustered before
if (Clusterer->Root == nullptr)
CreateClusterTree(Clusterer);
//deallocate the old prototype list if one exists
FreeProtoList (&Clusterer->ProtoList);
Clusterer->ProtoList = NIL_LIST;
//compute prototypes starting at the root node in the tree
ComputePrototypes(Clusterer, Config);
// We don't need the cluster pointers in the protos any more, so null them
// out, which makes it safe to delete the clusterer.
LIST proto_list = Clusterer->ProtoList;
iterate(proto_list) {
PROTOTYPE *proto = reinterpret_cast<PROTOTYPE *>(first_node(proto_list));
proto->Cluster = nullptr;
}
return Clusterer->ProtoList;
} // ClusterSamples
/**
* This routine frees all of the memory allocated to the
* specified data structure. It will not, however, free
* the memory used by the prototype list. The pointers to
* the clusters for each prototype in the list will be set
* to nullptr to indicate that the cluster data structures no
* longer exist. Any sample lists that have been obtained
* via calls to GetSamples are no longer valid.
* @param Clusterer pointer to data structure to be freed
* @return None
*/
void FreeClusterer(CLUSTERER *Clusterer) {
if (Clusterer != nullptr) {
free(Clusterer->ParamDesc);
if (Clusterer->KDTree != nullptr)
FreeKDTree (Clusterer->KDTree);
if (Clusterer->Root != nullptr)
FreeCluster (Clusterer->Root);
// Free up all used buckets structures.
for (int d = 0; d < DISTRIBUTION_COUNT; ++d) {
for (int c = 0; c < MAXBUCKETS + 1 - MINBUCKETS; ++c)
if (Clusterer->bucket_cache[d][c] != nullptr)
FreeBuckets(Clusterer->bucket_cache[d][c]);
}
free(Clusterer);
}
} // FreeClusterer
/**
* This routine frees all of the memory allocated to the
* specified list of prototypes. The clusters which are
* pointed to by the prototypes are not freed.
* @param ProtoList pointer to list of prototypes to be freed
* @return None
*/
void FreeProtoList(LIST *ProtoList) {
destroy_nodes(*ProtoList, FreePrototype);
} // FreeProtoList
/**
* This routine deallocates the memory consumed by the specified
* prototype and modifies the corresponding cluster so that it
* is no longer marked as a prototype. The cluster is NOT
* deallocated by this routine.
* @param arg prototype data structure to be deallocated
* @return None
*/
void FreePrototype(void *arg) { //PROTOTYPE *Prototype)
PROTOTYPE *Prototype = (PROTOTYPE *) arg;
// unmark the corresponding cluster (if there is one
if (Prototype->Cluster != nullptr)
Prototype->Cluster->Prototype = FALSE;
// deallocate the prototype statistics and then the prototype itself
free(Prototype->Distrib);
free(Prototype->Mean);
if (Prototype->Style != spherical) {
free(Prototype->Variance.Elliptical);
free(Prototype->Magnitude.Elliptical);
free(Prototype->Weight.Elliptical);
}
free(Prototype);
} // FreePrototype
/**
* This routine is used to find all of the samples which
* belong to a cluster. It starts by removing the top
* cluster on the cluster list (SearchState). If this cluster is
* a leaf it is returned. Otherwise, the right subcluster
* is pushed on the list and we continue the search in the
* left subcluster. This continues until a leaf is found.
* If all samples have been found, nullptr is returned.
* InitSampleSearch() must be called
* before NextSample() to initialize the search.
* @param SearchState ptr to list containing clusters to be searched
* @return Pointer to the next leaf cluster (sample) or nullptr.
*/
CLUSTER *NextSample(LIST *SearchState) {
CLUSTER *Cluster;
if (*SearchState == NIL_LIST)
return (nullptr);
Cluster = (CLUSTER *) first_node (*SearchState);
*SearchState = pop (*SearchState);
while (TRUE) {
if (Cluster->Left == nullptr)
return (Cluster);
*SearchState = push (*SearchState, Cluster->Right);
Cluster = Cluster->Left;
}
} // NextSample
/**
* This routine returns the mean of the specified
* prototype in the indicated dimension.
* @param Proto prototype to return mean of
* @param Dimension dimension whose mean is to be returned
* @return Mean of Prototype in Dimension
*/
float Mean(PROTOTYPE *Proto, uint16_t Dimension) {
return (Proto->Mean[Dimension]);
} // Mean
/**
* This routine returns the standard deviation of the
* prototype in the indicated dimension.
