roms-tools 1.7.0__py3-none-any.whl → 2.1.0__py3-none-any.whl

roms_tools/setup/surface_forcing.py

@@ -12,13 +12,13 @@ from roms_tools.setup.datasets import (
     CESMBGCSurfaceForcingDataset,
 )
 from roms_tools.setup.utils import (
+    get_target_coords,
     nan_check,
     substitute_nans_by_fillvalue,
     interpolate_from_climatology,
     get_variable_metadata,
     group_dataset,
     save_datasets,
-    get_target_coords,
     rotate_velocities,
     convert_to_roms_time,
     _to_yaml,
@@ -66,6 +66,10 @@ class SurfaceForcing:
         Reference date for the model. Default is January 1, 2000.
     use_dask: bool, optional
         Indicates whether to use dask for processing. If True, data is processed with dask; if False, data is processed eagerly. Defaults to False.
+    bypass_validation: bool, optional
+        Indicates whether to skip validation checks in the processed data. When set to True,
+        the validation process that ensures no NaN values exist at wet points
+        in the processed dataset is bypassed. Defaults to False.
 
     Examples
     --------
@@ -88,6 +92,7 @@ class SurfaceForcing:
     use_coarse_grid: bool = False
     model_reference_date: datetime = datetime(2000, 1, 1)
     use_dask: bool = False
+    bypass_validation: bool = False
 
     ds: xr.Dataset = field(init=False, repr=False)
 
@@ -105,8 +110,8 @@ class SurfaceForcing:
 
         data.apply_lateral_fill()
 
-        variable_info = self._set_variable_info(data)
-        var_names = variable_info.keys()
+        self._set_variable_info(data)
+        var_names = self.variable_info.keys()
 
         processed_fields = {}
         # lateral regridding
@@ -117,8 +122,8 @@ class SurfaceForcing:
                     data.ds[data.var_names[var_name]]
                 )
 
-        # rotation of velocities and interpolation to u/v points
-        if "uwnd" in variable_info and "vwnd" in variable_info:
+        # rotation of velocities
+        if "uwnd" in self.variable_info and "vwnd" in self.variable_info:
             processed_fields["uwnd"], processed_fields["vwnd"] = rotate_velocities(
                 processed_fields["uwnd"],
                 processed_fields["vwnd"],
@@ -134,7 +139,8 @@ class SurfaceForcing:
 
         ds = self._write_into_dataset(processed_fields, data, d_meta)
 
-        self._validate(ds, target_coords["mask"], variable_info)
+        if not self.bypass_validation:
+            self._validate(ds)
 
         # substitute NaNs over land by a fill value to avoid blow-up of ROMS
         for var_name in ds.data_vars:
@@ -213,9 +219,8 @@ class SurfaceForcing:
 
         Returns
         -------
-        dict
-            A dictionary where the keys are variable names and the values are dictionaries of metadata
-            about each variable, including 'location', 'is_vector', 'vector_pair', and 'is_3d'.
+        None
+            This method updates the instance attribute `variable_info` with the metadata dictionary for the variables.
         """
         default_info = {
             "location": "rho",
@@ -256,17 +261,15 @@ class SurfaceForcing:
                 else:
                     variable_info[var_name] = {**default_info, "validate": False}
 
-        return variable_info
+        object.__setattr__(self, "variable_info", variable_info)
 
     def _apply_correction(self, processed_fields, data):
 
         correction_data = self._get_correction_data()
         # choose same subdomain as forcing data so that we can use same mask
         coords_correction = {
-            correction_data.dim_names["latitude"]: data.ds[data.dim_names["latitude"]],
-            correction_data.dim_names["longitude"]: data.ds[
-                data.dim_names["longitude"]
-            ],
+            "lat": data.ds[data.dim_names["latitude"]],
+            "lon": data.ds[data.dim_names["longitude"]],
         }
         correction_data.choose_subdomain(
             coords_correction, straddle=self.target_coords["straddle"]
@@ -329,7 +332,7 @@ class SurfaceForcing:
 
         return ds
 
-    def _validate(self, ds, mask, variable_info):
+    def _validate(self, ds):
         """Validates the dataset by checking for NaN values at wet points, which would
         indicate missing raw data coverage over the target domain.
 
@@ -337,12 +340,6 @@ class SurfaceForcing:
         ----------
         ds : xarray.Dataset
             The dataset to validate.
-        mask : xarray.DataArray
-            Land mask (1=ocean, 0=land) to determine wet points in the domain.
-        variable_info : dict
-            A dictionary containing metadata about each variable (e.g., location,
-            whether it's a 3D variable, etc.). Used to retrieve information for
-            validating each variable.
 
         Raises
         ------
@@ -357,8 +354,8 @@ class SurfaceForcing:
 
         for var_name in ds.data_vars:
             # Only validate variables based on "validate" flag if use_dask is False
-            if not self.use_dask or variable_info[var_name]["validate"]:
-                nan_check(ds[var_name].isel(time=0), mask)
+            if not self.use_dask or self.variable_info[var_name]["validate"]:
+                nan_check(ds[var_name].isel(time=0), self.target_coords["mask"])
 
     def _add_global_metadata(self, ds=None):
 
@@ -548,7 +545,10 @@ class SurfaceForcing:
 
     @classmethod
     def from_yaml(
-        cls, filepath: Union[str, Path], use_dask: bool = False
+        cls,
+        filepath: Union[str, Path],
+        use_dask: bool = False,
+        bypass_validation: bool = False,
     ) -> "SurfaceForcing":
         """Create an instance of the SurfaceForcing class from a YAML file.
 
