cf-xarray 0.9.5__tar.gz → 0.10.1__tar.gz

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/.github/workflows/ci.yaml

@@ -36,7 +36,7 @@ jobs:
         run: |
           echo "PYTHON_VERSION=${{ matrix.python-version }}" >> $GITHUB_ENV
       - name: Set up conda environment
-        uses: mamba-org/setup-micromamba@v1
+        uses: mamba-org/setup-micromamba@v2
         with:
           environment-file: ci/environment.yml
           environment-name: cf_xarray_test
@@ -50,7 +50,7 @@ jobs:
         run: |
           pytest -n auto --cov=./ --cov-report=xml
       - name: Upload code coverage to Codecov
-        uses: codecov/codecov-action@v4.5.0
+        uses: codecov/codecov-action@v5.4.0
         with:
           file: ./coverage.xml
           flags: unittests
@@ -70,7 +70,7 @@ jobs:
           # need to fetch all tags to get a correct version
           fetch-depth: 0  # fetch all branches and tags
       - name: Set up conda environment
-        uses: mamba-org/setup-micromamba@v1
+        uses: mamba-org/setup-micromamba@v2
         with:
           environment-file: ci/environment-no-optional-deps.yml
           environment-name: cf_xarray_test
@@ -97,7 +97,7 @@ jobs:
         with:
           fetch-depth: 0 # Fetch all history for all branches and tags.
       - name: Set up conda environment
-        uses: mamba-org/setup-micromamba@v1
+        uses: mamba-org/setup-micromamba@v2
         with:
           environment-file: ci/environment.yml
           environment-name: cf_xarray_test
@@ -114,7 +114,7 @@ jobs:
         run: |
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report cf_xarray/
       - name: Upload mypy coverage to Codecov
-        uses: codecov/codecov-action@v4.5.0
+        uses: codecov/codecov-action@v5.4.0
         with:
           file: mypy_report/cobertura.xml
           flags: mypy

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/.github/workflows/pypi.yaml

@@ -72,7 +72,7 @@ jobs:
 
       - name: Publish package to TestPyPI
         if: github.event_name == 'push'
-        uses: pypa/gh-action-pypi-publish@v1.9.0
+        uses: pypa/gh-action-pypi-publish@v1.12.4
         with:
           password: ${{ secrets.TESTPYPI_TOKEN }}
           repository_url: https://test.pypi.org/legacy/
@@ -96,6 +96,6 @@ jobs:
           name: releases
           path: dist
       - name: Publish package to PyPI
-        uses: pypa/gh-action-pypi-publish@v1.9.0
+        uses: pypa/gh-action-pypi-publish@v1.12.4
         with:
           verbose: true

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/.github/workflows/upstream-dev-ci.yaml

@@ -38,7 +38,7 @@ jobs:
         run: |
           echo "PYTHON_VERSION=${{ matrix.python-version }}" >> $GITHUB_ENV
       - name: Set up conda environment
-        uses: mamba-org/setup-micromamba@v1
+        uses: mamba-org/setup-micromamba@v2
         with:
           environment-file: ci/upstream-dev-env.yml
           environment-name: cf_xarray_test

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/.pre-commit-config.yaml

@@ -3,22 +3,18 @@ ci:
 
 repos:
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.17.0
+    rev: v3.19.1
     hooks:
       - id: pyupgrade
         args: ["--py310-plus"]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: 'v0.6.1'
+    rev: 'v0.9.3'
     hooks:
       - id: ruff
-        args: ["--show-fixes", "--fix"]
-
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 24.8.0
-    hooks:
-      - id: black
+        args: ["--fix", "--show-fixes"]
+      - id: ruff-format
 
   - repo: https://github.com/rstcheck/rstcheck
     rev: v6.2.4
@@ -28,7 +24,7 @@ repos:
           args: ['--config', 'pyproject.toml']
 
   - repo: https://github.com/executablebooks/mdformat
-    rev: 0.7.17
+    rev: 0.7.21
     hooks:
     - id: mdformat
       additional_dependencies:
@@ -36,10 +32,8 @@ repos:
         - mdformat-myst
 
