def main():
# Setup needed parameters for the request, the user would need to vary these to suit their own needs and
# sites/instruments of interest. Site, node, sensor, stream and delivery method names can be obtained from the
# Ocean Observatories Initiative web site. The last two parameters (level and instrmt) will set path and naming
# conventions to save the data to the local disk.
site = 'CE02SHSM' # OOI Net site designator
node = 'SBD12' # OOI Net node designator
sensor = '04-PCO2AA000' # OOI Net sensor designator
stream = 'pco2a_a_dcl_instrument_air' # OOI Net stream name
method = 'telemetered' # OOI Net data delivery method
level = 'buoy' # local directory name, level below site
instrmt = 'pco2a' # local directory name, instrument below level
# We are after telemetered data. Determine list of deployments and use the last, presumably currently active,
# deployment to determine the start and end dates for our request.
vocab = get_vocabulary(site, node, sensor)[0]
deployments = list_deployments(site, node, sensor)
deploy = deployments[-1]
start, stop = get_deployment_dates(site, node, sensor, deploy)
# request and download the data -- air measurements
r = m2m_request(site, node, sensor, method, stream, start, stop)
air = m2m_collect(r, ('.*deployment%04d.*PCO2A.*air.*\\.nc$' % deploy))
# request and download the data -- water measurements
r = m2m_request(site, node, sensor, method, 'pco2a_a_dcl_instrument_water',
start, stop)
water = m2m_collect(r, ('.*deployment%04d.*PCO2A.*water.*\\.nc$' % deploy))
# clean-up and reorganize the air and water datasets
air = pco2a_datalogger(air, True)
air = update_dataset(air, vocab['maxdepth'])
water = pco2a_datalogger(water, True)
water = update_dataset(water, vocab['maxdepth'])
# save the data -- utilize groups for the air and water datasets
out_path = os.path.join(CONFIG['base_dir']['m2m_base'], site.lower(),
level, instrmt)
out_path = os.path.abspath(out_path)
if not os.path.exists(out_path):
os.makedirs(out_path)
out_file = ('%s.%s.%s.deploy%02d.%s.%s.nc' %
(site.lower(), level, instrmt, deploy, method, stream))
nc_out = os.path.join(out_path, out_file)
air.to_netcdf(nc_out,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS,
group='air')
water.to_netcdf(nc_out,
mode='a',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS,
group='water')
def main(argv=None):
# setup the input arguments
args = inputs(argv)
site = args.site
node = args.node
sensor = args.sensor
method = args.method
stream = args.stream
deploy = args.deploy
start = args.start
stop = args.stop
# determine the start and stop times for the data request based on either the deployment number or user entered
# beginning and ending dates.
if not deploy or (start and stop):
return SyntaxError('You must specify either a deployment number or beginning and end dates of interest.')
