def from_dataframe(cls, df, output, **kwargs):
axes = get_default_axes(kwargs.pop('axes', {}))
daxes = axes
_ = kwargs.pop('reduce_dims', False)
_ = kwargs.pop('unlimited', False)
unique_dims = kwargs.pop('unique_dims', False)
if unique_dims is True:
# Rename the dimension to avoid a dimension and coordinate having the same name
# which is not support in xarray
changed_axes = {
k: '{}_dim'.format(v)
for k, v in axes._asdict().items()
}
daxes = get_default_axes(changed_axes)
# Downcast anything from int64 to int32
# Convert any timezone aware datetimes to native UTC times
df = downcast_dataframe(nativize_times(df))
with ContiguousRaggedTrajectoryProfile(output, 'w') as nc:
trajectory_groups = df.groupby(axes.trajectory)
unique_trajectories = list(trajectory_groups.groups.keys())
num_trajectories = len(unique_trajectories)
nc.createDimension(daxes.trajectory, num_trajectories)
trajectory = nc.createVariable(axes.trajectory,
get_dtype(df[axes.trajectory]),
(daxes.trajectory, ))
trajectory[:] = np.array(unique_trajectories)
# Calculate the max number of profiles
unique_profiles = df[axes.profile].unique()
num_profiles = len(unique_profiles)
nc.createDimension(daxes.profile, num_profiles)
profile = nc.createVariable(axes.profile,
get_dtype(df[axes.profile]),
(daxes.profile, ))
profile[:] = np.array(unique_profiles)
# Get unique obs by grouping on traj and profile and getting the max size
num_obs = len(df)
nc.createDimension(daxes.sample, num_obs)
# The trajectory this profile belongs to
t_ind = nc.createVariable('trajectoryIndex', 'i4',
(daxes.profile, ))
# Number of observations in each profile
row_size = nc.createVariable('rowSize', 'i4', (daxes.profile, ))
# Create all of the axis variables
time = nc.createVariable(axes.t,
'f8', (daxes.profile, ),
fill_value=np.dtype('f8').type(
cls.default_fill_value))
latitude = nc.createVariable(
axes.y,
get_dtype(df[axes.y]), (daxes.profile, ),
fill_value=df[axes.y].dtype.type(cls.default_fill_value))
longitude = nc.createVariable(
axes.x,
get_dtype(df[axes.x]), (daxes.profile, ),
fill_value=df[axes.x].dtype.type(cls.default_fill_value))
# Axes variables are already processed so skip them
data_columns = [d for d in df.columns if d not in axes]
attributes = dict_update(nc.nc_attributes(axes, daxes),
kwargs.pop('attributes', {}))
# Variables defined on only the profile axis
profile_vars = kwargs.pop('profile_vars', [])
profile_columns = [p for p in profile_vars if p in data_columns]
for c in profile_columns:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
create_ncvar_from_series(nc,
var_name, (daxes.profile, ),
df[c],
zlib=True,
complevel=1)
for i, (_, trg) in enumerate(trajectory_groups):
for j, (_, pfg) in enumerate(trg.groupby(axes.profile)):
time[j] = get_ncdata_from_series(pfg[axes.t],
time).astype('f8')[0]
latitude[j] = get_ncdata_from_series(
pfg[axes.y], latitude)[0]
longitude[j] = get_ncdata_from_series(
pfg[axes.x], longitude)[0]
row_size[j] = len(pfg)