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.7
+    rev: 1.9.1
     hooks:
-        - id: nbqa-black
-        - id: nbqa-ruff
         - id: nbqa
           entry: nbqa mdformat
           name: nbqa-mdformat
@@ -47,7 +41,7 @@ repos:
           additional_dependencies: [mdformat==0.7.17]
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
@@ -55,19 +49,13 @@ repos:
       - id: check-yaml
       - id: debug-statements
 
-  - repo: https://github.com/keewis/blackdoc
-    rev: v0.3.9
-    hooks:
-      - id: blackdoc
-        files: .+\.py$
-
   - repo: https://github.com/citation-file-format/cff-converter-python
     rev: "44e8fc9"
     hooks:
     - id: validate-cff
 
   - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.19
+    rev: v0.23
     hooks:
       - id: validate-pyproject
 

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/.readthedocs.yml

@@ -1,5 +1,6 @@
 version: 2
-
+sphinx:
+  configuration: doc/conf.py
 build:
   os: ubuntu-lts-latest
   tools:

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/CITATION.cff

@@ -83,6 +83,10 @@ authors:
   - family-names: Haëck
     given-names: Clément
     affiliation: Laboratoire d'Océanographie et du Climat (LOCEAN), Paris
+  - family-names: Boutte
+    given-names: Jason
+    orcid: 'https://orcid.org/0009-0009-3996-3772'
+    affiliation: Lawrence Livermore National Laboratory
 identifiers:
   - type: doi
     value: 10.5281/zenodo.4749735

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: cf_xarray
-Version: 0.9.5
+Version: 0.10.1
 Summary: A convenience wrapper for using CF attributes on xarray objects
 License:                                  Apache License
                                    Version 2.0, January 2004
@@ -220,7 +220,7 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.10
 Description-Content-Type: text/x-rst
 License-File: LICENSE
-Requires-Dist: xarray
+Requires-Dist: xarray>=2022.03.0
 Provides-Extra: all
 Requires-Dist: matplotlib; extra == "all"
 Requires-Dist: pint!=0.24.0,>=0.18; extra == "all"

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/cf_xarray/__init__.py

@@ -9,6 +9,6 @@ from .helpers import bounds_to_vertices, vertices_to_bounds  # noqa
 from .options import set_options  # noqa
 from .utils import _get_version
 
-from . import geometry  # noqa
+from . import geometry, groupers  # noqa
 
 __version__ = _get_version()

cf_xarray-0.10.1/cf_xarray/_version.py

@@ -0,0 +1 @@
+__version__ = "0.10.1"

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/cf_xarray/accessor.py

@@ -18,7 +18,6 @@ from typing import (
     Any,
     Literal,
     TypeVar,
-    Union,
     cast,
     overload,
 )
@@ -31,7 +30,7 @@ from xarray.core.resample import Resample
 from xarray.core.rolling import Coarsen, Rolling
 from xarray.core.weighted import Weighted
 
-from . import sgrid
+from . import parametric, sgrid
 from .criteria import (
     _DSG_ROLES,
     _GEOMETRY_TYPES,
@@ -89,7 +88,7 @@ ATTRS["time"] = ATTRS["T"]
 ATTRS["vertical"] = ATTRS["Z"]
 
 # Type for Mapper functions
-Mapper = Callable[[Union[DataArray, Dataset], Hashable], list[Hashable]]
+Mapper = Callable[[DataArray | Dataset, Hashable], list[Hashable]]
 
 # Type for decorators
 F = TypeVar("F", bound=Callable[..., Any])
@@ -538,7 +537,7 @@ def _get_coords(obj: DataArray | Dataset, key: Hashable) -> list[Hashable]:
 def _variables(func: F) -> F:
     @functools.wraps(func)
     def wrapper(obj: DataArray | Dataset, key: Hashable) -> list[DataArray]:
-        return [obj[k] for k in func(obj, key)]  # type: ignore[misc]
+        return [obj[k] for k in func(obj, key)]
 
     return cast(F, wrapper)
 