else:
if deploy:
# Determine start and end dates based on the deployment number
start, stop = get_deployment_dates(site, node, sensor, deploy)
if not start or not stop:
exit_text = ('Deployment dates are unavailable for %s-%s-%s, deployment %02d.' % (site, node, sensor,
deploy))
raise SystemExit(exit_text)
# Request the data for download
r = m2m_request(site, node, sensor, method, stream, start, stop)
if not r:
exit_text = ('Request failed for %s-%s-%s. Check request.' % (site, node, sensor))
raise SystemExit(exit_text)
# Valid request, start downloading the data
if deploy:
phsen = m2m_collect(r, ('.*deployment%04d.*PHSEN.*\\.nc$' % deploy))
else:
phsen = m2m_collect(r, '.*PHSEN.*\\.nc$')
if not phsen:
exit_text = ('Data unavailable for %s-%s-%s. Check request.' % (site, node, sensor))
raise SystemExit(exit_text)
# clean-up and reorganize
if method in ['telemetered', 'recovered_host']:
if re.match('.*imodem.*', stream):
phsen = phsen_imodem(phsen)
else:
phsen = phsen_datalogger(phsen)
else:
phsen = phsen_instrument(phsen)
vocab = get_vocabulary(site, node, sensor)[0]
phsen = update_dataset(phsen, vocab['maxdepth'])
# save the data to disk
out_file = os.path.abspath(args.outfile)
if not os.path.exists(os.path.dirname(out_file)):
os.makedirs(os.path.dirname(out_file))
phsen.to_netcdf(out_file, mode='w', format='NETCDF4', engine='h5netcdf', encoding=ENCODINGS)
def main():
# Setup needed parameters for the request, the user would need to vary these to suit their own needs and
# sites/instruments of interest. Site, node, sensor, stream and delivery method names can be obtained from the
# Ocean Observatories Initiative web site. The last two will set path and naming conventions to save the data
# to the local disk
site = 'CE02SHSM' # OOI Net site designator
node = 'RID26' # OOI Net node designator
sensor = '06-PHSEND000' # OOI Net sensor designator
stream = 'phsen_abcdef_dcl_instrument' # OOI Net stream name
method = 'telemetered' # OOI Net data delivery method
level = 'nsif' # local directory name, level below site
instrmt = 'phsen' # local directory name, instrument below level
# We are after telemetered data. Determine list of deployments and use the last, presumably currently active,
# deployment to determine the start and end dates for our request.
vocab = get_vocabulary(site, node, sensor)[0]
deployments = list_deployments(site, node, sensor)
deploy = deployments[-1]
start, stop = get_deployment_dates(site, node, sensor, deploy)
# request and download the data
r = m2m_request(site, node, sensor, method, stream, start, stop)
phsen = m2m_collect(r, '.*PHSEN.*\\.nc$')
phsen = phsen.where(phsen.deployment == deploy,
drop=True) # limit to the deployment of interest
# clean-up and reorganize
phsen = phsen_datalogger(phsen)
phsen = update_dataset(phsen, vocab['maxdepth'])
# save the data
out_path = os.path.join(CONFIG['base_dir']['m2m_base'], site.lower(),
level, instrmt)
out_path = os.path.abspath(out_path)
if not os.path.exists(out_path):
os.makedirs(out_path)
out_file = ('%s.%s.%s.deploy%02d.%s.%s.nc' %
(site.lower(), level, instrmt, deploy, method, stream))
nc_out = os.path.join(out_path, out_file)
phsen.to_netcdf(nc_out,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS)
def main():
