-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathfunctions.py
5441 lines (4036 loc) · 191 KB
/
functions.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
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
import numpy as np
import numba
from astropy.time import Time
from astropy.io import fits
import glob
import matplotlib.dates as mdates
from matplotlib import cm
from matplotlib.colors import ListedColormap
from astropy import wcs
import requests
from bs4 import BeautifulSoup
import os
import pandas as pd
import datetime
from itertools import repeat
import matplotlib.pyplot as plt
import pickle
import cv2
import sys
from scipy.ndimage import shift
import warnings
from urllib3.exceptions import InsecureRequestWarning
from urllib3 import disable_warnings
from requests.adapters import HTTPAdapter, Retry
import psutil
from multiprocessing.pool import Pool
from multiprocessing import cpu_count
import traceback
import logging
from skimage import exposure
from matplotlib.ticker import MultipleLocator
from collections import Counter
from sunpy.coordinates.ephemeris import get_body_heliographic_stonyhurst
from sunpy.coordinates import Helioprojective
from sunpy.coordinates.ephemeris import get_horizons_coord
from astropy.coordinates import SkyCoord
from astropy import units as u
from skimage.transform import resize, rotate
import yaml
from skimage import morphology
from scipy.ndimage import zoom
from numpy.lib.stride_tricks import sliding_window_view
import time
import multiprocessing as mp
from itertools import repeat
warnings.filterwarnings("ignore")
#######################################################################################################################################
def load_jplot(path, instrument, ftpsc, bflag, start, end, jp_name):
savepath_jplot = os.path.join(path, 'jplot', ftpsc, bflag, instrument, str(start[:4]), 'plots')
savepath_param = os.path.join(path, 'jplot', ftpsc, bflag, instrument, str(start[:4]), 'params')
instrument_name = 'hi1' if instrument == 'hi_1' else 'hi2'
jplot_name = f"jplot_{instrument_name}_{start}_{end}_{ftpsc}_{bflag[0]}{jp_name}"
param_fil = glob.glob(f"{savepath_param}/{jplot_name}_params.pkl")[0]
plot_fil = glob.glob(f"{savepath_jplot}/{jplot_name}.pkl")[0]
with open(param_fil, 'rb') as f:
t_beg, t_end, e_beg, e_end = pickle.load(f)
with open(plot_fil, 'rb') as f:
img_rescale, orig = pickle.load(f)
return img_rescale, orig, t_beg, t_end, e_beg, e_end
#######################################################################################################################################
def track_jplot(imgs, origs, tbegs, tends, ebegs, eends, ftpsc, bflag, start, end, jp_name, instrument, path):
vmins = [np.nanmedian(img) - 0.1 * np.nanstd(img) for img in imgs]
vmaxs = [np.nanmedian(img) + 0.1 * np.nanstd(img) for img in imgs]
if bflag == 'beacon':
cadence_h1 = 120.0
cadence_h2 = 120.0
if bflag == 'science':
cadence_h1 = 40.0
cadence_h2 = 120.0
if instrument == 'hi1hi2':
cadence = [cadence_h1, cadence_h2]
instrument_name = 'hi1hi2'
elif instrument == 'hi_1':
cadence = [cadence_h1]
instrument_name = 'hi1'
elif instrument == 'hi_2':
cadence = [cadence_h2]
instrument_name = 'hi2'
datetime_series = [np.arange(tbegs[i], tends[i] + datetime.timedelta(minutes=cadence[i]), datetime.timedelta(minutes=cadence[i])).astype(datetime.datetime) for i in range(len(cadence))]