@@ -681,7 +680,7 @@ def _getattr(
             None,
         ):
             raise AttributeError(
-                f"{obj.__class__.__name__+'.cf'!r} object has no attribute {attr!r}"
+                f"{obj.__class__.__name__ + '.cf'!r} object has no attribute {attr!r}"
             ) from None
         raise AttributeError(
             f"{attr!r} is not a valid attribute on the underlying xarray object."
@@ -1150,9 +1149,10 @@ def create_flag_dict(da) -> Mapping[Hashable, FlagParam]:
         )
 
     flag_params = tuple(
-        FlagParam(mask, value) for mask, value in zip(flag_masks, flag_values)
+        FlagParam(mask, value)
+        for mask, value in zip(flag_masks, flag_values, strict=False)
     )
-    return dict(zip(flag_meanings, flag_params))
+    return dict(zip(flag_meanings, flag_params, strict=False))
 
 
 class CFAccessor:
@@ -1368,13 +1368,17 @@ class CFAccessor:
         kwargs: dict[str, Any] | None = None,
     ):
         if coords is not None:
-            if isinstance(coords, (Hashable, DataArray)):
+            if isinstance(coords, Hashable | DataArray):
                 coords_iter: Iterable[Hashable | DataArray] = [coords]
             else:
                 coords_iter = coords
             coords = [
                 apply_mapper(
-                    [_single(_get_coords)], self._obj, v, error=False, default=[v]  # type: ignore[arg-type]
+                    [_single(_get_coords)],  # type:ignore[arg-type]
+                    self._obj,
+                    v,
+                    error=False,
+                    default=[v],
                 )[0]
                 for v in coords_iter
             ]
@@ -1385,7 +1389,11 @@ class CFAccessor:
                 reduce_dims_iter = list(reduce_dims)
             reduce_dims = [
                 apply_mapper(
-                    [_single(_get_dims)], self._obj, v, error=False, default=[v]  # type: ignore[arg-type]
+                    [_single(_get_dims)],  # type:ignore[arg-type]
+                    self._obj,
+                    v,
+                    error=False,
+                    default=[v],
                 )[0]
                 for v in reduce_dims_iter
             ]
@@ -2754,18 +2762,13 @@ class CFDatasetAccessor(CFAccessor):
         """
         ds = self._obj
 
-        requirements = {
-            "ocean_s_coordinate_g1": {"depth_c", "depth", "s", "C", "eta"},
-            "ocean_s_coordinate_g2": {"depth_c", "depth", "s", "C", "eta"},
-            "ocean_sigma_coordinate": {"sigma", "eta", "depth"},
-        }
-
         allterms = self.formula_terms
+
         for dim in allterms:
             if prefix is None:
-                assert (
-                    outnames is not None
-                ), "if prefix is None, outnames must be provided"
+                assert outnames is not None, (
+                    "if prefix is None, outnames must be provided"
+                )
                 # set outnames here
                 try:
                     zname = outnames[dim]
@@ -2782,6 +2785,7 @@ class CFDatasetAccessor(CFAccessor):
                 suffix = dim.split("_")
                 zname = f"{prefix}_" + "_".join(suffix[1:])
 
+            # never touched, if standard name is missing it's not included in allterms
             if "standard_name" not in ds[dim].attrs:
                 continue
             stdname = ds[dim].attrs["standard_name"]
@@ -2790,46 +2794,23 @@ class CFDatasetAccessor(CFAccessor):
             terms = {}
             for key, value in allterms[dim].items():
                 if value not in ds:
+                    # is this ever hit, if variable is missing it's missing in decoded allterms
                     raise KeyError(
                         f"Variable {value!r} is required to decode coordinate for {dim!r}"
                         " but it is absent in the Dataset."
                     )
-                terms[key] = ds[value]
-
-            absent_terms = requirements[stdname] - set(terms)
-            if absent_terms:
-                raise KeyError(f"Required terms {absent_terms} absent in dataset.")
-
-            if stdname == "ocean_s_coordinate_g1":
-                # S(k,j,i) = depth_c * s(k) + (depth(j,i) - depth_c) * C(k)
-                S = (
-                    terms["depth_c"] * terms["s"]
-                    + (terms["depth"] - terms["depth_c"]) * terms["C"]
-                )
-
-                # z(n,k,j,i) = S(k,j,i) + eta(n,j,i) * (1 + S(k,j,i) / depth(j,i))
-                ztemp = S + terms["eta"] * (1 + S / terms["depth"])
+                # keys should be case insensitive
+                terms[key.lower()] = ds[value]
 
