Merge branch 'main' into fillna

Author: ecomodeller

.pre-commit-config.yaml

@@ -0,0 +1,9 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.8.6
+    hooks:
+      # Run the linter.
+      - id: ruff
+      # Run the formatter.
+      - id: ruff-format

mikeio/__init__.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 from importlib.metadata import PackageNotFoundError, version
 from pathlib import Path
-from platform import architecture
 from collections.abc import Sequence
 from typing import Any
 
@@ -15,9 +14,6 @@
 __dfs_version__: int = 220
 
 
-if "64" not in architecture()[0]:
-    raise Exception("This library has not been tested for a 32 bit system.")
-
 from .dataset import DataArray, Dataset, from_pandas, from_polars
 from .dfs import Dfs0, Dfs1, Dfs2, Dfs3
 from .dfsu import Dfsu, Mesh, Dfsu2DH, Dfsu2DV, Dfsu3D, DfsuSpectral
@@ -121,7 +117,9 @@ def read(
     ext = Path(filename).suffix.lower()
 
     if "dfs" not in ext:
-        raise ValueError("mikeio.read() is only supported for dfs files")
+        raise ValueError(
+            "mikeio.read() is only supported for dfs files. Use mikeio.open for mesh files."
+        )
 
     dfs = open(filename)
     if isinstance(dfs, Mesh):

mikeio/_track.py

@@ -19,7 +19,7 @@ def _extract_track(
     end_time: pd.Timestamp,
     timestep: float,
     geometry: GeometryFM2D,
-    track: str | Dataset | pd.DataFrame,
+    track: str | Path | Dataset | pd.DataFrame,
     items: Sequence[ItemInfo],
     item_numbers: Sequence[int],
     time_steps: Sequence[int],
@@ -36,6 +36,8 @@ def _extract_track(
     match track:
         case str():
             times, coords = _get_track_data_from_file(track)
+        case Path():
+            times, coords = _get_track_data_from_file(str(track))
         case Dataset():
             times, coords = _get_track_data_from_dataset(track)
         case pd.DataFrame():
@@ -193,20 +195,3 @@ def _get_track_data_from_file(track: str) -> tuple[pd.DatetimeIndex, np.ndarray]
     coords = df.iloc[:, 0:2].to_numpy(copy=True)
 
     return times, coords
-
-
-def _find_end_index(t_rel: pd.Index, end_time: pd.Timestamp) -> int:
-    # largest idx for which (times - self.end_time)<=0
-    tmp = np.where(t_rel <= 0)[0]
-    if len(tmp) == 0:
-        raise ValueError("No time overlap!")
-    i_end = tmp[-1]
-    return i_end
-
-
-def _find_start_index(t_rel: pd.Index, start_time: pd.Timestamp) -> int:
-    tmp = np.where(t_rel >= 0)[0]
-    if len(tmp) == 0:
-        raise ValueError("No time overlap!")
-    i_start = tmp[0]  # smallest idx for which t_rel>=0
-    return i_start

mikeio/dataset/_dataarray.py

@@ -81,6 +81,8 @@
     Grid3D,
 ]
 
+IndexType = Union[int, slice, Sequence[int], np.ndarray, None]
+
 
 class _DataArraySpectrumToHm0:
     def __init__(self, da: "DataArray") -> None:
@@ -98,12 +100,9 @@ def __call__(self, tail: bool = True) -> "DataArray":
         dims = tuple([d for d in self.da.dims if d not in ("frequency", "direction")])
         item = ItemInfo(EUMType.Significant_wave_height)
         g = self.da.geometry
-        if isinstance(g, GeometryFMPointSpectrum):
-            if g.x is not None and g.y is not None:
-                geometry: Any = GeometryPoint2D(x=g.x, y=g.y)
-            else:
-                geometry = GeometryUndefined()
-        elif isinstance(g, GeometryFMLineSpectrum):
+        geometry: Any = GeometryUndefined()
+
+        if isinstance(g, GeometryFMLineSpectrum):
             geometry = Grid1D(
                 nx=g.n_nodes,
                 dx=1.0,
@@ -119,8 +118,6 @@ def __call__(self, tail: bool = True) -> "DataArray":
                 element_table=g.element_table,
                 element_ids=g.element_ids,
             )
-        else:
-            geometry = GeometryUndefined()
 
         return DataArray(
             data=Hm0,
@@ -407,7 +404,11 @@ def type(self) -> EUMType:
     @property
     def unit(self) -> EUMUnit:
         """EUMUnit."""
-        return self.item.unit
+        return self.item._unit
+
+    @unit.setter
+    def unit(self, value: EUMUnit) -> None:
+        self.item.unit = value
 
     @property
     def start_time(self) -> datetime:
@@ -613,9 +614,18 @@ def __setitem__(self, key: Any, value: np.ndarray) -> None:
 
     def isel(
         self,
-        idx: int | Sequence[int] | slice | None = None,
+        idx: IndexType = None,
+        *,
+        time: IndexType = None,
+        x: IndexType = None,
+        y: IndexType = None,
+        z: IndexType = None,
+        element: IndexType = None,
+        node: IndexType = None,
+        layer: IndexType = None,
+        frequency: IndexType = None,
+        direction: IndexType = None,
         axis: int | str = 0,
-        **kwargs: Any,
     ) -> "DataArray":
         """Return a new DataArray whose data is given by
         integer indexing along the specified dimension(s).
@@ -646,11 +656,17 @@ def isel(
             y index, by default None
         z : int, optional
             z index, by default None
+        layer: int, optional
+            layer index, only used in dfsu 3d
+        direction: int, optional
+            direction index, only used in sprectra
+        frequency: int, optional
+            frequencey index, only used in spectra
+        node: int, optional
+            node index, only used in spectra
         element : int, optional
             Bounding box of coordinates (left lower and right upper)
             to be selected, by default None
-        **kwargs: Any
-            Not used
 
         Returns
         -------
@@ -683,10 +699,23 @@ def isel(
         ```
 
         """
-        if isinstance(self.geometry, Grid2D) and ("x" in kwargs and "y" in kwargs):
-            idx_x = kwargs["x"]
-            idx_y = kwargs["y"]
-            return self.isel(x=idx_x).isel(y=idx_y)
+        if isinstance(self.geometry, Grid2D) and (x is not None and y is not None):
+            return self.isel(x=x).isel(y=y)
+        kwargs = {
+            k: v
+            for k, v in dict(
+                time=time,
+                x=x,
+                y=y,
+                z=z,
+                element=element,
+                node=node,
+                layer=layer,
+                frequency=frequency,
+                direction=direction,
+            ).items()
+            if v is not None
+        }
         for dim in kwargs:
             if dim in self.dims:
                 axis = dim
@@ -727,7 +756,7 @@ def isel(
                 spatial_axis = axis - 1 if self.dims[0] == "time" else axis
                 geometry = self.geometry.isel(idx, axis=spatial_axis)
 
-            # TOOD this is ugly
+            # TODO this is ugly
             if isinstance(geometry, _GeometryFMLayered):
                 node_ids, _ = self.geometry._get_nodes_and_table_for_elements(
                     idx, node_layers="all"
@@ -770,7 +799,12 @@ def sel(
         self,
         *,
         time: str | pd.DatetimeIndex | "DataArray" | None = None,
-        **kwargs: Any,
+        x: float | slice | None = None,
+        y: float | slice | None = None,
+        z: float | slice | None = None,
+        coords: np.ndarray | None = None,
+        area: tuple[float, float, float, float] | None = None,
+        layers: int | str | Sequence[int | str] | None = None,
     ) -> "DataArray":
         """Return a new DataArray whose data is given by
         selecting index labels along the specified dimension(s).
@@ -809,8 +843,6 @@ def sel(
             layer(s) to be selected: "top", "bottom" or layer number
             from bottom 0,1,2,... or from the top -1,-2,... or as
             list of these; only for layered dfsu, by default None
-        **kwargs: Any
-            Additional keyword arguments
 
         Returns
         -------
@@ -852,24 +884,32 @@ def sel(
         ```
 
         """
+        # time is not part of kwargs
+        kwargs = {
+            k: v
+            for k, v in dict(
+                x=x, y=y, z=z, area=area, coords=coords, layers=layers
+            ).items()
+            if v is not None
+        }
         if any([isinstance(v, slice) for v in kwargs.values()]):
-            return self._sel_with_slice(kwargs)
+            return self._sel_with_slice(kwargs)  # type: ignore
 
         da = self
 
         # select in space
         if len(kwargs) > 0:
             idx = self.geometry.find_index(**kwargs)
+
+            # TODO this seems fragile
             if isinstance(idx, tuple):
                 # TODO: support for dfs3
                 assert len(idx) == 2
-                t_ax_offset = 1 if self._has_time_axis else 0
                 ii, jj = idx
                 if jj is not None:
-                    da = da.isel(idx=jj, axis=(0 + t_ax_offset))
+                    da = da.isel(y=jj)
                 if ii is not None:
-                    sp_axis = 0 if (jj is not None and len(jj) == 1) else 1
-                    da = da.isel(idx=ii, axis=(sp_axis + t_ax_offset))
+                    da = da.isel(x=ii)
             else:
                 da = da.isel(idx, axis="space")
 
@@ -1895,7 +1935,7 @@ def to_dfs(self, filename: str | Path, **kwargs: Any) -> None:
             Dfs0 only: set the dfs data type of the written data
             to e.g. np.float64, by default: DfsSimpleType.Float (=np.float32)
         **kwargs: Any
-            Additional keyword arguments, e.g. dtype for dfs0
+            additional arguments passed to the writing function, e.g. dtype for dfs0
 
         """
         self._to_dataset().to_dfs(filename, **kwargs)