# Setup needed parameters for the request, the user would need to vary these to suit their own needs and
# sites/instruments of interest. Site, node, sensor, stream and delivery method names can be obtained from the
# Ocean Observatories Initiative web site. The last two will set path and naming conventions to save the data
# to the local disk
site = 'CE01ISSM' # OOI Net site designator
node = 'SBD17' # OOI Net node designator
sensor = '06-FLORTD000' # OOI Net sensor designator
stream = 'flort_sample' # OOI Net stream name
method = 'recovered_inst' # OOI Net data delivery method
level = 'buoy' # local directory name, level below site
instrmt = 'flort' # local directory name, instrument below level
# We are after recovered instrument data. Determine list of deployments and use a more recent deployment to
# determine the start and end dates for our request.
vocab = get_vocabulary(site, node, sensor)[0]
deployments = list_deployments(site, node, sensor)
deploy = deployments[5]
start, stop = get_deployment_dates(site, node, sensor, deploy)
# request and download the data
r = m2m_request(site, node, sensor, method, stream, start, stop)
flort = m2m_collect(r, '.*FLORT.*\\.nc$')
flort = flort.where(flort.deployment == deploy,
drop=True) # limit to the deployment of interest
# clean-up and reorganize
flort = flort_instrument(flort)
flort = update_dataset(flort, vocab['maxdepth'])
# save the data
out_path = os.path.join(CONFIG['base_dir']['m2m_base'], site.lower(),
level, instrmt)
out_path = os.path.abspath(out_path)
if not os.path.exists(out_path):
os.makedirs(out_path)
out_file = ('%s.%s.%s.deploy%02d.%s.%s.nc' %
(site.lower(), level, instrmt, deploy, method, stream))
nc_out = os.path.join(out_path, out_file)
flort.to_netcdf(nc_out,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS)
def main():
# Setup needed parameters for the request, the user would need to vary these to suit their own needs and
# sites/instruments of interest. Site, node, sensor and stream names can be obtained from the Ocean Observatories
# Initiative web site
site = 'CE01ISSM' # OOI Net site designator
node = 'RID16' # OOI Net node designator
sensor = '05-PCO2WB000' # OOI Net sensor designator
stream = 'pco2w_abc_instrument' # OOI Net stream name
method = 'recovered_inst' # OOI Net data delivery method
level = 'nsif' # local directory name, level below site
instrmt = 'pco2w' # local directory name, instrument below level
# We are after recovered host data. Determine list of deployments and use a previous one to determine the
# start and end dates for our request.
vocab = get_vocabulary(site, node, sensor)[0]
deployments = list_deployments(site, node, sensor)
deploy = deployments[-3]
start, stop = get_deployment_dates(site, node, sensor, deploy)
# request and download the data
r = m2m_request(site, node, sensor, method, stream, start, stop)
pco2w = m2m_collect(r, '^(?!.*blank).*PCO2W.*nc$')
pco2w = pco2w.where(pco2w.deployment == deploy,
drop=True) # limit to the deployment of interest
# clean-up and reorganize
pco2w = pco2w_instrument(pco2w)
pco2w = update_dataset(pco2w, vocab['maxdepth'])
# save the data
out_path = os.path.join(CONFIG['base_dir']['m2m_base'], site.lower(),
level, instrmt)
out_path = os.path.abspath(out_path)
if not os.path.exists(out_path):
os.makedirs(out_path)
out_file = ('%s.%s.%s.deploy%02d.%s.%s.nc' %
(site.lower(), level, instrmt, deploy, method, stream))
nc_out = os.path.join(out_path, out_file)
pco2w.to_netcdf(nc_out,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS)
def request_data(site, node, sensor, method, stream, start, stop):
"""
Request and download data from the OOI M2M system
:param site:
:param node:
:param sensor:
:param method:
:param stream:
:param start:
:param stop:
:return data:
"""
# Request the data (this may take some time).
r = m2m_request(site, node, sensor, method, stream, start, stop)
# Use a regex tag to download the sensor data from the THREDDS catalog
# created by our request.
tag = ('.*{}.*\\.nc$'.format(sensor[3:8]))
data = m2m_collect(r, tag)
return data
def main(argv=None):
args = inputs(argv)
site = args.site
node = args.node
sensor = args.sensor
method = args.method
stream = args.stream
deploy = args.deploy
start = args.start
stop = args.stop
burst = args.burst
sensor_type = args.sensor_type
# determine the start and stop times for the data request based on either the deployment number or user entered
# beginning and ending dates.
if not deploy or (start and stop):
return SyntaxError(
'You must specify either a deployment number or beginning and end dates of interest.'
)
else:
if deploy:
# Determine start and end dates based on the deployment number
start, stop = get_deployment_dates(site, node, sensor, deploy)
if not start or not stop:
exit_text = (
'Deployment dates are unavailable for %s-%s-%s, deployment %02d.'