loc_ticks= int(np.ceil(((tends[0]-tbegs[0]).total_seconds()/(60*60*24)*1/7)))
fig, ax = plt.subplots(figsize=(10, 5))
plt.ylim(np.min(ebegs), np.max(eends))
plt.gca().xaxis.set_major_locator(mdates.HourLocator(byhour=range(0, 24, 24), interval=loc_ticks))
plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%d/%m/%y'))
plt.gca().xaxis.set_minor_locator(mdates.HourLocator(byhour=range(0, 24, 6), interval=loc_ticks))
plt.gca().yaxis.set_minor_locator(MultipleLocator(2))
ax.xaxis_date()
plt.xlabel('Date (d/m/y)')
plt.ylabel('Elongation (°)')
imgs = [img.astype(float) for img in imgs]
for i in range(len(imgs)):
ax.imshow(imgs[i], cmap='gray', aspect='auto', vmin=vmins[i], vmax=vmaxs[i], interpolation='none', origin=origs[i], extent=[mdates.date2num(tbegs[i] - datetime.timedelta(minutes=cadence[i]/2)), mdates.date2num(tends[i] + datetime.timedelta(minutes=cadence[i]/2)), ebegs[i], eends[i]])
ax.set_title(start + ' STEREO-' + ftpsc)
data = []
inp = fig.ginput(n=-1, timeout=0, mouse_add=1, mouse_pop=3, mouse_stop=2, show_clicks=True)
data.append(inp)
elon = [data[0][i][1] for i in range(len(data[0]))]
date_time_obj = [mdates.num2date(data[0][i][0]) for i in range(len(data[0]))]
date_obj_corrected = []
for p, dat_p in enumerate(date_time_obj):
if len(cadence) == 2:
if elon[p] >= eends[1]:
arr_ind = (np.abs(datetime_series[1] - dat_p.replace(tzinfo=None))).argmin()
dat_new = datetime_series[1][arr_ind]
else:
arr_ind = (np.abs(datetime_series[0] - dat_p.replace(tzinfo=None))).argmin()
dat_new = datetime_series[0][arr_ind]
else:
arr_ind = (np.abs(datetime_series[0] - dat_p.replace(tzinfo=None))).argmin()
dat_new = datetime_series[0][arr_ind]
date_obj_corrected.append(dat_new)
date = [datetime.datetime.strftime(x, '%Y-%b-%d %H:%M:%S.%f') for x in date_obj_corrected]
elon_stdd = np.zeros(len(data[0]))
SC = [ftpsc for x in range(len(data[0]))]
pd_data = {'TRACK_DATE': date, 'ELON': elon, 'ELON_STDD': elon_stdd, 'SC': SC}
savepath_tracks = os.path.join(path, 'jplot', ftpsc, bflag, instrument, str(start[:4]), 'tracks')
jplot_name = f"jplot_{instrument_name}_{start}_{end}_{ftpsc}_{bflag[0]}{jp_name}"
if not os.path.exists(savepath_tracks+'/'):
os.makedirs(savepath_tracks+'/')
prev_files = glob.glob(f"{savepath_tracks}/{jplot_name}_track_*.csv")
num_files = int(len(prev_files) + 1)
df = pd.DataFrame(pd_data, columns=['TRACK_DATE', 'ELON', 'SC', 'ELON_STDD'])
df.to_csv(f"{savepath_tracks}/{jplot_name}_track_{num_files}.csv", index=False, date_format='%Y-%m-%dT%H:%M:%S')
plt.close()
#######################################################################################################################################
def fix_secchi_hdr(hdr):
# Initialize default values
int_val = 0
lon_val = 0
flt_val = 0.0
fltd_val = 0.0
uint8_val = 0
uint16_val = 0
uint32_val = 0
int8_val = 0
int16_val = 0
int32_val = 0
str_val = ''
sta_val = [str_val] * 20
secchi_hdr = {
# SIMPLE: 'T',
'EXTEND': 'F',
# Most-used keywords
'BITPIX': int_val,
'NAXIS': int_val,
'NAXIS1': int_val,
'NAXIS2': int_val,
'DATE-OBS': str_val,
'TIME_OBS': str_val,
'FILEORIG': str_val,
'SEB_PROG': str_val,
'SYNC': str_val,
'SPWX': 'F',
'EXPCMD': -1.0,
'EXPTIME': -1.0,
'DSTART1': int_val,
'DSTOP1': int_val,
'DSTART2': int_val,
'DSTOP2': int_val,
'P1COL': int16_val,
'P2COL': int16_val,
'P1ROW': int16_val,
'P2ROW': int16_val,