-            elif stdname == "ocean_s_coordinate_g2":
-                # make sure all necessary terms are present in terms
-                # (depth_c * s(k) + depth(j,i) * C(k)) / (depth_c + depth(j,i))
-                S = (terms["depth_c"] * terms["s"] + terms["depth"] * terms["C"]) / (
-                    terms["depth_c"] + terms["depth"]
-                )
-
-                # z(n,k,j,i) = eta(n,j,i) + (eta(n,j,i) + depth(j,i)) * S(k,j,i)
-                ztemp = terms["eta"] + (terms["eta"] + terms["depth"]) * S
-
-            elif stdname == "ocean_sigma_coordinate":
-                # z(n,k,j,i) = eta(n,j,i) + sigma(k)*(depth(j,i)+eta(n,j,i))
-                ztemp = terms["eta"] + terms["sigma"] * (terms["depth"] + terms["eta"])
-
-            else:
+            try:
+                transform = parametric.TRANSFORM_FROM_STDNAME[stdname]
+            except KeyError:
+                # Should occur since stdname is check before
                 raise NotImplementedError(
-                    f"Coordinate function for {stdname!r} not implemented yet. Contributions welcome!"
-                )
+                    f"Coordinate function for {stdname!r} not implmented yet. Contributions welcome!"
+                ) from None
 
-            ds.coords[zname] = ztemp
+            ds.coords[zname] = transform.from_terms(terms)
 
 
 @xr.register_dataarray_accessor("cf")
@@ -3024,7 +3005,7 @@ class CFDataArrayAccessor(CFAccessor):
             x = self._obj.astype("i")
             bit_comp = x & bit_mask
 
-            for i, (flag, value) in enumerate(zip(flags_reduced, values)):
+            for i, (flag, value) in enumerate(zip(flags_reduced, values, strict=False)):
                 bit = bit_comp.isel(_mask=i)
                 if value is not None:
                     out[flag] = bit == value

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/cf_xarray/coding.py

@@ -46,7 +46,7 @@ def encode_multi_index_as_compress(ds, idxnames=None):
     encoded = ds.reset_index(idxnames)
     for idxname in idxnames:
         mindex = ds.indexes[idxname]
-        coords = dict(zip(mindex.names, mindex.levels))
+        coords = dict(zip(mindex.names, mindex.levels, strict=False))
         encoded.update(coords)
         for c in coords:
             encoded[c].attrs = ds[c].attrs
@@ -112,13 +112,16 @@ def decode_compress_to_multi_index(encoded, idxnames=None):
 
             variables = {
                 dim: encoded[dim].isel({dim: xr.Variable(data=index, dims=idxname)})
-                for dim, index in zip(names, indices)
+                for dim, index in zip(names, indices, strict=False)
             }
             decoded = decoded.assign_coords(variables).set_xindex(
                 names, PandasMultiIndex
             )
         except ImportError:
-            arrays = [encoded[dim].data[index] for dim, index in zip(names, indices)]
+            arrays = [
+                encoded[dim].data[index]
+                for dim, index in zip(names, indices, strict=False)
+            ]
             mindex = pd.MultiIndex.from_arrays(arrays, names=names)
             decoded.coords[idxname] = mindex
 

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/cf_xarray/datasets.py

@@ -21,15 +21,14 @@ ds_with_tuple = airds.rename({"air": (1, 2, 3)})
 
 # POM dataset
 pomds = xr.Dataset()
+# fmt: off
 pomds["sigma"] = (
-    # fmt: off
     "sigma",
     [-0.983333, -0.95    , -0.916667, -0.883333, -0.85    , -0.816667,
      -0.783333, -0.75    , -0.716667, -0.683333, -0.65    , -0.616667,
      -0.583333, -0.55    , -0.516667, -0.483333, -0.45    , -0.416667,
      -0.383333, -0.35    , -0.316667, -0.283333, -0.25    , -0.216667,
      -0.183333, -0.15    , -0.116667, -0.083333, -0.05    , -0.016667],
-    # fmt: on
     {
         "units": "sigma_level",
         "long_name": "Sigma Stretched Vertical Coordinate at Nodes",
@@ -38,6 +37,7 @@ pomds["sigma"] = (
         "formula_terms": "sigma: sigma eta: zeta depth: depth",
     }
 )
+# fmt: on
 pomds["depth"] = 175.0
 pomds["zeta"] = ("ocean_time", [-0.155356, -0.127435])
 
@@ -109,15 +109,14 @@ multiple["v2"] = (("x2", "y2"), np.ones((10, 5)) * 15)
 
 
 romsds = xr.Dataset()
+# fmt: off
 romsds["s_rho"] = (
-    # fmt: off
     "s_rho",
     [-0.983333, -0.95    , -0.916667, -0.883333, -0.85    , -0.816667,
      -0.783333, -0.75    , -0.716667, -0.683333, -0.65    , -0.616667,
      -0.583333, -0.55    , -0.516667, -0.483333, -0.45    , -0.416667,
      -0.383333, -0.35    , -0.316667, -0.283333, -0.25    , -0.216667,
      -0.183333, -0.15    , -0.116667, -0.083333, -0.05    , -0.016667],
-    # fmt: on
     {
         "long_name": "S-coordinate at RHO-points",
         "valid_min": -1.0,
@@ -125,13 +124,14 @@ romsds["s_rho"] = (
         "standard_name": "ocean_s_coordinate_g2",
         "formula_terms": "s: s_rho C: Cs_r eta: zeta depth: h depth_c: hc",
         "field": "s_rho, scalar",
-    }
+    },
 )
+# fmt: on
 romsds.coords["hc"] = 20.0
 romsds.coords["h"] = 603.9
 romsds.coords["Vtransform"] = 2.0
+# fmt: off
 romsds.coords["Cs_r"] = (
-    # fmt: off
     "s_rho",
     [-9.33010396e-01, -8.09234736e-01, -6.98779853e-01, -6.01008926e-01,
      -5.15058562e-01, -4.39938913e-01, -3.74609181e-01, -3.18031817e-01,
@@ -141,8 +141,8 @@ romsds.coords["Cs_r"] = (
      -2.53860004e-02, -1.95414261e-02, -1.46880431e-02, -1.06952600e-02,
      -7.45515186e-03, -4.87981407e-03, -2.89916971e-03, -1.45919898e-03,
      -5.20560097e-04, -5.75774004e-05],
-    # fmt: on
 )
+# fmt: on
 romsds["zeta"] = ("ocean_time", [-0.155356, -0.127435])
 romsds["temp"] = (
     ("ocean_time", "s_rho"),

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/cf_xarray/formatting.py

@@ -268,14 +268,14 @@ def _format_flags(accessor, rich):
         table.add_column("Value", justify="right")
         table.add_column("Bits", justify="center")
 
-        for val, bit, key in zip(value_text, bit_text, flag_dict):
+        for val, bit, key in zip(value_text, bit_text, flag_dict, strict=False):
             table.add_row(_format_cf_name(key, rich), val, bit)
 
         return table
 
     else:
         rows = []
-        for val, bit, key in zip(value_text, bit_text, flag_dict):
+        for val, bit, key in zip(value_text, bit_text, flag_dict, strict=False):
             rows.append(
                 f"{TAB}{_format_cf_name(key, rich):>{key_width}}: {TAB} {val} {bit}"
             )

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/cf_xarray/geometry.py

@@ -4,6 +4,7 @@ import copy
 from collections import ChainMap
 from collections.abc import Hashable, Sequence
 from dataclasses import dataclass
+from typing import TYPE_CHECKING
 
 import numpy as np
 import pandas as pd
@@ -21,6 +22,9 @@ __all__ = [
 ]
 
 
+if TYPE_CHECKING:
+    from shapely import MultiPoint, Point
+
 # Useful convention language:
 # 1. Whether linked to normal CF space-time coordinates with a nodes attribute or not, inclusion of such coordinates is
 #    recommended to maintain backward compatibility with software that has not implemented geometry capabilities.
@@ -324,7 +328,7 @@ def encode_geometries(ds: xr.Dataset):
             # TODO: this is incomplete. It works for vector data cubes where one of the geometry vars
             # is a dimension coordinate.
             if name in var.dims:
-                var = var.copy()
+                var = var.copy(deep=False)
                 var._attrs = copy.deepcopy(var._attrs)
                 var.attrs["geometry"] = container_name
                 # The grid_mapping and coordinates attributes can be carried by the geometry container
@@ -547,7 +551,11 @@ def cf_to_shapely(ds: xr.Dataset, *, container: Hashable = GEOMETRY_CONTAINER_NA
     return geometries.rename("geometry")
 
 
-def points_to_cf(pts: xr.DataArray | Sequence, *, names: GeometryNames | None = None):
+def points_to_cf(
+    pts: xr.DataArray | Sequence[Point | MultiPoint],
+    *,
+    names: GeometryNames | None = None,
+):
     """Get a list of points (shapely.geometry.[Multi]Point) and return a CF-compliant geometry dataset.
 
     Parameters
@@ -563,6 +571,7 @@ def points_to_cf(pts: xr.DataArray | Sequence, *, names: GeometryNames | None =
     """
     from shapely.geometry import MultiPoint
 
+    pts_: Sequence[Point | MultiPoint]
     if isinstance(pts, xr.DataArray):
         # TODO: Fix this hardcoding
         if pts.ndim != 1:

cf_xarray-0.10.1/cf_xarray/groupers.py

@@ -0,0 +1,34 @@
+from dataclasses import dataclass
+
+import numpy as np
+import pandas as pd
+from xarray.groupers import EncodedGroups, UniqueGrouper
+
+
+@dataclass
+class FlagGrouper(UniqueGrouper):
+    def factorize(self, group) -> EncodedGroups:
+        if "flag_values" not in group.attrs or "flag_meanings" not in group.attrs:
+            raise ValueError(
+                "FlagGrouper can only be used with flag variables that have"
+                "`flag_values` and `flag_meanings` specified in attrs."
+            )
+
+        values = np.array(group.attrs["flag_values"])
+        full_index = pd.Index(group.attrs["flag_meanings"].split(" "))
+
+        self.labels = values
+
+        # TODO: we could optimize here, since `group` is already factorized,
+        # but there are subtleties. For example, the attrs must be up to date,
+        # any value that is not in flag_values will cause an error, etc.
+        ret = super().factorize(group)
+
+        ret.codes.attrs.pop("flag_values")
+        ret.codes.attrs.pop("flag_meanings")
+
+        return EncodedGroups(
+            codes=ret.codes,
+            full_index=full_index,
+            group_indices=ret.group_indices,
+        )

{cf_xarray-0.9.5 → cf_xarray-0.10.1}/cf_xarray/options.py

@@ -38,7 +38,6 @@ class set_options:  # numpydoc ignore=PR01,PR02
     >>> ds = xr.Dataset({"elev": np.arange(1000)})
     >>> with cf_xarray.set_options(custom_criteria=my_custom_criteria):
     ...     xr.testing.assert_identical(ds["elev"], ds.cf["ssh"])
-    ...
 
     Or to set global options: