def add_instrument_variable(self, variable_name):
if variable_name not in self._nc.variables:
logger.error("Variable {} not found in file, cannot create instrument metadata variable")
return
elif 'id' not in self._nc.ncattrs() or 'naming_authority' not in self._nc.ncattrs():
logger.error("Global attributes 'id' and 'naming_authority' are required to create an instrument variable")
return
instr_var_name = "{}_instrument".format(variable_name)
instrument = self._nc.createVariable(instr_var_name, "i4")
datavar = self._nc.variables[variable_name]
vats = { k: getattr(datavar, k) for k in datavar.ncattrs() }
instrument_urn = urnify(self._nc.naming_authority, self._nc.id, vats)
inst_urn = IoosUrn.from_string(instrument_urn)
instrument.long_name = 'Instrument measuring {} from {}'.format(inst_urn.component, inst_urn.label)
instrument.ioos_code = instrument_urn
instrument.short_name = inst_urn.component
instrument.definition = "http://mmisw.org/ont/ioos/definition/sensorID"
datavar.instrument = instr_var_name
# Append the instrument to the ancilary variables
av = getattr(datavar, 'ancillary_variables', '')
av += ' {}'.format(instr_var_name)
datavar.ancillary_variables = av.strip()
self._nc.sync()
def bins(self, delta, starting, hard_start=None, hard_end=None):
ending = starting + delta
windows = []
member_length = len(self.aggregation.members)
last_member = self.aggregation.members[-1]
index = 0
if hard_start is None:
hard_start = starting
if hard_end is None:
hard_end = last_member.ending
# Loop until we process the last member of the aggregation
while last_member.ending >= starting:
# Window for this timedelta
member = None
window = DotDict(starting=starting, ending=ending, members=[])
for x in range(index, member_length):
member = self.aggregation.members[x]
if member.starting >= starting and member.ending < ending:
if member.starting >= hard_start and member.ending <= hard_end:
# The simplest case... completely part of this aggregation
# and within the specified 'hard' bounds
window.members.append(member)
index += 1
elif member.starting >= ending:
# This member is outside of the current window and we need to make
# new window(s) until it fits into one.
break
elif (member.starting >= starting and member.ending >= ending) or (
member.starting < starting and member.ending < ending
):
# This member overlaps where the cutoff would be. This is
# NOT supported at the moment
logger.error(
"Skipping {0}. Members that overlap a bin boundary are not supported at this time.".format(
member.path
)
)
index += 1
# Move the time window by the delta
if len(window.members) > 1:
windows.append(window)
starting = ending
ending = ending + delta
return windows
def bins(self, delta, starting, hard_start=None, hard_end=None):
ending = starting + delta
windows = []
member_length = len(self.aggregation.members)
last_member = self.aggregation.members[-1]
index = 0
if hard_start is None:
hard_start = starting
if hard_end is None:
hard_end = last_member.ending
# Loop until we process the last member of the aggregation
while last_member.ending >= starting:
# Window for this timedelta
member = None
window = DotDict(starting=starting, ending=ending, members=[])
for x in range(index, member_length):
member = self.aggregation.members[x]
if member.starting >= starting and member.ending < ending:
if member.starting >= hard_start and member.ending <= hard_end:
# The simplest case... completely part of this aggregation
# and within the specified 'hard' bounds
window.members.append(member)
index += 1
elif member.starting >= ending:
# This member is outside of the current window and we need to make
# new window(s) until it fits into one.
break
elif (member.starting >= starting and member.ending >= ending) or \
(member.starting < starting and member.ending < ending):
# This member overlaps where the cutoff would be. This is
# NOT supported at the moment
logger.error("Skipping {0}. Members that overlap a bin boundary are not supported at this time.".format(member.path))
index += 1
# Move the time window by the delta
if len(window.members) > 1:
windows.append(window)
starting = ending
ending = ending + delta
return windows
def valid(self):
ASSET_TYPES = ['station', 'network', 'sensor', 'survey']
try:
assert self.authority is not None
except AssertionError:
logger.error('An "authority" is required')
return False
try:
assert self.label is not None
except AssertionError:
logger.error('A "label" is required')
return False
try:
assert self.asset_type in ASSET_TYPES
except AssertionError:
logger.error(
'asset_type {0} is unknown. Must be one of: {1}'.format(
self.asset_type, ', '.join(ASSET_TYPES)))
return False
if self.asset_type == 'station':
try:
assert self.component is None
except AssertionError:
logger.error(
'An asset_type of "station" may not have a "component".')
return False
return True
def valid(self):
ASSET_TYPES = ['station', 'network', 'sensor', 'survey']
try:
assert self.authority is not None
except AssertionError:
logger.error('An "authority" is required')
return False
try:
assert self.label is not None
except AssertionError:
logger.error('A "label" is required')
return False
try:
assert self.asset_type in ASSET_TYPES
except AssertionError:
logger.error('asset_type {0} is unknown. Must be one of: {1}'.format(self.asset_type, ', '.join(ASSET_TYPES)))
return False
if self.asset_type == 'station':
try:
assert self.component is None
except AssertionError:
logger.error('An asset_type of "station" may not have a "component".')
return False
return True
def from_directory(cls, directory, suffix=".nc", subdirs=True, dimName='time', apply_to_members=None):
if not os.path.isdir(directory):
logger.error("Directory {0} does not exists or I do not have the correct permissions to access".format(directory))
# Create NcML pointing to the directory
ncml = """<?xml version="1.0" encoding="UTF-8"?>
<netcdf xmlns="http://www.unidata.ucar.edu/namespaces/netcdf/ncml-2.2">
<aggregation dimName="{0}" type="joinExisting">
<scan location="{1}" suffix="{2}" subdirs="{3}" />
</aggregation>
</netcdf>
""".format(dimName, directory, suffix, subdirs)
try:
return cls(pyncml.scan(ncml, apply_to_members=apply_to_members))
except BaseException:
logger.exception("Could not load Collection from Directory.")
def from_directory(cls, directory, suffix=".nc", subdirs=True, dimName='time', apply_to_members=None):
if not os.path.isdir(directory):
logger.error("Directory {0} does not exists or I do not have the correct permissions to access".format(directory))
# Create NcML pointing to the directory
ncml = """<?xml version="1.0" encoding="UTF-8"?>
<netcdf xmlns="http://www.unidata.ucar.edu/namespaces/netcdf/ncml-2.2">
<aggregation dimName="{0}" type="joinExisting">
<scan location="{1}" suffix="{2}" subdirs="{3}" />
</aggregation>
</netcdf>
""".format(dimName, directory, suffix, subdirs)
try:
return cls(pyncml.scan(ncml, apply_to_members=apply_to_members))
except BaseException:
logger.exception("Could not load Collection from Directory.")
def from_glob(cls, glob_string, timevar_name='time', ncml=None):
dataset_name = None
dataset_starting = None
dataset_ending = None
dataset_variables = []
dataset_members = []
files = glob(glob_string)
logger.info("Processing aggregation containing {!s} files".format(len(files)))
for i, filepath in enumerate(files):
logger.info("Processing member ({0}/{1}) - {2} ".format(i+1, len(files), filepath))
nc = None
try:
if ncml is not None:
# Apply NcML
tmp_f, tmp_fp = tempfile.mkstemp(prefix="nc")
os.close(tmp_f)
nc = pyncml.apply(filepath, ncml, output_file=tmp_fp)
else:
nc = netCDF4.Dataset(filepath)
if dataset_name is None:
if hasattr(nc, 'name'):
dataset_name = nc.name
elif hasattr(nc, 'title'):
dataset_name = nc.title
else:
dataset_name = "Pyaxiom Glob Dataset"
timevar = nc.variables.get(timevar_name)
if timevar is None:
logger.error("Time variable '{0}' was not found in file '{1}'. Skipping.".format(timevar_name, filepath))
continue
# Start/Stop of NetCDF file
starting = netCDF4.num2date(np.min(timevar[:]), units=timevar.units)
ending = netCDF4.num2date(np.max(timevar[:]), units=timevar.units)
variables = filter(None, [ nc.variables[v].standard_name if hasattr(nc.variables[v], 'standard_name') else None for v in nc.variables.keys() ])
dataset_variables = list(set(dataset_variables + variables))
if starting.tzinfo is None:
starting = starting.replace(tzinfo=pytz.utc)
if ending.tzinfo is None:
ending = ending.replace(tzinfo=pytz.utc)
if dataset_starting is None or starting < dataset_starting:
dataset_starting = starting
if dataset_ending is None or ending > dataset_ending:
dataset_ending = ending
member = DotDict(path=filepath, standard_names=variables, starting=starting, ending=ending)
dataset_members.append(member)
except BaseException:
logger.exception("Something went wrong with {0}".format(filepath))
continue
finally:
nc.close()
try:
os.remove(tmp_fp)
except (OSError, UnboundLocalError):
pass
dataset_members = sorted(dataset_members, key=operator.attrgetter('starting'))
return cls(DotDict(name=dataset_name,
timevar_name=timevar_name,
starting=dataset_starting,
ending=dataset_ending,
standard_names=dataset_variables,
members=dataset_members))
def dictify_urn(urn, combine_interval=True):
"""
By default, this will put the `interval` as part of the `cell_methods`
attribute (NetCDF CF style). To return `interval` as its own key, use
the `combine_interval=False` parameter.
"""
ioos_urn = IoosUrn.from_string(urn)
if ioos_urn.valid() is False:
return dict()
if ioos_urn.asset_type != 'sensor':
logger.error("This function only works on 'sensor' URNs.")
return dict()
if '#' in ioos_urn.component:
standard_name, extras = ioos_urn.component.split('#')
else:
standard_name = ioos_urn.component
extras = ''
d = dict(standard_name=standard_name)
# Discriminant
if '-' in ioos_urn.component:
d['discriminant'] = ioos_urn.component.split('-')[-1]
d['standard_name'] = ioos_urn.component.split('-')[0]
intervals = []
cell_methods = []
if extras:
for section in extras.split(';'):
key, values = section.split('=')
if key == 'interval':
# special case, intervals should be appended to the cell_methods
for v in values.split(','):
intervals.append(v)
else:
if key == 'cell_methods':
value = [ x.replace('_', ' ').replace(':', ': ') for x in values.split(',') ]
cell_methods = value
else:
value = ' '.join([x.replace('_', ' ').replace(':', ': ') for x in values.split(',')])
d[key] = value
if combine_interval is True:
if cell_methods and intervals:
if len(cell_methods) == len(intervals):
d['cell_methods'] = ' '.join([ '{} (interval: {})'.format(x[0], x[1].upper()) for x in zip(cell_methods, intervals) ])
else:
d['cell_methods'] = ' '.join(cell_methods)
for i in intervals:
d['cell_methods'] += ' (interval: {})'.format(i.upper())
elif cell_methods:
d['cell_methods'] = ' '.join(cell_methods)
for i in intervals:
d['cell_methods'] += ' (interval: {})'.format(i.upper())
elif intervals:
raise ValueError("An interval without a cell_method is not allowed! Not possible!")
else:
d['cell_methods'] = ' '.join(cell_methods)
d['interval'] = ','.join(intervals).upper()
if 'vertical_datum' in d:
d['vertical_datum'] = d['vertical_datum'].upper()
return d
def dictify_urn(urn, combine_interval=True):
"""
By default, this will put the `interval` as part of the `cell_methods`
attribute (NetCDF CF style). To return `interval` as its own key, use
the `combine_interval=False` parameter.
"""
ioos_urn = IoosUrn.from_string(urn)
if ioos_urn.valid() is False:
return dict()
if ioos_urn.asset_type != 'sensor':
logger.error("This function only works on 'sensor' URNs.")
return dict()
if '#' in ioos_urn.component:
standard_name, extras = ioos_urn.component.split('#')
else:
standard_name = ioos_urn.component
extras = ''
d = dict(standard_name=standard_name)
# Discriminant
if '-' in ioos_urn.component:
d['discriminant'] = standard_name.split('-')[-1]
d['standard_name'] = standard_name.split('-')[0]
intervals = []
cell_methods = []
if extras:
for section in extras.split(';'):
key, values = section.split('=')
if key == 'interval':
# special case, intervals should be appended to the cell_methods
for v in values.split(','):
intervals.append(v)
else:
if key == 'cell_methods':
value = [ x.replace('_', ' ').replace(':', ': ') for x in values.split(',') ]
cell_methods = value
else:
value = ' '.join([x.replace('_', ' ').replace(':', ': ') for x in values.split(',')])
d[key] = value
if combine_interval is True:
if cell_methods and intervals:
if len(cell_methods) == len(intervals):
d['cell_methods'] = ' '.join([ '{} (interval: {})'.format(x[0], x[1].upper()) for x in zip(cell_methods, intervals) ])
else:
d['cell_methods'] = ' '.join(cell_methods)
for i in intervals:
d['cell_methods'] += ' (interval: {})'.format(i.upper())
elif cell_methods:
d['cell_methods'] = ' '.join(cell_methods)
for i in intervals:
d['cell_methods'] += ' (interval: {})'.format(i.upper())
elif intervals:
raise ValueError("An interval without a cell_method is not allowed! Not possible!")
else:
d['cell_methods'] = ' '.join(cell_methods)
d['interval'] = ','.join(intervals).upper()
if 'vertical_datum' in d:
d['vertical_datum'] = d['vertical_datum'].upper()
return d
def from_glob(cls, glob_string, timevar_name='time', ncml=None):
dataset_name = None
dataset_starting = None
dataset_ending = None
dataset_variables = []
dataset_members = []
files = glob(glob_string)
logger.info("Processing aggregation containing {!s} files".format(len(files)))
for i, filepath in enumerate(files):
logger.info("Processing member ({0}/{1}) - {2} ".format(i+1, len(files), filepath))
nc = None
try:
if ncml is not None:
# Apply NcML
tmp_f, tmp_fp = tempfile.mkstemp(prefix="nc")
os.close(tmp_f)
nc = pyncml.apply(filepath, ncml, output_file=tmp_fp)
else:
nc = netCDF4.Dataset(filepath)
if dataset_name is None:
if 'name' in nc.ncattrs():
dataset_name = nc.name
elif 'title' in nc.ncattrs():
dataset_name = nc.title
else:
dataset_name = "Pyaxiom Glob Dataset"
timevar = nc.variables.get(timevar_name)
if timevar is None:
logger.error("Time variable '{0}' was not found in file '{1}'. Skipping.".format(timevar_name, filepath))
continue
# Start/Stop of NetCDF file
starting = netCDF4.num2date(np.min(timevar[:]), units=timevar.units)
ending = netCDF4.num2date(np.max(timevar[:]), units=timevar.units)
variables = list([_f for _f in [ nc.variables[v].standard_name if hasattr(nc.variables[v], 'standard_name') else None for v in list(nc.variables.keys()) ] if _f])
dataset_variables = list(set(dataset_variables + variables))
if starting.tzinfo is None:
starting = starting.replace(tzinfo=pytz.utc)
if ending.tzinfo is None:
ending = ending.replace(tzinfo=pytz.utc)
if dataset_starting is None or starting < dataset_starting:
dataset_starting = starting
if dataset_ending is None or ending > dataset_ending:
dataset_ending = ending
member = DotDict(path=filepath, standard_names=variables, starting=starting, ending=ending)
dataset_members.append(member)
except BaseException:
logger.exception("Something went wrong with {0}".format(filepath))
continue
finally:
nc.close()
try:
os.remove(tmp_fp)
except (OSError, UnboundLocalError):
pass
dataset_members = sorted(dataset_members, key=operator.attrgetter('starting'))
return cls(DotDict(name=dataset_name,
timevar_name=timevar_name,
starting=dataset_starting,
ending=dataset_ending,
standard_names=dataset_variables,
members=dataset_members))