'R1COL': int16_val,
'R2COL': int16_val,
'R1ROW': int16_val,
'R2ROW': int16_val,
'RECTIFY': 'F',
'RECTROTA': int_val,
'LEDCOLOR': str_val,
'LEDPULSE': uint32_val,
'OFFSET': 9999,
'BIASMEAN': flt_val,
'BIASSDEV': -1.0,
'GAINCMD': -1,
'GAINMODE': str_val,
'SUMMED': flt_val,
'SUMROW': 1,
'SUMCOL': 1,
'CEB_T': 999,
'TEMP_CCD': 9999.0,
'POLAR': -1.0,
'ENCODERP': -1,
'WAVELNTH': int_val,
'ENCODERQ': -1,
'FILTER': str_val,
'ENCODERF': -1,
'FPS_ON': str_val,
'OBS_PROG': 'schedule',
'DOORSTAT': -1,
'SHUTTDIR': str_val,
'READ_TBL': -1,
'CLR_TBL': -1,
'READFILE': str_val,
'DATE-CLR': str_val,
'DATE-RO': str_val,
'READTIME': -1.0,
'CLEARTIM': fltd_val,
'IP_TIME': -1,
'COMPRSSN': int_val,
'COMPFACT': flt_val,
'NMISSING': -1.0,
'MISSLIST': str_val,
'SETUPTBL': str_val,
'EXPOSTBL': str_val,
'MASK_TBL': str_val,
'IP_TBL': str_val,
'COMMENT': sta_val,
'HISTORY': sta_val,
'DIV2CORR': 'F',
'DISTCORR': 'F',
# Less-used keywords
'TEMPAFT1': 9999.0,
'TEMPAFT2': 9999.0,
'TEMPMID1': 9999.0,
'TEMPMID2': 9999.0,
'TEMPFWD1': 9999.0,
'TEMPFWD2': 9999.0,
'TEMPTHRM': 9999.0,
'TEMP_CEB': 9999.0,
'ORIGIN': str_val,
'DETECTOR': str_val,
'IMGCTR': uint16_val,
'TIMGCTR': uint16_val,
'OBJECT': str_val,
'FILENAME': str_val,
'DATE': str_val,
'INSTRUME': 'SECCHI',
'OBSRVTRY': str_val,
'TELESCOP': 'STEREO',
"DATE__OBS": " ",
"TELESCOP": "STEREO",
"WAVEFILE": str_val, # name of waveform table file used by fsw
"CCDSUM": flt_val, # (sumrow + sumcol) / 2.0
"IPSUM": flt_val, # (sebxsum + sebysum) / 2.0
"DATE-CMD": str_val, # originally scheduled observation time
"DATE-AVG": str_val, # date of midpoint of the exposure(s) (UTC standard)
"DATE-END": str_val, # Date/time of end of (last) exposure
"OBT_TIME": flt_val, # value of STEREO on-board-time since epoch ???
"APID": int_val, # application identifier / how downlinked
"OBS_ID": int_val, # observing sequence ID from planniing tool
"OBSSETID": int_val, # observing set (=campaign) ID from planning tool
"IP_PROG0": int_val, # description of onboard image processing sequence used
"IP_PROG1": int_val, # description of onboard image processing sequence used
"IP_PROG2": int_val, # description of onboard image processing sequence used
"IP_PROG3": int_val, # description of onboard image processing sequence used
"IP_PROG4": int_val, # description of onboard image processing sequence used
"IP_PROG5": int_val, # description of onboard image processing sequence used
"IP_PROG6": int_val, # description of onboard image processing sequence used
"IP_PROG7": int_val, # description of onboard image processing sequence used
"IP_PROG8": int_val, # description of onboard image processing sequence used
"IP_PROG9": int_val, # description of onboard image processing sequence used
"IP_00_19": str_val, # numeral char representation of values 0 - 19 in ip.Cmds
"IMGSEQ": -1, # number of image in current sequence (usually 0)
"OBSERVER": str_val, # Name of operator
"BUNIT": str_val, # unit of values in array
"BLANK": int_val, # value in array which means no data
"FPS_CMD": str_val, # T/F: from useFPS
"VERSION": str_val, # Identifier of FSW header version plus (EUVI only) pointing version
"CEB_STAT": -1, # CEB-Link-status (enum CAMERA_INTERFACE_STATUS)
"CAM_STAT": -1, # CCD-Interface-status (enum CAMERA_PROGRAM_STATE)
"READPORT": str_val, # CCD readout port
"CMDOFFSE": flt_val, # lightTravelOffsetTime/1000.
