def json_attributes(self, vfuncs=None):
"""
vfuncs can be any callable that accepts a single argument, the
Variable object, and returns a dictionary of new attributes to
set. These will overwrite existing attributes
"""
vfuncs = vfuncs or []
js = {'global': {}}
for k in self.ncattrs():
js['global'][k] = self.getncattr(k)
for varname, var in self.variables.items():
js[varname] = {}
for k in var.ncattrs():
z = var.getncattr(k)
try:
assert not np.isnan(z).all()
js[varname][k] = z
except AssertionError:
js[varname][k] = None
except TypeError:
js[varname][k] = z
for vf in vfuncs:
try:
js[varname].update(vfuncs(var))
except BaseException:
logger.exception(
"Could not apply custom variable attribue function")
return json.loads(json.dumps(js, cls=BasicNumpyEncoder))
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 to_dataframe(self, clean_cols=True, clean_rows=True):
# Z
zvar = self.z_axes()[0]
z = np.ma.fix_invalid(np.ma.MaskedArray(zvar[:]))
z = z.flatten().round(5)
logger.debug(['z data size: ', z.size])
# T
tvar = self.t_axes()[0]
t = np.ma.MaskedArray(nc4.num2date(tvar[:], tvar.units, getattr(tvar, 'calendar', 'standard'))).flatten()
# Patch the time variable back to its original mask, since num2date
# breaks any missing/fill values
if hasattr(tvar[0], 'mask'):
t.mask = tvar[:].mask
logger.debug(['time data size: ', t.size])
# X
xvar = self.x_axes()[0]
x = np.ma.fix_invalid(np.ma.MaskedArray(xvar[:])).flatten().round(5)
logger.debug(['x data size: ', x.size])
# Y
yvar = self.y_axes()[0]
y = np.ma.fix_invalid(np.ma.MaskedArray(yvar[:])).flatten().round(5)
logger.debug(['y data size: ', y.size])
# Trajectories
pvar = self.get_variables_by_attributes(cf_role='trajectory_id')[0]
try:
p = normalize_array(pvar)
except BaseException:
logger.exception('Could not pull trajectory values from the variable, using indexes.')
p = np.asarray(list(range(len(pvar))), dtype=np.integer)
# The Dimension that the trajectory id variable doesn't have is what
# the trajectory data needs to be repeated by
dim_diff = self.dimensions[list(set(tvar.dimensions).difference(set(pvar.dimensions)))[0]]
if dim_diff:
p = p.repeat(dim_diff.size)
logger.debug(['trajectory data size: ', p.size])
# Distance
d = np.append([0], great_distance(start_latitude=y[0:-1], end_latitude=y[1:], start_longitude=x[0:-1], end_longitude=x[1:])['distance'])
d = np.ma.fix_invalid(np.ma.MaskedArray(np.cumsum(d)).astype(np.float64).round(2))
logger.debug(['distance data size: ', d.size])
df_data = {
't': t,
'x': x,
'y': y,
'z': z,
'trajectory': p,
'distance': d
}
building_index_to_drop = np.ones(t.size, dtype=bool)
extract_vars = list(set(self.data_vars() + self.ancillary_vars()))
for i, dvar in enumerate(extract_vars):
vdata = np.ma.fix_invalid(np.ma.MaskedArray(dvar[:].round(3).flatten()))
building_index_to_drop = (building_index_to_drop == True) & (vdata.mask == True) # noqa
df_data[dvar.name] = vdata
df = pd.DataFrame(df_data)
# Drop all data columns with no data
if clean_cols:
df = df.dropna(axis=1, how='all')
# Drop all data rows with no data variable data
if clean_rows:
df = df.iloc[~building_index_to_drop]
return df
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 from_ncml_file(cls, ncml_path, apply_to_members=None):
try:
with open(ncml_path) as f:
return cls(pyncml.scan(f.read(), apply_to_members=apply_to_members))
except BaseException:
logger.exception("Could not load Collection from NcML. Please check the NcML.")
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))
def from_ncml_file(cls, ncml_path, apply_to_members=None):
try:
with open(ncml_path) as f:
return cls(pyncml.scan(f.read(), apply_to_members=apply_to_members))
except BaseException:
logger.exception("Could not load Collection from NcML. Please check the NcML.")
def add_variable(self, variable_name, values, times=None, verticals=None, sensor_vertical_datum=None, attributes=None, unlink_from_profile=None, fillvalue=None, raise_on_error=False):
if isinstance(values, (list, tuple,)) and values:
values = np.asarray(values)
if isinstance(times, (list, tuple,)) and times:
times = np.asarray(times)
if isinstance(verticals, (list, tuple,)) and verticals:
verticals = np.asarray(verticals)
# Set vertical datum on the CRS variable
if sensor_vertical_datum is not None:
try:
self.crs.geoid_name = sensor_vertical_datum
self.crs.vertical_datum = sensor_vertical_datum
self.crs.water_surface_reference_datum = sensor_vertical_datum
except AttributeError:
pass
# Set default fillvalue for new variables
if fillvalue is None:
fillvalue = -9999.9
used_values = None
try:
if unlink_from_profile is True:
used_values = np.ma.reshape(values, (self.time.size, ))
used_values = used_values[self.time_indexes]
# These next two cases should work for all but a few cases, which are caught below
elif self.z.size == 1:
used_values = np.ma.reshape(values, (self.time.size, ))
used_values = used_values[self.time_indexes]
else:
used_values = np.ma.reshape(values, (self.time.size, self.z.size, ))
used_values = used_values[self.time_indexes]
try:
used_values = used_values[:, self.vertical_indexes]
except IndexError:
# The vertical values most likely had duplicates. Ignore the
# falty index here and try to save the values as is.
pass
except ValueError:
if raise_on_error is True:
self.close()
raise
else:
logger.exception("Could not do a simple reshape of data, trying to match manually! Time:{!s}, Heights:{!s}, Values:{!s}".format(self.time.size, self.z.size, values.size))
if self.z.size > 1:
if times is not None and verticals is not None:
# Hmmm, we have two actual height values for this station.
# Not cool man, not cool.
# Reindex the entire values array. This is slow.
indexed = ((bisect.bisect_left(self.time[:], times[i]), bisect.bisect_left(self.z[:], verticals[i]), values[i]) for i in xrange(values.size))
used_values = np.ndarray((self.time.size, self.z.size, ), dtype=np.float64)
used_values.fill(float(fillvalue))
for (tzi, zzi, vz) in indexed:
if zzi < self.z.size and tzi < self.time.size:
used_values[tzi, zzi] = vz
else:
self.close()
raise ValueError("You need to pass in both 'times' and 'verticals' parameters that matches the size of the 'values' parameter.")
else:
if times is not None:
# Ugh, find the time indexes manually
indexed = ((bisect.bisect_left(self.time[:], times[i]), values[i]) for i in xrange(values.size))
used_values = np.ndarray((self.time.size, ), dtype=np.float64)
used_values.fill(float(fillvalue))
for (tzi, vz) in indexed:
if tzi < self.time.size:
used_values[tzi] = vz
else:
self.close()
raise ValueError("You need to pass in a 'times' parameter that matches the size of the 'values' parameter.")
logger.info("Setting values for {}...".format(variable_name))
if len(used_values.shape) == 1:
var = self.nc.createVariable(variable_name, "f8", ("time",), fill_value=fillvalue, chunksizes=(1000,), zlib=True)
if self.z.size == 1:
var.coordinates = "{} {} latitude longitude".format(self.time_axis_name, self.vertical_axis_name)
else:
# This is probably a bottom sensor on an ADCP or something, don't add the height coordinate
var.coordinates = "time latitude longitude"
if unlink_from_profile is True:
# Create metadata variable for the sensor_depth
if self.nc.variables.get('sensor_depth') is None:
logger.info("Setting the special case 'sensor_depth' metadata variable")
inst_depth = self.nc.createVariable('sensor_depth', 'f4')
inst_depth.units = 'm'
inst_depth.standard_name = 'surface_altitude'
inst_depth.long_name = 'sensor depth below datum'
inst_depth.positive = self.vertical_positive
inst_depth.datum = sensor_vertical_datum or 'Unknown'
inst_depth[:] = verticals[0] * -1
elif len(used_values.shape) == 2:
var = self.nc.createVariable(variable_name, "f8", ("time", "z",), fill_value=fillvalue, chunksizes=(1000, self.z.size,), zlib=True)
var.coordinates = "{} {} latitude longitude".format(self.time_axis_name, self.vertical_axis_name)
else:
raise ValueError("Could not create variable. Shape of data is {!s}. Expected a dimension of 1 or 2, not {!s}.".format(used_values.shape, len(used_values.shape)))
# Set the variable attributes as passed in
if attributes:
for k, v in attributes.iteritems():
if k == 'vertical_datum' and sensor_vertical_datum is None and v is not None:
# Use this as the vertical datum if it is specified and we didn't already have one
try:
self.crs.geoid_name = v
self.crs.vertical_datum = v
self.crs.water_surface_reference_datum = v
except AttributeError:
pass
if k != '_FillValue' and v is not None:
try:
setattr(var, k, v)
except BaseException:
logger.info('Could not add attribute {}: {}, skipping.'.format(k, v))
var.grid_mapping = 'crs'
var[:] = used_values
return var