t_ind[j] = i
# Save any profile variables on the "profile" index using the first value found
# in the column.
for c in profile_columns:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
continue
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(pfg[c], v)[0]
try:
v[j] = vvalues
except BaseException:
L.exception('Failed to add {}'.format(c))
continue
# Add back in the z axes that was removed when calculating data_columns
# and ignore variables that were stored in the profile index
sample_columns = [
f for f in data_columns + [axes.z] if f not in profile_columns
]
skips = ['trajectoryIndex', 'rowSize']
for c in [d for d in sample_columns if d not in skips]:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(nc,
var_name, (daxes.sample, ),
df[c],
zlib=True,
complevel=1)
else:
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(df[c], v)
try:
v[:] = vvalues.reshape(v.shape)
except BaseException:
L.exception('Failed to add {}'.format(c))
continue
# Metadata variables
if 'crs' not in nc.variables:
nc.createVariable('crs', 'i4')
# Set attributes
nc.update_attributes(attributes)
return ContiguousRaggedTrajectoryProfile(output, **kwargs)
def from_dataframe(cls, df, output, **kwargs):
axes = get_default_axes(kwargs.pop('axes', {}))
data_columns = [d for d in df.columns if d not in axes]
reduce_dims = kwargs.pop('reduce_dims', False)
unlimited = kwargs.pop('unlimited', False)
# Downcast anything from int64 to int32
df = downcast_dataframe(df)
# Make a new index that is the Cartesian product of all of the values from all of the
# values of the old index. This is so don't have to iterate over anything. The full column
# of data will be able to be shaped to the size of the final unique sized dimensions.
index_order = [axes.t, axes.z, axes.station]
df = df.set_index(index_order)
df = df.reindex(
pd.MultiIndex.from_product(df.index.levels, names=index_order))
unique_z = df.index.get_level_values(axes.z).unique().values
unique_t = df.index.get_level_values(
axes.t).unique().tolist() # tolist converts to Timestamp
all_stations = df.index.get_level_values(axes.station)
unique_s = all_stations.unique()
with OrthogonalMultidimensionalTimeseriesProfile(output, 'w') as nc:
if reduce_dims is True and unique_s.size == 1:
# If a singlular trajectory, we can reduce that dimension if it is of size 1
def ts():
return np.s_[:, :]
default_dimensions = (axes.t, axes.z)
station_dimensions = ()
else:
def ts():
return np.s_[:, :, :]
default_dimensions = (axes.t, axes.z, axes.station)
station_dimensions = (axes.station, )
nc.createDimension(axes.station, unique_s.size)
station = nc.createVariable(axes.station, get_dtype(unique_s),
station_dimensions)
latitude = nc.createVariable(axes.y, get_dtype(df[axes.y]),
station_dimensions)
longitude = nc.createVariable(axes.x, get_dtype(df[axes.x]),
station_dimensions)
# Assign over loop because VLEN variables (strings) have to be assigned by integer index
# and we need to find the lat/lon based on station index
for si, st in enumerate(unique_s):
station[si] = st
latitude[si] = df[axes.y][all_stations == st].dropna().iloc[0]
longitude[si] = df[axes.x][all_stations == st].dropna().iloc[0]
# Metadata variables
nc.createVariable('crs', 'i4')
# Create all of the variables
if unlimited is True:
nc.createDimension(axes.t, None)
else:
nc.createDimension(axes.t, len(unique_t))
time = nc.createVariable(axes.t, 'f8', (axes.t, ))
time[:] = nc4.date2num(unique_t, units=cls.default_time_unit)
nc.createDimension(axes.z, unique_z.size)
z = nc.createVariable(axes.z, get_dtype(unique_z), (axes.z, ))
z[:] = unique_z
attributes = dict_update(nc.nc_attributes(axes),
kwargs.pop('attributes', {}))
for c in data_columns:
# Create variable if it doesn't exist
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(nc,
var_name,
