-
Notifications
You must be signed in to change notification settings - Fork 1
/
loading_data.py
375 lines (271 loc) · 11.6 KB
/
loading_data.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
import numpy as np
from collections import defaultdict
import nibabel as nib
import pandas as pd
from tqdm import tqdm
def parse_string_list(string_list, index):
new_list = [string_list[index_now] for index_now in index]
return new_list
def parse_info(list_of_nifty_files_gm, subject_info, list_extract_subjects):
subject_info.set_index("Subject", inplace=True)
#########################################
### subject_info -- PANDAS data frame ###
#########################################
lista_outcomes = defaultdict()
control=0
for current_subject in list_extract_subjects:
print(current_subject)
#try:
############################################
###### check if there is a nifty file ######
############################################
plm = [s for s in list_of_nifty_files_gm if current_subject in s]
if len(plm)>0:
current_row_of_interest = subject_info.loc[current_subject]
lista_outcomes[control] = current_row_of_interest.Age
control+=1
else:
print('Did not have nifty file ')
#except:
# print('We could not find the nifti files')
return lista_outcomes
'''
def data_factory_whole_brain(list_of_nifty_files_gm,
list_of_nifty_files_wm, subject_info, list_extract_subjects):
subject_info.set_index("Subject", inplace=True)
#########################################
### subject_info -- PANDAS data frame ###
#########################################
lista_imagini = defaultdict()
lista_outcomes = defaultdict()
lista_gender = defaultdict()
lista_name = defaultdict()
### parse the GM and WM nifty lists for the ones presment in list_extract_subjects ###
list_parsed_gm = []
list_parsed_wm = []
control=0
for current_subject in list_extract_subjects:
print(current_subject)
#try:
############################################
###### check if there is a nifty file ######
############################################
plm = [s for s in list_of_nifty_files_gm if current_subject in s]
print(plm)
if len(plm)>0:
list_parsed_gm.append( [s for s in list_of_nifty_files_gm if current_subject in s][0])
list_parsed_wm.append( [s for s in list_of_nifty_files_wm if current_subject in s][0])
current_row_of_interest = subject_info.loc[current_subject]
lista_outcomes[control] = current_row_of_interest.Age
print(current_row_of_interest.Age)
lista_gender[control] = current_row_of_interest.Gender
print(current_row_of_interest.Gender)
lista_name[control] = current_subject
control+=1
else:
print('Did not have nifty file ')
#except:
# print('We could not find the nifti files')
control=0
for sth in list_parsed_gm:
lista_imagini[control] = []
control+=1
##### load GM data #####
control = 0
for nifty_file in list_parsed_gm:
nifti_name = nifty_file.rsplit('/')[-1]
if 'run-02' in nifti_name:
nifti_name = nifti_name.rsplit('_run-02')[0]+'_run-01_T1w.nii'
if 'run-03' in nifti_name:
nifti_name = nifti_name.rsplit('_run-03')[0]+'_run-01_T1w.nii'
if 'run-04' in nifti_name:
nifti_name = nifti_name.rsplit('_run-04')[0]+'_run-01_T1w.nii'
if 'run-05' in nifti_name:
nifti_name = nifti_name.rsplit('_run-05')[0]+'_run-01_T1w.nii'
nifti_name = '/data/my_data/OASIS3/gm_data/'+nifti_name
print('loading ... '+str(nifti_name))
temporar_object = nib.load(nifti_name)
temporar_data = temporar_object.get_data()
temporar_object.uncache()
#print(temporar_data_gm.shape)
lista_imagini[control].append(np.expand_dims(temporar_data,axis=-1))
control+=1
##### load WM data #####
control = 0
for nifty_file in list_parsed_wm:
nifti_name = nifty_file.rsplit('/')[-1]
if 'run-02' in nifti_name:
