def setUp(self):
rsexecute.set_client(use_dask=True)
from rascil.data_models.parameters import rascil_path
self.dir = rascil_path('test_results')
self.persist = os.getenv("RASCIL_PERSIST", True)
self.verbose = True
def setUp(self):
rsexecute.set_client(memory_limit=4 * 1024 * 1024 * 1024,
n_workers=4,
dashboard_address=None)
self.persist = os.getenv("RASCIL_PERSIST", False)
def setUp(self):
rsexecute.set_client(use_dask=True, processes=True, threads_per_worker=1)
from rascil.data_models.parameters import rascil_path, rascil_data_path
self.dir = rascil_path('test_results')
self.persist = os.getenv("RASCIL_PERSIST", False)
def set_client(client):
"""Set RASCIL Dask client.
:param client: Dask distributed client
"""
rsexecute.set_client(client=client, dask=True)
def setUp(self):
# super(rsexecuteTestCase, self).setUp()
import os
from rascil.workflows.rsexecute.execution_support.rsexecute import rsexecute
use_dask = os.environ.get('RASCIL_TESTS_USE_DASK', '1') == '1'
rsexecute.set_client(use_dask=use_dask)
def setUp(self):
rsexecute.set_client(verbose=False, memory_limit=4 * 1024 * 1024 * 1024, n_workers=4, dashboard_address=None)
from rascil.data_models.parameters import rascil_path
self.dir = rascil_path('test_results')
self.persist = os.getenv("RASCIL_PERSIST", False)
def setUp(self):
rsexecute.set_client(memory_limit=4 * 1024 * 1024 * 1024,
n_workers=4,
dashboard_address=None)
from rascil.data_models.parameters import rascil_path
self.dir = rascil_path('test_results')
self.frequency = numpy.linspace(1e8, 1.5e8, 3)
self.channel_bandwidth = numpy.array([2.5e7, 2.5e7, 2.5e7])
self.phasecentre = SkyCoord(ra=+15.0 * u.deg,
dec=-60.0 * u.deg,
frame='icrs',
equinox='J2000')
self.times = numpy.linspace(-300.0, 300.0, 3) * numpy.pi / 43200.0
def setUp(self):
rsexecute.set_client(use_dask=True,
processes=True,
threads_per_worker=1)
from rascil.data_models.parameters import rascil_path
self.dir = rascil_path('test_results')
self.frequency = numpy.linspace(1e8, 1.5e8, 3)
self.channel_bandwidth = numpy.array([2.5e7, 2.5e7, 2.5e7])
self.phasecentre = SkyCoord(ra=+15.0 * u.deg,
dec=-60.0 * u.deg,
frame='icrs',
equinox='J2000')
self.times = numpy.linspace(-300.0, 300.0, 3) * numpy.pi / 43200.0
def setUp(self):
rsexecute.set_client(use_dask=True,
processes=True,
threads_per_worker=1)
from rascil.data_models.parameters import rascil_path, rascil_data_path
self.dir = rascil_path('test_results')
self.frequency = numpy.linspace(1e8, 1.5e8, 3)
self.channel_bandwidth = numpy.array([2.5e7, 2.5e7, 2.5e7])
self.flux = numpy.array([[100.0], [100.0], [100.0]])
self.phasecentre = SkyCoord(ra=+15.0 * u.deg,
dec=-35.0 * u.deg,
frame='icrs',
equinox='J2000')
self.config = create_named_configuration('LOWBD2-CORE')
self.times = numpy.linspace(-300.0, 300.0, 3) * numpy.pi / 43200.0
nants = self.config.xyz.shape[0]
assert nants > 1
assert len(self.config.names) == nants
assert len(self.config.mount) == nants
self.persist = os.getenv("RASCIL_PERSIST", False)
def setUp(self):
rsexecute.set_client(use_dask=True, verbose=False)
show = args.show == 'True'
context = args.context
nworkers = args.nworkers
threads_per_worker = 1
nthreads = args.nthreads
memory = args.memory
serial = args.serial == "True"
basename = os.path.basename(os.getcwd())
if serial:
print("Will use serial processing")
use_serial_invert = True
use_serial_predict = True
rsexecute.set_client(use_dask=False)
print(rsexecute.client)
nworkers = 1
else:
print("Will use dask processing")
if nworkers > 0:
print(
"{nworkers} workers each with {memory}GB, worker files in {local_dir}"
.format(nworkers=nworkers,
memory=memory,
local_dir=args.dask_worker_space))
client = get_dask_client(n_workers=nworkers,
memory_limit=memory * 1024 * 1024 * 1024,
threads_per_worker=threads_per_worker,
local_dir=args.dask_worker_space)
rsexecute.set_client(client=client)
def setUp(self):
numpy.random.seed(180555)
rsexecute.set_client(use_dask=True, processes=True, threads_per_worker=1)
self.persist = os.getenv("RASCIL_PERSIST", False)
log = logging.getLogger()
log.setLevel(logging.DEBUG)
logging.getLogger('asyncio').setLevel(logging.WARNING)
if __name__ == '__main__':
print("Starting cluster_test_image")
# We pass in the scheduler from the invoking script
if len(sys.argv) > 1:
scheduler = sys.argv[1]
client = Client(scheduler)
else:
client = Client()
rsexecute.set_client(client=client)
from rascil.data_models.parameters import rascil_path
dir = rascil_path('test_results')
frequency = numpy.linspace(1e8, 1.5e8, 3)
channel_bandwidth = numpy.array([2.5e7, 2.5e7, 2.5e7])
flux = numpy.array([[100.0], [100.0], [100.0]])
config = create_named_configuration('LOWBD2-CORE')
times = numpy.linspace(-300.0, 300.0, 3) * numpy.pi / 43200.0
nants = config.xyz.shape[0]
assert nants > 1
assert len(config.names) == nants
assert len(config.mount) == nants
def simulation(self,
args,
time_series='wind',
band='B2',
context='singlesource',
vp_directory=''):
ra = args.ra
declination = args.declination
use_radec = args.use_radec == "True"
integration_time = args.integration_time
time_range = args.time_range
time_chunk = args.time_chunk
offset_dir = args.offset_dir
pbtype = args.pbtype
pbradius = args.pbradius
rmax = args.rmax
flux_limit = args.flux_limit
npixel = args.npixel
shared_directory = args.shared_directory
vp_directory = args.vp_directory
# Simulation specific parameters
global_pe = numpy.array(args.global_pe)
static_pe = numpy.array(args.static_pe)
dynamic_pe = args.dynamic_pe
seed = args.seed
basename = os.path.basename(os.getcwd())
use_dask = False
rsexecute.set_client(use_dask=use_dask)
# Set up details of simulated observation
nfreqwin = 1
if band == 'B1':
frequency = [0.765e9]
elif band == 'B2':
frequency = [1.36e9]
elif band == 'Ku':
frequency = [12.179e9]
else:
raise ValueError("Unknown band %s" % band)
phasecentre = SkyCoord(ra=ra * u.deg,
dec=declination * u.deg,
frame='icrs',
equinox='J2000')
bvis_graph = create_standard_mid_simulation_rsexecute_workflow(
band, rmax, phasecentre, time_range, time_chunk, integration_time,
shared_directory)
future_bvis_list = rsexecute.persist(bvis_graph)
vis_graph = [
rsexecute.execute(convert_blockvisibility_to_visibility)(bv)
for bv in future_bvis_list
]
future_vis_list = rsexecute.persist(vis_graph, sync=True)
# We need the HWHM of the primary beam, and the location of the nulls
HWHM_deg, null_az_deg, null_el_deg = find_pb_width_null(
pbtype, frequency)
HWHM = HWHM_deg * numpy.pi / 180.0
FOV_deg = 8.0 * 1.36e9 / frequency[0]
advice_list = rsexecute.execute(advise_wide_field)(
future_vis_list[0], guard_band_image=1.0, delA=0.02, verbose=False)
advice = rsexecute.compute(advice_list, sync=True)
pb_npixel = 1024
d2r = numpy.pi / 180.0
pb_cellsize = d2r * FOV_deg / pb_npixel
cellsize = advice['cellsize']
# Now construct the components
original_components, offset_direction = create_simulation_components(
context, phasecentre, frequency, pbtype, offset_dir, flux_limit,
pbradius * HWHM, pb_npixel, pb_cellsize)
vp_list = [
rsexecute.execute(create_image_from_visibility)(
bv,
npixel=pb_npixel,
frequency=frequency,
nchan=nfreqwin,
cellsize=pb_cellsize,
phasecentre=phasecentre,
override_cellsize=False) for bv in future_bvis_list
]
vp_list = [
rsexecute.execute(create_vp)(vp,
pbtype,
pointingcentre=phasecentre,
use_local=not use_radec)
for vp in vp_list
]
future_vp_list = rsexecute.persist(vp_list)
# Make one image per component
future_model_list = [
rsexecute.execute(create_image_from_visibility)(
future_vis_list[0],
npixel=npixel,
frequency=frequency,
nchan=nfreqwin,
cellsize=cellsize,
phasecentre=offset_direction,
polarisation_frame=PolarisationFrame("stokesI"))
for i, _ in enumerate(original_components)
]
a2r = numpy.pi / (3600.0 * 1800)
no_error_gtl = None
error_gtl = None
if time_series == '':
global_pointing_error = global_pe
static_pointing_error = static_pe
pointing_error = dynamic_pe
no_error_gtl, error_gtl = \
create_pointing_errors_gaintable_rsexecute_workflow(future_bvis_list, original_components,
sub_vp_list=future_vp_list,
use_radec=use_radec,
pointing_error=a2r * pointing_error,
static_pointing_error=a2r * static_pointing_error,
global_pointing_error=a2r * global_pointing_error,
seed=seed,
show=False, basename=basename)
elif time_series == 'wind':
no_error_gtl, error_gtl = \
create_pointing_errors_gaintable_rsexecute_workflow(future_bvis_list, original_components,
sub_vp_list=future_vp_list,
use_radec=use_radec,
time_series=time_series,
time_series_type='precision',
seed=seed,
show=False, basename=basename)
elif time_series == 'gravity':
no_error_gtl, error_gtl = \
create_surface_errors_gaintable_rsexecute_workflow(band, future_bvis_list, original_components,
vp_directory=vp_directory, use_radec=use_radec,
show=False, basename=basename)
else:
raise ValueError("Unknown type of error %s" % time_series)
# Now make all the residual images
vis_comp_chunk_dirty_list = \
calculate_residual_from_gaintables_rsexecute_workflow(future_bvis_list, original_components,
future_model_list,
no_error_gtl, error_gtl)
# Add the resulting images
error_dirty_list = sum_invert_results_rsexecute(
vis_comp_chunk_dirty_list)
# Actually compute the graph assembled above
error_dirty, sumwt = rsexecute.compute(error_dirty_list, sync=True)
return error_dirty, sumwt
def init_logging():
logging.basicConfig(
filename='%s/ska-pipeline.log' % results_dir,
filemode='a',
format='%(asctime)s,%(msecs)d %(name)s %(levelname)s %(message)s',
datefmt='%H:%M:%S',
level=logging.INFO)
if __name__ == '__main__':
log = logging.getLogger()
logging.info("Starting Imaging pipeline")
rsexecute.set_client(use_dask=True)
print(rsexecute.client)
rsexecute.run(init_logging)
nfreqwin = 8
ntimes = 5
rmax = 750.0
centre = nfreqwin // 2
# Load data from previous simulation
vis_list = [
rsexecute.execute(create_blockvisibility_from_ms)(rascil_path(
'%s/ska-pipeline_simulation_vislist_%d.ms' % (results_dir, v)))[0]
for v in range(nfreqwin)
]
def init_logging():
logging.basicConfig(
filename='%s/ska-pipeline.log' % results_dir,
filemode='a',
format='%%(asctime)s,%(msecs)d %(name)s %(levelname)s %(message)s',
datefmt='%H:%M:%S',
level=logging.INFO)
if __name__ == '__main__':
log = logging.getLogger()
print("Starting ska-pipelines simulation pipeline")
rsexecute.set_client(use_dask=True,
threads_per_worker=1,
memory_limit=32 * 1024 * 1024 * 1024,
n_workers=8,
local_dir=dask_dir)
print(rsexecute.client)
rsexecute.run(init_logging)
# We create a graph to make the visibility. The parameter rmax determines the distance of the
# furthest antenna/stations used. All over parameters are determined from this number.
nfreqwin = 41
ntimes = 5
rmax = 750.0
centre = nfreqwin // 2
frequency = numpy.linspace(0.9e8, 1.1e8, nfreqwin)
channel_bandwidth = numpy.array(nfreqwin * [frequency[1] - frequency[0]])
def trial_case(results,
seed=180555,
context='wstack',
nworkers=8,
threads_per_worker=1,
memory=8,
processes=True,
order='frequency',
nfreqwin=7,
ntimes=3,
rmax=750.0,
facets=1,
wprojection_planes=1,
use_dask=True,
use_serial_imaging=True,
flux_limit=0.3,
nmajor=5,
dft_threshold=1.0,
use_serial_clean=True,
write_fits=False):
""" Single trial for performance-timings
Simulates visibilities from GLEAM including phase errors
Makes dirty image and PSF
Runs ICAL pipeline
The results are in a dictionary:
'context': input - a string describing concisely the purpose of the test
'time overall', overall execution time (s)
'time predict', time to execute GLEAM prediction graph
'time invert', time to make dirty image
'time invert graph', time to make dirty image graph
'time ICAL graph', time to create ICAL graph
'time ICAL', time to execute ICAL graph
'context', type of imaging e.g. 'wstack'
'nworkers', number of workers to create
'threads_per_worker',
'nnodes', Number of nodes,
'processes', 'order', Ordering of data_models
'nfreqwin', Number of frequency windows in simulation
'ntimes', Number of hour angles in simulation
'rmax', Maximum radius of stations used in simulation (m)
'facets', Number of facets in deconvolution and imaging
'wprojection_planes', Number of wprojection planes
'vis_slices', Number of visibility slices (per Visibbility)
'npixel', Number of pixels in image
'cellsize', Cellsize in radians
'seed', Random number seed
'dirty_max', Maximum in dirty image
'dirty_min', Minimum in dirty image
'restored_max',
'restored_min',
'deconvolved_max',
'deconvolved_min',
'residual_max',
'residual_min',
'git_info', GIT hash (not definitive since local mods are possible)
:param results: Initial state
:param seed: Random number seed (used in gain simulations)
:param context: imaging context
:param context: Type of context: '2d'|'timeslice'|'wstack'
:param nworkers: Number of dask workers to use
:param threads_per_worker: Number of threads per worker
:param processes: Use processes instead of threads 'processes'|'threads'
:param order: See simulate_list_list_rsexecute_workflow_workflowkflow
:param nfreqwin: See simulate_list_list_rsexecute_workflow_workflowkflow
:param ntimes: See simulate_list_list_rsexecute_workflow_workflowkflow
:param rmax: See simulate_list_list_rsexecute_workflow_workflowkflow
:param facets: Number of facets to use
:param wprojection_planes: Number of wprojection planes to use
:param use_dask: Use dask or immediate evaluation
:return: results dictionary
"""
if use_dask:
scheduler = os.getenv('RASCIL_DASK_SCHEDULER', None)
if scheduler is not None:
client = get_dask_client(n_workers=nworkers,
memory_limit=memory * 1024 * 1024 * 1024,
threads_per_worker=threads_per_worker)
rsexecute.set_client(client=client)
else:
rsexecute.set_client(threads_per_worker=threads_per_worker,
processes=threads_per_worker == 1,
memory_limit=memory * 1024 * 1024 * 1024,
n_workers=nworkers)
print("Defined %d workers" % (nworkers))
else:
rsexecute.set_client(use_dask=use_dask)
results['nnodes'] = 1
def init_logging():
logging.basicConfig(
filename='pipelines_rsexecute_timings.log',
filemode='w',
format='%(asctime)s,%(msecs)d %(name)s %(levelname)s %(message)s',
datefmt='%H:%M:%S',
level=logging.INFO)
init_logging()
log = logging.getLogger()
# Initialise logging on the workers. This appears to only work using the process scheduler.
rsexecute.run(init_logging)
def lprint(*args):
log.info(*args)
print(*args)
lprint("Starting pipelines_rsexecute_timings")
numpy.random.seed(seed)
results['seed'] = seed
start_all = time.time()
results['context'] = context
results['hostname'] = socket.gethostname()
results['git_hash'] = git_hash()
results['epoch'] = time.strftime("%Y-%m-%d %H:%M:%S")
lprint("Context is %s" % context)
results['nworkers'] = nworkers
results['threads_per_worker'] = threads_per_worker
results['processes'] = processes
results['memory'] = memory
results['order'] = order
results['nfreqwin'] = nfreqwin
results['ntimes'] = ntimes
results['rmax'] = rmax
results['facets'] = facets
results['wprojection_planes'] = wprojection_planes
results['dft threshold'] = dft_threshold
results['use_dask'] = use_dask
lprint("At start, configuration is:")
lprint(sort_dict(results))
# Parameters determining scale of simulation.
frequency = numpy.linspace(1.0e8, 1.2e8, nfreqwin)
centre = nfreqwin // 2
if nfreqwin > 1:
channel_bandwidth = numpy.array(nfreqwin *
[frequency[1] - frequency[0]])
else:
channel_bandwidth = numpy.array([1e6])
times = numpy.linspace(-numpy.pi / 4.0, numpy.pi / 4.0, ntimes)
phasecentre = SkyCoord(ra=+0.0 * u.deg,
dec=-40.0 * u.deg,
frame='icrs',
equinox='J2000')
lprint("****** Visibility creation ******")
# Create the empty BlockVisibility's and persist these on the cluster
tmp_bvis_list = simulate_list_rsexecute_workflow(
'LOWBD2',
frequency=frequency,
channel_bandwidth=channel_bandwidth,
times=times,
phasecentre=phasecentre,
order=order,
format='blockvis',
rmax=rmax)
tmp_vis_list = [
rsexecute.execute(convert_blockvisibility_to_visibility)(bv)
for bv in tmp_bvis_list
]
tmp_vis_list = rsexecute.client.compute(tmp_vis_list, sync=True)
vis_list = rsexecute.gather(tmp_vis_list)
import matplotlib.pyplot as plt
plt.clf()
plt.hist(vis_list[0].w, bins=100)
plt.title('Histogram of w samples: rms=%.1f (wavelengths)' %
numpy.std(vis_list[0].w))
plt.xlabel('W (wavelengths)')
#plt.show()
plt.clf()
plt.hist(vis_list[0].uvdist, bins=100)
plt.title('Histogram of uvdistance samples')
plt.xlabel('UV Distance (wavelengths)')
#plt.show()
rsexecute.client.cancel(tmp_vis_list)
future_vis_list = rsexecute.scatter(vis_list)
# Find the best imaging parameters but don't bring the vis_list back here
print("****** Finding wide field parameters ******")
future_advice = [
rsexecute.execute(advise_wide_field)(
v,
guard_band_image=6.0,
delA=0.1,
facets=facets,
wprojection_planes=wprojection_planes,
oversampling_synthesised_beam=4.0) for v in future_vis_list
]
future_advice = rsexecute.compute(future_advice)
advice = rsexecute.client.gather(future_advice)[-1]
rsexecute.client.cancel(future_advice)
# Deconvolution via sub-images requires 2^n
npixel = advice['npixels2']
results['npixel'] = npixel
cellsize = advice['cellsize']
results['cellsize'] = cellsize
lprint("Image will have %d by %d pixels, cellsize = %.6f rad" %
(npixel, npixel, cellsize))
# Create an empty model image
tmp_model_list = [
rsexecute.execute(create_image)(
npixel=npixel,
cellsize=cellsize,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"))
for f, freq in enumerate(frequency)
]
model_list = rsexecute.compute(tmp_model_list, sync=True)
future_model_list = rsexecute.scatter(model_list)
lprint("****** Setting up imaging parameters ******")
# Now set up the imaging parameters
template_model = create_image(
npixel=npixel,
cellsize=cellsize,
frequency=[frequency[centre]],
phasecentre=phasecentre,
channel_bandwidth=[channel_bandwidth[centre]],
polarisation_frame=PolarisationFrame("stokesI"))
gcfcf = [create_pswf_convolutionfunction(template_model)]
if context == 'timeslice':
vis_slices = ntimes
lprint("Using timeslice with %d slices" % vis_slices)
elif context == '2d':
vis_slices = 1
elif context == "wprojection":
wstep = advice['wstep']
nw = advice['wprojection_planes']
vis_slices = 1
support = advice['nwpixels']
results['wprojection_planes'] = nw
lprint("****** Starting W projection kernel creation ******")
lprint("Using wprojection with %d planes with wstep %.1f wavelengths" %
(nw, wstep))
lprint("Support of wprojection = %d pixels" % support)
gcfcf = [
create_awterm_convolutionfunction(template_model,
nw=nw,
wstep=wstep,
oversampling=4,
support=support,
use_aaf=True)
]
lprint("Size of W projection gcf, cf = %.2E bytes" % get_size(gcfcf))
else:
context = 'wstack'
vis_slices = advice['vis_slices']
lprint("Using wstack with %d slices" % vis_slices)
gcfcf = rsexecute.scatter(gcfcf, broadcast=True)
results['vis_slices'] = vis_slices
# Make a skymodel from gleam, with bright sources as components and weak sources in an image
lprint("****** Starting GLEAM skymodel creation ******")
future_skymodel_list = [
rsexecute.execute(create_low_test_skymodel_from_gleam)(
npixel=npixel,
cellsize=cellsize,
frequency=[frequency[f]],
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
flux_limit=flux_limit,
flux_threshold=dft_threshold,
flux_max=5.0) for f, freq in enumerate(frequency)
]
# We use predict_skymodel so that we can use skycomponents as well as images
lprint("****** Starting GLEAM skymodel prediction ******")
predicted_vis_list = [
predict_skymodel_list_rsexecute_workflow(future_vis_list[f],
[future_skymodel_list[f]],
context=context,
vis_slices=vis_slices,
facets=facets,
gcfcf=gcfcf)[0]
for f, freq in enumerate(frequency)
]
# Corrupt the visibility for the GLEAM model
lprint("****** Visibility corruption ******")
tmp_corrupted_vis_list = corrupt_list_rsexecute_workflow(
predicted_vis_list, phase_error=1.0, seed=seed)
lprint("****** Weighting and tapering ******")
tmp_corrupted_vis_list = weight_list_rsexecute_workflow(
tmp_corrupted_vis_list, future_model_list)
tmp_corrupted_vis_list = taper_list_rsexecute_workflow(
tmp_corrupted_vis_list, 0.003 * 750.0 / rmax)
tmp_corrupted_vis_list = rsexecute.compute(tmp_corrupted_vis_list,
sync=True)
corrupted_vis_list = rsexecute.gather(tmp_corrupted_vis_list)
# rsexecute.client.cancel(predicted_vis_list)
rsexecute.client.cancel(tmp_corrupted_vis_list)
future_corrupted_vis_list = rsexecute.scatter(corrupted_vis_list)
# At this point the only futures are of scatter'ed data so no repeated calculations should be
# incurred.
lprint("****** Starting dirty image calculation ******")
start = time.time()
dirty_list = invert_list_rsexecute_workflow(
future_corrupted_vis_list,
future_model_list,
vis_slices=vis_slices,
context=context,
facets=facets,
use_serial_invert=use_serial_imaging,
gcfcf=gcfcf)
results['size invert graph'] = get_size(dirty_list)
lprint('Size of dirty graph is %.3E bytes' %
(results['size invert graph']))
end = time.time()
results['time invert graph'] = end - start
lprint("Construction of invert graph took %.3f seconds" % (end - start))
start = time.time()
dirty, sumwt = rsexecute.compute(dirty_list, sync=True)[centre]
end = time.time()
results['time invert'] = end - start
lprint("Dirty image invert took %.3f seconds" % (end - start))
lprint("Maximum in dirty image is %f, sumwt is %s" %
(numpy.max(numpy.abs(dirty.data)), str(sumwt)))
qa = qa_image(dirty)
results['dirty_max'] = qa.data['max']
results['dirty_min'] = qa.data['min']
if write_fits:
export_image_to_fits(
dirty, "pipelines_rsexecute_timings-%s-dirty.fits" % context)
lprint("****** Starting prediction ******")
start = time.time()
tmp_vis_list = predict_list_rsexecute_workflow(
future_corrupted_vis_list,
future_model_list,
vis_slices=vis_slices,
context=context,
facets=facets,
use_serial_predict=use_serial_imaging,
gcfcf=gcfcf)
result = rsexecute.compute(tmp_vis_list, sync=True)
# rsexecute.client.cancel(tmp_vis_list)
end = time.time()
results['time predict'] = end - start
lprint("Predict took %.3f seconds" % (end - start))
# Create the ICAL pipeline to run major cycles, starting selfcal at cycle 1. A global solution across all
# frequencies (i.e. Visibilities) is performed.
print("Using subimage clean")
deconvolve_facets = 8
deconvolve_overlap = 16
deconvolve_taper = 'tukey'
lprint("****** Starting ICAL graph creation ******")
controls = create_calibration_controls()
controls['T']['first_selfcal'] = 1
controls['T']['timeslice'] = 'auto'
start = time.time()
ical_list = ical_list_rsexecute_workflow(
future_corrupted_vis_list,
model_imagelist=future_model_list,
context=context,
vis_slices=vis_slices,
scales=[0, 3, 10],
algorithm='mmclean',
nmoment=3,
niter=1000,
fractional_threshold=0.1,
threshold=0.01,
nmajor=nmajor,
gain=0.25,
psf_support=64,
deconvolve_facets=deconvolve_facets,
deconvolve_overlap=deconvolve_overlap,
deconvolve_taper=deconvolve_taper,
timeslice='auto',
global_solution=True,
do_selfcal=True,
calibration_context='T',
controls=controls,
use_serial_predict=use_serial_imaging,
use_serial_invert=use_serial_imaging,
use_serial_clean=use_serial_clean,
gcfcf=gcfcf)
results['size ICAL graph'] = get_size(ical_list)
lprint('Size of ICAL graph is %.3E bytes' % results['size ICAL graph'])
end = time.time()
results['time ICAL graph'] = end - start
lprint("Construction of ICAL graph took %.3f seconds" % (end - start))
print("Current objects on cluster: ")
pp.pprint(rsexecute.client.who_has())
#
# Execute the graph
lprint("****** Executing ICAL graph ******")
start = time.time()
deconvolved, residual, restored, gaintables = rsexecute.compute(ical_list,
sync=True)
end = time.time()
results['time ICAL'] = end - start
lprint("ICAL graph execution took %.3f seconds" % (end - start))
qa = qa_image(deconvolved[centre])
results['deconvolved_max'] = qa.data['max']
results['deconvolved_min'] = qa.data['min']
deconvolved_cube = image_gather_channels(deconvolved)
if write_fits:
export_image_to_fits(
deconvolved_cube,
"pipelines_rsexecute_timings-%s-ical_deconvolved.fits" % context)
qa = qa_image(residual[centre][0])
results['residual_max'] = qa.data['max']
results['residual_min'] = qa.data['min']
residual_cube = remove_sumwt(residual)
residual_cube = image_gather_channels(residual_cube)
if write_fits:
export_image_to_fits(
residual_cube,
"pipelines_rsexecute_timings-%s-ical_residual.fits" % context)
qa = qa_image(restored[centre])
results['restored_max'] = qa.data['max']
results['restored_min'] = qa.data['min']
restored_cube = image_gather_channels(restored)
if write_fits:
export_image_to_fits(
restored_cube,
"pipelines_rsexecute_timings-%s-ical_restored.fits" % context)
#
rsexecute.close()
end_all = time.time()
results['time overall'] = end_all - start_all
lprint("At end, results are:")
results = sort_dict(results)
lprint(results)
return results
logging.basicConfig(
filename='%s/dprepb-pipeline.log' % results_dir,
filemode='a',
format='%(asctime)s,%(msecs)d %(name)s %(levelname)s %(message)s',
datefmt='%H:%M:%S',
level=logging.INFO)
log = logging.getLogger()
logging.info("Starting Imaging pipeline")
# Set up rsexecute to use Dask. This means that all computation is delayed until an
# explicit rsexecute.compute call. If use_dask is False, all calls are computed immediately.
# If running on a cluster, create a scheduler externally and pass in the IP address
if args.scheduler is not None:
c = Client(args.scheduler)
rsexecute.set_client(c)
else:
rsexecute.set_client(use_dask=args.use_dask == 'True',
threads_per_worker=args.threads,
n_workers=args.nworkers,
local_directory=dask_dir)
print(rsexecute.client)
rsexecute.run(init_logging)
nchan = args.nchan
uvmax = 450.0
cellsize = 0.00015
npixel = args.npixel
context = args.context
if context == 'wstack':
def setUp(self):
rsexecute.set_client(use_dask=True,
processes=True,
threads_per_worker=1)
