forked from soltesz-lab/dentate
-
Notifications
You must be signed in to change notification settings - Fork 0
/
graph.py
431 lines (336 loc) · 17 KB
/
graph.py
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
"""Classes and procedures related to neuronal connectivity graph analysis. """
import gc, math, time, pickle, base64
from collections import defaultdict
try:
from collections import ChainMap
except ImportError as e:
print(('dentate.graph: problem importing ChainMap:', e))
import numpy as np
from mpi4py import MPI
from dentate.utils import get_module_logger, list_find_all, range, str, zip, viewitems, zip_longest
from dentate.utils import Struct, add_bins, update_bins, finalize_bins
from neuroh5.io import NeuroH5ProjectionGen, bcast_cell_attributes, read_cell_attributes, read_population_names, read_population_ranges, read_projection_names
import h5py
## This logger will inherit its setting from its root logger, dentate,
## which is created in module env
logger = get_module_logger(__name__)
def vertex_metrics(connectivity_path, coords_path, vertex_metrics_namespace, distances_namespace, destination, sources, bin_size = 50., metric='Indegree'):
"""
Obtain vertex metrics with respect to septo-temporal position (longitudinal and transverse arc distances to reference points).
:param connectivity_path:
:param coords_path:
:param distances_namespace:
:param destination:
:param source:
:param bin_size:
:param metric:
"""
(population_ranges, _) = read_population_ranges(coords_path)
destination_start = population_ranges[destination][0]
destination_count = population_ranges[destination][1]
if sources == ():
sources = []
for (src, dst) in read_projection_names(connectivity_path):
if dst == destination:
sources.append(src)
degrees_dict = {}
with h5py.File(connectivity_path, 'r') as f:
for source in sources:
degrees_dict[source] = f['Nodes'][vertex_metrics_namespace]['%s %s -> %s' % (metric, source, destination)]['Attribute Value'][0:destination_count]
for source in sources:
logger.info('projection: %s -> %s: max: %i min: %i mean: %i stdev: %i (%d units)' % \
(source, destination, \
np.max(degrees_dict[source]), \
np.min(degrees_dict[source]), \
np.mean(degrees_dict[source]), \
np.std(degrees_dict[source]), \
len(degrees_dict[source])))
if metric == 'Indegree':
distances = read_cell_attributes(coords_path, destination, namespace=distances_namespace)
soma_distances = { k: (v['U Distance'][0], v['V Distance'][0]) for (k,v) in distances }
del distances
elif metric == 'Outdegree':
distances = read_cell_attributes(coords_path, sources[0], namespace=distances_namespace)
soma_distances = { k: (v['U Distance'][0], v['V Distance'][0]) for (k,v) in distances }
del distances
gids = sorted(soma_distances.keys())
distance_U = np.asarray([ soma_distances[gid][0] for gid in gids ])
distance_V = np.asarray([ soma_distances[gid][1] for gid in gids ])
return (distance_U, distance_V, degrees_dict)
def vertex_distribution(connectivity_path, coords_path, distances_namespace, destination, sources,
bin_size=20.0, cache_size=100, comm=None):
"""
Obtain spatial histograms of source vertices connecting to a given destination population.
:param connectivity_path:
:param coords_path:
:param distances_namespace:
:param destination:
:param source:
"""
if comm is None:
comm = MPI.COMM_WORLD
rank = comm.Get_rank()
color = 0
if rank == 0:
color = 1
comm0 = comm.Split(color, 0)
(population_ranges, _) = read_population_ranges(coords_path)
destination_start = population_ranges[destination][0]
destination_count = population_ranges[destination][1]
destination_soma_distances = {}
if rank == 0:
logger.info(f'Reading {destination} distances...')
distances_iter = read_cell_attributes(coords_path, destination, comm=comm0,
mask=set(['U Distance', 'V Distance']),
namespace=distances_namespace)
destination_soma_distances = { k: (float(v['U Distance'][0]),
float(v['V Distance'][0])) for (k,v) in distances_iter }
gc.collect()
comm.barrier()
destination_soma_distances = comm.bcast(destination_soma_distances, root=0)
destination_soma_distance_U = {}
destination_soma_distance_V = {}
for k,v in viewitems(destination_soma_distances):
destination_soma_distance_U[k] = v[0]
destination_soma_distance_V[k] = v[1]
del(destination_soma_distances)
if sources == ():
sources = []
for (src, dst) in read_projection_names(connectivity_path):
if dst == destination:
sources.append(src)
source_soma_distances = {}
if rank == 0:
for s in sources:
logger.info(f'Reading {s} distances...')