nifti_name = nifti_name.rsplit('_run-02')[0]+'_run-01_T1w.nii'
if 'run-03' in nifti_name:
nifti_name = nifti_name.rsplit('_run-03')[0]+'_run-01_T1w.nii'
if 'run-04' in nifti_name:
nifti_name = nifti_name.rsplit('_run-04')[0]+'_run-01_T1w.nii'
if 'run-05' in nifti_name:
nifti_name = nifti_name.rsplit('_run-05')[0]+'_run-01_T1w.nii'
nifti_name = '/data/my_data/OASIS3/wm_data/'+nifti_name
print('loading ... '+str(nifti_name))
temporar_object = nib.load(nifti_name)
temporar_data = temporar_object.get_data()
temporar_object.uncache()
#print(temporar_data_gm.shape)
lista_imagini[control].append(np.expand_dims(temporar_data,axis=-1))
control+=1
###################################################################
########### concatenate the dictionary entries ####################
###################################################################
for key in lista_imagini.keys():
print('concatenating --- '+str(key))
lista_imagini[key] = np.concatenate(lista_imagini[key], axis=-1)
return lista_imagini, lista_outcomes, lista_gender, list_parsed_gm, list_parsed_wm, lista_name
'''
def data_factory_whole_brain(list_of_nifty_files_gm,
list_of_nifty_files_wm, subject_info, list_extract_subjects):
subject_info.set_index("Subject", inplace=True)
#########################################
### subject_info -- PANDAS data frame ###
#########################################
lista_imagini = defaultdict()
lista_outcomes = defaultdict()
lista_gender = defaultdict()
lista_name = defaultdict()
### parse the GM and WM nifty lists for the ones presment in list_extract_subjects ###
list_parsed_gm = []
list_parsed_wm = []
control=0
for current_subject in list_extract_subjects:
print(current_subject)
try:
############################################
###### check if there is a nifty file ######
############################################
plm = [s for s in list_of_nifty_files_gm if current_subject in s]
print(plm)
if len(plm)>0:
list_parsed_gm.append( [s for s in list_of_nifty_files_gm if current_subject in s][0])
list_parsed_wm.append( [s for s in list_of_nifty_files_wm if current_subject in s][0])
current_row_of_interest = subject_info.loc[current_subject]
lista_outcomes[control] = current_row_of_interest.Age
print(current_row_of_interest.Age)
lista_gender[control] = current_row_of_interest.Gender
print(current_row_of_interest.Gender)
lista_name[control] = current_subject
lista_imagini[control] = []
##### load GM data #####
nifty_file = list_parsed_gm[-1]
nifti_name = nifty_file.rsplit('/')[-1]
if 'run-02' in nifti_name:
nifti_name = nifti_name.rsplit('_run-02')[0]+'_run-01_T1w.nii'
if 'run-03' in nifti_name:
nifti_name = nifti_name.rsplit('_run-03')[0]+'_run-01_T1w.nii'
if 'run-04' in nifti_name:
nifti_name = nifti_name.rsplit('_run-04')[0]+'_run-01_T1w.nii'
if 'run-05' in nifti_name:
nifti_name = nifti_name.rsplit('_run-05')[0]+'_run-01_T1w.nii'
nifti_name = '/data/my_data/OASIS3/gm_data/'+nifti_name
print('loading ... '+str(nifti_name))
temporar_object = nib.load(nifti_name)
temporar_data = temporar_object.get_data()
temporar_object.uncache()
#print(temporar_data_gm.shape)
lista_imagini[control].append(np.expand_dims(temporar_data,axis=-1))
##### load WM data #####
nifty_file = list_parsed_wm[-1]
nifti_name = nifty_file.rsplit('/')[-1]
if 'run-02' in nifti_name:
nifti_name = nifti_name.rsplit('_run-02')[0]+'_run-01_T1w.nii'
if 'run-03' in nifti_name:
nifti_name = nifti_name.rsplit('_run-03')[0]+'_run-01_T1w.nii'
if 'run-04' in nifti_name:
nifti_name = nifti_name.rsplit('_run-04')[0]+'_run-01_T1w.nii'
if 'run-05' in nifti_name:
nifti_name = nifti_name.rsplit('_run-05')[0]+'_run-01_T1w.nii'