* @param Proto prototype to return standard deviation of
* @param Dimension dimension whose stddev is to be returned
* @return Standard deviation of Prototype in Dimension
*/
float StandardDeviation(PROTOTYPE *Proto, uint16_t Dimension) {
switch (Proto->Style) {
case spherical:
return ((float) sqrt ((double) Proto->Variance.Spherical));
case elliptical:
return ((float)
sqrt ((double) Proto->Variance.Elliptical[Dimension]));
case mixed:
switch (Proto->Distrib[Dimension]) {
case normal:
return ((float)
sqrt ((double) Proto->Variance.Elliptical[Dimension]));
case uniform:
case D_random:
return (Proto->Variance.Elliptical[Dimension]);
case DISTRIBUTION_COUNT:
ASSERT_HOST(!"Distribution count not allowed!");
}
}
return 0.0f;
} // StandardDeviation
/*---------------------------------------------------------------------------
Private Code
----------------------------------------------------------------------------*/
/**
* This routine performs a bottoms-up clustering on the samples
* held in the kd-tree of the Clusterer data structure. The
* result is a cluster tree. Each node in the tree represents
* a cluster which conceptually contains a subset of the samples.
* More precisely, the cluster contains all of the samples which
* are contained in its two sub-clusters. The leaves of the
* tree are the individual samples themselves; they have no
* sub-clusters. The root node of the tree conceptually contains
* all of the samples.
* @param Clusterer data structure holdings samples to be clustered
* @return None (the Clusterer data structure is changed)
*/
static void CreateClusterTree(CLUSTERER *Clusterer) {
ClusteringContext context;
ClusterPair HeapEntry;
TEMPCLUSTER *PotentialCluster;
// each sample and its nearest neighbor form a "potential" cluster
// save these in a heap with the "best" potential clusters on top
context.tree = Clusterer->KDTree;
context.candidates = (TEMPCLUSTER *)
Emalloc(Clusterer->NumberOfSamples * sizeof(TEMPCLUSTER));
context.next = 0;
context.heap = new ClusterHeap(Clusterer->NumberOfSamples);
KDWalk(context.tree, (void_proc)MakePotentialClusters, &context);
// form potential clusters into actual clusters - always do "best" first
while (context.heap->Pop(&HeapEntry)) {
PotentialCluster = HeapEntry.data;
// if main cluster of potential cluster is already in another cluster
// then we don't need to worry about it
if (PotentialCluster->Cluster->Clustered) {
continue;
}
// if main cluster is not yet clustered, but its nearest neighbor is
// then we must find a new nearest neighbor
else if (PotentialCluster->Neighbor->Clustered) {
PotentialCluster->Neighbor =
FindNearestNeighbor(context.tree, PotentialCluster->Cluster,
&HeapEntry.key);
if (PotentialCluster->Neighbor != nullptr) {
context.heap->Push(&HeapEntry);
}
}
// if neither cluster is already clustered, form permanent cluster
else {
PotentialCluster->Cluster =
MakeNewCluster(Clusterer, PotentialCluster);
PotentialCluster->Neighbor =
FindNearestNeighbor(context.tree, PotentialCluster->Cluster,
&HeapEntry.key);
if (PotentialCluster->Neighbor != nullptr) {
context.heap->Push(&HeapEntry);
}
}
}
// the root node in the cluster tree is now the only node in the kd-tree
Clusterer->Root = (CLUSTER *) RootOf(Clusterer->KDTree);
// free up the memory used by the K-D tree, heap, and temp clusters
FreeKDTree(context.tree);
Clusterer->KDTree = nullptr;
delete context.heap;
free(context.candidates);
} // CreateClusterTree
/**
* This routine is designed to be used in concert with the
* KDWalk routine. It will create a potential cluster for
* each sample in the kd-tree that is being walked. This
* potential cluster will then be pushed on the heap.
* @param context ClusteringContext (see definition above)
* @param Cluster current cluster being visited in kd-tree walk
* @param Level level of this cluster in the kd-tree
*/
static void MakePotentialClusters(ClusteringContext* context,
CLUSTER* Cluster, int32_t /*Level*/) {
ClusterPair HeapEntry;
int next = context->next;
context->candidates[next].Cluster = Cluster;
HeapEntry.data = &(context->candidates[next]);
context->candidates[next].Neighbor =
FindNearestNeighbor(context->tree,
context->candidates[next].Cluster,
&HeapEntry.key);
if (context->candidates[next].Neighbor != nullptr) {
context->heap->Push(&HeapEntry);
context->next++;
}
} // MakePotentialClusters
/**
* This routine searches the specified kd-tree for the nearest
* neighbor of the specified cluster. It actually uses the
* kd routines to find the 2 nearest neighbors since one of them
* will be the original cluster. A pointer to the nearest
* neighbor is returned, if it can be found, otherwise nullptr is
* returned. The distance between the 2 nodes is placed
* in the specified variable.
* @param Tree kd-tree to search in for nearest neighbor
* @param Cluster cluster whose nearest neighbor is to be found
* @param Distance ptr to variable to report distance found
* @return Pointer to the nearest neighbor of Cluster, or nullptr
*/
static CLUSTER*
FindNearestNeighbor(KDTREE* Tree, CLUSTER* Cluster, float* Distance)
#define MAXNEIGHBORS 2
#define MAXDISTANCE FLT_MAX
{
CLUSTER *Neighbor[MAXNEIGHBORS];
float Dist[MAXNEIGHBORS];
int NumberOfNeighbors;
int32_t i;
CLUSTER *BestNeighbor;
// find the 2 nearest neighbors of the cluster
KDNearestNeighborSearch(Tree, Cluster->Mean, MAXNEIGHBORS, MAXDISTANCE,
&NumberOfNeighbors, (void **)Neighbor, Dist);
// search for the nearest neighbor that is not the cluster itself
*Distance = MAXDISTANCE;
BestNeighbor = nullptr;
for (i = 0; i < NumberOfNeighbors; i++) {
if ((Dist[i] < *Distance) && (Neighbor[i] != Cluster)) {
*Distance = Dist[i];
BestNeighbor = Neighbor[i];
}
}
return BestNeighbor;
} // FindNearestNeighbor
/**
* This routine creates a new permanent cluster from the
* clusters specified in TempCluster. The 2 clusters in
* TempCluster are marked as "clustered" and deleted from
* the kd-tree. The new cluster is then added to the kd-tree.
* @param Clusterer current clustering environment
* @param TempCluster potential cluster to make permanent
* @return Pointer to the new permanent cluster
*/
static CLUSTER* MakeNewCluster(CLUSTERER* Clusterer,
TEMPCLUSTER* TempCluster) {
CLUSTER *Cluster;
// allocate the new cluster and initialize it
Cluster = (CLUSTER *) Emalloc(
sizeof(CLUSTER) + (Clusterer->SampleSize - 1) * sizeof(float));
Cluster->Clustered = FALSE;
Cluster->Prototype = FALSE;
Cluster->Left = TempCluster->Cluster;
Cluster->Right = TempCluster->Neighbor;
Cluster->CharID = -1;
// mark the old clusters as "clustered" and delete them from the kd-tree
Cluster->Left->Clustered = TRUE;
Cluster->Right->Clustered = TRUE;
KDDelete(Clusterer->KDTree, Cluster->Left->Mean, Cluster->Left);
KDDelete(Clusterer->KDTree, Cluster->Right->Mean, Cluster->Right);
// compute the mean and sample count for the new cluster
Cluster->SampleCount =
MergeClusters(Clusterer->SampleSize, Clusterer->ParamDesc,
Cluster->Left->SampleCount, Cluster->Right->SampleCount,
Cluster->Mean, Cluster->Left->Mean, Cluster->Right->Mean);
// add the new cluster to the KD tree
KDStore(Clusterer->KDTree, Cluster->Mean, Cluster);
return Cluster;
} // MakeNewCluster
/**
* This routine merges two clusters into one larger cluster.
* To do this it computes the number of samples in the new
* cluster and the mean of the new cluster. The ParamDesc
* information is used to ensure that circular dimensions
* are handled correctly.
* @param N # of dimensions (size of arrays)
* @param ParamDesc array of dimension descriptions
* @param n1, n2 number of samples in each old cluster
* @param m array to hold mean of new cluster
* @param m1, m2 arrays containing means of old clusters
* @return The number of samples in the new cluster.
*/
int32_t MergeClusters(int16_t N,
PARAM_DESC ParamDesc[],
int32_t n1,
int32_t n2,
float m[],
float m1[], float m2[]) {
int32_t i, n;
n = n1 + n2;
for (i = N; i > 0; i--, ParamDesc++, m++, m1++, m2++) {
if (ParamDesc->Circular) {
// if distance between means is greater than allowed
// reduce upper point by one "rotation" to compute mean
// then normalize the mean back into the accepted range
if ((*m2 - *m1) > ParamDesc->HalfRange) {
*m = (n1 * *m1 + n2 * (*m2 - ParamDesc->Range)) / n;
if (*m < ParamDesc->Min)
*m += ParamDesc->Range;
}
else if ((*m1 - *m2) > ParamDesc->HalfRange) {
*m = (n1 * (*m1 - ParamDesc->Range) + n2 * *m2) / n;
if (*m < ParamDesc->Min)
*m += ParamDesc->Range;
}
else
*m = (n1 * *m1 + n2 * *m2) / n;
}
else
*m = (n1 * *m1 + n2 * *m2) / n;
}
return n;
} // MergeClusters
/**
* This routine decides which clusters in the cluster tree
* should be represented by prototypes, forms a list of these
* prototypes, and places the list in the Clusterer data
* structure.
* @param Clusterer data structure holding cluster tree
* @param Config parameters used to control prototype generation
* @return None
*/
static void ComputePrototypes(CLUSTERER* Clusterer, CLUSTERCONFIG* Config) {
LIST ClusterStack = NIL_LIST;
CLUSTER *Cluster;
PROTOTYPE *Prototype;
// use a stack to keep track of clusters waiting to be processed
// initially the only cluster on the stack is the root cluster
if (Clusterer->Root != nullptr)
ClusterStack = push (NIL_LIST, Clusterer->Root);
// loop until we have analyzed all clusters which are potential prototypes
while (ClusterStack != NIL_LIST) {
// remove the next cluster to be analyzed from the stack
// try to make a prototype from the cluster
// if successful, put it on the proto list, else split the cluster
Cluster = (CLUSTER *) first_node (ClusterStack);
ClusterStack = pop (ClusterStack);
Prototype = MakePrototype(Clusterer, Config, Cluster);
if (Prototype != nullptr) {
Clusterer->ProtoList = push (Clusterer->ProtoList, Prototype);
}
else {
ClusterStack = push (ClusterStack, Cluster->Right);
ClusterStack = push (ClusterStack, Cluster->Left);
}
}
} // ComputePrototypes
/**
* This routine attempts to create a prototype from the
* specified cluster that conforms to the distribution
* specified in Config. If there are too few samples in the
* cluster to perform a statistical analysis, then a prototype
* is generated but labelled as insignificant. If the
* dimensions of the cluster are not independent, no prototype
* is generated and nullptr is returned. If a prototype can be
* found that matches the desired distribution then a pointer
* to it is returned, otherwise nullptr is returned.
* @param Clusterer data structure holding cluster tree
* @param Config parameters used to control prototype generation
* @param Cluster cluster to be made into a prototype
* @return Pointer to new prototype or nullptr
*/
static PROTOTYPE* MakePrototype(CLUSTERER* Clusterer, CLUSTERCONFIG* Config,
CLUSTER* Cluster) {
STATISTICS *Statistics;
PROTOTYPE *Proto;
BUCKETS *Buckets;
// filter out clusters which contain samples from the same character
if (MultipleCharSamples (Clusterer, Cluster, Config->MaxIllegal))
return nullptr;
// compute the covariance matrix and ranges for the cluster
Statistics =
ComputeStatistics(Clusterer->SampleSize, Clusterer->ParamDesc, Cluster);
// check for degenerate clusters which need not be analyzed further
// note that the MinSamples test assumes that all clusters with multiple
// character samples have been removed (as above)
Proto = MakeDegenerateProto(
Clusterer->SampleSize, Cluster, Statistics, Config->ProtoStyle,
(int32_t) (Config->MinSamples * Clusterer->NumChar));
if (Proto != nullptr) {
FreeStatistics(Statistics);
return Proto;
}
// check to ensure that all dimensions are independent
if (!Independent(Clusterer->ParamDesc, Clusterer->SampleSize,
Statistics->CoVariance, Config->Independence)) {
FreeStatistics(Statistics);
return nullptr;
}
if (HOTELLING && Config->ProtoStyle == elliptical) {
Proto = TestEllipticalProto(Clusterer, Config, Cluster, Statistics);
if (Proto != nullptr) {
FreeStatistics(Statistics);
return Proto;
}
}
// create a histogram data structure used to evaluate distributions
Buckets = GetBuckets(Clusterer, normal, Cluster->SampleCount,
Config->Confidence);
// create a prototype based on the statistics and test it
switch (Config->ProtoStyle) {
case spherical:
Proto = MakeSphericalProto(Clusterer, Cluster, Statistics, Buckets);
break;
case elliptical:
Proto = MakeEllipticalProto(Clusterer, Cluster, Statistics, Buckets);
break;
case mixed:
Proto = MakeMixedProto(Clusterer, Cluster, Statistics, Buckets,
Config->Confidence);
break;
case automatic:
Proto = MakeSphericalProto(Clusterer, Cluster, Statistics, Buckets);
if (Proto != nullptr)
break;
Proto = MakeEllipticalProto(Clusterer, Cluster, Statistics, Buckets);
if (Proto != nullptr)
break;
Proto = MakeMixedProto(Clusterer, Cluster, Statistics, Buckets,
Config->Confidence);
break;
}
FreeStatistics(Statistics);
return Proto;
} // MakePrototype
/**
* This routine checks for clusters which are degenerate and
* therefore cannot be analyzed in a statistically valid way.
* A cluster is defined as degenerate if it does not have at
* least MINSAMPLESNEEDED samples in it. If the cluster is
* found to be degenerate, a prototype of the specified style
* is generated and marked as insignificant. A cluster is
* also degenerate if it does not have at least MinSamples
* samples in it.
*
* If the cluster is not degenerate, nullptr is returned.
*
* @param N number of dimensions
* @param Cluster cluster being analyzed
* @param Statistics statistical info about cluster
* @param Style type of prototype to be generated