-
Notifications
You must be signed in to change notification settings - Fork 0
/
wtoDatabase.py
1319 lines (1179 loc) · 48.5 KB
/
wtoDatabase.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
"""
wtoDatabase.py: the gWTO database library.
==========================================
This library contains the classes and functions required to query, parse and
organize the Projects and SchedBlock information stored at the OSF archive in
different tables.
"""
__author__ = 'itoledo'
__metaclass__ = type
import numpy as np
import pandas as pd
import csv
import cx_Oracle
import os
from lxml import objectify
from subprocess import call
import arrayResolution2p as ARes
conx_string = os.environ['CON_STR']
prj = '{Alma/ObsPrep/ObsProject}'
val = '{Alma/ValueTypes}'
sbl = '{Alma/ObsPrep/SchedBlock}'
# noinspection PyPep8Naming
class WtoDatabase(object):
"""
WtoDatabase is the class that stores the Projects and SB information in
dataframes, and it also has the methods to connect and query the OSF
archive for this info.
A default instance will use the directory $HOME/.wto as a cache, and by
default find the approved Cycle 2 projects and carried-over Cycle 1
projects. If a file name or list are given as 'source' parameter, only the
information of the projects in that list or filename will be ingested.
Setting *forcenew* to True will force the cleaning of the cache dir, and
all information will be processed again.
:param path: Path for data cache.
:type path: str, default '$HOME/.wto'
:param source: File or list of strings with the codes of the projects
to be ingested by WtoDatabase.
:type source: list or str
:param forcenew: Force cache cleaning and reload from archive.
:type forcenew: boolean, default False
"""
def __init__(self, path='/.wto/', source=None, forcenew=False):
"""
"""
self.source = source
self.new = forcenew
# Default Paths and Preferences
if path[-1] != '/':
path += '/'
self.path = os.environ['HOME'] + path
self.wto_path = os.environ['WTO']
self.sbxml = self.path + 'sbxml/'
self.obsxml = self.path + 'obsxml/'
self.preferences = pd.Series(
['obsproject.pandas', source, 'sciencegoals.pandas',
'scheduling.pandas', 'special.list', 'pwvdata.pandas',
'executive.pandas', 'sbxml_table.pandas', 'sbinfo.pandas',
'newar.pandas', 'fieldsource.pandas', 'target.pandas',
'spectralconf.pandas'],
index=['obsproject_table', 'source', 'sciencegoals_table',
'scheduling_table', 'special', 'pwv_data',
'executive_table', 'sbxml_table', 'sbinfo_table',
'newar_table', 'fieldsource_table', 'target_table',
'spectralconf_table'])
self.states = ["Approved", "Phase1Submitted", "Broken",
"Canceled", "Rejected"]
# Global SQL search expressions
self.sql1 = str(
"SELECT PRJ_ARCHIVE_UID,DELETED,PI,PRJ_NAME,"
"CODE,PRJ_TIME_OF_CREATION,PRJ_SCIENTIFIC_RANK,PRJ_VERSION,"
"PRJ_LETTER_GRADE,DOMAIN_ENTITY_STATE,"
"OBS_PROJECT_ID "
"FROM ALMA.BMMV_OBSPROJECT obs1, ALMA.OBS_PROJECT_STATUS obs2 "
"WHERE regexp_like (CODE, '^201[23].*\.[AST]') "
"AND (PRJ_LETTER_GRADE='A' OR PRJ_LETTER_GRADE='B' "
"OR PRJ_LETTER_GRADE='C') "
"AND obs2.OBS_PROJECT_ID = obs1.PRJ_ARCHIVE_UID")
self.sqlsched_proj = str(
"SELECT * FROM SCHEDULING_AOS.OBSPROJECT "
"WHERE regexp_like (CODE, '^201[23].*\.[AST]')")
self.sqlstates = str(
"SELECT DOMAIN_ENTITY_STATE,DOMAIN_ENTITY_ID,OBS_PROJECT_ID "
"FROM ALMA.SCHED_BLOCK_STATUS")
self.sqlqa0 = str(
"SELECT SCHEDBLOCKUID,QA0STATUS FROM ALMA.AQUA_EXECBLOCK "
"WHERE regexp_like (OBSPROJECTCODE, '^201[23].*\.[AST]')")