nifti_name = '/data/my_data/OASIS3/wm_data/'+nifti_name
print('loading ... '+str(nifti_name))
temporar_object = nib.load(nifti_name)
temporar_data = temporar_object.get_data()
temporar_object.uncache()
#print(temporar_data_gm.shape)
lista_imagini[control].append(np.expand_dims(temporar_data,axis=-1))
control+=1
else:
print('Did not have nifty file ')
except:
print('We could not find the nifti files')
###################################################################
########### concatenate the dictionary entries ####################
###################################################################
for key in lista_imagini.keys():
print('concatenating --- '+str(key))
lista_imagini[key] = np.concatenate(lista_imagini[key], axis=-1)
return lista_imagini, lista_outcomes, lista_gender, list_parsed_gm, list_parsed_wm, lista_name
def data_factory_whole_brain_training(list_of_nifty_files_gm,
list_of_nifty_files_wm, subject_info, list_extract_subjects):
subject_info.set_index("Subject", inplace=True)
#########################################
### subject_info -- PANDAS data frame ###
#########################################
lista_imagini = defaultdict()
lista_outcomes = defaultdict()
lista_gender = defaultdict()
lista_name = defaultdict()
### parse the GM and WM nifty lists for the ones presment in list_extract_subjects ###
list_parsed_gm = []
list_parsed_wm = []
control=0
for current_subject in list_extract_subjects:
#print(current_subject)
#try:
############################################
###### check if there is a nifty file ######
############################################
plm = [s for s in list_of_nifty_files_gm if current_subject in s]
if len(plm)>0:
list_parsed_gm.append( [s for s in list_of_nifty_files_gm if current_subject in s][0])
list_parsed_wm.append( [s for s in list_of_nifty_files_wm if current_subject in s][0])
current_row_of_interest = subject_info.loc[current_subject]
lista_outcomes[control] = current_row_of_interest.Age
#print(current_row_of_interest.Age)
lista_gender[control] = current_row_of_interest.Gender
#print(current_row_of_interest.Gender)
lista_name[control] = current_subject
control+=1
else:
print('Did not have nifty file ')
#except:
# print('We could not find the nifti files')
control=0
for sth in list_parsed_gm:
lista_imagini[control] = []
control+=1
##### load GM data #####
control = 0
for nifty_file in tqdm(list_parsed_gm, desc="Loading Gray Matter..."):
# print('name of subject')
# print(lista_name[control])
# print('loading ... '+str(nifty_file))
temporar_object = nib.load(nifty_file)
temporar_data = temporar_object.get_data()
temporar_object.uncache()
#print(temporar_data_gm.shape)
lista_imagini[control].append(np.expand_dims(temporar_data,axis=-1))
control+=1
##### load WM data #####
control = 0
for nifty_file in tqdm(list_parsed_wm, desc="Loading White Matter..."):
#for nifty_file in list_parsed_wm:
# print('name of subject')
# print(lista_name[control])
# print('loading ... '+str(nifty_file))
temporar_object = nib.load(nifty_file)
temporar_data = temporar_object.get_data()
temporar_object.uncache()
#print(temporar_data_gm.shape)
lista_imagini[control].append(np.expand_dims(temporar_data,axis=-1))
control+=1
###################################################################
########### concatenate the dictionary entries ####################
###################################################################
for i, key in enumerate(tqdm(lista_imagini.keys(), desc="Concating...")):
#print('concatenating --- '+str(key))
lista_imagini[key] = np.concatenate(lista_imagini[key], axis=-1)
return lista_imagini, lista_outcomes, lista_gender, list_parsed_gm, list_parsed_wm, lista_name