def create_netcdf_storage_unit(filename,
crs,
coordinates,
variables,
variable_params,
global_attributes=None,
netcdfparams=None):
"""
Create a NetCDF file on disk.
:param pathlib.Path filename: filename to write to
:param datacube.utils.geometry.CRS crs: Datacube CRS object defining the spatial projection
:param dict coordinates: Dict of named `datacube.model.Coordinate`s to create
:param dict variables: Dict of named `datacube.model.Variable`s to create
:param dict variable_params:
Dict of dicts, with keys matching variable names, of extra parameters for variables
:param dict global_attributes: named global attributes to add to output file
:param dict netcdfparams: Extra parameters to use when creating netcdf file
:return: open netCDF4.Dataset object, ready for writing to
"""
filename = Path(filename)
if filename.exists():
raise RuntimeError('Storage Unit already exists: %s' % filename)
try:
filename.parent.mkdir(parents=True)
except OSError:
pass
_LOG.info('Creating storage unit: %s', filename)
nco = netcdf_writer.create_netcdf(str(filename), **(netcdfparams or {}))
for name, coord in coordinates.items():
netcdf_writer.create_coordinate(nco, name, coord.values, coord.units)
netcdf_writer.create_grid_mapping_variable(nco, crs)
for name, variable in variables.items():
set_crs = all(dim in variable.dims for dim in crs.dimensions)
var_params = variable_params.get(name, {})
data_var = netcdf_writer.create_variable(nco,
name,
variable,
set_crs=set_crs,
**var_params)
for key, value in var_params.get('attrs', {}).items():
setattr(data_var, key, value)
for key, value in (global_attributes or {}).items():
setattr(nco, key, value)
return nco
def test_create_epsg4326_netcdf(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
create_coordinate(nco, 'latitude', numpy.array([1., 2., 3.]), 'm')
create_coordinate(nco, 'longitude', numpy.array([1., 2., 3.]), 'm')
create_grid_mapping_variable(nco, GEO_PROJ)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'crs' in nco.variables
assert nco['crs'].grid_mapping_name == 'latitude_longitude'
_ensure_spheroid(nco['crs'])
_ensure_geospatial(nco)
def test_create_epsg4326_netcdf(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
create_coordinate(nco, 'latitude', numpy.array([1., 2., 3.]), 'm')
create_coordinate(nco, 'longitude', numpy.array([1., 2., 3.]), 'm')
create_grid_mapping_variable(nco, GEO_PROJ)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'crs' in nco.variables
assert nco['crs'].grid_mapping_name == 'latitude_longitude'
_ensure_spheroid(nco['crs'])
_ensure_geospatial(nco)
def test_create_sinus_netcdf(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
create_coordinate(nco, 'x', numpy.array([1., 2., 3.]), 'm')
create_coordinate(nco, 'y', numpy.array([1., 2., 3.]), 'm')
create_grid_mapping_variable(nco, SINIS_PROJ)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'crs' in nco.variables
assert nco['crs'].grid_mapping_name == 'sinusoidal'
assert 'longitude_of_central_meridian' in nco['crs'].ncattrs()
_ensure_spheroid(nco['crs'])
_ensure_geospatial(nco)
def test_create_sinus_netcdf(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
create_coordinate(nco, 'x', numpy.array([1., 2., 3.]), 'm')
create_coordinate(nco, 'y', numpy.array([1., 2., 3.]), 'm')
create_grid_mapping_variable(nco, SINIS_PROJ)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'crs' in nco.variables
assert nco['crs'].grid_mapping_name == 'sinusoidal'
assert 'longitude_of_central_meridian' in nco['crs'].ncattrs()
_ensure_spheroid(nco['crs'])
_ensure_geospatial(nco)
def test_chunksizes(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
coord1 = create_coordinate(nco, 'greg', numpy.array([1.0, 2.0, 3.0]), 'cubic gregs')
coord2 = create_coordinate(nco, 'bleh', numpy.array([1.0, 2.0, 3.0, 4.0, 5.0]), 'metric blehs')
no_chunks = create_variable(nco, 'no_chunks', Variable(numpy.dtype('int16'), None, ('greg', 'bleh'), None))
min_max_chunks = create_variable(nco, 'min_max_chunks', Variable(numpy.dtype('int16'), None,
('greg', 'bleh'), None), chunksizes=[2, 50])
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert nco['no_chunks'].chunking() == 'contiguous'
assert nco['min_max_chunks'].chunking() == [2, 5]
def test_chunksizes(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