self.sqlsched_sb = str(
"SELECT ou.OBSUNIT_UID,sb.NAME,sb.REPR_BAND,"
"sb.SCHEDBLOCK_CTRL_EXEC_COUNT,sb.SCHEDBLOCK_CTRL_STATE,"
"sb.MIN_ANG_RESOLUTION,sb.MAX_ANG_RESOLUTION,"
"ou.OBSUNIT_PROJECT_UID "
"FROM SCHEDULING_AOS.SCHEDBLOCK sb, SCHEDULING_AOS.OBSUNIT ou "
"WHERE sb.SCHEDBLOCKID = ou.OBSUNITID AND sb.CSV = 0")
self.execbal_sql = str(
"select ALMA.mv_obsproject.cycle, ALMA.mv_obsproject.executive,"
"sum(ALMA.mv_schedblock.USED_TIME) / 3600,"
"sum(ALMA.mv_schedblock.TIME) / 3600 "
"from ALMA.mv_schedblock join ALMA.mv_obsproject "
"on ALMA.mv_schedblock.prj_ref = ALMA.mv_obsproject.PRJ_ARCHIVE_UID"
" join ALMA.obs_project_status "
"on ALMA.obs_project_status.DOMAIN_ENTITY_ID "
"= ALMA.mv_obsproject.PRJ_ARCHIVE_UID "
"where (ALMA.obs_project_status.domain_entity_state !='Canceled' "
"and ALMA.obs_project_status.domain_entity_state !='Rejected' "
"and ALMA.obs_project_status.domain_entity_state !='CSVReady') "
"and (ALMA.mv_obsproject.CYCLE='2013.1' or "
" ALMA.mv_obsproject.CYCLE='2013.A' or "
" ALMA.mv_obsproject.CYCLE='2012.1' or "
" ALMA.mv_obsproject.CYCLE='2012.A') "
"and mv_schedblock.requested_array = 'TWELVE-M' "
"group by ALMA.mv_obsproject.cycle, ALMA.mv_obsproject.executive")
# Global Oracle Connection
self.connection = cx_Oracle.connect(conx_string)
self.cursor = self.connection.cursor()
# Populate different dataframes related to projects and SBs statuses
self.cursor.execute(self.sqlsched_proj)
self.scheduling_proj = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('CODE', drop=False)
self.cursor.execute(self.sqlstates)
self.sbstates = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('DOMAIN_ENTITY_ID')
self.cursor.execute(self.sqlqa0)
self.qa0 = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('SCHEDBLOCKUID', drop=False)
self.cursor.execute(self.sqlsched_sb)
self.scheduling_sb = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('OBSUNIT_UID', drop=False)
# Initialize with saved data and update, Default behavior.
if not self.new:
try:
self.obsproject = pd.read_pickle(
self.path + self.preferences.obsproject_table)
self.sciencegoals = pd.read_pickle(
self.path + self.preferences.sciencegoals_table)
self.schedblocks = pd.read_pickle(
self.path + self.preferences.sbxml_table)
self.schedblock_info = pd.read_pickle(
self.path + self.preferences.sbinfo_table)
self.newar = pd.read_pickle(
self.path + self.preferences.newar_table)
self.fieldsource = pd.read_pickle(
self.path + self.preferences.fieldsource_table)
self.target = pd.read_pickle(
self.path + self.preferences.target_table)
self.spectralconf = pd.read_pickle(
self.path + self.preferences.spectralconf_table)
self.filter_c1()
self.update()
except IOError, e:
print e
self.new = True
# Create main dataframes
if self.new:
call(['rm', '-rf', self.path])
print(self.path + ": creating preferences dir")
os.mkdir(self.path)
os.mkdir(self.sbxml)
os.mkdir(self.obsxml)
self.start_wto()
self.populate_sciencegoals_sbxml()
self.populate_schedblocks()
self.populate_schedblock_info()
self.populate_newar()
self.create_summary()
def start_wto(self):
"""
Initializes the wtoDatabase dataframes.
The function queries the archive to look for cycle 1 and cycle 2
projects, disregarding any projects with status "Approved",
"Phase1Submitted", "Broken", "Canceled" or "Rejected".
The archive tables used are ALMA.BMMV_OBSPROPOSAL,
ALMA.OBS_PROJECT_STATUS, ALMA.BMMV_OBSPROJECT and
ALMA.XML_OBSPROJECT_ENTITIES.
