Python xarray.open_mfdataset方法代码示例

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def to_netcdf(inpaths, outpath, cdm, engine):
    import cf2cdm
    import xarray as xr

    # NOTE: noop if no input argument
    if len(inpaths) == 0:
        return

    if not outpath:
        outpath = os.path.splitext(inpaths[0])[0] + '.nc'

    ds = xr.open_mfdataset(inpaths, engine=engine, combine='by_coords')
    if cdm:
        coord_model = getattr(cf2cdm, cdm)
        ds = cf2cdm.translate_coords(ds, coord_model=coord_model)
    ds.to_netcdf(outpath) 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def _get_grid_files(self):
        """Get the files holding grid data for an aospy object."""
        grid_file_paths = self.grid_file_paths
        datasets = []
        if isinstance(grid_file_paths, str):
            grid_file_paths = [grid_file_paths]
        for path in grid_file_paths:
            try:
                ds = xr.open_dataset(path, decode_times=False)
            except (TypeError, AttributeError):
                ds = xr.open_mfdataset(path, decode_times=False,
                                       combine='by_coords').load()
            except (RuntimeError, OSError) as e:
                msg = str(e) + ': {}'.format(path)
                raise RuntimeError(msg)
            datasets.append(ds)
        return tuple(datasets) 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def _open_ds_from_store(fname, store_mod=None, store_cls=None, **kwargs):
    """Open a dataset and return it"""
    if isinstance(fname, xr.Dataset):
        return fname
    if not isstring(fname):
        try:  # test iterable
            fname[0]
        except TypeError:
            pass
        else:
            if store_mod is not None and store_cls is not None:
                if isstring(store_mod):
                    store_mod = repeat(store_mod)
                if isstring(store_cls):
                    store_cls = repeat(store_cls)
                fname = [_open_store(sm, sc, f)
                         for sm, sc, f in zip(store_mod, store_cls, fname)]
                kwargs['engine'] = None
                kwargs['lock'] = False
                return open_mfdataset(fname, **kwargs)
    if store_mod is not None and store_cls is not None:
        fname = _open_store(store_mod, store_cls, fname)
    return open_dataset(fname, **kwargs) 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def open(self, exact_dates=True, concat_dim='time', **dataset_kwargs):
        """
        Open an xarray multi-file Dataset for the processed files with dates set using set_dates(), retrieve(), or
        write(). Once opened, this Dataset is accessible by self.Dataset.

        :param exact_dates: bool: if True, set the Dataset to have the exact dates of this instance; otherwise,
            keep all of the monthly dates in the opened files
        :param concat_dim: passed to xarray.open_mfdataset()
        :param dataset_kwargs: kwargs passed to xarray.open_mfdataset()
        """
        nc_file_dir = '%s/processed' % self._root_directory
        if not self.dataset_dates:
            raise ValueError("use set_dates() to specify times of data to load")
        dates_index = pd.DatetimeIndex(self.dataset_dates).sort_values()
        months = dates_index.to_period('M')
        unique_months = months.unique()
        nc_files = ['%s/%s%s.nc' % (nc_file_dir, self._file_id, d.strftime('%Y%m')) for d in unique_months]
        self.Dataset = xr.open_mfdataset(nc_files, concat_dim=concat_dim, **dataset_kwargs)
        if exact_dates:
            self.Dataset = self.Dataset.sel(time=self.dataset_dates)
        self.dataset_variables = list(self.Dataset.variables.keys()) 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def prepare_meta_sarah(xs, ys, year, month, template_sis, template_sid, module, resolution=resolution):
    fns = [next(glob.iglob(t.format(year=year, month=month)))
           for t in (template_sis, template_sid)]

    with xr.open_mfdataset(fns, compat='identical') as ds:
        ds = _rename_and_clean_coords(ds)
        ds = ds.coords.to_dataset()

        t = pd.Timestamp(year=year, month=month, day=1)
        ds['time'] = pd.date_range(t, t + pd.DateOffset(months=1),
                                   freq='1h', closed='left')

        if resolution is not None:
            def p(s):
                s += 0.1*resolution
                return s - (s % resolution)
            xs = np.arange(p(xs.start), p(xs.stop) + 1.1*resolution, resolution)
            ys = np.arange(p(ys.start), p(ys.stop) - 0.1*resolution, - resolution)
            ds = ds.sel(x=xs, y=ys, method='nearest')
        else:
            ds = ds.sel(x=as_slice(xs), y=as_slice(ys))

        return ds.load() 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def _open_dataset(self):
        import xarray as xr
        url = self.urlpath

        kwargs = self.xarray_kwargs

        if "*" in url or isinstance(url, list):
            _open_dataset = xr.open_mfdataset
            if self.pattern:
                kwargs.update(preprocess=self._add_path_to_ds)
            if self.combine is not None:
                if 'combine' in kwargs:
                    raise Exception("Setting 'combine' argument twice  in the catalog is invalid")
                kwargs.update(combine=self.combine)
            if self.concat_dim is not None:
                if 'concat_dim' in kwargs:
                    raise Exception("Setting 'concat_dim' argument twice  in the catalog is invalid")
                kwargs.update(concat_dim=self.concat_dim)
        else:
            _open_dataset = xr.open_dataset
        url = fsspec.open_local(url, **self.storage_options)

        self._ds = _open_dataset(url, chunks=self.chunks, **kwargs) 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def open_glm_time_series(filenames, chunks=None):
    """ Convenience function for combining individual 1-min GLM gridded imagery
    files into a single xarray.Dataset with a time dimension.
    