distances_iter = read_cell_attributes(coords_path, s, comm=comm0,
mask=set(['U Distance', 'V Distance']),
namespace=distances_namespace)
source_soma_distances[s] = { k: (float(v['U Distance'][0]),
float(v['V Distance'][0])) for (k,v) in distances_iter }
gc.collect()
comm.barrier()
comm0.Free()
source_soma_distances = comm.bcast(source_soma_distances, root=0)
source_soma_distance_U = {}
source_soma_distance_V = {}
for s in sources:
this_source_soma_distance_U = {}
this_source_soma_distance_V = {}
for k,v in viewitems(source_soma_distances[s]):
this_source_soma_distance_U[k] = v[0]
this_source_soma_distance_V[k] = v[1]
source_soma_distance_U[s] = this_source_soma_distance_U
source_soma_distance_V[s] = this_source_soma_distance_V
del(source_soma_distances)
if rank == 0:
logger.info('Reading connections %s -> %s...' % (str(sources), destination))
dist_bins = defaultdict(dict)
dist_u_bins = defaultdict(dict)
dist_v_bins = defaultdict(dict)
gg = [ NeuroH5ProjectionGen (connectivity_path, source, destination,
cache_size=cache_size, comm=comm) for source in sources ]
for prj_gen_tuple in zip_longest(*gg):
destination_gid = prj_gen_tuple[0][0]
if rank == 0 and destination_gid is not None:
logger.info('%d' % destination_gid)
if not all([prj_gen_elt[0] == destination_gid for prj_gen_elt in prj_gen_tuple]):
raise RuntimeError('destination %s: destination gid %i not matched across multiple projection generators: '
'%s' % (destination, destination_gid, [prj_gen_elt[0] for prj_gen_elt in prj_gen_tuple]))
if destination_gid is not None:
for (source, (this_destination_gid,rest)) in zip_longest(sources, prj_gen_tuple):
this_source_soma_distance_U = source_soma_distance_U[source]
this_source_soma_distance_V = source_soma_distance_V[source]
this_dist_bins = dist_bins[source]
this_dist_u_bins = dist_u_bins[source]
this_dist_v_bins = dist_v_bins[source]
(source_indexes, attr_dict) = rest
dst_U = destination_soma_distance_U[destination_gid]
dst_V = destination_soma_distance_V[destination_gid]
for source_gid in source_indexes:
dist_u = dst_U - this_source_soma_distance_U[source_gid]
dist_v = dst_V - this_source_soma_distance_V[source_gid]
dist = abs(dist_u) + abs(dist_v)
update_bins(this_dist_bins, bin_size, dist)
update_bins(this_dist_u_bins, bin_size, dist_u)
update_bins(this_dist_v_bins, bin_size, dist_v)
add_bins_op = MPI.Op.Create(add_bins, commute=True)
for source in sources:
dist_bins[source] = comm.reduce(dist_bins[source], op=add_bins_op)
dist_u_bins[source] = comm.reduce(dist_u_bins[source], op=add_bins_op)
dist_v_bins[source] = comm.reduce(dist_v_bins[source], op=add_bins_op)
dist_hist_dict = defaultdict(dict)
dist_u_hist_dict = defaultdict(dict)
dist_v_hist_dict = defaultdict(dict)
if rank == 0:
for source in sources:
dist_hist_dict[destination][source] = finalize_bins(dist_bins[source], bin_size)
dist_u_hist_dict[destination][source] = finalize_bins(dist_u_bins[source], bin_size)
dist_v_hist_dict[destination][source] = finalize_bins(dist_v_bins[source], bin_size)
return {'Total distance': dist_hist_dict,
'U distance': dist_u_hist_dict,
'V distance': dist_v_hist_dict }
def spatial_bin_graph(connectivity_path, coords_path, distances_namespace, destination, sources, extents,
bin_size=20.0, cache_size=100, comm=None):
"""
Obtain reduced graphs of the specified projections by binning nodes according to their spatial position.