coord1 = create_coordinate(nco, 'greg', numpy.array([1.0, 2.0, 3.0]), 'cubic gregs')
coord2 = create_coordinate(nco, 'bleh', numpy.array([1.0, 2.0, 3.0, 4.0, 5.0]), 'metric blehs')
no_chunks = create_variable(nco, 'no_chunks', Variable(numpy.dtype('int16'), None, ('greg', 'bleh'), None))
min_max_chunks = create_variable(nco, 'min_max_chunks', Variable(numpy.dtype('int16'), None,
('greg', 'bleh'), None), chunksizes=[2, 50])
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert nco['no_chunks'].chunking() == 'contiguous'
assert nco['min_max_chunks'].chunking() == [2, 5]
def test_create_albers_projection_netcdf(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
create_coordinate(nco, 'x', numpy.array([1., 2., 3.]), 'm')
create_coordinate(nco, 'y', numpy.array([1., 2., 3.]), 'm')
create_grid_mapping_variable(nco, ALBERS_PROJ)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'crs' in nco.variables
assert nco['crs'].grid_mapping_name == 'albers_conical_equal_area'
assert 'standard_parallel' in nco['crs'].ncattrs()
assert 'longitude_of_central_meridian' in nco['crs'].ncattrs()
assert 'latitude_of_projection_origin' in nco['crs'].ncattrs()
_ensure_spheroid(nco['crs'])
_ensure_gdal(nco['crs'])
_ensure_geospatial(nco)
def test_create_albers_projection_netcdf(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
create_coordinate(nco, 'x', numpy.array([1., 2., 3.]), 'm')
create_coordinate(nco, 'y', numpy.array([1., 2., 3.]), 'm')
create_grid_mapping_variable(nco, ALBERS_PROJ)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'crs' in nco.variables
assert nco['crs'].grid_mapping_name == 'albers_conical_equal_area'
assert 'standard_parallel' in nco['crs'].ncattrs()
assert 'longitude_of_central_meridian' in nco['crs'].ncattrs()
assert 'latitude_of_projection_origin' in nco['crs'].ncattrs()
_ensure_spheroid(nco['crs'])
_ensure_gdal(nco['crs'])
_ensure_geospatial(nco)
def saveNC(output,filename, history):
nco=netcdf_writer.create_netcdf(filename)
nco.history = (history.decode('utf-8').encode('ascii','replace'))
coords=output.coords
cnames=()
for x in coords:
netcdf_writer.create_coordinate(nco, x, coords[x].values, coords[x].units)
cnames=cnames+(x,)
netcdf_writer.create_grid_mapping_variable(nco, output.crs)
for band in output.data_vars:
output.data_vars[band].values[np.isnan(output.data_vars[band].values)]=nodata
var= netcdf_writer.create_variable(nco, band, Variable(output.data_vars[band].dtype, nodata, cnames, None) ,set_crs=True)
var[:] = netcdf_writer.netcdfy_data(output.data_vars[band].values)
nco.close()
def test_create_lambert_conformal_conic_2sp_projection_netcdf(
tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
create_coordinate(nco, 'x', numpy.array([1., 2., 3.]), 'm')
create_coordinate(nco, 'y', numpy.array([1., 2., 3.]), 'm')
create_grid_mapping_variable(nco, LCC2_PROJ)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'crs' in nco.variables
assert nco['crs'].grid_mapping_name == 'lambert_conformal_conic'
assert 'standard_parallel' in nco['crs'].ncattrs()
assert 'longitude_of_central_meridian' in nco['crs'].ncattrs()
assert 'latitude_of_projection_origin' in nco['crs'].ncattrs()
assert 'false_easting' in nco['crs'].ncattrs()
assert 'false_northing' in nco['crs'].ncattrs()
_ensure_spheroid(nco['crs'])
_ensure_gdal(nco['crs'])
_ensure_geospatial(nco)
def write_dataset_to_netcdf(access_unit, global_attributes, variable_params,
filename):
if filename.exists():
raise RuntimeError('Storage Unit already exists: %s' % filename)
try:
filename.parent.mkdir(parents=True)
except OSError:
pass
# _LOG.info("Writing storage unit: %s", filename)
nco = netcdf_writer.create_netcdf(str(filename))
for name, coord in access_unit.coords.items():
netcdf_writer.create_coordinate(nco, name, coord.values, coord.units)
netcdf_writer.create_grid_mapping_variable(nco, access_unit.crs)
for name, variable in access_unit.data_vars.items():
# Create variable
var_params = variable_params.get(name, {})
data_var = netcdf_writer.create_variable(
nco, name,
Variable(variable.dtype, getattr(variable, 'nodata',
None), variable.dims,
getattr(variable, 'units', '1')), **var_params)
# Write data
data_var[:] = netcdf_writer.netcdfy_data(variable.values)