:return: None
"""
# noinspection PyUnusedLocal
states = self.states
sql2 = str(
"SELECT PROJECTUID,ASSOCIATEDEXEC "
"FROM ALMA.BMMV_OBSPROPOSAL "
"WHERE (CYCLE='2012.1' OR CYCLE='2013.1' OR CYCLE='2013.A' "
"OR CYCLE='2012.A')")
self.cursor.execute(sql2)
self.executive = pd.DataFrame(
self.cursor.fetchall(), columns=['PRJ_ARCHIVE_UID', 'EXEC'])
if self.source is None:
self.cursor.execute(self.sql1)
df1 = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description])
print(len(df1.query('DOMAIN_ENTITY_STATE not in @states')))
self.obsproject = pd.merge(
df1.query('DOMAIN_ENTITY_STATE not in @states'), self.executive,
on='PRJ_ARCHIVE_UID').set_index('CODE', drop=False)
else:
if type(self.source) is not str and type(self.source) is not list:
print "The source should be a string or a list"
return None
try:
if type(self.source) is str:
fp = open(self.source, 'r')
read_csv = csv.reader(fp)
else:
read_csv = self.source
c = 0
for l in read_csv:
if type(self.source) is str:
l = l[0]
sql3 = self.sql1 + ' AND OBS1.PRJ_CODE = ' + '\'%s\'' % l
self.cursor.execute(sql3)
if c == 0:
df2 = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description])
else:
df2.ix[c] = pd.Series(
self.cursor.fetchall()[0], index=df2.columns)
c += 1
self.obsproject = pd.merge(
df2.query('DOMAIN_ENTITY_STATE not in @states'),
self.executive,
on='PRJ_ARCHIVE_UID').set_index('CODE', drop=False)
except IOError:
print "Source filename does not exist"
return None
timestamp = pd.Series(
np.zeros(len(self.obsproject), dtype=object),
index=self.obsproject.index)
self.obsproject['timestamp'] = timestamp
self.obsproject['obsproj'] = pd.Series(
np.zeros(len(self.obsproject), dtype=object),
index=self.obsproject.index)
codes = self.obsproject.CODE.tolist()
for c in codes:
self.get_obsproject(c)
self.filter_c1()
print len(self.obsproject)
self.obsproject.to_pickle(
self.path + self.preferences.obsproject_table)
self.cursor.execute(self.execbal_sql)
self.balance = pd.DataFrame(
self.cursor.fetchall(), columns=['CYCLE', 'EXEC', 'usedTime',
'totalTime'])
def update(self, connect=True):
"""
:param connect:
:return:
"""
self.cursor.execute(self.execbal_sql)
self.balance = pd.DataFrame(
self.cursor.fetchall(), columns=['CYCLE', 'EXEC', 'usedTime',
'totalTime'])
self.cursor.execute(self.sqlsched_proj)
self.scheduling_proj = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('CODE', drop=False)
self.cursor.execute(self.sqlsched_sb)
self.scheduling_sb = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('OBSUNIT_UID', drop=False)
self.cursor.execute(self.sqlstates)
self.sbstates = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('DOMAIN_ENTITY_ID')
self.cursor.execute(self.sqlqa0)
self.qa0 = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('SCHEDBLOCKUID', drop=False)
if not connect:
self.create_summary()
return None
newest = self.obsproject.timestamp.max()
changes = []
sql = str(
"SELECT ARCHIVE_UID, TIMESTAMP FROM ALMA.XML_OBSPROJECT_ENTITIES "
"WHERE TIMESTAMP > to_date('%s', 'YYYY-MM-DD HH24:MI:SS')" %
str(newest).split('.')[0])
self.cursor.execute(sql)
new_data = self.cursor.fetchall()
if len(new_data) > 0:
for n in new_data:
print "Changes? %s, %s, newest %s" % (n[0], n[1], newest)
if n[1] <= newest:
print "\t Not Changes to apply (1)"
continue
puid = n[0]
try:
code = self.obsproject[
self.obsproject.PRJ_ARCHIVE_UID == puid].ix[0, 'CODE']
