def _build_stack(self):
"""
Building file stack and initialize netCDF4.mfdataset.
"""
if self.inventory is not None:
if self._dims == 2:
self.mfdataset = xr.open_mfdataset(
self.inventory.dropna()['filepath'].tolist(),
chunks=self.chunks,
combine="nested",
concat_dim=self.inventory.index.name,
mask_and_scale=self.auto_decode,
use_cftime=False)
self.mfdataset = self.mfdataset.assign_coords(
{self.inventory.index.name: self.inventory.index})
gm_name = NcFile.get_gm_name(self.mfdataset)
if gm_name is not None:
self.mfdataset[gm_name] = self.mfdataset[gm_name].sel(
**{self.inventory.index.name: 0}, drop=True)
else:
self.mfdataset = xr.open_mfdataset(
self.inventory.dropna()['filepath'].tolist(),
chunks=self.chunks,
combine='by_coords',
mask_and_scale=self.auto_decode,
use_cftime=False)
else:
raise RuntimeError('Building stack failed')
def read(self,
row=None,
col=None,
n_rows=1,
n_cols=1,
band="1",
nodataval=-9999,
decoder=None,
decoder_kwargs=None):
"""
Read data from netCDF4 file.
Parameters
----------
row : int, optional
Row number/index.
If None and `col` is not None, then `row_size` rows with the respective column number will be loaded.
col : int, optional
Column number/index.
If None and `row` is not None, then `col_size` columns with the respective row number will be loaded.
n_rows : int, optional
Number of rows to read (default is 1).
n_cols : int, optional
Number of columns to read (default is 1).
band : str or list of str, optional
Band numbers/names. If None, all bands will be read.
nodataval : tuple or list, optional
List of no data values for each band.
Default: -9999 for each band.
decoder : function, optional
Decoding function expecting a NumPy array as input.
decoder_kwargs : dict, optional
Keyword arguments for the decoder.
Returns
-------
data : xarray.Dataset
Data set with the dimensions [time, y, x] and one data variable.
"""
decoder_kwargs = {} if decoder_kwargs is None else decoder_kwargs
if row is None and col is None: # read whole dataset
row = 0
col = 0
n_rows = self.shape[-2]
n_cols = self.shape[-1]
elif row is None and col is not None: # read by row
row = 0
n_cols = self.shape[-1]
elif row is not None and col is None: # read by column
col = 0
n_rows = self.shape[-2]
if len(self.shape) == 3:
slices = (slice(None), slice(row, row + n_rows),
slice(col, col + n_cols))
else:
slices = (slice(row, row + n_rows), slice(col, col + n_cols))
data_ar = self.mfdataset[band][slices]
if decoder:
data_ar.data = decoder(data_ar.data, nodataval, **decoder_kwargs)
data = data_ar.to_dataset()
if 'time' in list(
data.dims.keys()) and data.variables['time'].dtype == 'float':
timestamps = netCDF4.num2date(data['time'],
self.time_units,
only_use_cftime_datetimes=False)
data = data.assign_coords({'time': timestamps})
# add projection informations again
gm_name = NcFile.get_gm_name(self.mfdataset)
if gm_name is not None:
data[gm_name] = self.mfdataset[gm_name]
#add attributes
data.attrs = self.mfdataset.attrs
return self._fill_nan(data)