-
Notifications
You must be signed in to change notification settings - Fork 5
/
gda_clustering.h
399 lines (364 loc) · 14 KB
/
gda_clustering.h
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
#ifndef __JSGEODSA_GDA_CLUSTERING__
#define __JSGEODSA_GDA_CLUSTERING__
#include <vector>
#include <string>
#include "./weights/GeodaWeight.h"
class AbstractGeoDa;
// APIs of clustering
/**
*
* @param p
* @param w
* @param data
* @param inits
* @param min_bounds
* @param max_bounds
* @param init_regions
* @param distance_method
* @param rnd_seed
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_azp_greedy(int p, GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
int inits,
const std::vector<std::pair<double, std::vector<double> > >& min_bounds,
const std::vector<std::pair<double, std::vector<double> > >& max_bounds,
const std::vector<int>& init_regions,
const std::string &distance_method,
int rnd_seed,
double** dist_matrix);
/**
*
* @param p
* @param w
* @param data
* @param inits
* @param cooling_rate
* @param sa_maxit
* @param min_bounds
* @param max_bounds
* @param init_regions
* @param distance_method
* @param rnd_seed
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_azp_sa(int p, GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
int inits,
double cooling_rate,
int sa_maxit,
const std::vector<std::pair<double, std::vector<double> > >& min_bounds,
const std::vector<std::pair<double, std::vector<double> > >& max_bounds,
const std::vector<int>& init_regions,
const std::string &distance_method,
int rnd_seed,
double** dist_matrix);
/**
*
* @param p
* @param w
* @param data
* @param inits
* @param tabu_length
* @param conv_tabu
* @param min_bounds
* @param max_bounds
* @param init_regions
* @param distance_method
* @param rnd_seed
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_azp_tabu(int p, GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
int inits,
int tabu_length,
int conv_tabu,
const std::vector<std::pair<double, std::vector<double> > >& min_bounds,
const std::vector<std::pair<double, std::vector<double> > >& max_bounds,
const std::vector<int>& init_regions,
const std::string &distance_method,
int rnd_seed,
double** dist_matrix);
/**
*
* @param w
* @param data
* @param iterations
* @param min_bounds
* @param max_bounds
* @param init_regions
* @param distance_method
* @param rnd_seed
* @param cpu_threads
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_maxp_greedy(GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
int iterations,
const std::vector<std::pair<double, std::vector<double> > >& min_bounds,
const std::vector<std::pair<double, std::vector<double> > >& max_bounds,
const std::vector<int>& init_regions,
const std::string &distance_method,
int rnd_seed,
int cpu_threads,
double** dist_matrix);
/**
*
* @param w
* @param data
* @param iterations
* @param cooling_rate
* @param sa_maxit
* @param min_bounds
* @param max_bounds
* @param init_regions
* @param distance_method
* @param rnd_seed
* @param cpu_threads
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_maxp_sa(GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
int iterations,
double cooling_rate,
int sa_maxit,
const std::vector<std::pair<double, std::vector<double> > >& min_bounds,
const std::vector<std::pair<double, std::vector<double> > >& max_bounds,
const std::vector<int>& init_regions,
const std::string &distance_method,
int rnd_seed,
int cpu_threads,
double** dist_matrix);
/**
*
* @param w
* @param data
* @param iterations
* @param tabu_length
* @param conv_tabu
* @param min_bounds
* @param max_bounds
* @param init_regions
* @param distance_method
* @param rnd_seed
* @param cpu_threads
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_maxp_tabu(GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
int iterations,
int tabu_length,
int conv_tabu,
const std::vector<std::pair<double, std::vector<double> > >& min_bounds,
const std::vector<std::pair<double, std::vector<double> > >& max_bounds,
const std::vector<int>& init_regions,
const std::string &distance_method,
int rnd_seed,
int cpu_threads,
double** dist_matrix);
/**
*
* @param k
* @param w
* @param data
* @param redcap_method
* @param distance_method
* @param bound_vals
* @param min_bound
* @param rand_seed
* @param cpu_threads
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_redcap(unsigned int k,
GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
const std::string &redcap_method,
const std::string &distance_method,
const std::vector<double>& bound_vals,
double min_bound,
int rand_seed,
int cpu_threads,
double** dist_matrix);
/**
*
* @param k
* @param w
* @param data
* @param distance_method
* @param bound_vals
* @param min_bound
* @param rand_seed
* @param cpu_threads
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_skater(unsigned int k,
GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
const std::string &distance_method,
const std::vector<double>& bound_vals,
double min_bound,
int rand_seed,
int cpu_threads,
double** dist_matrix);
/**
*
* @param k
* @param w
* @param data
* @param linkage_method
* @param distance_method
* @param bound_vals
* @param min_bound
* @param rand_seed
* @param cpu_threads
* @param dist_matrix lower triangle precomputed distance matrix
* @return
*/
const std::vector<std::vector<int> > gda_schc(unsigned int k,
GeoDaWeight *w,
const std::vector<std::vector<double> > &_data,
const std::string& scale_method,
const std::string &linkage_method,
const std::string &distance_method,
const std::vector<double>& bound_vals,
double min_bound,
double** dist_matrix);
/**
*
* @param vals
* @return
*/
double gda_sumofsquares(const std::vector<double>& vals);
/**
*
* @param vals
* @return
*/
double gda_totalsumofsquare(const std::vector<std::vector<double> >& vals);
/**
*
* @param solution
* @param vals
* @return
*/
std::vector<double> gda_withinsumofsquare(const std::vector<std::vector<int> >& solution,
const std::vector<std::vector<double> >& vals);
/**
*
* @param solution
* @param data
* @return
*/
double gda_betweensumofsquare(const std::vector<std::vector<int> >& solution,
const std::vector<std::vector<double> >& data);
struct Fragmentation {
int n;
double entropy;
double std_entropy;
double simpson;
double std_simpson;
int min_cluster_size;
int max_cluster_size;
double mean_cluster_size;
bool is_spatially_contiguous;
double fraction;
Fragmentation() : n(0), entropy(0), std_entropy(0), simpson(0), std_simpson(0),
min_cluster_size(0), max_cluster_size(0), mean_cluster_size(0),
is_spatially_contiguous(true), fraction(0) {}
Fragmentation& operator = (const Fragmentation& item) {
n = item.n;
entropy = item.entropy;
std_entropy = item.std_entropy;
simpson = item.simpson;
std_simpson = item.std_simpson;
min_cluster_size = item.min_cluster_size;
max_cluster_size = item.max_cluster_size;
mean_cluster_size = item.mean_cluster_size;
is_spatially_contiguous = item.is_spatially_contiguous;
return *this;
}
};
struct Compactness {
double isoperimeter_quotient;
double area;
double perimeter;
Compactness() : isoperimeter_quotient(0), area(0), perimeter(0) {}
Compactness& operator = (const Compactness& item) {
isoperimeter_quotient = item.isoperimeter_quotient;
area = item.area;
perimeter = item.perimeter;
return *this;
}
};
struct Diameter {
int steps;
double ratio;
Diameter() : steps(0), ratio(0) {}
Diameter& operator = (const Diameter& item) {
steps = item.steps;
ratio = item.ratio;
return *this;
}
};
struct JoinCountRatio {
int cluster;
int n;
int totalNeighbors;
int totalJoinCount;
double ratio;
JoinCountRatio(): cluster(0), n(0), totalNeighbors(0), totalJoinCount(0),ratio(0) {}
};
struct ValidationResult {
bool spatially_constrained;
Fragmentation fragmentation;
std::vector<Fragmentation> cluster_fragmentation;
std::vector<Diameter> cluster_diameter;
std::vector<Compactness> cluster_compactness;
std::vector<JoinCountRatio> joincount_ratio;
};
/**
*
* @param geoda
* @param clusters
* @param w
* @return
*/
ValidationResult gda_spatialvalidation(AbstractGeoDa* geoda, const std::vector<int>& clusters, GeoDaWeight *w);
/**
* Make spatially constrained clusters from non-spatially constrained clusters
*
* @param clusters
* @param w
* @return
*/
std::vector<int> gda_makespatial(const std::vector<int>& clusters, GeoDaWeight* w);
/**
*
* @param items
* @return
*/
JoinCountRatio gda_all_joincount_ratio(const std::vector<JoinCountRatio>& items);
/**
*
* @param clusters
* @param w
* @return
*/
std::vector<JoinCountRatio> gda_joincount_ratio(const std::vector<int>& clusters, GeoDaWeight *w);
#endif