"RO_DELAY": -1.0, # time (sec) between issuing ro command to the CEB and the start of the ro operation
"LINE_CLR": -1.0, # time (sec) per line for clear operation
"LINE_RO": -1.0, # time (sec) per line for readout operation
"RAVG": -999.0, # average error in star position (pixels)
"BSCALE": 1.0, # scale factor for FITS
"BZERO": flt_val, # value corresponding to zero in array for FITS
"SCSTATUS": -1, # spacecraft status message before exposure
"SCANT_ON": str_val, # T/F: derived from s/c status before and after
"SCFP_ON": str_val, # T/F: from actualSCFinePointMode
"CADENCE": int_val, # Number of seconds between exposures/sequences for the current observing program
"CRITEVT": str_val, # 0xHHHH (uppercase hex word)
"EVENT": 'F', # A flare IP event has (not) been triggered
"EVCOUNT": str_val, # count of number of times evtDetect has run ('0'..'127') ... remains a string
"EVROW": int_val, # X-coordinate of centroid of triggered event
"EVCOL": int_val, # Y-coordinate of centroid of triggered event
"COSMICS": int_val, # Number of pixels removed from image by cosmic ray removal algorithm in FSW
"N_IMAGES": int_val, # Number of CCD readouts used to compute the image
"VCHANNEL": int_val, # Virtual channel of telemetry downlink
"OFFSETCR": flt_val, # Offset bias subtracted from image.
"DOWNLINK": str_val, # How the image came down
"DATAMIN": -1.0, # Minimum value of the image, including the bias derived
"DATAMAX":-1.0, # Maximum value of the image, including the bias derived
"DATAZER": -1, # Number of zero pixels in the image derived
"DATASAT": -1, # Number of saturated values in the image derived
"DSATVAL": -1.0, # Value used as saturated constant
"DATAAVG": -1.0, # Average value of the image derived
"DATASIG": -1.0, # Standard deviation in computing the average derived
"DATAP01": -1.0, # Intensity of 1st percentile of image derived
"DATAP10": -1.0, # Intensity of 10th percentile image derived
"DATAP25": -1.0, # Intensity of 25th percentile of image derived
"DATAP50": -1.0, # Intensity of 50th percentile of image derived (median)
"DATAP75": -1.0, # Intensity of 75th percentile of image derived
"DATAP90": -1.0, # Intensity of 90th percentile of image derived
"DATAP95": -1.0, # Intensity of 95th percentile of image derived
"DATAP98": -1.0, # Intensity of 98th percentile of image derived
"DATAP99": -1.0, # Intensity of 99th percentile of image derived
"CALFAC": 0.0, # Calibration factor applied, NOT including binning correction
"CRPIX1": flt_val,
"CRPIX2": flt_val,
"CRPIX1A": flt_val,
"CRPIX2A": flt_val,
"RSUN": flt_val,
"CTYPE1": 'HPLN-TAN',
"CTYPE2": 'HPLT-TAN',
"CRVAL1": flt_val,
"CRVAL2": flt_val,
"CROTA": flt_val,
"PC1_1": 1.0,
"PC1_2": flt_val,
"PC2_1": flt_val,
"PC2_2": 1.0,
"CUNIT1": str_val, # ARCSEC or DEG for HI
"CUNIT2": str_val, # ARCSEC or DEG for HI
"CDELT1": flt_val,
"CDELT2": flt_val,
"PV2_1": flt_val, # parameter for AZP projection (HI only)
"PV2_1A": flt_val, # parameter for AZP projection (HI only)
"SC_ROLL": 9999.0, # values from get_stereo_hpc_point: (deg) - HI from scc_sunvec (GT)
"SC_PITCH": 9999.0,# arcsec, HI deg
"SC_YAW": 9999.0, # arcsec, HI deg
"SC_ROLLA": 9999.0,# RA/Dec values: (deg)
"SC_PITA": 9999.0, # degrees
"SC_YAWA": 9999.0, # degrees
"INS_R0": 0.0, # applied instrument offset in roll
"INS_Y0": 0.0, # applied instrument offset in pitch (Y-axis)
"INS_X0": 0.0, # applied instrument offset in yaw (X-axis) from
"CTYPE1A": 'RA---TAN',
"CTYPE2A": 'DEC--TAN',
"CUNIT1A": 'deg', # DEG
"CUNIT2A": 'deg', # DEG
"CRVAL1A": flt_val,
"CRVAL2A": flt_val,
"PC1_1A": 1.0,
"PC1_2A": flt_val,
"PC2_1A": flt_val,
"PC2_2A": 1.0,
"CDELT1A": flt_val,
"CDELT2A": flt_val,
"CRLN_OBS": flt_val,
"CRLT_OBS": flt_val,
"XCEN": 9999.0,
"YCEN": 9999.0,
"EPHEMFIL": str_val, # ephemeris SPICE kernel
"ATT_FILE": str_val, # attitude SPICE kernel
"DSUN_OBS": flt_val,
"HCIX_OBS": flt_val,
"HCIY_OBS": flt_val,
"HCIZ_OBS": flt_val,
"HAEX_OBS": flt_val,
"HAEY_OBS": flt_val,
"HAEZ_OBS": flt_val,
"HEEX_OBS": flt_val,
"HEEY_OBS": flt_val,
"HEEZ_OBS": flt_val,
"HEQX_OBS": flt_val,
"HEQY_OBS": flt_val,
"HEQZ_OBS": flt_val,
"LONPOLE": 180,
"HGLN_OBS": flt_val,
"HGLT_OBS": flt_val,
"EAR_TIME": flt_val,
"SUN_TIME": flt_val,