# TODO: 'flags_definition', 'spectral_definition'?
for key, value in variable_params.get(name, {}).get('attrs',
{}).items():
setattr(data_var, key, value)
# write global atrributes
for key, value in global_attributes.items():
setattr(nco, key, value)
nco.close()
def create_netcdf_storage_unit(filename,
crs,
coordinates,
variables,
variable_params,
global_attributes=None,
netcdfparams=None):
if filename.exists():
raise RuntimeError('Storage Unit already exists: %s' % filename)
try:
filename.parent.mkdir(parents=True)
except OSError:
pass
nco = netcdf_writer.create_netcdf(str(filename), **(netcdfparams or {}))
for name, coord in coordinates.items():
netcdf_writer.create_coordinate(nco, name, coord.values, coord.units)
netcdf_writer.create_grid_mapping_variable(nco, crs)
for name, variable in variables.items():
set_crs = all(dim in variable.dims for dim in crs.dimensions)
var_params = variable_params.get(name, {})
data_var = netcdf_writer.create_variable(nco,
name,
variable,
set_crs=set_crs,
**var_params)
for key, value in var_params.get('attrs', {}).items():
setattr(data_var, key, value)
for key, value in (global_attributes or {}).items():
setattr(nco, key, value)
return nco
def test_create_string_variable(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
coord = create_coordinate(nco, 'greg', numpy.array([1.0, 3.0, 9.0]), 'cubic gregs')
dtype = numpy.dtype('S100')
data = numpy.array(["test-str1", "test-str2", "test-str3"], dtype=dtype)
var = create_variable(nco, 'str_var', Variable(dtype, None, ('greg',), None))
var[:] = netcdfy_data(data)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'str_var' in nco.variables
assert netCDF4.chartostring(nco['str_var'][0]) == data[0]
def test_chunksizes(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
x = numpy.arange(3, dtype='float32')
y = numpy.arange(5, dtype='float32')
coord1 = create_coordinate(nco, 'x', x, 'm')
coord2 = create_coordinate(nco, 'y', y, 'm')
assert coord1 is not None and coord2 is not None
no_chunks = create_variable(
nco, 'no_chunks', Variable(numpy.dtype('int16'), None, ('x', 'y'),
None))
min_max_chunks = create_variable(nco,
'min_max_chunks',
Variable(numpy.dtype('int16'), None,
('x', 'y'), None),
chunksizes=(2, 50))
assert no_chunks is not None
assert min_max_chunks is not None
strings = numpy.array(["AAa", 'bbb', 'CcC'], dtype='S')
strings = xr.DataArray(strings, dims=['x'], coords={'x': x})
create_variable(nco, 'strings_unchunked', strings)
create_variable(nco, 'strings_chunked', strings, chunksizes=(1, ))
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert nco['no_chunks'].chunking() == 'contiguous'
assert nco['min_max_chunks'].chunking() == [2, 5]
assert nco['strings_unchunked'].chunking() == 'contiguous'
assert nco['strings_chunked'].chunking() == [1, 3]
def test_create_string_variable(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
coord = create_coordinate(nco, 'greg', numpy.array([1.0, 3.0, 9.0]),
'cubic gregs')
dtype = numpy.dtype('S100')
data = numpy.array(["test-str1", "test-str2", "test-str3"], dtype=dtype)
var = create_variable(nco, 'str_var',
Variable(dtype, None, ('greg', ), None))
var[:] = netcdfy_data(data)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert 'str_var' in nco.variables
assert netCDF4.chartostring(nco['str_var'][0]) == data[0]
def test_create_string_variable(tmpdir, s1, s2, s3):
tmpnetcdf_filename = get_tmpnetcdf_filename(tmpdir)
str_var = 'str_var'
nco = create_netcdf(tmpnetcdf_filename)
coord = create_coordinate(nco, 'greg', numpy.array([1.0, 3.0, 9.0]), 'cubic gregs')
dtype = numpy.dtype('S100')
data = numpy.array([s1, s2, s3], dtype=dtype)
var = create_variable(nco, str_var, Variable(dtype, None, ('greg',), None))
var[:] = netcdfy_data(data)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert str_var in nco.variables
for returned, expected in zip(read_strings_from_netcdf(tmpnetcdf_filename, variable=str_var), (s1, s2, s3)):
assert returned == expected