    Creates an index on the time dimension.
    
    The time dimension will be in the order in which the files are listed
    due to the behavior of combine='nested' in open_mfdataset.
    
    Adjusts the time_coverage_start and time_coverage_end metadata.
    """
    # Need to fix time_coverage_start and _end in concat dataset
    starts = [t for t in gen_file_times(filenames)]
    ends = [t for t in gen_file_times(filenames, time_attr='time_coverage_end')]
    
    d = xr.open_mfdataset(filenames, concat_dim='time', chunks=chunks, combine='nested')
    d['time'] = starts
    d = d.set_index({'time':'time'})
    d = d.set_coords('time')
    
    d.attrs['time_coverage_start'] = pd.Timestamp(min(starts)).isoformat()
    d.attrs['time_coverage_end'] = pd.Timestamp(max(ends)).isoformat()

    return d 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def _preprocess_and_rename_grid_attrs(func, grid_attrs=None, **kwargs):
    """Call a custom preprocessing method first then rename grid attrs.

    This wrapper is needed to generate a single function to pass to the
    ``preprocesss`` of xr.open_mfdataset.  It makes sure that the
    user-specified preprocess function is called on the loaded Dataset before
    aospy's is applied.  An example for why this might be needed is output from
    the WRF model; one needs to add a CF-compliant units attribute to the time
    coordinate of all input files, because it is not present by default.

    Parameters
    ----------
    func : function
       An arbitrary function to call before calling
       ``grid_attrs_to_aospy_names`` in ``_load_data_from_disk``.  Must take
       an xr.Dataset as an argument as well as ``**kwargs``.
    grid_attrs : dict (optional)
        Overriding dictionary of grid attributes mapping aospy internal
        names to names of grid attributes used in a particular model.

    Returns
    -------
    function
        A function that calls the provided function ``func`` on the Dataset
        before calling ``grid_attrs_to_aospy_names``; this is meant to be
        passed as a ``preprocess`` argument to ``xr.open_mfdataset``.
    """

    def func_wrapper(ds):
        return grid_attrs_to_aospy_names(func(ds, **kwargs), grid_attrs)
    return func_wrapper 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def open_mfdataset_glob(self):
        """
        Use xarray.open_mfdataset to read multiple netcdf files with a glob
        pattern.
        """
        pattern = os.path.join(self.data_dir, "*PropertiesRhineMeuse30min.nc")
        xarray.open_mfdataset(pattern) 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def open_mfdataset_list(self):
        """
        Use xarray.open_mfdataset to read multiple netcdf files from a list.
        """
        file_names = [os.path.join(self.data_dir, f)
                      for f in ('soilPropertiesRhineMeuse30min.nc',
                                'topoPropertiesRhineMeuse30min.nc')]
        xarray.open_mfdataset(file_names) 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def track_start_volume(self, gdirs):
        self.cfg_init()
        path = os.path.join(cfg.PATHS['working_dir'], 'run_output_tstar*.nc')
        with xr.open_mfdataset(path, combine='by_coords') as ds:
            return float(ds.volume.sum(dim='rgi_id').isel(time=0)) * 1e-9 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def track_tstar_run_final_volume(self, gdirs):
        self.cfg_init()
        path = os.path.join(cfg.PATHS['working_dir'], 'run_output_tstar*.nc')
        with xr.open_mfdataset(path, combine='by_coords') as ds:
            return float(ds.volume.sum(dim='rgi_id').isel(time=-1)) * 1e-9 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def track_1990_run_final_volume(self, gdirs):
        self.cfg_init()
        path = os.path.join(cfg.PATHS['working_dir'], 'run_output_pd*.nc')
        with xr.open_mfdataset(path, combine='by_coords') as ds:
            return float(ds.volume.sum(dim='rgi_id').isel(time=-1)) * 1e-9 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def track_avg_temp_full_period(self, gdirs):
        self.cfg_init()
        path = os.path.join(cfg.PATHS['working_dir'], 'climate_input*.nc')
        with xr.open_mfdataset(path, combine='by_coords') as ds:
            return float(ds.temp.mean()) 

# 需要导入模块: import xarray [as 别名]
# 或者: from xarray import open_mfdataset [as 别名]
def track_avg_prcp_full_period(self, gdirs):
        self.cfg_init()
        path = os.path.join(cfg.PATHS['working_dir'], 'climate_input*.nc')
        with xr.open_mfdataset(path, combine='by_coords') as ds:
            return float(ds.prcp.mean())