default_dimensions,
df[c],
zlib=True,
complevel=1)
attributes[var_name] = dict_update(
attributes.get(var_name, {}), {
'coordinates':
'{} {} {} {}'.format(axes.t, axes.z, axes.x,
axes.y)
})
else:
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(df[c], v)
v[ts()] = vvalues.reshape(len(unique_t), unique_z.size,
unique_s.size)
nc.update_attributes(attributes)
return OrthogonalMultidimensionalTimeseriesProfile(output, **kwargs)
def from_dataframe(cls, df, output, **kwargs):
axes = get_default_axes(kwargs.pop('axes', {}))
daxes = axes
data_columns = [d for d in df.columns if d not in axes]
unlimited = kwargs.pop('unlimited', False)
unique_dims = kwargs.pop('unique_dims', False)
if unique_dims is True:
# Rename the dimension to avoid a dimension and coordinate having the same name
# which is not support in xarray
changed_axes = {
k: '{}_dim'.format(v)
for k, v in axes._asdict().items()
}
daxes = get_default_axes(changed_axes)
# Downcast anything from int64 to int32
# Convert any timezone aware datetimes to native UTC times
df = downcast_dataframe(nativize_times(df))
with IncompleteMultidimensionalProfile(output, 'w') as nc:
profile_group = df.groupby(axes.profile)
if unlimited is True:
max_profiles = None
else:
max_profiles = df[axes.profile].unique().size
nc.createDimension(daxes.profile, max_profiles)
max_zs = profile_group.size().max()
nc.createDimension(daxes.z, max_zs)
# Metadata variables
nc.createVariable('crs', 'i4')
profile = nc.createVariable(axes.profile,
get_dtype(df[axes.profile]),
(daxes.profile, ))
# Create all of the variables
time = nc.createVariable(axes.t, 'f8', (daxes.profile, ))
latitude = nc.createVariable(axes.y, get_dtype(df[axes.y]),
(daxes.profile, ))
longitude = nc.createVariable(axes.x, get_dtype(df[axes.x]),
(daxes.profile, ))
z = nc.createVariable(
axes.z,
get_dtype(df[axes.z]), (daxes.profile, daxes.z),
fill_value=df[axes.z].dtype.type(cls.default_fill_value))
attributes = dict_update(nc.nc_attributes(axes, daxes),
kwargs.pop('attributes', {}))
# Create vars based on full dataframe (to get all variables)
for c in data_columns:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(nc,
var_name,
(daxes.profile, daxes.z),
df[c],
zlib=True,
complevel=1)
attributes[var_name] = dict_update(
attributes.get(var_name, {}), {
'coordinates':
'{} {} {} {}'.format(axes.t, axes.z, axes.x,
axes.y)
})
# Write values for each profile within profile_group
for i, (uid, pdf) in enumerate(profile_group):
profile[i] = uid
time[i] = date2num(pdf[axes.t].iloc[0],
units=cls.default_time_unit)
latitude[i] = pdf[axes.y].iloc[0]
longitude[i] = pdf[axes.x].iloc[0]
zvalues = pdf[axes.z].fillna(z._FillValue).values
sl = slice(0, zvalues.size)
z[i, sl] = zvalues
for c in data_columns:
var_name = cf_safe_name(c)
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(pdf[c], v)
sl = slice(0, vvalues.size)
v[i, sl] = vvalues
# Set global attributes
nc.update_attributes(attributes)
return IncompleteMultidimensionalProfile(output, **kwargs)
def from_dataframe(cls, df, output, **kwargs):
axes = get_default_axes(kwargs.pop('axes', {}))
daxes = axes
reduce_dims = kwargs.pop('reduce_dims', False)
unlimited = kwargs.pop('unlimited', False)
unique_dims = kwargs.pop('unique_dims', False)
if unique_dims is True:
# Rename the dimension to avoid a dimension and coordinate having the same name
# which is not supported in xarray
changed_axes = { k: '{}_dim'.format(v) for k, v in axes._asdict().items() }
daxes = get_default_axes(changed_axes)
# Downcast anything from int64 to int32
# Convert any timezone aware datetimes to native UTC times
df = downcast_dataframe(nativize_times(df))
with RaggedTimeseriesProfile(output, 'w') as nc:
station_groups = df.groupby(axes.station)
unique_stations = list(station_groups.groups.keys())