# "JITRSDEV": flt_val, # std deviation of jitter from FPS or GT values
# "FPSNUMS": 99999, # Number of FPS samples
# "FPSOFFY": 0, # Y offset
# "FPSOFFZ": 0, # Z offset
# "FPSGTSY": 0, # FPS Y sum
# "FPSGTSZ": 0, # FPS Z sum
# "FPSGTQY": 0, # FPS Y square
# "FPSGTQZ": 0, # FPS Z square
# "FPSERS1": 0, # PZT Error sum [0]
# "FPSERS2": 0, # PZT Error sum [1]
# "FPSERS3": 0, # PZT Error sum [2]
# "FPSERQ1": 0, # PZT Error square [0]
# "FPSERQ2": 0, # PZT Error square [1]
# "FPSERQ3": 0, # PZT Error square [2]
# "FPSDAS1": 0, # PZT DAC sum [0]
# "FPSDAS2": 0, # PZT DAC sum [1]
# "FPSDAS3": 0, # PZT DAC sum [2]
# "FPSDAQ1": 0, # PZT DAC square [0]
# "FPSDAQ2": 0, # PZT DAC square [1]
# "FPSDAQ3": 0 # PZT DAC square [2]
}
for key in secchi_hdr.keys():
if not key in hdr:
hdr[key] = secchi_hdr[key]
return hdr
#######################################################################################################################################
def parse_yml(config_path):
"""
Parses configuration file.
@return: Configuration file content
"""
with open(config_path) as stream:
try:
content = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
return content
#######################################################################################################################################
def limit_cpu():
"""
Is called when starting a new multiprocessing pool. Decreases priority of processes to limit total CPU usage.
"""
p = psutil.Process(os.getpid())
# set to lowest priority
p.nice(19)
#######################################################################################################################################
def listfd(input_url, extension):
"""
Provides list of urls and corresponding file names to download.
@param input_url: URL of STEREO-HI image files
@param extension: File ending of STEREO-HI image files
@return: List of URLs and corresponding filenames to be downloaded
"""
disable_warnings(InsecureRequestWarning)
session = requests.Session()
retry = Retry(connect=3, backoff_factor=0.5)
adapter = HTTPAdapter(max_retries=retry)
session.mount('http://', adapter)
session.mount('https://', adapter)
output_urls = []
page = session.get(input_url).text
#page = requests.get(input_url, verify=False).text
soup = BeautifulSoup(page, 'html.parser')
url_found = [input_url + '/' + node.get('href') for node in soup.find_all('a') if node.get('href').endswith(extension)]
filename = [node.get('href') for node in soup.find_all('a') if node.get('href').endswith(extension)]
for i in range(len(filename)):
output_urls.append((filename[i], url_found[i]))
return output_urls
#######################################################################################################################################
def fetch_url(path, entry):
"""
Downloads URLs specified by listfd.
@param path: Path where downloaded files are to be saved
@param entry: Combination of filename and URL of downloaded file
"""
filename, uri = entry
if not os.path.exists(path + '/' + filename):
r = requests.get(uri, allow_redirects=True)
open(path + '/' + filename, 'wb').write(r.content)
#######################################################################################################################################
def check_calfiles(path):
"""
Checks if SSW IDL HI calibration files are present - creates appropriate directory and downloads them if not.
@param path: Path in which calibration files are located/should be located
"""
url_cal = "https://soho.nascom.nasa.gov/solarsoft/stereo/secchi/calibration/"
print('Checking calibration files...')
if not os.path.exists(path + 'calibration/'):
os.makedirs(path + 'calibration/')
try:
uri = listfd(url_cal, '.fts')
for entry in uri:
if not os.path.isfile(path + 'calibration/' + entry[0]):
fetch_url(path + 'calibration', entry)
else:
pass
return
except KeyboardInterrupt:
return
except Exception as e:
logging.error(traceback.format_exc())
sys.exit()
#######################################################################################################################################
def check_pointfiles(path):
"""
Checks if SSW IDL HI calibration files are present - creates appropriate directory and downloads them if not.
