logger.info('computing gpsstop from current time')
gpsstop = t ### We do not require boundaries to be integer multiples of stride
gpsstart = opts.gpsstart
if not gpsstart:
logger.info('computing gpsstart from gpsstop')
gpsstart = gpsstop - stride
lookback = 0
### directory into which we write data
output_dir = "%s/%d_%d/"%(traindir, gpsstart, gpsstart + stride)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
pat = idq.pat(output_dir, ifo, usertag, gpsstart-lookback, lookback+gpsstop-gpsstart)
##### Get Science Segments
logger.info('test - Begin: querying science segments')
"""if not opts.ignore_science_segments:
try:
### this returns a string
seg_xml_file = idq.segment_query(config, gpsstart - lookback , gpsstop, url=segdb_url)
### load xml document
xmldoc = ligolw_utils.load_fileobj(seg_xml_file, contenthandler=ligolw.LIGOLWContentHandler)[0]
### science segments xml filename
seg_file = idq.segxml(output_dir, "_%s"%dq_name, gpsstart - lookback , lookback+stride)
if opts.force:
raise e
else:
gpsstart += stride
continue
logger.info('Done.')
#===============================================================================================
# preparing auxmvc training samples
#===============================================================================================
if mla:
logger.info('preparing training auxmvc samples')
### output file for training samples
pat = idq.pat(output_dir, ifo, usertag, gpsstart-lookback, lookback+stride)
if not build_auxmvc_vectors: ### we cat together pat files instead of building vectors from scratch
### run job that prepares training samples
(ptas_exit_status, _) = idq.execute_prepare_training_auxmvc_samples(output_dir, realtimedir, config, gpsstart - lookback, gpsstart + stride, pat, dq_segments=seg_file, dq_segments_name=dq_name )
os.chdir(cwd) ### go back to starting directory
if build_auxmvc_vectors or ptas_exit_status!=0: ### we need to build vectors
if build_auxmvc_vectors: ### no realtime directory...
logger.warning('WARNING: building auxmvc vectors, this should be necessary only at the very first training cycle')
else:
logger.warning('WARNING: patfile generation failed for some reason. Attempt to build auxmvc vectors from scratch')
if ovl and (not opts.ignore_science_segments): ### need to reset sciseg pointer!
### write segments to ascii list
sciseg_path = idq.segascii(output_dir, "_%s"%dq_name, gpsstart-lookback, lookback+stride)
logger.info('writing science segments to file : '+sciseg_path)
if opts.force:
raise e
else:
gpsstart += stride
continue
logger.info('Done.')
#===============================================================================================
# preparing auxmvc training samples
#===============================================================================================
if mla:
logger.info('preparing training auxmvc samples')
### output file for training samples
pat = idq.pat(output_dir, ifo, usertag, gpsstart - lookback,
lookback + stride)
if not build_auxmvc_vectors: ### we cat together pat files instead of building vectors from scratch
### run job that prepares training samples
(ptas_exit_status,
_) = idq.execute_prepare_training_auxmvc_samples(
output_dir,
realtimedir,
config,
gpsstart - lookback,
gpsstart + stride,
pat,
dq_segments=seg_file,
dq_segments_name=dq_name)
os.chdir(cwd) ### go back to starting directory
### get rid of unwanted AUX triggers
trgdict.include(
[[min(mintime - padding, t),
max(maxtime + padding, t + stride)]])
### get rid of unwanted GW triggers from previous or next strides; these will be evaluated in their own strides
trgdict.include([[t, t + stride]], channels=[gwchannel])
#====================
# generate patfiles for mla classifiers
#====================
if mla: # only build patfiles if machine-learning algorithms are present
print 'building auxmvc feature vectors ...'
pat = idq.pat(
opts.outdir, ifo, usertag, gps_start, twopadding
) #"%s/%s_%d-%d.pat"%(opts.outdir, ifo, gps_start, twopadding)
# generating auxmvc vector samples. result is saved into pat file
# FIXME: depending how padding is done we should adjust behavior of build_auxmvc_vectors
# Currently it keeps gw trigger from [t, t + stride] and uses time_window to pad this segment for auxiliary triggers
# we do not filter out unclean beacuse it is already done when clean_gps times are formed
auxmvc_vectors = idq.build_auxmvc_vectors(
trgdict,
gwchannel,
auxmvc_coinc_window,
auxmc_gw_signif_thr,
pat,
gps_start_time=gps_start,
gps_end_time=gps_padd,
channels=auxmvc_selected_channels,
trgdict.resort() ### make sure the trgdict's trigger lists are stored in the correct order
### get rid of unwanted AUX triggers
trgdict.include([[min(mintime - padding, t), max(maxtime + padding, t + stride)]])
### get rid of unwanted GW triggers from previous or next strides; these will be evaluated in their own strides
trgdict.include([[t, t + stride]], channels=[gwchannel])
#====================
# generate patfiles for mla classifiers
#====================
if mla: # only build patfiles if machine-learning algorithms are present
print 'building auxmvc feature vectors ...'
pat = idq.pat(opts.outdir, ifo, usertag, gps_start, twopadding) #"%s/%s_%d-%d.pat"%(opts.outdir, ifo, gps_start, twopadding)
# generating auxmvc vector samples. result is saved into pat file
# FIXME: depending how padding is done we should adjust behavior of build_auxmvc_vectors
# Currently it keeps gw trigger from [t, t + stride] and uses time_window to pad this segment for auxiliary triggers
# we do not filter out unclean beacuse it is already done when clean_gps times are formed
auxmvc_vectors = idq.build_auxmvc_vectors(trgdict, gwchannel, auxmvc_coinc_window, auxmc_gw_signif_thr, pat, gps_start_time=gps_start,
gps_end_time=gps_padd, channels=auxmvc_selected_channels, unsafe_channels=auxmvc_unsafe_channels, clean_times=clean_gps,
clean_window=clean_window, filter_out_unclean=False )
#=============================================
# predictions
#=============================================
dats = {}
for classifier in classifiers:
flavor = classifiersD[classifier]['flavor']
print("Number of cleans: " + str(len(clean_gps)))
## keep only the most relevant cleans
if len(clean_gps) > max_cln_samples:
clean_gps = clean_gps[-max_cln_samples:]
print("Number of cleans after max cap: " + str(len(clean_gps)))
### keep only times that are within science time
if not opts.ignore_science_segments:
logger.info(' filtering trigger_dict through scisegs')
trigger_dict.include(scisegs) ### already loaded into memory above here
print("Number of trigs in scisegs: " + str(len(trigger_dict[gwchannel])))
print("Number of triggers def into build_auxmvc_vectors(): " + str(len(trigger_dict[gwchannel])))
### build vectors, also writes them into pat
pat = idq.pat(output_dir, ifo, usertag, gpsstart, gpsstop-gpsstart)
logger.info(' writing %s'%pat)
idq.build_auxmvc_vectors(trigger_dict, gwchannel, auxmvc_coinc_window, auxmc_gw_signif_thr, pat, gps_start_time=gpsstart,
gps_end_time=gpsstop, channels=auxmvc_selected_channels, unsafe_channels=auxmvc_unsafe_channels, clean_times=clean_gps,
clean_window=clean_window, filter_out_unclean=False, locked_segments = "segment_times.txt", include_time_locked = opts.include_time_locked,
include_time_until_end = opts.include_time_until_end)
print("Done with pat file building")
ptas_exit_status = 0 ### used to check for success
if ptas_exit_status != 0: ### check that process executed correctly
logger.warning('WARNING: Preparing training auxmvc samples failed')
if opts.force:
raise StandardError, "auxmvc samples required for successful training"
else:
logger.warning('WARNING: skipping re-training the MLA classifiers')
else:
#evaluate_all_combinations(patfile, trainedforestbase, trainedforestend, config)
#pR.plot_ROC_combinations("ER7_ROC_Curves-A.png", 1117329857, 1118336935)
gpsstart = 1117329857
gpsstop = 1118336935
### get start and end seg times formatted as list of lists
tl.get_segments(gpsstart, gpsstop)
scisegs = tl.parse_segments("segment_times.txt")
newsegs = []
for seg in scisegs:
if (seg[1]-seg[0] >= 3600):
newsegs.append(seg)
scisegs=newsegs
for seg in scisegs:
patf = idq.pat("/home/jessica.hyde/test/dev-branch/now/train/%s_%s/" % (gpsstart, gpsstop), "L1", "LowThresh", seg[0], seg[1]-seg[0])
patfile = patf
trainedforestbase = "/home/jessica.hyde/test/dev-branch/now/train/%s_%s/mvsc/" % (gpsstart, gpsstop)
trainedforestend = "L1_mla-%s-%s-A.spr" % (int(seg[0]), int(seg[1]-seg[0]))
evaluate_all_combinations(patfile, trainedforestbase, trainedforestend, config)
pR.plot_ROC_combinations("LowThreshROCSegment%s-%s-A.png" % (seg[0], seg[1]), gpsstart, gpsstop, seg[0], seg[1])
# trainedforestend = "L1_mla-%s-%s-B.spr" % (int(seg[0]), int(seg[1]-seg[0]))
# evaluate_all_combinations(patfile, trainedforestbase, trainedforestend, config)
# pR.plot_ROC_combinations("LowThreshROCSegment%s-%s-B.png" % (seg[0], seg[1]), gpsstart, gpsstop, seg[0], seg[1])
"""for seg in scisegs:
patf = idq.pat("/home/jessica.hyde/test/dev-branch/now/train/%s_%s/" % (gpsstart, gpsstop), "L1", "", seg[0], seg[1]-seg[0])
patfile = patf[:-4] + "-B.pat"
trainedforestbase = "/home/jessica.hyde/test/dev-branch/now/train/%s_%s/mvsc/" % (gpsstart, gpsstop)
trainedforestend = "L1_mla-%s-%s-A.spr" % (int(seg[0]), int(seg[1]-seg[0]))