:param connectivity_path:
:param coords_path:
:param distances_namespace:
:param destination:
:param source:
"""
import networkx as nx
if comm is None:
comm = MPI.COMM_WORLD
rank = comm.Get_rank()
(population_ranges, _) = read_population_ranges(coords_path)
destination_start = population_ranges[destination][0]
destination_count = population_ranges[destination][1]
if rank == 0:
logger.info('reading %s distances...' % destination)
destination_soma_distances = bcast_cell_attributes(coords_path, destination, namespace=distances_namespace, comm=comm, root=0)
((x_min, x_max), (y_min, y_max)) = extents
u_bins = np.arange(x_min, x_max, bin_size)
v_bins = np.arange(y_min, y_max, bin_size)
dest_u_bins = {}
dest_v_bins = {}
destination_soma_distance_U = {}
destination_soma_distance_V = {}
for k,v in destination_soma_distances:
dist_u = v['U Distance'][0]
dist_v = v['V Distance'][0]
dest_u_bins[k] = np.searchsorted(u_bins, dist_u, side='left')
dest_v_bins[k] = np.searchsorted(v_bins, dist_v, side='left')
destination_soma_distance_U[k] = dist_u
destination_soma_distance_V[k] = dist_v
del(destination_soma_distances)
if (sources == ()) or (sources == []) or (sources is None):
sources = []
for (src, dst) in read_projection_names(connectivity_path):
if dst == destination:
sources.append(src)
source_soma_distances = {}
for s in sources:
if rank == 0:
logger.info('reading %s distances...' % s)
source_soma_distances[s] = bcast_cell_attributes(coords_path, s, namespace=distances_namespace, comm=comm, root=0)
source_u_bins = {}
source_v_bins = {}
source_soma_distance_U = {}
source_soma_distance_V = {}
for s in sources:
this_source_soma_distance_U = {}
this_source_soma_distance_V = {}
this_source_u_bins = {}
this_source_v_bins = {}
for k,v in source_soma_distances[s]:
dist_u = v['U Distance'][0]
dist_v = v['V Distance'][0]
this_source_u_bins[k] = np.searchsorted(u_bins, dist_u, side='left')
this_source_v_bins[k] = np.searchsorted(v_bins, dist_v, side='left')
this_source_soma_distance_U[k] = dist_u
this_source_soma_distance_V[k] = dist_v
source_soma_distance_U[s] = this_source_soma_distance_U
source_soma_distance_V[s] = this_source_soma_distance_V
source_u_bins[s] = this_source_u_bins
source_v_bins[s] = this_source_v_bins
del(source_soma_distances)
if rank == 0:
logger.info('reading connections %s -> %s...' % (str(sources), destination))
gg = [ NeuroH5ProjectionGen (connectivity_path, source, destination, cache_size=cache_size, comm=comm) for source in sources ]
dist_bins = defaultdict(dict)
dist_u_bins = defaultdict(dict)
dist_v_bins = defaultdict(dict)
local_u_bin_graph = defaultdict(dict)
local_v_bin_graph = defaultdict(dict)
for prj_gen_tuple in zip_longest(*gg):
destination_gid = prj_gen_tuple[0][0]
if not all([prj_gen_elt[0] == destination_gid for prj_gen_elt in prj_gen_tuple]):
raise RuntimeError('destination %s: destination_gid %i not matched across multiple projection generators: '
'%s' % (destination, destination_gid, [prj_gen_elt[0] for prj_gen_elt in prj_gen_tuple]))
if destination_gid is not None:
dest_u_bin = dest_u_bins[destination_gid]
dest_v_bin = dest_v_bins[destination_gid]
for (source, (this_destination_gid,rest)) in zip_longest(sources, prj_gen_tuple):
this_source_u_bins = source_u_bins[source]
this_source_v_bins = source_v_bins[source]
(source_indexes, attr_dict) = rest
source_u_bin_dict = defaultdict(int)
source_v_bin_dict = defaultdict(int)
for source_gid in source_indexes:
source_u_bin = this_source_u_bins[source_gid]
source_v_bin = this_source_v_bins[source_gid]
source_u_bin_dict[source_u_bin] += 1
source_v_bin_dict[source_v_bin] += 1
local_u_bin_graph[dest_u_bin][source] = source_u_bin_dict
local_v_bin_graph[dest_v_bin][source] = source_v_bin_dict
local_u_bin_graphs = comm.gather(dict(local_u_bin_graph), root=0)
local_v_bin_graphs = comm.gather(dict(local_v_bin_graph), root=0)
u_bin_graph = None
v_bin_graph = None
nu = None
nv = None
if rank == 0:
u_bin_edges = { destination: dict(ChainMap(*local_u_bin_graphs)) }
v_bin_edges = { destination: dict(ChainMap(*local_v_bin_graphs)) }
nu = len(u_bins)
u_bin_graph = nx.Graph()
for pop in [destination]+list(sources):
for i in range(nu):
u_bin_graph.add_node((pop, i))
for i, ss in viewitems(u_bin_edges[destination]):
for source, ids in viewitems(ss):
u_bin_graph.add_weighted_edges_from([((source, j), (destination, i), count) for j, count in viewitems(ids)])
nv = len(v_bins)
v_bin_graph = nx.Graph()
for pop in [destination]+list(sources):
for i in range(nv):
v_bin_graph.add_node((pop, i))
for i, ss in viewitems(v_bin_edges[destination]):
for source, ids in viewitems(ss):
v_bin_graph.add_weighted_edges_from([((source, j), (destination, i), count) for j, count in viewitems(ids)])
label = '%s to %s' % (str(sources), destination)
return { 'label': label, 'bin size': bin_size, 'destination': destination, 'sources': sources,
'U graph': u_bin_graph, 'V graph': v_bin_graph }
def save_spatial_bin_graph(output_path, graph_dict):
bin_size = graph_dict['bin size']
label_pkl = pickle.dumps(graph_dict['label'])
label_pkl_str = base64.b64encode(label_pkl)
destination_pkl = pickle.dumps(graph_dict['destination'])
destination_pkl_str = base64.b64encode(destination_pkl)
sources_pkl = pickle.dumps(graph_dict['sources'])
sources_pkl_str = base64.b64encode(sources_pkl)
u_bin_graph = graph_dict['U graph']
u_bin_graph_pkl = pickle.dumps(u_bin_graph)
u_bin_graph_pkl_str = base64.b64encode(u_bin_graph_pkl)
v_bin_graph = graph_dict['V graph']
v_bin_graph_pkl = pickle.dumps(v_bin_graph)
v_bin_graph_pkl_str = base64.b64encode(v_bin_graph_pkl)
f = h5py.File(output_path)
dataset_path = 'Spatial Bin Graph/%.02f' % bin_size
grp = f.create_group(dataset_path)
grp['bin size'] = bin_size
grp['label.pkl'] = label_pkl_str
grp['destination.pkl'] = destination_pkl_str
grp['sources.pkl'] = sources_pkl_str
grp['U graph.pkl'] = u_bin_graph_pkl_str
grp['V graph.pkl'] = v_bin_graph_pkl_str
f.close()
def load_spatial_bin_graph(input_path, dataset_path):
f = h5py.File(input_path, 'r')
grp = f[dataset_path]
bin_size = grp['bin size'][()]
label_dset = grp['label.pkl']
destination_dset = grp['destination.pkl']
sources_dset = grp['sources.pkl']
u_bin_graph_dset = grp['U graph.pkl']
v_bin_graph_dset = grp['V graph.pkl']
label = pickle.loads(base64.b64decode(label_dset[()]))
destination = pickle.loads(base64.b64decode(destination_dset[()]))
sources = pickle.loads(base64.b64decode(sources_dset[()]))
u_bin_graph = pickle.loads(base64.b64decode(u_bin_graph_dset[()]))
v_bin_graph = pickle.loads(base64.b64decode(v_bin_graph_dset[()]))
f.close()
return { 'label': label, 'bin size': bin_size, 'destination': destination, 'sources': sources,
'U graph': u_bin_graph, 'V graph': v_bin_graph }