@@ -558,6 +558,10 @@ class SurfaceForcing:
             The path to the YAML file from which the parameters will be read.
         use_dask: bool, optional
             Indicates whether to use dask for processing. If True, data is processed with dask; if False, data is processed eagerly. Defaults to False.
+        bypass_validation: bool, optional
+            Indicates whether to skip validation checks in the processed data. When set to True,
+            the validation process that ensures no NaN values exist at wet points
+            in the processed dataset is bypassed. Defaults to False.
 
         Returns
         -------
@@ -569,4 +573,6 @@ class SurfaceForcing:
         grid = Grid.from_yaml(filepath)
         params = _from_yaml(cls, filepath)
 
-        return cls(grid=grid, **params, use_dask=use_dask)
+        return cls(
+            grid=grid, **params, use_dask=use_dask, bypass_validation=bypass_validation
+        )

roms_tools/setup/tides.py

@@ -51,6 +51,10 @@ class TidalForcing:
         The reference date for the ROMS simulation. Default is datetime(2000, 1, 1).
     use_dask: bool, optional
         Indicates whether to use dask for processing. If True, data is processed with dask; if False, data is processed eagerly. Defaults to False.
+    bypass_validation: bool, optional
+        Indicates whether to skip validation checks in the processed data. When set to True,
+        the validation process that ensures no NaN values exist at wet points
+        in the processed dataset is bypassed. Defaults to False.
 
     Examples
     --------
@@ -65,6 +69,7 @@ class TidalForcing:
     allan_factor: float = 2.0
     model_reference_date: datetime = datetime(2000, 1, 1)
     use_dask: bool = False
+    bypass_validation: bool = False
 
     ds: xr.Dataset = field(init=False, repr=False)
 
@@ -85,8 +90,8 @@ class TidalForcing:
 
         data.apply_lateral_fill()
 
-        variable_info = self._set_variable_info()
-        var_names = variable_info.keys()
+        self._set_variable_info()
+        var_names = self.variable_info.keys()
 
         processed_fields = {}
         # lateral regridding
@@ -98,7 +103,7 @@ class TidalForcing:
                 )
 
         # rotation of velocities and interpolation to u/v points
-        vector_pairs = get_vector_pairs(variable_info)
+        vector_pairs = get_vector_pairs(self.variable_info)
         for pair in vector_pairs:
             u_component = pair[0]
             v_component = pair[1]
@@ -129,7 +134,8 @@ class TidalForcing:
 
         ds = self._add_global_metadata(ds)
 
-        self._validate(ds, variable_info)
+        if not self.bypass_validation:
+            self._validate(ds)
 
         # substitute NaNs over land by a fill value to avoid blow-up of ROMS
         for var_name in ds.data_vars:
@@ -163,9 +169,8 @@ class TidalForcing:
 
         Returns
         -------
-        dict
-            A dictionary where the keys are variable names and the values are dictionaries of metadata
-            about each variable, including 'location', 'is_vector', 'vector_pair', and 'is_3d'.
+        None
+            This method updates the instance attribute `variable_info` with the metadata dictionary for the variables.
         """
         default_info = {
             "location": "rho",
@@ -210,7 +215,7 @@ class TidalForcing:
             },
         }
 
-        return variable_info
+        object.__setattr__(self, "variable_info", variable_info)
 
     def _write_into_dataset(self, processed_fields, d_meta):
 
@@ -243,7 +248,7 @@ class TidalForcing:
 
         return ds
 
-    def _validate(self, ds, variable_info):
+    def _validate(self, ds):
         """Validates the dataset by checking for NaN values at wet points for specified
         variables, which would indicate missing raw data coverage over the target
         domain.
@@ -252,8 +257,6 @@ class TidalForcing:
         ----------
         ds : xarray.Dataset
             The dataset to validate, containing tidal variables and a mask for wet points.
-        variable_info : dict
-            A dictionary containing metadata about the variables, including whether to validate them.
 
         Raises
         ------
@@ -268,7 +271,7 @@ class TidalForcing:
         """
         for var_name in ds.data_vars:
             # only validate variables based on "validate" flag if use_dask is false
-            if not self.use_dask or variable_info[var_name]["validate"]:
+            if not self.use_dask or self.variable_info[var_name]["validate"]:
                 nan_check(ds[var_name].isel(ntides=0), self.grid.ds.mask_rho)
 
     def plot(self, var_name, ntides=0) -> None:
@@ -423,7 +426,10 @@ class TidalForcing:
 
     @classmethod
     def from_yaml(
-        cls, filepath: Union[str, Path], use_dask: bool = False
+        cls,
+        filepath: Union[str, Path],
+        use_dask: bool = False,
+        bypass_validation: bool = False,
     ) -> "TidalForcing":
         """Create an instance of the TidalForcing class from a YAML file.
 
@@ -433,6 +439,10 @@ class TidalForcing:
             The path to the YAML file from which the parameters will be read.
         use_dask: bool, optional
             Indicates whether to use dask for processing. If True, data is processed with dask; if False, data is processed eagerly. Defaults to False.
+        bypass_validation: bool, optional
+            Indicates whether to skip validation checks in the processed data. When set to True,
+            the validation process that ensures no NaN values exist at wet points
+            in the processed dataset is bypassed. Defaults to False.
 
         Returns
         -------
@@ -443,7 +453,12 @@ class TidalForcing:
 
         grid = Grid.from_yaml(filepath)
         tidal_forcing_params = _from_yaml(cls, filepath)
-        return cls(grid=grid, **tidal_forcing_params, use_dask=use_dask)
+        return cls(
+            grid=grid,
+            **tidal_forcing_params,
+            use_dask=use_dask,
+            bypass_validation=bypass_validation
+        )
 
     def _correct_tides(self, data):
         """Apply tidal corrections to the dataset. This method corrects the dataset for