diff --git a/mlair/data_handler/data_handler_wrf_chem.py b/mlair/data_handler/data_handler_wrf_chem.py
index c89442c0b4e19a0f523c89c31e3d7abd3c58065b..902d55ffe069dcc4937e644de5d7e6f72195ef65 100644
--- a/mlair/data_handler/data_handler_wrf_chem.py
+++ b/mlair/data_handler/data_handler_wrf_chem.py
@@ -311,18 +311,6 @@ class SingleGridColumnWrfChemDataLoader(BaseWrfChemDataLoader):
self._nearest_coords = None
self.external_coords_file = external_coords_file
- # self.open_data()
- #
- # if self.physical_t_coord_name != self.time_dim_name:
- # self.assign_coords(
- # {self.physical_t_coord_name: (self.time_dim_name, self._data[self.physical_t_coord_name].values)})
- #
- # self._set_dims_as_coords()
- # if external_coords_file is not None:
- # self._apply_external_coordinates()
- # self.apply_staged_transormation()
- # self.rechunk_data(self.rechunk_values)
- # self._set_geoinfos()
logging.debug("SingleGridColumnWrfChemDataLoader Initialised")
def __enter__(self):
@@ -344,7 +332,6 @@ class SingleGridColumnWrfChemDataLoader(BaseWrfChemDataLoader):
self.data.close()
gc.collect()
- @TimeTrackingWrapper
def _set_geoinfos(self):
# identify nearest coords
self._set_nearest_icoords(dim=[self.logical_x_coord_name, self.logical_y_coord_name])
@@ -505,24 +492,18 @@ class DataHandlerSingleGridColumn(DataHandlerSingleStation):
except ValueError as e:
raise ValueError(f"Pass an iterable with two items; (station, path)")
lat, lon = self.coord_str2coords(station)
- with TimeTracking(name="Initialise loader (sgcWRFdh)"):
- # preprocess_fkt_for_loader = self.preprocess_fkt_for_loader()
-
- loader = SingleGridColumnWrfChemDataLoader((lat, lon),
- data_path=path,
- external_coords_file=self.external_coords_file,
- time_dim_name=self.time_dim,
- rechunk_values=self.rechunk_values,
- variables=self.variables,
- z_coord_selector=self._joint_z_coord_selector,
- start_time=self.start,
- end_time=self.end,
-
- # preprocess_open_mfdataset=preprocess_fkt_for_loader,
- )
+ loader = SingleGridColumnWrfChemDataLoader((lat, lon),
+ data_path=path,
+ external_coords_file=self.external_coords_file,
+ time_dim_name=self.time_dim,
+ rechunk_values=self.rechunk_values,
+ variables=self.variables,
+ z_coord_selector=self._joint_z_coord_selector,
+ start_time=self.start,
+ end_time=self.end,
+ )
self.__loader = loader
- @TimeTrackingWrapper
def load_data(self, path, station, statistics_per_var, sampling, station_type=None, network=None,
store_data_locally=False, data_origin: Dict = None, start=None, end=None):
@@ -540,11 +521,9 @@ class DataHandlerSingleGridColumn(DataHandlerSingleStation):
# transpose dataarray: set first three fixed and keep remaining as is
data = data.transpose(self.iter_dim, self.time_dim, self.target_dim, ...)
- with ProgressBar(), TimeTracking(name="DataHandlerSingleGridColumn.load_data: compute data for slice_prep"):
+ with ProgressBar(), TimeTracking(name=f"{self.station}: compute data for slice_prep"):
data = dask.compute(self._slice_prep(data, start=start, end=end))[0]
- # ToDo
- # data should somehow look like this:
- # < xarray.DataArray(Stations: 1, datetime: 7670, variables: 9) (From DataHandlerSingleStation)
+ # ToDo add metadata
meta = None
return data, meta
@@ -581,13 +560,6 @@ class DataHandlerSingleGridColumn(DataHandlerSingleStation):
"""
return self.label.squeeze([self.iter_dim, self.target_dim]).transpose(self.time_dim, self.window_dim, ...).copy()
- # def set_inputs_and_targets(self):
- # # inputs = self._data.sel({self.target_dim: helpers.to_list(self.variables)})
- # # targets = self._data.sel(
- # # {self.target_dim: helpers.to_list(self.target_var)}) # ToDo: is it right to expand this dim??
- # # self.input_data = inputs
- # # self.target_data = targets
- # raise NotImplementedError
@TimeTrackingWrapper
def make_samples(self):
self.make_history_window(self.target_dim, self.window_history_size, self.time_dim)
@@ -643,22 +615,6 @@ class DataHandlerSingleGridColumn(DataHandlerSingleStation):
"""
return all(self._transformation)
- # @TimeTrackingWrapper
- # def setup_samples(self):
- # """
- # Setup samples. This method prepares and creates samples X, and labels Y.
- # """
- # data, self.meta = self.load_data(self.path, self.station, self.statistics_per_var, self.sampling,
- # self.station_type, self.network, self.store_data_locally, self.data_origin,
- # self.start, self.end)
- # self._data = self.interpolate(data, dim=self.time_dim, method=self.interpolation_method,
- # limit=self.interpolation_limit)
- # # self.set_inputs_and_targets()
- # # if self.do_transformation is True:
- # # self.call_transform()
- # # self.make_samples()
- # raise NotImplementedError
-
class DataHandlerWRF(DefaultDataHandler):
"""Data handler using DataHandlerSingleGridColumn."""
@@ -766,23 +722,14 @@ class DataHandlerSectorGrid(DataHandlerSingleGridColumn):
drop=True).values
sector_history.loc[{self.time_dim: time_index_of_sector}] = sec_data_history.sel(
{self.time_dim: time_index_of_sector}).values
- # sector_history = xr.where(sector_allocation.squeeze() == sect,
- # sec_data_history.sel({self.time_dim: sector_history[self.time_dim]}),
- # sector_history * 1.)
-
sector_history = sector_history.assign_coords({self.target_dim: sector_history_var_names})
- # with ProgressBar():
- # logging.info(f"compute `sector_history' for modify_history")
- # sector_history = sector_history.compute()
-
combined_history = xr.concat([self.history, sector_history], dim=self.target_dim)
return combined_history
else:
return self.history
- @TimeTrackingWrapper
def get_section_data_from_circle(self, grid_data, loader, sect, compute=True):
sec_data = grid_data.where(
self.windsector.is_in_sector(sect, loader.geo_infos.bearing.drop('points').squeeze()))
@@ -820,29 +767,20 @@ class DataHandlerSectorGrid(DataHandlerSingleGridColumn):
else:
return grid_data
- @TimeTrackingWrapper
- def apply_aggregation_method_on_sector_data(self, data, loader):
+ @staticmethod
+ def apply_aggregation_method_on_sector_data(data, loader):
data = data.mean(dim=(loader.logical_x_coord_name, loader.logical_y_coord_name))
return data
- @TimeTrackingWrapper
def compute_wind_dir_of_interest(self):
wind_dir_of_intrest = self.history.sel({self.target_dim: self.wind_dir_name, self.window_dim: 0})
return wind_dir_of_intrest
- @TimeTrackingWrapper
def get_applied_transdormation_on_wind_sector_edges(self):
ws_edges = self._get_left_and_right_wind_sector_edges(return_as='xr.da', dim=self.wind_sector_edge_dim_name)
ws_edges = self.apply_transformation_on_data(ws_edges)
return ws_edges
- # def set_inputs_and_targets(self):
- # inputs = self._data.sel({self.target_dim: helpers.to_list(self.variables) + helpers.to_list(self.sector_dim_name)})
- # targets = self._data.sel(
- # {self.target_dim: helpers.to_list(self.target_var)}) # ToDo: is it right to expand this dim??
- # self.input_data = inputs
- # self.target_data = targets
-
class DataHandlerMainSectWRF(DefaultDataHandler):
"""Data handler using DataHandlerSectorGrid."""