@param path: Path in which calibration files are located/should be located
"""
url_point = "https://soho.nascom.nasa.gov/solarsoft/stereo/secchi/data/hi/"
print('Checking pointing files...')
if not os.path.exists(path + 'data/hi/'):
os.makedirs(path + 'data/hi/')
try:
uri = listfd(url_point, '.fts')
for entry in uri:
if not os.path.isfile(path + 'data/hi/' + entry[0]):
fetch_url(path + 'data/hi', entry)
else:
pass
return
except KeyboardInterrupt:
return
except Exception as e:
logging.error(traceback.format_exc())
sys.exit()
#######################################################################################################################################
def download_files(datelist, save_path, ftpsc, instrument, bflag, silent):
"""
Downloads STEREO images from NASA pub directory
@param datelist: List of dates for which to download files
@param save_path: Path for saving downloaded files
@param ftpsc: Spacecraft (STEREO-A/STEREO-B) for which to download files
@param instrument: Instrument (HI-1/HI-2) for which to download files
@param bflag: Data type (science/beacon) for which to download files
@param silent: Run in silent mode
"""
if ftpsc == 'A':
sc = 'ahead'
if ftpsc == 'B':
sc = 'behind'
if not silent:
print('Fetching files...')
for ins in instrument:
for date in datelist:
if bflag == 'beacon':
url = 'https://stereo-ssc.nascom.nasa.gov/pub/beacon/' + sc + '/secchi/img/' + ins + '/' + str(date)
else:
url = 'https://stereo-ssc.nascom.nasa.gov/pub/ins_data/secchi/L0/' + sc[0] + '/img/' + ins + '/' + str(date)
if bflag == 'beacon':
path_flg = 'beacon'
path_dir = save_path + 'stereo' + sc[0] + '/' + path_flg + '/secchi/img/' + ins + '/' + str(date)
if ins == 'hi_1':
if sc == 'ahead':
ext = 's7h1A.fts'
if sc == 'behind':
ext = 's7h1B.fts'
if ins == 'hi_2':
if sc == 'ahead':
ext = 's7h2A.fts'
if sc == 'behind':
ext = 's7h2B.fts'
if bflag == 'science':
path_flg = 'L0'
path_dir = save_path + 'stereo' + sc[0] + '/secchi/' + path_flg + '/img/' + ins + '/' + str(date)
if ins == 'hi_1':
if sc == 'ahead':
ext = 's4h1A.fts'
if sc == 'behind':
ext = 's4h1B.fts'
if ins == 'hi_2':
if sc == 'ahead':
ext = 's4h2A.fts'
if sc == 'behind':
ext = 's4h2B.fts'
if not os.path.exists(path_dir):
os.makedirs(path_dir)
num_cpus = cpu_count()
pool = Pool(int(num_cpus/2), limit_cpu)
urls = listfd(url, ext)
inputs = zip(repeat(path_dir), urls)
try:
results = pool.starmap(fetch_url, inputs, chunksize=5)
except ValueError:
continue
pool.close()
pool.join()
#######################################################################################################################################
def hi_remove_saturation(data, header, saturation_limit=14000, nsaturated=5):
"""Direct conversion of hi_remove_saturation.pro for IDL.
Detects and masks saturated pixels with nan. Takes image data and header as input. Returns fixed image.
@param data: Data of .fits file
@param header: Header of .fits file
@param saturation_limit: Threshold value before pixel is considered saturated
@param nsaturated: Number of pixels in a column before column is considered saturated
@return: Data with oversaturated columns removed"""
info="$Id: hi_remove_saturation.pro,v 1.3 2009/06/08 11:03:38 crothers Exp $"
n_im = header['imgseq'] + 1
imsum = header['summed']
dsatval = saturation_limit * n_im * (2 ** (imsum - 1)) ** 2
ind = np.where(data > dsatval)
# if a pixel has a value greater than the dsatval, begin check to test if column is saturated
if ind[0].size > 0:
# all pixels are set to zero, except ones exceeding the saturation limit
mask = np.zeros(np.shape(data))
ans = data.copy()
mask[ind] = 1
# pixels are summed up column-wise
# where nsaturated is exceeded, values are replaced by nan
colmask = np.sum(mask, 0)
ii = np.array(np.where(colmask > nsaturated))
if len(ii) > 0:
ans[:, ii] = np.nan #np.nanmedian(data)
else:
ans = data.copy()
else:
ans = data.copy()
return ans
#######################################################################################################################################
def hi_remove_saturation_rdif(data):
"""Direct conversion of hi_remove_saturation.pro for IDL.