num_stations = len(unique_stations)
# Calculate the max number of profiles
profile_groups = df.groupby(axes.profile)
unique_profiles = list(profile_groups.groups.keys())
num_profiles = len(unique_profiles)
nc.createDimension(daxes.profile, num_profiles)
if reduce_dims is True and num_stations == 1:
# If a singular station, remove the dimension
station_dimensions = ()
s_ind = None
else:
station_dimensions = (daxes.station,)
nc.createDimension(daxes.station, num_stations)
# The station this profile belongs to
s_ind = nc.createVariable('stationIndex', 'i4', (daxes.profile,))
station = nc.createVariable(axes.station, get_dtype(unique_stations), station_dimensions)
profile = nc.createVariable(axes.profile, get_dtype(df[axes.profile]), (daxes.profile,))
latitude = nc.createVariable(axes.y, get_dtype(df[axes.y]), station_dimensions)
longitude = nc.createVariable(axes.x, get_dtype(df[axes.x]), station_dimensions)
# Get unique obs by grouping on traj and profile and getting the max size
if unlimited is True:
nc.createDimension(daxes.sample, None)
else:
nc.createDimension(daxes.sample, len(df))
# Number of observations in each profile
row_size = nc.createVariable('rowSize', 'i4', (daxes.profile,))
# Axes variables are already processed so skip them
data_columns = [ d for d in df.columns if d not in axes ]
data_columns += [axes.t, axes.z] # time isn't really special, its dimensioned by obs
attributes = dict_update(nc.nc_attributes(axes, daxes), kwargs.pop('attributes', {}))
for i, (sname, srg) in enumerate(station_groups):
station[i] = sname
latitude[i] = df[axes.y][df[axes.station] == sname].dropna().iloc[0]
longitude[i] = df[axes.x][df[axes.station] == sname].dropna().iloc[0]
for j, (pname, pfg) in enumerate(profile_groups):
profile[j] = pname
row_size[j] = len(pfg)
if s_ind is not None:
s_ind[j] = np.asscalar(np.argwhere(station[:] == pfg[axes.station].dropna().iloc[0]))
# Add back in the z axes that was removed when calculating data_columns
# and ignore variables that were stored in the profile index
skips = ['stationIndex', 'rowSize']
for c in [ d for d in data_columns if d not in skips ]:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(
nc,
var_name,
(daxes.sample,),
df[c],
zlib=True,
complevel=1
)
else:
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(df[c], v)
try:
if unlimited is True:
v[:] = vvalues
else:
v[:] = vvalues.reshape(v.shape)
except BaseException:
L.exception('Failed to add {}'.format(c))
continue
# Metadata variables
nc.createVariable('crs', 'i4')
# Set attributes
nc.update_attributes(attributes)
return RaggedTimeseriesProfile(output, **kwargs)
def from_dataframe(cls, df, output, **kwargs):
axes = get_default_axes(kwargs.pop('axes', {}))
daxes = axes
data_columns = [d for d in df.columns if d not in axes]
reduce_dims = kwargs.pop('reduce_dims', False)
_ = kwargs.pop('unlimited', False)
unique_dims = kwargs.pop('unique_dims', False)
if unique_dims is True:
# Rename the dimension to avoid a dimension and coordinate having the same name
# which is not support in xarray
changed_axes = {
k: '{}_dim'.format(v)
for k, v in axes._asdict().items()
}
daxes = get_default_axes(changed_axes)
# Downcast anything from int64 to int32
# Convert any timezone aware datetimes to native UTC times
df = downcast_dataframe(nativize_times(df))
with OrthogonalMultidimensionalTimeseries(output, 'w') as nc:
station_group = df.groupby(axes.station)
num_stations = len(station_group)
has_z = axes.z is not None
if reduce_dims is True and num_stations == 1:
# If a station, we can reduce that dimension if it is of size 1
def ts(i):
return np.s_[:]
default_dimensions = (daxes.t, )
station_dimensions = ()
else:
def ts(i):
return np.s_[i, :]
default_dimensions = (daxes.station, daxes.t)
station_dimensions = (daxes.station, )
nc.createDimension(daxes.station, num_stations)
# Set the coordinates attribute correctly
coordinates = [axes.t, axes.x, axes.y]
if has_z is True:
coordinates.insert(1, axes.z)
coordinates = ' '.join(coordinates)
# assume all groups are the same size and have identical times
_, sdf = list(station_group)[0]
t = sdf[axes.t]
# Metadata variables
nc.createVariable('crs', 'i4')
# Create all of the variables
nc.createDimension(daxes.t, t.size)
time = nc.createVariable(axes.t, 'f8', (daxes.t, ))
station = nc.createVariable(axes.station,
get_dtype(df[axes.station]),
station_dimensions)
latitude = nc.createVariable(axes.y, get_dtype(df[axes.y]),
station_dimensions)
longitude = nc.createVariable(axes.x, get_dtype(df[axes.x]),
station_dimensions)
if has_z is True:
z = nc.createVariable(axes.z,
get_dtype(df[axes.z]),
station_dimensions,
fill_value=df[axes.z].dtype.type(
cls.default_fill_value))
attributes = dict_update(nc.nc_attributes(axes, daxes),
kwargs.pop('attributes', {}))
time[:] = get_ncdata_from_series(t, time)
# Create vars based on full dataframe (to get all variables)
for c in data_columns:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(nc,
var_name,
default_dimensions,
df[c],
zlib=True,
complevel=1)
attributes[var_name] = dict_update(
attributes.get(var_name, {}),
{'coordinates': coordinates})
for i, (uid, sdf) in enumerate(station_group):
station[i] = uid
latitude[i] = sdf[axes.y].iloc[0]
longitude[i] = sdf[axes.x].iloc[0]
if has_z is True:
# TODO: write a test for a Z with a _FillValue
z[i] = sdf[axes.z].iloc[0]
for c in data_columns:
# Create variable if it doesn't exist
var_name = cf_safe_name(c)
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(sdf[c], v)
try:
v[ts(i)] = vvalues
except BaseException:
L.debug(
'{} was not written. Likely a metadata variable'.
format(v.name))
# Set global attributes
nc.update_attributes(attributes)
return OrthogonalMultidimensionalTimeseries(output, **kwargs)
def from_dataframe(cls, df, output, **kwargs):
axes = get_default_axes(kwargs.pop('axes', {}))
daxes = axes
# Should never be a CR file with one trajectory so we ignore the "reduce_dims" attribute
_ = kwargs.pop('reduce_dims', False) # noqa
unlimited = kwargs.pop('unlimited', False)
unique_dims = kwargs.pop('unique_dims', False)
if unique_dims is True:
# Rename the dimension to avoid a dimension and coordinate having the same name
# which is not support in xarray
changed_axes = {
k: '{}_dim'.format(v)
for k, v in axes._asdict().items()
}
daxes = get_default_axes(changed_axes)
# Downcast anything from int64 to int32
# Convert any timezone aware datetimes to native UTC times
df = downcast_dataframe(nativize_times(df))
with ContiguousRaggedTrajectory(output, 'w') as nc:
trajectory_groups = df.groupby(axes.trajectory)
unique_trajectories = list(trajectory_groups.groups.keys())
num_trajectories = len(unique_trajectories)
nc.createDimension(daxes.trajectory, num_trajectories)
trajectory = nc.createVariable(axes.trajectory,
get_dtype(df[axes.trajectory]),
(daxes.trajectory, ))
# Get unique obs by grouping on traj getting the max size
if unlimited is True:
nc.createDimension(daxes.sample, None)
else:
nc.createDimension(daxes.sample, len(df))
# Number of observations in each trajectory
row_size = nc.createVariable('rowSize', 'i4', (daxes.trajectory, ))
attributes = dict_update(nc.nc_attributes(axes, daxes),
kwargs.pop('attributes', {}))
# Variables defined on only the trajectory axis
traj_vars = kwargs.pop('traj_vars', [])
traj_columns = [p for p in traj_vars if p in df.columns]
for c in traj_columns:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
create_ncvar_from_series(nc,
var_name, (daxes.trajectory, ),
df[c],
zlib=True,
complevel=1)
for i, (trajid, trg) in enumerate(trajectory_groups):
trajectory[i] = trajid
row_size[i] = len(trg)
# Save any trajectory variables using the first value found
# in the column.
for c in traj_columns:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
continue
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(trg[c], v)[0]
try:
v[i] = vvalues
except BaseException:
L.exception('Failed to add {}'.format(c))
continue
# Add all of the columns based on the sample dimension. Take all columns and remove the
# trajectory, rowSize and other trajectory based columns.
sample_columns = [
f for f in df.columns
if f not in traj_columns + ['rowSize', axes.trajectory]
]
for c in sample_columns:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(nc,
var_name, (daxes.sample, ),
df[c],
zlib=True,
complevel=1)
else:
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(df[c], v)
try:
if unlimited is True:
v[:] = vvalues
else:
v[:] = vvalues.reshape(v.shape)
except BaseException:
L.exception('Failed to add {}'.format(c))
continue
# Metadata variables
if 'crs' not in nc.variables:
nc.createVariable('crs', 'i4')
# Set attributes
nc.update_attributes(attributes)
return ContiguousRaggedTrajectory(output, **kwargs)
def from_dataframe(cls, df, output, **kwargs):
axes = get_default_axes(kwargs.pop('axes', {}))
daxes = axes
data_columns = [d for d in df.columns if d not in axes]
reduce_dims = kwargs.pop('reduce_dims', False)
unlimited = kwargs.pop('unlimited', False)
unique_dims = kwargs.pop('unique_dims', False)
if unique_dims is True:
# Rename the dimension to avoid a dimension and coordinate having the same name
# which is not supported in xarray
changed_axes = {
k: '{}_dim'.format(v)
for k, v in axes._asdict().items()
}
daxes = get_default_axes(changed_axes)
# Downcast anything from int64 to int32
# Convert any timezone aware datetimes to native UTC times
df = downcast_dataframe(nativize_times(df))
# Make a new index that is the Cartesian product of all of the values from all of the
# values of the old index. This is so don't have to iterate over anything. The full column
# of data will be able to be shaped to the size of the final unique sized dimensions.
index_order = [axes.t, axes.z, axes.station]
df = df.set_index(index_order)
df = df.reindex(
pd.MultiIndex.from_product(df.index.levels, names=index_order))
unique_z = df.index.get_level_values(axes.z).unique().values
unique_t = df.index.get_level_values(
axes.t).unique().tolist() # tolist converts to Timestamp
all_stations = df.index.get_level_values(axes.station)
unique_s = all_stations.unique()
with OrthogonalMultidimensionalTimeseriesProfile(output, 'w') as nc:
if reduce_dims is True and unique_s.size == 1:
# If a singular trajectory, we can reduce that dimension if it is of size 1
default_dimensions = (daxes.t, daxes.z)
station_dimensions = ()
else:
default_dimensions = (daxes.t, daxes.z, daxes.station)
station_dimensions = (daxes.station, )
nc.createDimension(daxes.station, unique_s.size)
station = nc.createVariable(axes.station, get_dtype(unique_s),
station_dimensions)
latitude = nc.createVariable(axes.y, get_dtype(df[axes.y]),
station_dimensions)
longitude = nc.createVariable(axes.x, get_dtype(df[axes.x]),
station_dimensions)
# Assign over loop because VLEN variables (strings) have to be assigned by integer index
# and we need to find the lat/lon based on station index
for si, st in enumerate(unique_s):
station[si] = st
latitude[si] = df[axes.y][all_stations == st].dropna().iloc[0]
longitude[si] = df[axes.x][all_stations == st].dropna().iloc[0]
# Metadata variables
nc.createVariable('crs', 'i4')
# Create all of the variables
if unlimited is True:
nc.createDimension(daxes.t, None)
else:
nc.createDimension(daxes.t, len(unique_t))
time = nc.createVariable(axes.t, 'f8', (daxes.t, ))
time[:] = date2num(unique_t,
units=cls.default_time_unit).astype('f8')
nc.createDimension(daxes.z, unique_z.size)
z = nc.createVariable(axes.z, get_dtype(unique_z), (daxes.z, ))
z[:] = unique_z
attributes = dict_update(nc.nc_attributes(axes, daxes),
kwargs.pop('attributes', {}))
# Variables defined on only the time axis and not the depth axis
detach_z_vars = kwargs.pop('detach_z', [])
detach_z_columnms = [p for p in detach_z_vars if p in data_columns]
for c in detach_z_columnms:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(
nc,
var_name,
default_dimensions[
0::2], # this removes the second dimension (z)
df[c],
zlib=True,
complevel=1)
attributes[var_name] = dict_update(
attributes.get(var_name, {}), {
'coordinates':
'{} {} {}'.format(axes.t, axes.x, axes.y)
})
else:
v = nc.variables[var_name]
# Because we need access to the fillvalues here, we ask not to return
# the values with them already filled.
vvalues = get_ncdata_from_series(df[c], v, fillna=False)
# Reshape to the full array, with Z
vvalues = vvalues.reshape(len(unique_t), unique_z.size,
unique_s.size)
# The Z axis is always the second axis, take the mean over that axis
vvalues = np.apply_along_axis(np.nanmean, 1, vvalues).flatten()
# Now reshape to the array without Z
vvalues = vvalues.reshape(len(unique_t), unique_s.size)
try:
v[:] = vvalues.reshape(v.shape)
except BaseException:
L.exception('Failed to add {}'.format(c))
continue
full_columns = [
f for f in data_columns if f not in detach_z_columnms
]
for c in full_columns:
# Create variable if it doesn't exist
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(nc,
var_name,
default_dimensions,
df[c],
zlib=True,
complevel=1)
attributes[var_name] = dict_update(
attributes.get(var_name, {}), {
'coordinates':
'{} {} {} {}'.format(axes.t, axes.z, axes.x,
axes.y)
})
else:
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(df[c], v)
v[:] = vvalues.reshape(v.shape)
nc.update_attributes(attributes)
return OrthogonalMultidimensionalTimeseriesProfile(output, **kwargs)
def from_dataframe(cls, df, output, **kwargs):
axes = get_default_axes(kwargs.pop('axes', {}))
daxes = axes
data_columns = [ d for d in df.columns if d not in axes ]
reduce_dims = kwargs.pop('reduce_dims', False)
unlimited = kwargs.pop('unlimited', False)
unique_dims = kwargs.pop('unique_dims', False)
if unique_dims is True:
# Rename the dimension to avoid a dimension and coordinate having the same name
# which is not support in xarray
changed_axes = { k: '{}_dim'.format(v) for k, v in axes._asdict().items() }
daxes = get_default_axes(changed_axes)
# Downcast anything from int64 to int32
# Convert any timezone aware datetimes to native UTC times
df = downcast_dataframe(nativize_times(df))
with IncompleteMultidimensionalTrajectory(output, 'w') as nc:
trajectory_group = df.groupby(axes.trajectory)
if unlimited is True:
max_obs = None
else:
max_obs = trajectory_group.size().max()
nc.createDimension(daxes.sample, max_obs)
num_trajectories = len(trajectory_group)
if reduce_dims is True and num_trajectories == 1:
# If a singlular trajectory, we can reduce that dimension if it is of size 1
def ts(t_index, size):
return np.s_[0:size]
default_dimensions = (daxes.sample,)
trajectory = nc.createVariable(axes.trajectory, get_dtype(df[axes.trajectory]))
else:
def ts(t_index, size):
return np.s_[t_index, 0:size]
default_dimensions = (daxes.trajectory, daxes.sample)
nc.createDimension(daxes.trajectory, num_trajectories)
trajectory = nc.createVariable(axes.trajectory, get_dtype(df[axes.trajectory]), (daxes.trajectory,))
# Create all of the variables
time = nc.createVariable(axes.t, 'f8', default_dimensions, fill_value=np.dtype('f8').type(cls.default_fill_value))
z = nc.createVariable(axes.z, get_dtype(df[axes.z]), default_dimensions, fill_value=df[axes.z].dtype.type(cls.default_fill_value))
latitude = nc.createVariable(axes.y, get_dtype(df[axes.y]), default_dimensions, fill_value=df[axes.y].dtype.type(cls.default_fill_value))
longitude = nc.createVariable(axes.x, get_dtype(df[axes.x]), default_dimensions, fill_value=df[axes.x].dtype.type(cls.default_fill_value))
attributes = dict_update(nc.nc_attributes(axes, daxes), kwargs.pop('attributes', {}))
# Create vars based on full dataframe (to get all variables)
for c in data_columns:
var_name = cf_safe_name(c)
if var_name not in nc.variables:
v = create_ncvar_from_series(
nc,
var_name,
default_dimensions,
df[c],
zlib=True,
complevel=1
)
attributes[var_name] = dict_update(attributes.get(var_name, {}), {
'coordinates': '{} {} {} {}'.format(
axes.t, axes.z, axes.x, axes.y
)
})
for i, (uid, gdf) in enumerate(trajectory_group):
trajectory[i] = uid
times = get_ncdata_from_series(gdf[axes.t], time)
time[ts(i, times.size)] = times
lats = get_ncdata_from_series(gdf[axes.y], latitude)
latitude[ts(i, lats.size)] = lats
lons = get_ncdata_from_series(gdf[axes.x], longitude)
longitude[ts(i, lons.size)] = lons
zs = gdf[axes.z].fillna(get_fill_value(z)).values
z[ts(i, zs.size)] = zs
for c in data_columns:
# Create variable if it doesn't exist
var_name = cf_safe_name(c)
v = nc.variables[var_name]
vvalues = get_ncdata_from_series(gdf[c], v)
slicer = ts(i, vvalues.size)
v[slicer] = vvalues
# Metadata variables
if 'crs' not in nc.variables:
nc.createVariable('crs', 'i4')
# Set attributes
nc.update_attributes(attributes)
return IncompleteMultidimensionalTrajectory(output, **kwargs)
"longitude": {"units": "degrees_east", "standard_name": "longitude",},
"latitude": {"units": "degrees_north", "standard_name": "latitude",},
"z": {"units": "m", "standard_name": "depth", "positive": "down",},
"u": {"units": "m/s", "standard_name": "eastward_sea_water_velocity",},
"v": {"units": "m/s", "standard_name": "northward_sea_water_velocity",},
"station": {"cf_role": "timeseries_id"},
}
We also need to map the our data axes to [`pocean`'s defaults](https://github.com/pyoceans/pocean-core/blob/master/pocean/utils.py#L50-L59). This step is not needed if the data axes are already named like the default ones.
axes = {"t": "time", "x": "longitude", "y": "latitude", "z": "depth"}
from pocean.dsg.timeseries.om import OrthogonalMultidimensionalTimeseries
from pocean.utils import downcast_dataframe
df = downcast_dataframe(df) # safely cast depth np.int64 to np.int32
dsg = OrthogonalMultidimensionalTimeseries.from_dataframe(
df, output="fake_buoy.nc", attributes=attributes, axes=axes,
)
The `OrthogonalMultidimensionalTimeseries` saves the DataFrame into a CF-1.6 TimeSeries DSG.
!ncdump -h fake_buoy.nc
It also outputs the dsg object for inspection. Let us check a few things to see if our objects was created as expected. (Note that some of the metadata was "free" due t the built-in defaults in `pocean`.
dsg.getncattr("featureType")
type(dsg)
In addition to standard `netCDF4-python` object `.variables` method `pocean`'s DSGs provides an "categorized" version of the variables in the `data_vars`, `ancillary_vars`, and the DSG axes methods.