% (site, node, sensor, deploy))
raise SystemExit(exit_text)
# Request the data for download
r = m2m_request(site, node, sensor, method, stream, start, stop)
if not r:
exit_text = ('Request failed for %s-%s-%s. Check request.' %
(site, node, sensor))
raise SystemExit(exit_text)
# Valid request, start downloading the data
if deploy:
dosta = m2m_collect(r, ('.*deployment%04d.*DOSTA.*\\.nc$' % deploy))
else:
dosta = m2m_collect(r, '.*DOSTA.*\\.nc$')
if not dosta:
exit_text = ('Data unavailable for %s-%s-%s. Check request.' %
(site, node, sensor))
raise SystemExit(exit_text)
if not sensor_type in ['solo', 'ctdbp']:
exit_text = 'You need to specify the type of DOSTA in order to process: solo or ctdbp'
raise SystemExit(exit_text)
# clean-up and reorganize based on the type and data delivery method
if sensor_type == 'solo':
dosta = dosta_datalogger(dosta, burst)
if sensor_type == 'ctdbp':
if method in ['telemetered', 'recovered_host']:
dosta = dosta_ctdbp_datalogger(dosta)
else:
dosta = dosta_ctdbp_instrument(dosta)
vocab = get_vocabulary(site, node, sensor)[0]
dosta = update_dataset(dosta, vocab['maxdepth'])
# save the data to disk
out_file = os.path.abspath(args.outfile)
if not os.path.exists(os.path.dirname(out_file)):
os.makedirs(os.path.dirname(out_file))
dosta.to_netcdf(out_file,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS)
def main(argv=None):
args = inputs(argv)
site = args.site
node = args.node
sensor = args.sensor
method = args.method
stream = args.stream
deploy = args.deploy
start = args.start
stop = args.stop
burst = args.burst
# check if we are specifying a deployment or a specific date and time range
if not deploy or (start and stop):
return SyntaxError(
'You must specify either a deployment number or beginning and end dates of interest.'
)
# if we are specifying a deployment number, then get the data from the Gold Copy THREDDS server
if deploy:
# download the data for the deployment
flort = load_gc_thredds(site, node, sensor, method, stream,
('.*deployment%04d.*FLORT.*\\.nc$' % deploy))
# check to see if we downloaded any data
if not flort:
exit_text = (
'Data unavailable for %s-%s-%s, %s, %s, deployment %d.' %
(site, node, sensor, method, stream, deploy))
raise SystemExit(exit_text)
else:
# otherwise, request the data for download from OOINet via the M2M API using the specified dates
r = m2m_request(site, node, sensor, method, stream, start, stop)
if not r:
exit_text = (
'Request failed for %s-%s-%s, %s, %s, from %s to %s.' %
(site, node, sensor, method, stream, start, stop))
raise SystemExit(exit_text)
# Valid M2M request, start downloading the data
flort = m2m_collect(r, '.*FLORT.*\\.nc$')
# check to see if we downloaded any data
if not flort:
exit_text = (
'Data unavailable for %s-%s-%s, %s, %s, from %s to %s.' %
(site, node, sensor, method, stream, start, stop))
raise SystemExit(exit_text)
# clean-up and reorganize the data
if node == 'SP001':
# this FLORT is part of a CSPP
flort = flort_cspp(flort)
elif node == 'WFP01':
# this FLORT is part of a Wire-Following Profiler
flort = flort_wfp(flort)
elif node == 'SBD17':
# this FLORT is connected to the CTDBP on an EA Inshore Surface Mooring
flort = flort_instrument(flort)
if not flort:
# there was no data after removing all the 0's
sys.exit()
else:
# this FLORT is stand-alone on one of the moorings
flort = flort_datalogger(flort, burst)
vocab = get_vocabulary(site, node, sensor)[0]
flort = update_dataset(flort, vocab['maxdepth'])
# save the data to disk
out_file = os.path.abspath(args.outfile)
if not os.path.exists(os.path.dirname(out_file)):
os.makedirs(os.path.dirname(out_file))
flort.to_netcdf(out_file,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS)
def main(argv=None):
# setup the input arguments
args = inputs(argv)
site = args.site
node = args.node
sensor = args.sensor
method = args.method
stream = args.stream
deploy = args.deploy
start = args.start
stop = args.stop
burst = args.burst
# determine the start and stop times for the data request based on either the deployment number or user entered
# beginning and ending dates.
if not deploy or (start and stop):
return SyntaxError(
'You must specify either a deployment number or beginning and end dates of interest.'
)
else:
if deploy:
# Determine start and end dates based on the deployment number
start, stop = get_deployment_dates(site, node, sensor, deploy)
if not start or not stop:
exit_text = (
'Deployment dates are unavailable for %s-%s-%s, deployment %02d.'
% (site, node, sensor, deploy))
raise SystemExit(exit_text)
# Request the data for download
r = m2m_request(site, node, sensor, method, stream, start, stop)
if not r:
exit_text = ('Request failed for %s-%s-%s. Check request.' %
(site, node, sensor))
raise SystemExit(exit_text)
# Valid request, start downloading the data
if re.match(r'.*_air.*', stream):
if deploy:
pco2a = m2m_collect(
r, ('.*deployment%04d.*PCO2A.*air.*\\.nc$' % deploy))
else:
pco2a = m2m_collect(r, '.*PCO2A.*air.*\\.nc$')
nc_group = 'air'
else:
if deploy:
pco2a = m2m_collect(
r, ('.*deployment%04d.*PCO2A.*water.*\\.nc$' % deploy))
else:
pco2a = m2m_collect(r, '.*PCO2A.*water.*\\.nc$')
nc_group = 'water'
if not pco2a:
exit_text = ('Data unavailable for %s-%s-%s. Check request.' %
(site, node, sensor))
raise SystemExit(exit_text)
# clean-up and reorganize
pco2a = pco2a_datalogger(pco2a, burst)
vocab = get_vocabulary(site, node, sensor)[0]
pco2a = update_dataset(pco2a, vocab['maxdepth'])
# save the data to disk
out_file = os.path.abspath(args.outfile)
if not os.path.exists(os.path.dirname(out_file)):
os.makedirs(os.path.dirname(out_file))
if os.path.isfile(out_file):
pco2a.to_netcdf(out_file,
mode='a',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS,
group=nc_group)
else:
pco2a.to_netcdf(out_file,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS,
group=nc_group)
def main(argv=None):
# setup the input arguments
args = inputs(argv)
site = args.site
node = args.node
sensor = args.sensor
method = args.method
stream = args.stream
deploy = args.deploy
start = args.start
stop = args.stop
# check if we are specifying a deployment or a specific date and time range
if not deploy or (start and stop):
return SyntaxError(
'You must specify either a deployment number or beginning and end dates of interest.'
)
# if we are specifying a deployment number, then get the data from the Gold Copy THREDDS server
if deploy:
# download the data for the deployment
pco2w = load_gc_thredds(
site, node, sensor, method, stream,
('^(?!.*blank).*deployment%04d.*PCO2W.*\\.nc$' % deploy))
# check to see if we downloaded any data
if not pco2w:
exit_text = (
'Data unavailable for %s-%s-%s, %s, %s, deployment %d.' %
(site, node, sensor, method, stream, deploy))
raise SystemExit(exit_text)
else:
# otherwise, request the data for download from OOINet via the M2M API using the specified dates
r = m2m_request(site, node, sensor, method, stream, start, stop)
if not r:
exit_text = (
'Request failed for %s-%s-%s, %s, %s, from %s to %s.' %
(site, node, sensor, method, stream, start, stop))
raise SystemExit(exit_text)
# Valid M2M request, start downloading the data
pco2w = m2m_collect(r, '^(?!.*blank).*PCO2W.*\\.nc$')
# check to see if we downloaded any data
if not pco2w:
exit_text = (
'Data unavailable for %s-%s-%s, %s, %s, from %s to %s.' %
(site, node, sensor, method, stream, start, stop))
raise SystemExit(exit_text)
# clean-up and reorganize
if method in ['telemetered', 'recovered_host']:
pco2w = pco2w_datalogger(pco2w)
else:
pco2w = pco2w_instrument(pco2w)
vocab = get_vocabulary(site, node, sensor)[0]
pco2w = update_dataset(pco2w, vocab['maxdepth'])
# save the data to disk
out_file = os.path.abspath(args.outfile)
if not os.path.exists(os.path.dirname(out_file)):
os.makedirs(os.path.dirname(out_file))
pco2w.to_netcdf(out_file,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS)
def data_request(site, assembly, instrument, method, **kwargs):
"""
Requests data via the OOI M2M API using the site code, assembly type,
instrument class and data delivery method as defined in the m2m_urls.yml to
construct the OOI specific data request.
:param site: OOI site code as an 8 character string
:param assembly: The assembly type where the instrument is located
:param instrument: the OOI instrument class name for the instrument of
interest
:param method: The data delivery method for the system of interest
:param kwargs: Takes the following optional keyword arguments:
start: Starting date/time for the data request in a dateutil.parser
recognizable form. If ``None``, the default, the beginning of the
data record will be used
stop: Ending date/time for the data request in a dateutil.parser
recognizable form If ``None``, the default, the end of the data
record will be used
deploy: Use the deployment number, entered as an integer, to set the
starting and ending dates If ``None``, the default, the starting
and ending dates are used. If you enter both, the deployment number
will take priority in setting the start and end dates
aggregate: In cases where more than one instance of an instrument class
is part of an assembly, will collect all of the data if the integer
value entered is ``0``, or the specific instance of the instrument
is requested if any value greater than ``0`` is used. If ``None``,
the default, the first instance of an instrument will be used.
:return data: Returns the request data as an xarray dataset for further analysis
"""
# setup inputs to the function, make sure case is correct
site = site.upper()
assembly = assembly.lower()
instrument = instrument.lower()
method = method.lower()
# parse the keyword arguments
start = None
stop = None
deploy = None
aggregate = None
for key, value in kwargs.items():
if key not in ['start', 'stop', 'deploy', 'aggregate']:
raise KeyError('Unknown keyword (%s) argument.' % key)
else:
if key == 'start':
start = value
if key == 'stop':
stop = value
if key == 'deploy':
deploy = value
if key == 'aggregate':
aggregate = value
# use the assembly, instrument and data delivery methods to find the system of interest
node, sensor, stream = filter_urls(site, assembly, instrument, method)
# check the formatting of the start and end dates. We need to be able to parse and convert to an ISO format.
if start:
# check the formatting of the start date string and convert to the ISO format used by the M2M API
try:
start = parser.parse(start)
start = start.astimezone(pytz.utc)
start = start.strftime('%Y-%m-%dT%H:%M:%S.000Z')
except parser.ParserError:
raise SyntaxError('Formatting of the starting date string needs to be in a recognizable format')
if stop:
# check the formatting of the stop date string and convert to the ISO format used by the M2M API
try:
stop = parser.parse(stop)
stop = stop.astimezone(pytz.utc)
stop = stop.strftime('%Y-%m-%dT%H:%M:%S.000Z')
except parser.ParserError:
raise SyntaxError('Formatting of the ending date string needs to be in a recognizable format')
if deploy:
# Determine start and end dates based on the deployment number
start, stop = get_deployment_dates(site, node[0], sensor[0], deploy)
if not start or not stop:
exit_text = ('Deployment dates are unavailable for %s-%s-%s-%s, deployment %02d.' % (site.lower(), assembly,
instrument, method,
deploy))
raise RuntimeWarning(exit_text)
# for some cases, there maybe more than 1 stream, but in general, we only want the first one
if isinstance(stream[0], list):
stream = stream[0][0]
else:
stream = stream[0]
tag = ('.*{instrument}.*\\.nc$'.format(instrument=instrument.upper())) # set regex tag to use when downloading
data = None # setup the default data set
# check if there are multiple instances of this instrument class on the assembly
if len(node) > 1:
print('There are multiple instances of the instrument %s under %s-%s.' % (instrument, site.lower(), assembly))
# check if we are aggregating the multiple instruments into a single data set
if isinstance(aggregate, int):
if aggregate == 0:
# request all of the instruments associated with this site, assembly, instrument and method
print(('Requesting all %d instances of this instrument. Data sets will be concatenated\n'
'and a new variable called `sensor_count` will be added to help distinguish the \n'
'instruments for later processing.') % len(node))
for i in range(len(node)):
r = m2m_request(site, node[i], sensor[i], method, stream, start, stop)
if r:
temp = m2m_collect(r, tag)
temp['sensor_count'] = temp['deployment'] * 0 + i + 1
if not data:
data = temp
else:
data = xr.concat([data, temp], dim='time')
else:
# request a specific instrument of the multiple instruments associated with this site, assembly,
# instrument and method.
if aggregate > len(node):
raise SyntaxError('Only %d instruments available, you selected %d' % (len(node), aggregate))
print('Requesting instrument %d out of %d.' % (aggregate, len(node)))
i = aggregate - 1
r = m2m_request(site, node[i], sensor[i], method, stream, start, stop)
if r:
data = m2m_collect(r, tag)
else:
r = m2m_request(site, node[0], sensor[0], method, stream, start, stop)
if r:
data = m2m_collect(r, tag)
if not data:
raise RuntimeWarning('Data unavailable for %s-%s-%s-%s.' % (site.lower(), assembly, instrument, method))
# return the resulting data, which is an xarray.Dataset object
for v in data.variables:
# first convert strings with data types set as objects or S64 with binary encoding
if data[v].dtype == np.dtype('O') or data[v].dtype == np.dtype('S64'):
data[v] = data[v].astype(np.str)
return data
def main(argv=None):
args = inputs(argv)
site = args.site
node = args.node
sensor = args.sensor
method = args.method
stream = args.stream
deploy = args.deploy
start = args.start
stop = args.stop
burst = args.burst
# determine the start and stop times for the data request based on either the deployment number or user entered
# beginning and ending dates.
if not deploy or (start and stop):
return SyntaxError(
'You must specify either a deployment number or beginning and end dates of interest.'
)
else:
if deploy:
# Determine start and end dates based on the deployment number
start, stop = get_deployment_dates(site, node, sensor, deploy)
if not start or not stop:
exit_text = (
'Deployment dates are unavailable for %s-%s-%s, deployment %02d.'
% (site, node, sensor, deploy))
raise SystemExit(exit_text)
if stream not in ['suna_dcl_recovered']:
exit_text = (
'Currently the only stream supported is suna_dcl_recovered, you requested %s.'
% stream)
raise SystemExit(exit_text)
# Request the data for download
r = m2m_request(site, node, sensor, method, stream, start, stop)
if not r:
exit_text = ('Request failed for %s-%s-%s. Check request.' %
(site, node, sensor))
raise SystemExit(exit_text)
# Valid request, start downloading the data
if deploy:
nutnr = m2m_collect(r, ('.*deployment%04d.*NUTNR.*\\.nc$' % deploy))
else:
nutnr = m2m_collect(r, '.*NUTNR.*\\.nc$')
if not nutnr:
exit_text = ('Data unavailable for %s-%s-%s. Check request.' %
(site, node, sensor))
raise SystemExit(exit_text)
# clean-up and reorganize
nutnr = nutnr_datalogger(nutnr, burst)
vocab = get_vocabulary(site, node, sensor)[0]
nutnr = update_dataset(nutnr, vocab['maxdepth'])
# save the data to disk
out_file = os.path.abspath(args.outfile)
if not os.path.exists(os.path.dirname(out_file)):
os.makedirs(os.path.dirname(out_file))
nutnr.to_netcdf(out_file,
mode='w',
format='NETCDF4',
engine='h5netcdf',
encoding=ENCODINGS)