Detects and masks saturated pixels with nan. Takes image data and header as input. Returns fixed image.
@param data: Data of .fits file
@param header: Header of .fits file
@return: Data with oversaturated columns removed"""
# number of pixels in a column before column is considered saturated
nsaturated = 3
dsatval = np.nanmedian(data) + 2 * np.std(data)
ind = np.where(np.abs(data) > dsatval)
# if a pixel has a value greater than the dsatval, begin check to test if column is saturated
if ind[0].size > 0:
# all pixels are set to zero, except ones exceeding the saturation limit
mask = data * 0
ans = data.copy()
mask[ind] = 1
# pixels are summed up column-wise
# where nsaturated is exceeded, values are replaced by nan
colmask = np.sum(mask, 0)
ii = np.where(colmask > nsaturated)
if ii[0].size > 0:
ans[:, ii] = np.nan # np.nanmedian(data)
else:
ans = data.copy()
else:
ans = data.copy()
return ans
#######################################################################################################################################
def remove_bad_col(data):
"""
Removes saturated columns from .fits files.
@param data: Data of .fits file
@return: Data with saturated columns removed
"""
nsaturated = 3
dsatval = 0.95
ind = np.where(np.abs(data) > dsatval)
# if a pixel has a value greater than the dsatval, begin check to test if column is saturated
if ind[0].size > 0:
# all pixels are set to zero, except ones exceeding the saturation limit
mask = data * 0
ans = data.copy()
mask[ind] = 1
# pixels are summed up column-wise
# where nsaturated is exceeded, values are replaced by nan
colmask = np.sum(mask, 0)
ii = np.where(colmask > nsaturated)
if ii[0].size > 0:
ans[:, ii] = np.nanmedian(data)
else:
ans = data.copy()
else:
ans = data.copy()
return ans
#######################################################################################################################################
def scc_sebip(data, header, silent):
"""Direct conversion of scc_sebip.pro for IDL.
Determines what has happened in terms of on-board sebip binning and corrects it.
Takes image data and header as input and returns fixed image.
@param data: Data of .fits file
@param header: Header of .fits file
@param silent: Run in silent mode
@return: Data corrected for on-board binning"""
# IP_00_19= '41128 31114 37113121 7 41 37120129 7 40 87 50 3 53 1100'
# IP_00_19= '41128 31 34 37113121 7 41 37120129 7 0 0 0 0 0 0 0' /
ip_raw = header['IP_00_19']
while len(ip_raw) < 60:
ip_raw = ' ' + ip_raw
header['IP_00_19'] = ip_raw
ip_bytes = bytearray(ip_raw, encoding='ascii')
ip_arr = np.array(ip_bytes)
ip_reform = ip_arr.reshape(-1, 3).transpose()
ip_temp = []
ip = []
for i in range(ip_reform.shape[1]):
ip_temp.append(ip_reform[:, i].tostring())
for i in range(len(ip_temp)):
ip.append(ip_temp[i].decode('ascii'))
cnt = ip.count('117')
if cnt == 1:
ind = np.where(ip == '117')
ip = ip[3 * ind:]
while len(ip) < 60:
ip = ip.append(' 0')
header['IP_00_19'] = ''.join(ip)
## CHANGE updated header, added count16 + count17 to match IDL behaviour (was xor before)
cnt1 = ip.count(' 1')
cnt2 = ip.count(' 2')
cntspw = ip.count(' 16') + ip.count(' 17')
cnt50 = ip.count(' 50')
cnt53 = ip.count(' 53')
cnt82 = ip.count(' 82')
cnt83 = ip.count(' 83')
cnt84 = ip.count(' 84')
cnt85 = ip.count(' 85')
cnt86 = ip.count(' 86')
cnt87 = ip.count(' 87')
cnt88 = ip.count(' 88')
cnt118 = ip.count('118')
# print(cnt1,cnt2,cntspw,cnt50,cnt53,cnt82,cnt83,cnt84,cnt85,cnt86,cnt87,cnt88,cnt118)
if header['DIV2CORR']:
cnt1 = cnt1 - 1
if cnt1 < 0:
cnt1 = 0
if cnt1 > 0:
data = data * (2.0 ** cnt1)
if not silent:
print('Corrected for divide by 2 x {}'.format(cnt1))
header['HISTORY'] = 'seb_ip Corrected for divide by 2 x {}'.format(cnt1)
if cnt2 > 0:
## CHANGE to square instead of multiply
data = data ** (2.0 ** cnt2)
if not silent:
print('Corrected for square root x {}'.format(cnt2))
header['HISTORY'] = 'seb_ip Corrected for square root x {}'.format(cnt2)
if cntspw > 0:
data = data * (64.0 ** cntspw)
if not silent:
print('Corrected for HI SPW divide by 64 x {}'.format(cntspw))
header['HISTORY'] = 'seb_ip Corrected for HI SPW divide by 64 x {}'.format(cntspw)
if cnt50 > 0:
data = data * (4.0 ** cnt50)
if not silent:
print('Corrected for divide by 4 x {}'.format(cnt50))
header['HISTORY'] = 'seb_ip Corrected for divide by 4 x {}'.format(cnt50)
if cnt53 > 0 and header['ipsum'] > 0:
data = data * (4.0 ** cnt53)
if not silent:
print('Corrected for divide by 4 x {}'.format(cnt53))
header['HISTORY'] = 'seb_ip Corrected for divide by 4 x {}'.format(cnt53)
if cnt82 > 0:
data = data * (2.0 ** cnt82)
if not silent:
print('Corrected for divide by 2 x {}'.format(cnt82))
header['HISTORY'] = 'seb_ip Corrected for divide by 2 x {}'.format(cnt82)
if cnt83 > 0:
data = data * (4.0 ** cnt83)
if not silent:
print('Corrected for divide by 4 x {}'.format(cnt83))
header['HISTORY'] = 'seb_ip Corrected for divide by 4 x {}'.format(cnt83)
if cnt84 > 0:
data = data * (8.0 ** cnt84)
if not silent:
print('Corrected for divide by 8 x {}'.format(cnt84))
header['HISTORY'] = 'seb_ip Corrected for divide by 8 x {}'.format(cnt84)
if cnt85 > 0:
data = data * (16.0 ** cnt85)
if not silent:
print('Corrected for divide by 16 x {}'.format(cnt85))
header['HISTORY'] = 'seb_ip Corrected for divide by 16 x {}'.format(cnt85)
if cnt86 > 0:
data = data * (32.0 ** cnt86)
if not silent:
print('Corrected for divide by 32 x {}'.format(cnt86))
header['HISTORY'] = 'seb_ip Corrected for divide by 32 x {}'.format(cnt86)
if cnt87 > 0:
data = data * (64.0 ** cnt87)
if not silent:
print('Corrected for divide by 64 x {}'.format(cnt87))
header['HISTORY'] = 'seb_ip Corrected for divide by 64 x {}'.format(cnt87)
if cnt88 > 0:
data = data * (128.0 ** cnt88)
if not silent:
print('Corrected for divide by 128 x {}'.format(cnt88))
header['HISTORY'] = 'seb_ip Corrected for divide by 128 x {}'.format(cnt88)
if cnt118 > 0:
data = data * (3.0 ** cnt118)
if not silent:
print('Corrected for divide by 3 x {}'.format(cnt118))
header['HISTORY'] = 'seb_ip Corrected for divide by 3 x {}'.format(cnt118)
if not silent:
print('------------------------------------------------------')
return data, header
#######################################################################################################################################
def scc_get_missing(hdr, silent=True):
"""
This function returns the index of the missing pixels.
Args:
hdr: Image header, either FITS or SECCHI structure.
silent: Boolean flag to suppress output.
Returns:
missing: 1D array of longword vector containing the subscripts of the missing pixels.
"""
# Convert MISSLIST to Superpixel 1D index
base = 34
misslist_str = hdr['MISSLIST']
len_misslist = len(misslist_str)
if len_misslist % 2 != 0:
misslist_str = ' ' + misslist_str
len_misslist += 1
dex = np.arange(0, len_misslist, 2)
misslist = np.asarray([int(misslist_str[i:i+2].strip(), base) for i in dex])
n = len(misslist)
if n != hdr['NMISSING']:
if not silent: