def Main():
filter_obj = {
'dendrite_type': 'spiny',
'structure_layer_name': '5',
'structure_area_abbrev': 'VISp'
}
ctc = CellTypesCache()
cells = ctc.get_cells(species=['Mus musculus'])
cells_df = pd.DataFrame(cells)
for filt_key, filt_val in filter_obj.items():
cells_df = cells_df.loc[cells_df[filt_key] == filt_val, :]
cell_ids = list(cells_df['id'].values)
rc = Client(profile=os.getenv('IPYTHON_PROFILE'))
logger.debug('Using ipyparallel with %d engines', len(rc))
lview = rc.load_balanced_view()
func = partial(get_fi_data, ctc)
filter_fi_data = lview.map_sync(func, cell_ids)
filter_fi_data = [data for data in filter_fi_data if data is not None]
file_name = 'fi_data.pkl'
with open(file_name, 'wb') as fh:
pickle.dump(filter_fi_data, fh)
plot_fi_data(filter_fi_data)
rc.shutdown(hub=True)
def test_distributed_executor():
from distributed import Client
learner = Learner1D(linear, (-1, 1))
client = Client(n_workers=1)
BlockingRunner(learner, trivial_goal, executor=client)
client.shutdown()
assert learner.npoints > 0
def stop_server(is_slurm=False):
'''
programmatically stops the ipyparallel server
'''
sys.stdout.write("Stopping cluster...\n")
sys.stdout.flush()
if is_slurm:
from ipyparallel import Client
pdir, profile = os.environ['IPPPDIR'], os.environ['IPPPROFILE']
c = Client(ipython_dir=pdir, profile=profile)
ee = c[:]
ne = len(ee)
print 'Shutting down %d engines.'%(ne)
c.shutdown(hub=True)
shutil.rmtree('profile_' + str(profile))
try:
shutil.rmtree('./log/')
except:
print 'creating log folder'
files = glob.glob('*.log')
os.mkdir('./log')
for fl in files:
shutil.move(fl, './log/')
else:
proc = subprocess.Popen(["ipcluster stop"], shell=True, stderr=subprocess.PIPE)
line_out = proc.stderr.readline()
if 'CRITICAL' in line_out:
sys.stdout.write("No cluster to stop...")
sys.stdout.flush()
elif 'Stopping' in line_out:
st = time.time()
sys.stdout.write('Waiting for cluster to stop...')
while (time.time() - st) < 4:
sys.stdout.write('.')
sys.stdout.flush()
time.sleep(1)
else:
print '**** Unrecognized Syntax in ipcluster output, waiting for server to stop anyways ****'
sys.stdout.write(" done\n")
def stop_server(is_slurm=False):
'''
programmatically stops the ipyparallel server
'''
sys.stdout.write("Stopping cluster...\n")
sys.stdout.flush()
if is_slurm:
from ipyparallel import Client
pdir, profile = os.environ['IPPPDIR'], os.environ['IPPPROFILE']
c = Client(ipython_dir=pdir, profile=profile)
ee = c[:]
ne = len(ee)
print 'Shutting down %d engines.' % (ne)
c.shutdown(hub=True)
shutil.rmtree('profile_' + str(profile))
try:
shutil.rmtree('./log/')
except:
print 'creating log folder'
files = glob.glob('*.log')
os.mkdir('./log')
for fl in files:
shutil.move(fl, './log/')
else:
proc = subprocess.Popen(["ipcluster stop"],
shell=True,
stderr=subprocess.PIPE)
line_out = proc.stderr.readline()
if 'CRITICAL' in line_out:
sys.stdout.write("No cluster to stop...")
sys.stdout.flush()
elif 'Stopping' in line_out:
st = time.time()
sys.stdout.write('Waiting for cluster to stop...')
while (time.time() - st) < 4:
sys.stdout.write('.')
sys.stdout.flush()
time.sleep(1)
else:
print '**** Unrecognized Syntax in ipcluster output, waiting for server to stop anyways ****'
sys.stdout.write(" done\n")
lb_view = None
rc = None
meshFile = 'mesh/striatum-mesh.obj'
# meshFile = "mesh/cortex-mesh-200.obj"
sm = RegionMesh(meshFile,
d_view=d_view,
lb_view=lb_view,
raytrace_borders=False)
# import cProfile
# cProfile.run("neuronPos = sm.placeNeurons(1000)")
# sm.plotStruct()
nNeurons = 1730000
neuronPos = sm.place_neurons(nNeurons)
# sm.verify_d_min()
sm.plot_neurons(pdf_name="figures/striatum-fig-somas.png")
sm.plot_struct(pdf_name="figures/striatum-fig-struct.png")
# sm.testPlot()
# sm.testPlotCached()
# tp = (sm.minCoord + sm.maxCoord)/2
# sm.rayCasting(np.array(tp))
if d_view and rc:
rc.shutdown(hub=True)
def gibbs(table_fp, mapping_fp, output_dir, loo, jobs, alpha1, alpha2, beta,
source_rarefaction_depth, sink_rarefaction_depth, restarts,
draws_per_restart, burnin, delay, cluster_start_delay,
source_sink_column, source_column_value, sink_column_value,
source_category_column):
'''Gibb's sampler for Bayesian estimation of microbial sample sources.
For details, see the project README file.
'''
# Create results directory. Click has already checked if it exists, and
# failed if so.
os.mkdir(output_dir)
# Load the mapping file and biom table and remove samples which are not
# shared.
o = open(mapping_fp, 'U')
sample_metadata_lines = o.readlines()
o.close()
sample_metadata, biom_table = \
_cli_sync_biom_and_sample_metadata(
parse_mapping_file(sample_metadata_lines),
load_table(table_fp))
# If biom table has fractional counts, it can produce problems in indexing
# later on.
biom_table.transform(lambda data, id, metadata: np.ceil(data))
# If biom table has sample metadata, there will be pickling errors when
# submitting multiple jobs. We remove the metadata by making a copy of the
# table without metadata.
biom_table = Table(biom_table._data.toarray(),
biom_table.ids(axis='observation'),
biom_table.ids(axis='sample'))
# Parse the mapping file and options to get the samples requested for
# sources and sinks.
source_samples, sink_samples = sinks_and_sources(
sample_metadata,
column_header=source_sink_column,
source_value=source_column_value,
sink_value=sink_column_value)
# If we have no source samples neither normal operation or loo will work.
# Will also likely get strange errors.
if len(source_samples) == 0:
raise ValueError('Mapping file or biom table passed contain no '
'`source` samples.')
# Prepare the 'sources' matrix by collapsing the `source_samples` by their
# metadata values.
sources_envs, sources_data = collapse_sources(source_samples,
sample_metadata,
source_category_column,
biom_table,
sort=True)
# Rarefiy data if requested.
sources_data, biom_table = \
subsample_sources_sinks(sources_data, sink_samples, biom_table,
source_rarefaction_depth,
sink_rarefaction_depth)
# Build function that require only a single parameter -- sample -- to
# enable parallel processing if requested.
if loo:
f = partial(_cli_loo_runner,
source_category=source_category_column,
alpha1=alpha1,
alpha2=alpha2,
beta=beta,
restarts=restarts,
draws_per_restart=draws_per_restart,
burnin=burnin,
delay=delay,
sample_metadata=sample_metadata,
sources_data=sources_data,
sources_envs=sources_envs,
biom_table=biom_table,
output_dir=output_dir)
sample_iter = source_samples
else:
f = partial(_cli_sink_source_prediction_runner,
alpha1=alpha1,
alpha2=alpha2,
beta=beta,
restarts=restarts,
draws_per_restart=draws_per_restart,
burnin=burnin,
delay=delay,
sources_data=sources_data,
biom_table=biom_table,
output_dir=output_dir)
sample_iter = sink_samples
if jobs > 1:
# Launch the ipcluster and wait for it to come up.
subprocess.Popen('ipcluster start -n %s --quiet' % jobs, shell=True)
time.sleep(cluster_start_delay)
c = Client()
c[:].map(f, sample_iter, block=True)
# Shut the cluster down. Answer taken from SO:
# http://stackoverflow.com/questions/30930157/stopping-ipcluster-engines-ipython-parallel
c.shutdown(hub=True)
else:
for sample in sample_iter:
f(sample)
# Format results for output.
samples = []
samples_data = []
for sample_fp in glob.glob(os.path.join(output_dir, '*')):
samples.append(sample_fp.strip().split('/')[-1].split('.txt')[0])
samples_data.append(np.loadtxt(sample_fp, delimiter='\t'))
mp, mps = _cli_collate_results(samples, samples_data, sources_envs)
o = open(os.path.join(output_dir, 'mixing_proportions.txt'), 'w')
o.writelines(mp)
o.close()
o = open(os.path.join(output_dir, 'mixing_proportions_stds.txt'), 'w')
o.writelines(mps)
o.close()
def stop_server(ipcluster='ipcluster', pdir=None, profile=None, dview=None):
"""
programmatically stops the ipyparallel server
Parameters:
----------
ipcluster : str
ipcluster binary file name; requires 4 path separators on Windows
Default: "ipcluster"
"""
if 'multiprocessing' in str(type(dview)):
dview.terminate()
else:
sys.stdout.write("Stopping cluster...\n")
sys.stdout.flush()
try:
pdir, profile = os.environ['IPPPDIR'], os.environ['IPPPROFILE']
is_slurm = True
except:
print('NOT SLURM')
is_slurm = False
if is_slurm:
if pdir is None and profile is None:
pdir, profile = os.environ['IPPPDIR'], os.environ['IPPPROFILE']
c = Client(ipython_dir=pdir, profile=profile)
ee = c[:]
ne = len(ee)
print(('Shutting down %d engines.' % (ne)))
c.close()
c.shutdown(hub=True)
shutil.rmtree('profile_' + str(profile))
try:
shutil.rmtree('./log/')
except:
print('creating log folder')
files = glob.glob('*.log')
os.mkdir('./log')
for fl in files:
shutil.move(fl, './log/')
else:
if ipcluster == "ipcluster":
proc = subprocess.Popen("ipcluster stop",
shell=True,
stderr=subprocess.PIPE,
close_fds=(os.name != 'nt'))
else:
proc = subprocess.Popen(shlex.split(ipcluster + " stop"),
shell=True,
stderr=subprocess.PIPE,
close_fds=(os.name != 'nt'))
line_out = proc.stderr.readline()
if b'CRITICAL' in line_out:
sys.stdout.write("No cluster to stop...")
sys.stdout.flush()
elif b'Stopping' in line_out:
st = time.time()
sys.stdout.write('Waiting for cluster to stop...')
while (time.time() - st) < 4:
sys.stdout.write('.')
sys.stdout.flush()
time.sleep(1)
else:
print(line_out)
print(
'**** Unrecognized Syntax in ipcluster output, waiting for server to stop anyways ****'
)
proc.stderr.close()
sys.stdout.write(" done\n")
def slurm_map(fnc, iterables, resource_spec,
env='root', job_name=None, output_path=None,
n_retries=5, patience=30):
"""
Args:
fnc
iterables
resource_spec
env: virtual env to launch engines in
job_name: name of job to use. Derived from fnc name if not specified
output_path: location to direct output to.
If unspecified output is sent to a file (based on job name and timestamp) in ~/logs/slurm
n_retries: number of times to retry connecting to client if less than the requested number
of workers are available.
patience: seconds to wait after failed attempt to connect to client
"""
resource_spec = process_resource_spec(resource_spec)
if not profile_installed(PROFILE_NAME):
print("No profile found for {}, installing".format(PROFILE_NAME))
install_profile(PROFILE_NAME)
submission_time = time.strftime("%Y%m%d-%H%M%S")
cluster_id = '{}_{}'.format(fnc.__name__, submission_time)
print("Using cluster id: {}".format(cluster_id))
# break down by line:
# run in bash
# activate the specified environment
# launch controller with desired settings
controller_cmd_template = ("exec bash -c '"
"source activate {env};"
" ipcontroller --profile={profile} --sqlitedb --location={hostname} --ip=\'*\' --cluster-id={cluster_id}'")
controller_cmd = controller_cmd_template.format(
env=env, profile=PROFILE_NAME, hostname=socket.gethostname(), cluster_id=cluster_id
)
print("Starting controller with: {} \n".format(controller_cmd))
# runs in the background if executed this way
subprocess.Popen(controller_cmd, shell=True)
print("Sleeping for 10")
time.sleep(10)
engine_cmd_template_path = package_path() + '/templates/slurm_template.sh'
with open(engine_cmd_template_path, 'r') as engine_cmd_template_file:
engine_command_template = engine_cmd_template_file.read()
# prepare engine commands
if job_name is None:
job_name = fnc.__name__ + '_slurm_map'
else:
assert isinstance(job_name, str)
if output_path is None:
output_dir = os.path.expanduser('~/logs/slurm')
output_path = '{}/{}_{}'.format (output_dir, job_name, submission_time)
if not os.path.exists(output_dir):
os.makedirs(output_path)
else:
assert isinstance(output_path, str)
assert os.path.exists(output_path)
# find path to engine based on specified environment
if env == 'root':
engine_path = 'bin/ipengine'
else:
engine_path = 'envs/{}/bin/ipengine'.format(env)
full_engine_path = os.path.expanduser('~/anaconda3/{}'.format(engine_path))
assert os.path.exists(full_engine_path)
engine_command = engine_command_template.format(
job_name=job_name,
output_path=output_path,
n_tasks=resource_spec['max_workers'],
mem_mb=resource_spec['worker_mem_mb'],
n_cpus=resource_spec['worker_n_cpus'],
n_gpus=resource_spec['worker_n_gpus'],
engine_path=engine_path,
profile=PROFILE_NAME,
controller_hostname=socket.gethostname(),
cluster_id=cluster_id,
comment=job_name
)
sbatch_file_path = '/tmp/slurm_map_sbatch_{}.sh'.format(cluster_id)
with open(sbatch_file_path, 'w') as sbatch_file:
sbatch_file.write(engine_command)
# wrap command to execute in bash
sbatch_command = "exec bash -c 'sbatch {}'".format(sbatch_file_path)
print("Starting engines")
# runs in the background if executed this way
subprocess.Popen(sbatch_command, shell=True)
print("Sleeping for {}".format(patience))
time.sleep(patience)
# TODO: shut down unused engines
connected = False
for attempt_idx in range(n_retries):
print("Attempt {} to connect to cluster".format(attempt_idx))
try:
client = Client(profile=PROFILE_NAME, cluster_id=cluster_id)
if resource_spec['min_workers'] <= len(client.ids) <= resource_spec['max_workers']:
connected = True
print('Succesfully connected to cluster with {} engines out of {} requested'.format(
len(client.ids), resource_spec['max_workers']))
if len(client.ids) < resource_spec['max_workers']:
warn("{} slurm jobs submitted but only {} are being used.".format(
resource_spec['max_workers'], len(client.ids)))
break
else:
print("{} available engines less than minimum requested of {}".format(
len(client.ids), resource_spec['min_workers']))
print("Retrying after {}".format(patience))
client.close()
time.sleep(patience)
except OSError as os_err:
print("Caught OSError while attempting to connect to {}: {}.".format(PROFILE_NAME, os_err))
print("Retrying after {}".format(patience))
time.sleep(patience)
except TimeoutError as timeout_err:
print("Caught TimeoutError while attempting to connect to {}: {}".format(PROFILE_NAME, timeout_err))
print("Retrying after {}".format(patience))
time.sleep(patience)
if not connected:
raise TimeoutError("Failed to connect to client after {} retries".format(n_retries))
# run tasks
print("Submitting tasks")
start_time = time.time()
client[:].use_cloudpickle()
lb_view = client.load_balanced_view()
result = lb_view.map(fnc, iterables, block=True)
print("Tasks finished after {} seconds".format(time.time() - start_time))
print("Shutting down cluster")
client.shutdown(hub=True)
print("Relinquishing slurm nodes")
shutdown_cmd = 'scancel -n={job_name}'.format(job_name=job_name)
shutdown_cmd = "exec bash -c '{}'".format(shutdown_cmd)
# runs in the background if executed this way
subprocess.Popen(shutdown_cmd, shell=True)
print("Removing sbatch script")
os.remove(sbatch_file_path)
return result
def gibbs_cli(table_fp, mapping_fp, output_dir, loo, jobs, alpha1, alpha2,
beta, source_rarefaction_depth, sink_rarefaction_depth, restarts,
draws_per_restart, burnin, delay, cluster_start_delay,
per_sink_feature_assignments, sample_with_replacement,
source_sink_column, source_column_value,
sink_column_value, source_category_column):
'''Gibb's sampler for Bayesian estimation of microbial sample sources.
For details, see the project README file.
'''
# Create results directory. Click has already checked if it exists, and
# failed if so.
os.mkdir(output_dir)
# Load the metadata file and feature table.
sample_metadata = parse_sample_metadata(open(mapping_fp, 'U'))
feature_table = biom_to_df(load_table(table_fp))
# Do high level check on feature data.
feature_table = validate_gibbs_input(feature_table)
# Remove samples not shared by both feature and metadata tables and order
# rows equivalently.
sample_metadata, feature_table = \
intersect_and_sort_samples(sample_metadata, feature_table)
# Identify source and sink samples.
source_samples = get_samples(sample_metadata, source_sink_column,
source_column_value)
sink_samples = get_samples(sample_metadata, source_sink_column,
sink_column_value)
# If we have no source samples neither normal operation or loo will work.
# Will also likely get strange errors.
if len(source_samples) == 0:
raise ValueError(('You passed %s as the `source_sink_column` and %s '
'as the `source_column_value`. There are no samples '
'which are sources under these values. Please see '
'the help documentation and check your mapping '
'file.') % (source_sink_column, source_column_value))
# Prepare the 'sources' matrix by collapsing the `source_samples` by their
# metadata values.
csources = collapse_source_data(sample_metadata, feature_table,
source_samples, source_category_column,
'mean')
# Rarify collapsed source data if requested.
if source_rarefaction_depth > 0:
d = (csources.sum(1) >= source_rarefaction_depth)
if not d.all():
count_too_shallow = (~d).sum()
shallowest = csources.sum(1).min()
raise ValueError(('You requested rarefaction of source samples at '
'%s, but there are %s collapsed source samples '
'that have less sequences than that. The '
'shallowest of these is %s sequences.') %
(source_rarefaction_depth, count_too_shallow,
shallowest))
else:
csources = subsample_dataframe(csources, source_rarefaction_depth,
replace=sample_with_replacement)
# Prepare to rarify sink data if we are not doing LOO. If we are doing loo,
# we skip the rarefaction, and set sinks to `None`.
if not loo:
sinks = feature_table.loc[sink_samples, :]
if sink_rarefaction_depth > 0:
d = (sinks.sum(1) >= sink_rarefaction_depth)
if not d.all():
count_too_shallow = (~d).sum()
shallowest = sinks.sum(1).min()
raise ValueError(('You requested rarefaction of sink samples '
'at %s, but there are %s sink samples that '
'have less sequences than that. The '
'shallowest of these is %s sequences.') %
(sink_rarefaction_depth, count_too_shallow,
shallowest))
else:
sinks = subsample_dataframe(sinks, sink_rarefaction_depth,
replace=sample_with_replacement)
else:
sinks = None
# If we've been asked to do multiple jobs, we need to spin up a cluster.
if jobs > 1:
# Launch the ipcluster and wait for it to come up.
subprocess.Popen('ipcluster start -n %s --quiet' % jobs, shell=True)
time.sleep(cluster_start_delay)
cluster = Client()
else:
cluster = None
# Run the computations.
mpm, mps, fas = gibbs(csources, sinks, alpha1, alpha2, beta, restarts,
draws_per_restart, burnin, delay, cluster=cluster,
create_feature_tables=per_sink_feature_assignments)
# If we started a cluster, shut it down.
if jobs > 1:
cluster.shutdown(hub=True)
# Write results.
mpm.to_csv(os.path.join(output_dir, 'mixing_proportions.txt'), sep='\t')
mps.to_csv(os.path.join(output_dir, 'mixing_proportions_stds.txt'),
sep='\t')
if per_sink_feature_assignments:
for sink, fa in zip(mpm.index, fas):
fa.to_csv(os.path.join(output_dir, sink + '.feature_table.txt'),
sep='\t')
# Plot contributions.
fig, ax = plot_heatmap(mpm)
fig.savefig(os.path.join(output_dir, 'mixing_proportions.pdf'), dpi=300)
def gibbs(table_fp, mapping_fp, output_dir, loo, jobs, alpha1, alpha2, beta,
source_rarefaction_depth, sink_rarefaction_depth,
restarts, draws_per_restart, burnin, delay, cluster_start_delay,
source_sink_column, source_column_value, sink_column_value,
source_category_column):
'''Gibb's sampler for Bayesian estimation of microbial sample sources.
For details, see the project README file.
'''
# Create results directory. Click has already checked if it exists, and
# failed if so.
os.mkdir(output_dir)
# Load the mapping file and biom table and remove samples which are not
# shared.
o = open(mapping_fp, 'U')
sample_metadata_lines = o.readlines()
o.close()
sample_metadata, biom_table = \
_cli_sync_biom_and_sample_metadata(
parse_mapping_file(sample_metadata_lines),
load_table(table_fp))
# If biom table has fractional counts, it can produce problems in indexing
# later on.
biom_table.transform(lambda data, id, metadata: np.ceil(data))
# If biom table has sample metadata, there will be pickling errors when
# submitting multiple jobs. We remove the metadata by making a copy of the
# table without metadata.
biom_table = Table(biom_table._data.toarray(),
biom_table.ids(axis='observation'),
biom_table.ids(axis='sample'))
# Parse the mapping file and options to get the samples requested for
# sources and sinks.
source_samples, sink_samples = sinks_and_sources(
sample_metadata, column_header=source_sink_column,
source_value=source_column_value, sink_value=sink_column_value)
# If we have no source samples neither normal operation or loo will work.
# Will also likely get strange errors.
if len(source_samples) == 0:
raise ValueError('Mapping file or biom table passed contain no '
'`source` samples.')
# Prepare the 'sources' matrix by collapsing the `source_samples` by their
# metadata values.
sources_envs, sources_data = collapse_sources(source_samples,
sample_metadata,
source_category_column,
biom_table, sort=True)
# Rarefiy data if requested.
sources_data, biom_table = \
subsample_sources_sinks(sources_data, sink_samples, biom_table,
source_rarefaction_depth,
sink_rarefaction_depth)
# Build function that require only a single parameter -- sample -- to
# enable parallel processing if requested.
if loo:
f = partial(_cli_loo_runner, source_category=source_category_column,
alpha1=alpha1, alpha2=alpha2, beta=beta,
restarts=restarts, draws_per_restart=draws_per_restart,
burnin=burnin, delay=delay,
sample_metadata=sample_metadata,
sources_data=sources_data, sources_envs=sources_envs,
biom_table=biom_table, output_dir=output_dir)
sample_iter = source_samples
else:
f = partial(_cli_sink_source_prediction_runner, alpha1=alpha1,
alpha2=alpha2, beta=beta, restarts=restarts,
draws_per_restart=draws_per_restart, burnin=burnin,
delay=delay, sources_data=sources_data,
biom_table=biom_table, output_dir=output_dir)
sample_iter = sink_samples
if jobs > 1:
# Launch the ipcluster and wait for it to come up.
subprocess.Popen('ipcluster start -n %s --quiet' % jobs, shell=True)
time.sleep(cluster_start_delay)
c = Client()
c[:].map(f, sample_iter, block=True)
# Shut the cluster down. Answer taken from SO:
# http://stackoverflow.com/questions/30930157/stopping-ipcluster-engines-ipython-parallel
c.shutdown(hub=True)
else:
for sample in sample_iter:
f(sample)
# Format results for output.
samples = []
samples_data = []
for sample_fp in glob.glob(os.path.join(output_dir, '*')):
samples.append(sample_fp.strip().split('/')[-1].split('.txt')[0])
samples_data.append(np.loadtxt(sample_fp, delimiter='\t'))
mp, mps = _cli_collate_results(samples, samples_data, sources_envs)
o = open(os.path.join(output_dir, 'mixing_proportions.txt'), 'w')
o.writelines(mp)
o.close()
o = open(os.path.join(output_dir, 'mixing_proportions_stds.txt'), 'w')
o.writelines(mps)
o.close()
def gibbs_cli(table_fp, mapping_fp, output_dir, loo, jobs, alpha1, alpha2,
beta, source_rarefaction_depth, sink_rarefaction_depth, restarts,
draws_per_restart, burnin, delay, cluster_start_delay,
per_sink_feature_assignments, sample_with_replacement,
source_sink_column, source_column_value, sink_column_value,
source_category_column):
'''Gibb's sampler for Bayesian estimation of microbial sample sources.
For details, see the project README file.
'''
# Create results directory. Click has already checked if it exists, and
# failed if so.
os.mkdir(output_dir)
# Load the metadata file and feature table.
sample_metadata = parse_sample_metadata(open(mapping_fp, 'U'))
feature_table = biom_to_df(load_table(table_fp))
# Do high level check on feature data.
feature_table = validate_gibbs_input(feature_table)
# Remove samples not shared by both feature and metadata tables and order
# rows equivalently.
sample_metadata, feature_table = \
intersect_and_sort_samples(sample_metadata, feature_table)
# Identify source and sink samples.
source_samples = get_samples(sample_metadata, source_sink_column,
source_column_value)
sink_samples = get_samples(sample_metadata, source_sink_column,
sink_column_value)
# If we have no source samples neither normal operation or loo will work.
# Will also likely get strange errors.
if len(source_samples) == 0:
raise ValueError(('You passed %s as the `source_sink_column` and %s '
'as the `source_column_value`. There are no samples '
'which are sources under these values. Please see '
'the help documentation and check your mapping '
'file.') % (source_sink_column, source_column_value))
# Prepare the 'sources' matrix by collapsing the `source_samples` by their
# metadata values.
csources = collapse_source_data(sample_metadata, feature_table,
source_samples, source_category_column,
'mean')
# Rarify collapsed source data if requested.
if source_rarefaction_depth > 0:
d = (csources.sum(1) >= source_rarefaction_depth)
if not d.all():
count_too_shallow = (~d).sum()
shallowest = csources.sum(1).min()
raise ValueError(
('You requested rarefaction of source samples at '
'%s, but there are %s collapsed source samples '
'that have less sequences than that. The '
'shallowest of these is %s sequences.') %
(source_rarefaction_depth, count_too_shallow, shallowest))
else:
csources = subsample_dataframe(csources,
source_rarefaction_depth,
replace=sample_with_replacement)
# Prepare to rarify sink data if we are not doing LOO. If we are doing loo,
# we skip the rarefaction, and set sinks to `None`.
if not loo:
sinks = feature_table.loc[sink_samples, :]
if sink_rarefaction_depth > 0:
d = (sinks.sum(1) >= sink_rarefaction_depth)
if not d.all():
count_too_shallow = (~d).sum()
shallowest = sinks.sum(1).min()
raise ValueError(
('You requested rarefaction of sink samples '
'at %s, but there are %s sink samples that '
'have less sequences than that. The '
'shallowest of these is %s sequences.') %
(sink_rarefaction_depth, count_too_shallow, shallowest))
else:
sinks = subsample_dataframe(sinks,
sink_rarefaction_depth,
replace=sample_with_replacement)
else:
sinks = None
# If we've been asked to do multiple jobs, we need to spin up a cluster.
if jobs > 1:
# Launch the ipcluster and wait for it to come up.
subprocess.Popen('ipcluster start -n %s --quiet' % jobs, shell=True)
time.sleep(cluster_start_delay)
cluster = Client()
else:
cluster = None
# Run the computations.
mpm, mps, fas = gibbs(csources,
sinks,
alpha1,
alpha2,
beta,
restarts,
draws_per_restart,
burnin,
delay,
cluster=cluster,
create_feature_tables=per_sink_feature_assignments)
# If we started a cluster, shut it down.
if jobs > 1:
cluster.shutdown(hub=True)
# Write results.
mpm.to_csv(os.path.join(output_dir, 'mixing_proportions.txt'), sep='\t')
mps.to_csv(os.path.join(output_dir, 'mixing_proportions_stds.txt'),
sep='\t')
if per_sink_feature_assignments:
for sink, fa in zip(mpm.index, fas):
fa.to_csv(os.path.join(output_dir, sink + '.feature_table.txt'),
sep='\t')
# Plot contributions.
fig, ax = plot_heatmap(mpm)
fig.savefig(os.path.join(output_dir, 'mixing_proportions.pdf'), dpi=300)
class Snudda(object):
############################################################################
def __init__(self, networkPath):
if (networkPath[-1] == "/"):
self.networkPath = networkPath[:-1]
else:
self.networkPath = networkPath
# Add current dir to python path
sys.path.append(os.getcwd())
self.start = timeit.default_timer()
############################################################################
def helpInfo(self, args):
from .snudda_help import snudda_help_text
print(snudda_help_text())
############################################################################
def initConfig(self, args):
# self.networkPath = args.path
print("Creating config file")
print("Network path: " + str(self.networkPath))
assert args.size is not None, \
"You need to speicfy --size when initialising config for network2"
from .init import SnuddaInit
structDef = {
"Striatum": args.size,
"GPe": 0,
"GPi": 0,
"SNr": 0,
"STN": 0,
"Cortex": 0,
"Thalamus": 0
}
# Cortex and thalamus axons disabled right now, set to 1 to include one
if not args.overwrite:
assert not os.path.exists(self.networkPath), \
"Network path " + str(self.networkPath) + " already exists" \
+ " (aborting to prevent accidental overwriting)"
self.makeDirIfNeeded(self.networkPath)
nChannels = args.nchannels
configFile = self.networkPath + "/network-config.json"
SnuddaInit(structDef=structDef,
configName=configFile,
nChannels=nChannels)
if (args.size > 1e5):
print("Make sure there is enough disk space in " +
str(self.networkPath))
print("Large networks take up ALOT of space")
############################################################################
def placeNeurons(self, args):
# self.networkPath = args.path
print("Placing neurons")
print("Network path: " + str(self.networkPath))
configFile = self.networkPath + "/network-config.json"
positionFile = self.networkPath + "/network-neuron-positions.hdf5"
logFileName = self.networkPath + "/log/logFile-place-neurons.txt"
self.setupLogFile(logFileName) # sets self.logFile
self.setupParallel() # sets self.dView and self.lbView
from .place import SnuddaPlace
if (args.h5legacy):
h5libver = "earliest"
else:
h5libver = "latest" # default
npn = SnuddaPlace(config_file=configFile,
logFile=self.logFile,
verbose=True,
dView=self.dView,
h5libver=h5libver)
npn.writeDataHDF5(positionFile)
self.stopParallel()
self.closeLogFile()
############################################################################
def touchDetection(self, args):
# self.networkPath = args.path
print("Touch detection")
print("Network path: " + str(self.networkPath))
if (args.hvsize is not None):
hyperVoxelSize = int(args.hvsize)
else:
hyperVoxelSize = 100
if (args.volumeID is not None):
volumeID = args.volumeID
else:
volumeID = None
logDir = self.networkPath + "/log"
configFile = self.networkPath + "/network-config.json"
positionFile = self.networkPath + "/network-neuron-positions.hdf5"
logFileName = self.networkPath + "/log/logFile-touch-detection.txt"
saveFile = self.networkPath + "/voxels/network-putative-synapses.hdf5"
voxelDir = self.networkPath + "/voxels"
self.makeDirIfNeeded(voxelDir)
self.setupLogFile(logFileName) # sets self.logFile
self.setupParallel() # sets self.dView and self.lbView
if (args.h5legacy):
h5libver = "earliest"
else:
h5libver = "latest" # default
from .detect import SnuddaDetect
if (args.cont):
# Continue previous run
print("Continuing previous touch detection")
ncv = SnuddaDetect(configFile=configFile,
positionFile=positionFile,
logFile=self.logFile,
saveFile=saveFile,
SlurmID=self.SlurmID,
volumeID=volumeID,
rc=self.rc,
hyperVoxelSize=hyperVoxelSize,
h5libver=h5libver,
restartDetectionFlag=False)
else:
ncv = SnuddaDetect(configFile=configFile,
positionFile=positionFile,
logFile=self.logFile,
saveFile=saveFile,
SlurmID=self.SlurmID,
volumeID=volumeID,
rc=self.rc,
h5libver=h5libver,
hyperVoxelSize=hyperVoxelSize)
self.stopParallel()
self.closeLogFile()
############################################################################
def pruneSynapses(self, args):
# self.networkPath = args.path
print("Prune synapses")
print("Network path: " + str(self.networkPath))
from .prune import SnuddaPrune
logFileName = self.networkPath + "/log/logFile-synapse-pruning.txt"
workLog = self.networkPath + "/log/network-detect-worklog.hdf5"
self.setupLogFile(logFileName) # sets self.logFile
self.setupParallel() # sets self.dView and self.lbView
# Optionally set this
scratchPath = None
if (args.mergeonly):
preMergeOnly = True
else:
preMergeOnly = False
print("preMergeOnly : " + str(preMergeOnly))
if (args.h5legacy):
h5libver = "earliest"
else:
h5libver = "latest" # default
ncvp = SnuddaPrune(workHistoryFile=workLog,
logFile=self.logFile,
logFileName=logFileName,
dView=self.dView,
lbView=self.lbView,
scratchPath=scratchPath,
h5libver=h5libver,
preMergeOnly=preMergeOnly)
self.stopParallel()
self.closeLogFile()
############################################################################
def setupInput(self, args):
from .input import SnuddaInput
print("Setting up inputs, assuming input.json exists")
logFileName = self.networkPath + "/log/logFile-setup-input.log"
self.setupLogFile(logFileName) # sets self.logFile
self.setupParallel() # sets self.dView and self.lbView
if "input" in args:
inputConfig = args.input
else:
inputConfig = self.networkPath + "/input.json"
if (not os.path.isfile(inputConfig)):
print("Missing input config file: " + str(inputConfig))
return
if (args.networkFile):
networkFile = args.networkFile
else:
networkFile = self.networkPath \
+ "/network-pruned-synapses.hdf5"
if (args.inputFile):
spikeFile = args.inputFile
else:
spikeFile = self.networkPath + "/input-spikes.hdf5"
if (args.time):
inputTime = args.time
print("Writing input spikes to " + spikeFile)
ni = SnuddaInput(inputConfigFile=inputConfig,
HDF5networkFile=networkFile,
spikeDataFileName=spikeFile,
time=inputTime,
logFile=self.logFile)
self.stopParallel()
self.closeLogFile()
############################################################################
def exportToSONATA(self, args):
from ConvertNetwork import ConvertNetwork
print("Exporting to SONATA format")
print("Network path: " + str(self.networkPath))
if (args.networkFile):
networkFile = args.networkFile
else:
networkFile = self.networkPath \
+ "/network-pruned-synapses.hdf5"
if (args.inputFile):
inputFile = args.inputFile
else:
inputFile = self.networkPath + "/input-spikes.hdf5"
outDir = self.networkPath + "/SONATA/"
cn = ConvertNetwork(networkFile=networkFile,
inputFile=inputFile,
outDir=outDir)
############################################################################
def simulate(self, args):
start = timeit.default_timer()
from .simulate import SnuddaSimulate
if (args.networkFile):
networkFile = args.networkFile
else:
networkFile = self.networkPath \
+ "/network-pruned-synapses.hdf5"
if (args.inputFile):
inputFile = args.inputFile
else:
inputFile = self.networkPath + "/input-spikes.hdf5"
self.makeDirIfNeeded(self.networkPath + "/simulation")
print("Using input file " + inputFile)
#nWorkers = args.ncores
#print("Using " + str(nWorkers) + " workers for neuron")
# Problems with nested symbolic links when the second one is a relative
# path going beyond the original base path
if (args.mechDir is None):
mechDir = os.path.dirname(networkFile) + "/mechanisms"
# !!! problem with paths, testing to create mechanism dir in current dir
mechDir = "mechanisms"
if (not os.path.exists(mechDir)):
mDir = os.path.dirname(__file__) + "/data/cellspecs/mechanisms"
os.symlink(mDir, mechDir)
else:
mechDir = args.mechDir
# !!! These are saved in current directory x86_64
# --- problem since nrnivmodl seems to want a relative path...
makeModsStr = "nrnivmodl " + mechDir
if (not os.path.exists('x86_64')):
print("Please first run: " + makeModsStr)
exit(-1)
# I was having problems when running nrnivmodl in the script, but
# running it manually in bash works... WHY?!!
# os.system(makeModsStr)
saveDir = os.path.dirname(networkFile) + "/simulation/"
if (not os.path.exists(saveDir)):
print("Creating directory " + saveDir)
os.makedirs(saveDir, exist_ok=True)
# Get the SlurmID, used in default file names
SlurmID = os.getenv('SLURM_JOBID')
if (SlurmID is None):
SlurmID = str(666)
print("args: " + str(args))
if (args.voltOut is not None):
# Save neuron voltage
if (args.voltOut == "default"):
voltFile = saveDir + 'network-voltage-' + SlurmID + '.csv'
else:
voltFile = args.voltOut
else:
voltFile = None
if (args.spikesOut is None or args.spikesOut == "default"):
spikesFile = saveDir + 'network-output-spikes-' + SlurmID + '.txt'
else:
spikesFile = args.spikesOut
disableGJ = args.disableGJ
if (disableGJ):
print("!!! WE HAVE DISABLED GAP JUNCTIONS !!!")
logFile = os.path.dirname(networkFile) \
+ "/log/network-simulation-log.txt"
logDir = os.path.dirname(networkFile) + "/log"
if (not os.path.exists(logDir)):
print("Creating directory " + logDir)
os.makedirs(logDir, exist_ok=True)
from mpi4py import MPI # This must be imported before neuron, to run parallel
from neuron import h #, gui
pc = h.ParallelContext()
sim = SnuddaSimulate(networkFile=networkFile,
inputFile=inputFile,
disableGapJunctions=disableGJ,
logFile=logFile,
verbose=args.verbose)
sim.addExternalInput()
sim.checkMemoryStatus()
if (voltFile is not None):
sim.addRecording(
sideLen=None) # Side len let you record from a subset
#sim.addRecordingOfType("dSPN",5) # Side len let you record from a subset
tSim = args.time * 1000 # Convert from s to ms for Neuron simulator
sim.checkMemoryStatus()
print("Running simulation for " + str(tSim) + " ms.")
sim.run(tSim) # In milliseconds
print("Simulation done, saving output")
if (spikesFile is not None):
sim.writeSpikes(spikesFile)
if (voltFile is not None):
sim.writeVoltage(voltFile)
stop = timeit.default_timer()
if (sim.pc.id() == 0):
print("Program run time: " + str(stop - start))
# sim.plot()
exit(0)
#cmdStr = "nrnivmodl " + mechDir + " && mpiexec -n " + str(nWorkers) + " -map-by socket:OVERSUBSCRIBE python3 " + os.path.dirname(__file__) + " simulate.py " + networkFile + " " + inputFile + " --time " + str(args.time)
#if(args.voltOut is not None):
# cmdStr += " --voltOut " + args.voltOut
#os.system(cmdStr)
############################################################################
def analyse(self, args):
print("Add analysis code here, see Network_analyse.py")
############################################################################
def setupParallel(self):
self.SlurmID = os.getenv('SLURM_JOBID')
if (self.SlurmID is None):
self.SlurmID = self.nextRunID()
else:
self.SlurmID = int(self.SlurmID)
self.logFile.write("Using SlurmID: " + str(self.SlurmID))
if (os.getenv('IPYTHON_PROFILE') is not None):
self.logFile.write('Creating ipyparallel client\n')
from ipyparallel import Client
#self.rc = Client(profile=os.getenv('IPYTHON_PROFILE'),
# # sshserver='127.0.0.1',
# debug=False)
ufile = os.getenv('IPYTHONDIR') + "/profile_" \
+ os.getenv('IPYTHON_PROFILE') \
+ "/security/ipcontroller-client.json"
self.rc = Client(url_file=ufile, timeout=120, debug=False)
self.logFile.write('Client IDs: ' + str(self.rc.ids))
# http://davidmasad.com/blog/simulation-with-ipyparallel/
# http://people.duke.edu/~ccc14/sta-663-2016/19C_IPyParallel.html
self.dView = self.rc.direct_view(
targets='all') # rc[:] # Direct view into clients
self.lbView = self.rc.load_balanced_view(targets='all')
# Define nc globally
# self.dView.execute("nc = None",block=True)
else:
self.logFile.write(
"No IPYTHON_PROFILE enviroment variable set, running in serial"
)
self.dView = None
self.lbView = None
self.rc = None
############################################################################
def stopParallel(self):
# Disable this function, keep the pool running for now
return
if (self.rc is not None):
print("Stopping ipyparallel")
self.rc.shutdown(hub=True)
############################################################################
def setupLogFile(self, logFileName):
dataDir = os.path.dirname(logFileName)
self.makeDirIfNeeded(dataDir)
try:
self.logFile = open(logFileName, 'w')
self.logFile.write('Starting log file\n')
except:
print("Unable to set up log file " + str(logFileName))
############################################################################
def closeLogFile(self):
stop = timeit.default_timer()
print("\nProgram run time: " + str(stop - self.start))
self.logFile.write("Program run time: " + str(stop - self.start))
self.logFile.write("End of log. Closing file.")
self.logFile.close()
##############################################################################
def nextRunID(self):
import pickle
runIDfile = ".runID.pickle"
try:
if (os.path.isfile(runIDfile)):
with open(runIDfile, 'rb') as f:
runID = pickle.load(f)
nextID = int(np.ceil(np.max(runID)) + 1)
runID.append(nextID)
with open(runIDfile, 'wb') as f:
pickle.dump(runID, f, -1)
else:
with open(runIDfile, 'wb') as f:
nextID = 1
runID = [1]
pickle.dump(runID, f, -1)
except Exception as e:
import traceback
tstr = traceback.format_exc()
print(tstr)
print("Problem reading .runID.pickle file, setting runID to 0")
import pdb
pdb.set_trace()
return 0
print("Using runID = " + str(nextID))
return nextID
############################################################################
def makeDirIfNeeded(self, dirPath):
if (not os.path.exists(dirPath)):
print("Creating missing directory " + dirPath)
os.makedirs(dirPath)
def stop_server(ipcluster='ipcluster', pdir=None, profile=None, dview=None):
"""
programmatically stops the ipyparallel server
Parameters:
----------
ipcluster : str
ipcluster binary file name; requires 4 path separators on Windows
Default: "ipcluster"
"""
if 'multiprocessing' in str(type(dview)):
dview.terminate()
else:
logger.info("Stopping cluster...")
try:
pdir, profile = os.environ['IPPPDIR'], os.environ['IPPPROFILE']
is_slurm = True
except:
logger.debug('stop_server: not a slurm cluster')
is_slurm = False
if is_slurm:
if pdir is None and profile is None:
pdir, profile = os.environ['IPPPDIR'], os.environ['IPPPROFILE']
c = Client(ipython_dir=pdir, profile=profile)
ee = c[:]
ne = len(ee)
print(('Shutting down %d engines.' % (ne)))
c.close()
c.shutdown(hub=True)
shutil.rmtree('profile_' + str(profile))
try:
shutil.rmtree('./log/')
except:
print('creating log folder')
files = glob.glob('*.log')
os.mkdir('./log')
for fl in files:
shutil.move(fl, './log/')
else:
if ipcluster == "ipcluster":
proc = subprocess.Popen(
"ipcluster stop", shell=True, stderr=subprocess.PIPE, close_fds=(os.name != 'nt'))
else:
proc = subprocess.Popen(shlex.split(ipcluster + " stop"),
shell=True, stderr=subprocess.PIPE, close_fds=(os.name != 'nt'))
line_out = proc.stderr.readline()
if b'CRITICAL' in line_out:
logger.info("No cluster to stop...")
elif b'Stopping' in line_out:
st = time.time()
logger.debug('Waiting for cluster to stop...')
while (time.time() - st) < 4:
sys.stdout.write('.')
sys.stdout.flush()
time.sleep(1)
else:
print(line_out)
print(
'**** Unrecognized syntax in ipcluster output, waiting for server to stop anyways ****')
proc.stderr.close()
logger.info("stop_cluster(): done")