if code in self.checked.CODE.tolist():
changes.append(code)
else:
print "\t Not Changes to apply (2)"
continue
except IndexError:
try:
self.cursor.execute(
self.sql1 + " AND OBS1.PRJ_ARCHIVE_UID = '%s'" %
puid)
row = list(self.cursor.fetchall()[0])
except IndexError:
print("\t %s must be a CSV project. Not ingesting" %
puid)
continue
code = row[4]
if (code not in self.checked.CODE.tolist() and
code.startswith('2012')):
print("\t %s didn't pass filter C1" % code)
continue
self.cursor.execute(
"SELECT ASSOCIATEDEXEC FROM ALMA.BMMV_OBSPROPOSAL "
"WHERE PROJECTUID = '%s'" % puid)
row.append(self.cursor.fetchall()[0][0])
row.append(n[1])
row.append(self.obsproject.ix[0, 'obsproj'])
self.obsproject.ix[code] = row
changes.append(code)
for code in changes:
print "Updating Project %s" % code
self.get_obsproject(code)
self.row_sciencegoals(code)
pidlist = self.sciencegoals[
self.sciencegoals.CODE == code].partId.tolist()
for pid in pidlist:
sblist = self.sciencegoals.ix[pid].SBS
print sblist.split(',')
for sb in sblist.split(','):
print "\tUpdating sb %s of project %s" % (sb, code)
self.row_schedblocks(sb, pid)
self.row_schedblock_info(sb)
self.row_newar(sb)
self.filter_c1()
self.schedblocks.to_pickle(
self.path + self.preferences.sbxml_table)
self.sciencegoals.to_pickle(
self.path + self.preferences.sciencegoals_table)
self.schedblock_info.to_pickle(
self.path + self.preferences.sbinfo_table)
self.newar.to_pickle(
self.path + self.preferences.newar_table)
self.fieldsource.to_pickle(
self.path + self.preferences.fieldsource_table)
self.target.to_pickle(
self.path + self.preferences.target_table)
self.spectralconf.to_pickle(
self.path + self.preferences.spectralconf_table)
newest = self.schedblocks.timestamp.max()
sql = str(
"SELECT ARCHIVE_UID, TIMESTAMP FROM ALMA.XML_SCHEDBLOCK_ENTITIES "
"WHERE TIMESTAMP > to_date('%s', 'YYYY-MM-DD HH24:MI:SS')" %
str(newest).split('.')[0])
self.cursor.execute(sql)
new_data = self.cursor.fetchall()
if len(new_data) > 0:
for n in new_data:
if n[1] <= newest:
continue
sbuid = n[0]
try:
pid = self.schedblocks[
self.schedblocks.SB_UID == sbuid].ix[0, 'partId']
except IndexError:
continue
print "Updating SB %s" % sbuid
self.row_schedblocks(sbuid, pid)
self.row_schedblock_info(sbuid)
self.row_newar(sbuid)
self.schedblocks.to_pickle(
self.path + self.preferences.sbxml_table)
self.schedblock_info.to_pickle(
self.path + self.preferences.sbinfo_table)
self.newar.to_pickle(
self.path + self.preferences.newar_table)
self.fieldsource.to_pickle(
self.path + self.preferences.fieldsource_table)
self.target.to_pickle(
self.path + self.preferences.target_table)
self.spectralconf.to_pickle(
self.path + self.preferences.spectralconf_table)
self.cursor.execute("SELECT OBS_PROJECT_ID, DOMAIN_ENTITY_STATE "
"FROM ALMA.OBS_PROJECT_STATUS")
newprstate = pd.DataFrame(
self.cursor.fetchall(),
columns=[rec[0] for rec in self.cursor.description]
).set_index('OBS_PROJECT_ID', drop=False)
ori = self.obsproject[['DOMAIN_ENTITY_STATE']]
self.obsproject.loc[:, 'DOMAIN_ENTITY_STATE'] = self.obsproject.apply(
lambda r: newprstate.loc[r['PRJ_ARCHIVE_UID'],
'DOMAIN_ENTITY_STATE'],
axis=1)
self.obsproject.to_pickle(
self.path + self.preferences.obsproject_table)
new = self.obsproject[['DOMAIN_ENTITY_STATE']]
# i = ori != new
if len(new[new != ori]) > 0:
print("Detected PRJ state changes: ")
print(new[new != ori])
else:
print("No PRJ states changes.")
self.create_summary()
def populate_sciencegoals_sbxml(self):
"""
"""
try:
type(self.sciencegoals)
new = False
except AttributeError:
new = True
codes = self.obsproject.CODE.tolist()
print len(codes)
for c in codes:
self.row_sciencegoals(c, new=new)
new = False
self.sciencegoals.to_pickle(
self.path + self.preferences.sciencegoals_table)
def populate_schedblock_info(self):
"""
"""
new = True
sb_uid_list = self.schedblocks.SB_UID.tolist()
numsb = len(sb_uid_list)
cou = 1
for s in sb_uid_list:
self.row_schedblock_info(s, new=new)
print("SB %s processed (%d/%d)" % (s, cou, numsb))
new = False
cou += 1
self.schedblock_info.to_pickle(
self.path + self.preferences.sbinfo_table)
self.fieldsource.to_pickle(
self.path + self.preferences.fieldsource_table)
self.target.to_pickle(
self.path + self.preferences.target_table)
self.spectralconf.to_pickle(
self.path + self.preferences.spectralconf_table)
def populate_schedblocks(self):
"""
"""
new = True
sbpartid = self.sciencegoals.index.tolist()
sizel = len(sbpartid)
c = 1
for pid in sbpartid:
sblist = self.sciencegoals.ix[pid].SBS
for sb in sblist.split(','):
sta = self.sbstates.query(
'DOMAIN_ENTITY_ID == @sb').DOMAIN_ENTITY_STATE.values[0]
if sta in self.states:
continue
self.row_schedblocks(sb, pid, new=new)
new = False
print "%d/%d ScienceGoals SBs ingested" % (c, sizel)
c += 1
self.schedblocks.to_pickle(
self.path + self.preferences.sbxml_table)
def populate_newar(self):
"""
"""
new = True
sblist = self.schedblock_info.SB_UID.tolist()
for sbuid in sblist:
self.row_newar(sbuid, new=new)
new = False
self.newar.to_pickle(
self.path + self.preferences.newar_table)
def get_obsproject(self, code):
"""
:param code:
"""
print("Downloading Project %s obsproject.xml" % code)
self.cursor.execute(
"SELECT TIMESTAMP, XMLTYPE.getClobVal(xml) "
"FROM ALMA.XML_OBSPROJECT_ENTITIES "
"WHERE ARCHIVE_UID = '%s'" % self.obsproject.ix[
code, 'PRJ_ARCHIVE_UID'])
data = self.cursor.fetchall()[0]
xml_content = data[1].read()
xmlfilename = code + '.xml'
self.obsproject.loc[code, 'timestamp'] = data[0]
filename = self.obsxml + xmlfilename
io_file = open(filename, 'w')
io_file.write(xml_content)
io_file.close()
self.obsproject.loc[code, 'obsproj'] = xmlfilename
def row_sciencegoals(self, code, new=False):
"""
:param code:
:param new:
:return:
"""
c = code
proj = self.obsproject[self.obsproject.CODE == c].ix[0]
obsproj = ObsProject(proj.obsproj, self.obsxml)
assoc_sbs = obsproj.assoc_sched_blocks()
try:
for sg in range(len(obsproj.ObsProgram.ScienceGoal)):
code = code
sciencegoal = obsproj.ObsProgram.ScienceGoal[sg]
try:
partid = sciencegoal.ObsUnitSetRef.attrib['partId']
except AttributeError:
continue
perfparam = sciencegoal.PerformanceParameters
ar = perfparam.desiredAngularResolution.pyval
arunit = perfparam.desiredAngularResolution.attrib['unit']
ar = convert_sec(ar, arunit)
las = perfparam.desiredLargestScale.pyval
lasunit = perfparam.desiredLargestScale.attrib['unit']
las = convert_sec(las, lasunit)
bands = sciencegoal.requiredReceiverBands.pyval
istimeconst = perfparam.isTimeConstrained.pyval
if istimeconst:
try:
temppar = perfparam.TemporalParameters
starttime = temppar.startTime.pyval
endtime = temppar.endTime.pyval
try:
allowedmarg = temppar.allowedMargin.pyval
allowedmarg_unit = temppar.allowedMargin.attrib[
'unit']
except AttributeError:
allowedmarg = pd.np.nan
allowedmarg_unit = pd.np.nan
repeats = temppar.repeats.pyval
note = temppar.note.pyval
try:
isavoid = temppar.isAvoidConstraint.pyval
except AttributeError:
isavoid = pd.np.nan
except AttributeError, e:
print("Project %s is timeconstrain but no parameters?"
"(%s)" % (code, e))
temppar, starttime, endtime, allowedmarg = (
pd.np.nan, pd.np.nan, pd.np.nan, pd.np.nan)
allowedmarg_unit, repeats, note, isavoid = (
pd.np.nan, pd.np.nan, pd.np.nan, pd.np.nan)
else:
temppar, starttime, endtime, allowedmarg = (
pd.np.nan, pd.np.nan, pd.np.nan, pd.np.nan)
allowedmarg_unit, repeats, note, isavoid = (
pd.np.nan, pd.np.nan, pd.np.nan, pd.np.nan)
try:
# noinspection PyUnusedLocal
ss = sciencegoal.SpectralSetupParameters.SpectralScan
isspectralscan = True
except AttributeError:
isspectralscan = False
useaca = sciencegoal.PerformanceParameters.useACA.pyval
usetp = sciencegoal.PerformanceParameters.useTP.pyval
ps = sciencegoal.PerformanceParameters.isPointSource.pyval
if new:
self.sciencegoals = pd.DataFrame(
[(code, partid, ar, las, bands, isspectralscan,
istimeconst, useaca, usetp, ps,
','.join(assoc_sbs[partid]),
starttime, endtime, allowedmarg,
allowedmarg_unit, repeats, note, isavoid)],
columns=['CODE', 'partId', 'AR', 'LAS', 'bands',
'isSpectralScan', 'isTimeConstrained',
'useACA', 'useTP', 'ps', 'SBS', 'startTime',
'endTime', 'allowedMargin', 'allowedUnits',
'repeats', 'note', 'isavoid'],
index=[partid])
new = False
else:
self.sciencegoals.loc[partid] = (
code, partid, ar, las, bands, isspectralscan,
istimeconst, useaca, usetp, ps,
','.join(assoc_sbs[partid]),
starttime, endtime, allowedmarg,
allowedmarg_unit, repeats, note, isavoid)
except AttributeError, e:
print "Project %s has no ObsUnitSets (%s)" % (code, e)
return 0
return 0
def row_schedblock_info(self, sb_uid, new=False):
# Open SB with SB parser class
"""
:param sb_uid:
:param new:
"""
sb = self.schedblocks.ix[sb_uid]
pid = sb.partId
xml = SchedBlocK(sb.sb_xml, self.sbxml)
new_orig = new
# Extract root level data
array = xml.data.findall(
'.//' + prj + 'ObsUnitControl')[0].attrib['arrayRequested']
name = xml.data.findall('.//' + prj + 'name')[0].pyval
status = xml.data.attrib['status']
schedconstr = xml.data.SchedulingConstraints
schedcontrol = xml.data.SchedBlockControl
preconditions = xml.data.Preconditions
weather = preconditions.findall('.//' + prj + 'WeatherConstraints')[0]
try:
ampliparam = xml.data.AmplitudeCalParameters
amplitude = str(ampliparam.attrib['entityPartId'])
except AttributeError:
amplitude = None
try:
phaseparam = xml.data.PhaseCalParameters
phase = str(phaseparam.attrib['entityPartId'])
except AttributeError:
phase = None
try:
bandpassparam = xml.data.BandpassCalParameters
bandpass = str(bandpassparam.attrib['entityPartId'])
except AttributeError:
bandpass = None
try:
polarparam = xml.data.PolarizationCalParameters
polarization = str(polarparam.attrib['entityPartId'])
ispolarization = True
except AttributeError:
ispolarization = False
polarization = None
try:
delayparam = xml.data.DelayCalParameters
delay = str(delayparam.attrib['entityPartId'])
except AttributeError:
delay = None
try:
scienceparam = xml.data.ScienceParameters
science = str(scienceparam.attrib['entityPartId'])
integrationtime = scienceparam.integrationTime.pyval
integrationtime_unit = scienceparam.integrationTime.attrib['unit']
integrationtime = convert_tsec(integrationtime, integrationtime_unit)
subscandur = scienceparam.subScanDuration.pyval
subscandur_unit = scienceparam.subScanDuration.attrib['unit']
subscandur = convert_tsec(subscandur, subscandur_unit)
except AttributeError:
science = ''
integrationtime = 0
subscandur = 0
repfreq = schedconstr.representativeFrequency.pyval
ra = schedconstr.representativeCoordinates.findall(
val + 'longitude')[0].pyval
dec = schedconstr.representativeCoordinates.findall(
val + 'latitude')[0].pyval
minar_old = schedconstr.minAcceptableAngResolution.pyval
maxar_old = schedconstr.maxAcceptableAngResolution.pyval
band = schedconstr.attrib['representativeReceiverBand']
execount = schedcontrol.executionCount.pyval
maxpwv = weather.maxPWVC.pyval
n_fs = len(xml.data.FieldSource)
n_tg = len(xml.data.Target)
n_ss = len(xml.data.SpectralSpec)
for n in range(n_fs):
if new:
self.row_fieldsource(xml.data.FieldSource[n], sb_uid, array,
new=new)
new = False
else:
self.row_fieldsource(xml.data.FieldSource[n], sb_uid, array)
new = new_orig
for n in range(n_tg):
if new:
self.row_target(xml.data.Target[n], sb_uid, new=new)
new = False
else:
self.row_target(xml.data.Target[n], sb_uid)
new = new_orig
for n in range(n_ss):
if new:
self.row_spectralconf(xml.data.SpectralSpec[n], sb_uid, new=new)
new = False
else:
self.row_spectralconf(xml.data.SpectralSpec[n], sb_uid)
new = new_orig
if new:
self.schedblock_info = pd.DataFrame(
[(sb_uid, pid, name, status,
repfreq, band, array, ra, dec, minar_old,
maxar_old, execount, ispolarization, amplitude,
bandpass, polarization, phase, delay,
science, integrationtime, subscandur, maxpwv)],
columns=['SB_UID', 'partId', 'name', 'status_xml',
'repfreq', 'band', 'array', 'RA', 'DEC', 'minAR_old',
'maxAR_old', 'execount', 'isPolarization', 'amplitude',
'bandpass', 'polarization', 'phase', 'delay',
'science', 'integrationTime', 'subScandur', 'maxPWVC'],
index=[sb_uid])
else:
self.schedblock_info.ix[sb_uid] = (
sb_uid, pid, name, status, repfreq, band, array, ra, dec,
minar_old, maxar_old, execount, ispolarization,
amplitude, bandpass, polarization, phase, delay, science,
integrationtime, subscandur, maxpwv)
def row_fieldsource(self, fs, sbuid, array, new=False):
"""
:param fs:
:param sbuid:
:param new:
"""
partid = fs.attrib['entityPartId']
coord = fs.sourceCoordinates
solarsystem = fs.attrib['solarSystemObject']
sourcename = fs.sourceName.pyval
name = fs.name.pyval
isquery = fs.isQuery.pyval
pointings = len(fs.findall(sbl + 'PointingPattern/' + sbl +
'phaseCenterCoordinates'))
try:
ismosaic = fs.PointingPattern.isMosaic.pyval
except AttributeError:
ismosaic = False
if isquery:
querysource = fs.QuerySource
qc_intendeduse = querysource.attrib['intendedUse']
qcenter = querysource.queryCenter
qc_ra = qcenter.findall(val + 'longitude')[0].pyval
qc_dec = qcenter.findall(val + 'latitude')[0].pyval
qc_use = querysource.use.pyval
qc_radius = querysource.searchRadius.pyval
qc_radius_unit = querysource.searchRadius.attrib['unit']
else:
qc_intendeduse, qc_ra, qc_dec, qc_use, qc_radius, qc_radius_unit = (
None, None, None, None, None, None
)
ra = coord.findall(val + 'longitude')[0].pyval
dec = coord.findall(val + 'latitude')[0].pyval
if solarsystem == 'Ephemeris':
ephemeris = fs.sourceEphemeris.pyval
else:
ephemeris = None
if new:
self.fieldsource = pd.DataFrame(
[(partid, sbuid, solarsystem, sourcename, name, ra, dec,
isquery, qc_intendeduse, qc_ra, qc_dec, qc_use, qc_radius,
qc_radius_unit, ephemeris, pointings, ismosaic, array)],
columns=['fieldRef', 'SB_UID', 'solarSystem', 'sourcename',
'name', 'RA',
'DEC', 'isQuery', 'intendedUse', 'qRA', 'qDEC', 'use',
'search_radius', 'rad_unit', 'ephemeris',
'pointings', 'isMosaic', 'arraySB'],
index=[partid]
)
self.fieldsource.ix[partid] = (
partid, sbuid, solarsystem, sourcename, name, ra, dec, isquery,
qc_intendeduse, qc_ra, qc_dec, qc_use, qc_radius, qc_radius_unit,
ephemeris, pointings, ismosaic, array)
def row_target(self, tg, sbuid, new=False):
"""
:param tg:
:param sbuid:
:param new:
"""
partid = tg.attrib['entityPartId']
specref = tg.AbstractInstrumentSpecRef.attrib['partId']
fieldref = tg.FieldSourceRef.attrib['partId']
paramref = tg.ObservingParametersRef.attrib['partId']
if new:
self.target = pd.DataFrame(
[(sbuid, specref, fieldref, paramref)],
columns=['SB_UID', 'specRef', 'fieldRef', 'paramRef'],
index=[partid])
else:
self.target.ix[partid] = (sbuid, specref, fieldref, paramref)
def row_spectralconf(self, ss, sbuid, new=False):
"""
:param ss:
:param sbuid:
:param new:
"""
partid = ss.attrib['entityPartId']
try:
corrconf = ss.BLCorrelatorConfiguration
nbb = len(corrconf.BLBaseBandConfig)
nspw = 0
for n in range(nbb):
bbconf = corrconf.BLBaseBandConfig[n]
nspw += len(bbconf.BLSpectralWindow)
except AttributeError:
corrconf = ss.ACACorrelatorConfiguration
nbb = len(corrconf.ACABaseBandConfig)
nspw = 0
for n in range(nbb):
bbconf = corrconf.ACABaseBandConfig[n]
nspw += len(bbconf.ACASpectralWindow)
if new:
self.spectralconf = pd.DataFrame(
[(partid, sbuid, nbb, nspw)],
columns=['specRef', 'SB_UID', 'BaseBands', 'SPWs'],
index=[partid])
else:
self.spectralconf.ix[partid] = (partid, sbuid, nbb, nspw)
def row_schedblocks(self, sb_uid, partid, new=False):
"""
:param sb_uid:
:param partid:
:param new:
"""
sql = "SELECT TIMESTAMP, XMLTYPE.getClobVal(xml) " \
"FROM ALMA.xml_schedblock_entities " \
"WHERE archive_uid = '%s'" % sb_uid
self.cursor.execute(sql)
data = self.cursor.fetchall()
xml_content = data[0][1].read()
filename = sb_uid.replace(':', '_').replace('/', '_') +\
'.xml'
io_file = open(self.sbxml + filename, 'w')
io_file.write(xml_content)
io_file.close()
xml = filename
if new:
self.schedblocks = pd.DataFrame(
[(sb_uid, partid, data[0][0], xml)],
columns=['SB_UID', 'partId', 'timestamp', 'sb_xml'],
index=[sb_uid])
else:
self.schedblocks.ix[sb_uid] = (sb_uid, partid, data[0][0], xml)
# noinspection PyUnboundLocalVariable
def row_newar(self, sbuid, new=False):
"""
:param sbuid:
:param new:
"""
sbinfo = self.schedblock_info.ix[sbuid]
sb = self.schedblocks.ix[sbuid]
pid = sb.partId
sg = self.sciencegoals.ix[pid]
repfreq = sbinfo.repfreq
dec = sbinfo.DEC
c_bmax = 0.4001 / pd.np.cos(pd.np.radians(-23.0262015) -
pd.np.radians(dec)) + 0.6103
c_freq = repfreq / 100.
corr = c_freq / c_bmax
useaca = sg.useACA
if useaca:
useaca = 'Y'
else:
useaca = 'N'
ar = sg.AR
las = sg.LAS
name = sbinfo['name']
sbnum = 1
sbuidE = sbuid
if name.endswith('TC'):
name_e = name[:-2] + 'TE'
try:
sbinfoE = self.schedblock_info[
(self.schedblock_info.name == name_e) &
(self.schedblock_info.partId == pid)].ix[0]
sbnum = 2
sbuidE = sbinfoE.SB_UID
sbuidC = sbuid
print name, name_e
except IndexError:
print "Can't find TE for sb %s" % name
sbnum = 1
if name.endswith('TE'):
name_e = name[:-2] + 'TC'
try:
sbinfoC = self.schedblock_info[
(self.schedblock_info.name == name_e) &
(self.schedblock_info.partId == pid)].ix[0]
sbnum = 2
sbuidC = sbinfoC.SB_UID
print name, name_e
except IndexError:
sbnum = 1
newAR = ARes.arrayRes([self.wto_path, ar, las, repfreq, useaca, sbnum])
newAR.silentRun()
minarE, maxarE, minarC, maxarC = newAR.run()
if new and sbnum == 1:
self.newar = pd.DataFrame(
[(minarE, maxarE, minarE * corr, maxarE * corr)],
columns=['minAR', 'maxAR', 'arrayMinAR', 'arrayMaxAR'],
index=[sbuidE])
elif new and sbnum == 2:
self.newar = pd.DataFrame(
[(minarE, maxarE, minarE * corr, maxarE * corr)],
columns=['minAR', 'maxAR', 'arrayMinAR', 'arrayMaxAR'],
index=[sbuidE])
self.newar.ix[sbuidC] = (minarC, maxarC, minarC * corr,
maxarC * corr)
else:
if sbnum == 1:
maxarEc = maxarE * corr
if maxarEc < 0.44:
maxarEc = 0.44
self.newar.ix[sbuidE] = (minarE, maxarE, minarE * corr,
maxarEc)
if sbnum == 2:
maxarEc = maxarE * corr
if maxarEc < 0.44:
maxarEc = 0.44
self.newar.ix[sbuidE] = (minarE, maxarE, minarE * corr,
maxarEc)
self.newar.ix[sbuidC] = (minarC, maxarC, minarC * corr,
maxarC * corr)
def filter_c1(self):
"""