Merge branch 'main' into eschalk/make-illegal-path-like-variable-names-when-dt-from-ds

Author: TomNicholas

.github/workflows/pypi-release.yaml

@@ -88,7 +88,7 @@ jobs:
           path: dist
       - name: Publish package to TestPyPI
         if: github.event_name == 'push'
-        uses: pypa/[email protected].0
+        uses: pypa/[email protected].1
         with:
           repository_url: https://test.pypi.org/legacy/
           verbose: true
@@ -111,6 +111,6 @@ jobs:
           name: releases
           path: dist
       - name: Publish package to PyPI
-        uses: pypa/[email protected].0
+        uses: pypa/[email protected].1
         with:
           verbose: true

.pre-commit-config.yaml

@@ -1,6 +1,7 @@
 # https://pre-commit.com/
 ci:
     autoupdate_schedule: monthly
+    autoupdate_commit_msg: 'Update pre-commit hooks'
 exclude: 'xarray/datatree_.*'
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks

asv_bench/benchmarks/dataset_io.py

@@ -724,7 +724,7 @@ class PerformanceBackend(xr.backends.BackendEntrypoint):
             def open_dataset(
                 self,
                 filename_or_obj: str | os.PathLike | None,
-                drop_variables: tuple[str] = None,
+                drop_variables: tuple[str, ...] = None,
                 *,
                 mask_and_scale=True,
                 decode_times=True,

asv_bench/benchmarks/datatree.py

@@ -6,7 +6,7 @@ class Datatree:
     def setup(self):
         run1 = DataTree.from_dict({"run1": xr.Dataset({"a": 1})})
         self.d_few = {"run1": run1}
-        self.d_many = {f"run{i}": run1.copy() for i in range(100)}
+        self.d_many = {f"run{i}": xr.Dataset({"a": 1}) for i in range(100)}
 
     def time_from_dict_few(self):
         DataTree.from_dict(self.d_few)

asv_bench/benchmarks/groupby.py

@@ -174,7 +174,7 @@ def setup(self, use_cftime, use_flox):
         # GH9426 - deep-copying CFTime object arrays is weirdly slow
         asda = xr.DataArray(time)
         labeled_time = []
-        for year, month in zip(asda.dt.year, asda.dt.month):
+        for year, month in zip(asda.dt.year, asda.dt.month, strict=True):
             labeled_time.append(cftime.datetime(year, month, 1))
 
         self.da = xr.DataArray(

asv_bench/benchmarks/rolling.py

@@ -64,7 +64,7 @@ def time_rolling_long(self, func, pandas, use_bottleneck):
     def time_rolling_np(self, window_, min_periods, use_bottleneck):
         with xr.set_options(use_bottleneck=use_bottleneck):
             self.ds.rolling(x=window_, center=False, min_periods=min_periods).reduce(
-                getattr(np, "nansum")
+                np.nansum
             ).load()
 
     @parameterized(

doc/user-guide/testing.rst

@@ -193,7 +193,7 @@ different type:
 
 .. ipython:: python
 
-    def sparse_random_arrays(shape: tuple[int]) -> sparse._coo.core.COO:
+    def sparse_random_arrays(shape: tuple[int, ...]) -> sparse._coo.core.COO:
         """Strategy which generates random sparse.COO arrays"""
         if shape is None:
             shape = npst.array_shapes()

doc/whats-new.rst

@@ -14,16 +14,50 @@ What's New
 
     np.random.seed(123456)
 
+.. _whats-new.2024.09.1:
 
-.. _whats-new.2024.07.1:
-
-v2024.07.1 (unreleased)
+v2024.09.1 (unreleased)
 -----------------------
 
 New Features
 ~~~~~~~~~~~~
 
-- Add :py:attr:`~core.accessor_dt.DatetimeAccessor.days_in_year` and :py:attr:`~core.accessor_dt.DatetimeAccessor.decimal_year` to the Datetime accessor on DataArrays. (:pull:`9105`).
+
+Breaking changes
+~~~~~~~~~~~~~~~~
+
+
+Deprecations
+~~~~~~~~~~~~
+
+
+Bug fixes
+~~~~~~~~~
+
+
+Documentation
+~~~~~~~~~~~~~
+
+
+Internal Changes
+~~~~~~~~~~~~~~~~
+
+
+.. _whats-new.2024.09.0:
+
+v2024.09.0 (Sept 11, 2024)
+--------------------------
+This release drops support for Python 3.9, and adds support for grouping by :ref:`multiple arrays <groupby.multiple>`, while providing numerous performance improvements and bug fixes.
+
+Thanks to the 33 contributors to this release:
+Alfonso Ladino, Andrew Scherer, Anurag Nayak, David Hoese, Deepak Cherian, Diogo Teles Sant'Anna, Dom, Elliott Sales de Andrade, Eni, Holly Mandel, Illviljan, Jack Kelly, Julius Busecke, Justus Magin, Kai Mühlbauer, Manish Kumar Gupta, Matt Savoie, Maximilian Roos, Michele Claus, Miguel Jimenez, Niclas Rieger, Pascal Bourgault, Philip Chmielowiec, Spencer Clark, Stephan Hoyer, Tao Xin, Tiago Sanona, TimothyCera-NOAA, Tom Nicholas, Tom White, Virgile Andreani, oliverhiggs and tiago
+
+New Features
+~~~~~~~~~~~~
+
+- Add :py:attr:`~core.accessor_dt.DatetimeAccessor.days_in_year` and
+  :py:attr:`~core.accessor_dt.DatetimeAccessor.decimal_year` to the
+  ``DatetimeAccessor`` on ``xr.DataArray``. (:pull:`9105`).
   By `Pascal Bourgault <https://github.com/aulemahal>`_.
 
 Performance
@@ -38,6 +72,8 @@ Performance
   By `Deepak Cherian <https://github.com/dcherian>`_.
 - Allow data variable specific ``constant_values`` in the dataset ``pad`` function (:pull:`9353``).
   By `Tiago Sanona <https://github.com/tsanona>`_.
+- Speed up grouping by avoiding deep-copy of non-dimension coordinates (:issue:`9426`, :pull:`9393`)
+  By `Deepak Cherian <https://github.com/dcherian>`_.
 
 Breaking changes
 ~~~~~~~~~~~~~~~~
@@ -61,11 +97,6 @@ Breaking changes
     zarr                    2.14      2.16
   ===================== =========  =======
 
-
-Deprecations
-~~~~~~~~~~~~
-
-
 Bug fixes
 ~~~~~~~~~
 
@@ -93,24 +124,12 @@ Bug fixes
   (:issue:`9408`, :pull:`9413`).
   By `Oliver Higgs <https://github.com/oliverhiggs>`_.
 
-Performance
-~~~~~~~~~~~
-
-- Speed up grouping by avoiding deep-copy of non-dimension coordinates (:issue:`9426`, :pull:`9393`)
-  By `Deepak Cherian <https://github.com/dcherian>`_.
-
-Documentation
-~~~~~~~~~~~~~
-
-
 Internal Changes
 ~~~~~~~~~~~~~~~~
 
 - Re-enable testing ``pydap`` backend with ``numpy>=2`` (:pull:`9391`).
   By `Miguel Jimenez <https://github.com/Mikejmnez>`_ .
 
-
-
 .. _whats-new.2024.07.0:
 
 v2024.07.0 (Jul 30, 2024)

properties/test_pandas_roundtrip.py

@@ -80,7 +80,7 @@ def test_roundtrip_dataarray(data, arr) -> None:
             tuple
         )
     )
-    coords = {name: np.arange(n) for (name, n) in zip(names, arr.shape)}
+    coords = {name: np.arange(n) for (name, n) in zip(names, arr.shape, strict=True)}
     original = xr.DataArray(arr, dims=names, coords=coords)
     roundtripped = xr.DataArray(original.to_pandas())
     xr.testing.assert_identical(original, roundtripped)

pyproject.toml

@@ -42,7 +42,7 @@ dev = [
   "ruff",
   "xarray[complete]",
 ]
-io = ["netCDF4", "h5netcdf", "scipy", 'pydap; python_version<"3.10"', "zarr", "fsspec", "cftime", "pooch"]
+io = ["netCDF4", "h5netcdf", "scipy", 'pydap; python_version<"3.10"', "zarr<3", "fsspec", "cftime", "pooch"]
 parallel = ["dask[complete]"]
 viz = ["matplotlib", "seaborn", "nc-time-axis"]
 
@@ -84,14 +84,13 @@ source = ["xarray"]
 exclude_lines = ["pragma: no cover", "if TYPE_CHECKING"]
 
 [tool.mypy]
-enable_error_code = "redundant-self"
+enable_error_code = ["ignore-without-code", "redundant-self", "redundant-expr"]
 exclude = [
   'build',
   'xarray/util/generate_.*\.py',
   'xarray/datatree_/doc/.*\.py',
 ]
 files = "xarray"
-show_error_codes = true
 show_error_context = true
 warn_redundant_casts = true
 warn_unused_configs = true
@@ -240,7 +239,6 @@ extend-exclude = [
   "doc",
   "_typed_ops.pyi",
 ]
-target-version = "py310"
 
 [tool.ruff.lint]
 # E402: module level import not at top of file
@@ -249,13 +247,13 @@ target-version = "py310"
 extend-safe-fixes = [
   "TID252", # absolute imports
 ]
-ignore = [
+extend-ignore = [
   "E402",
   "E501",
   "E731",
   "UP007",
 ]
-select = [
+extend-select = [
   "F", # Pyflakes
   "E", # Pycodestyle
   "W",

xarray/backends/api.py

@@ -51,7 +51,7 @@
     try:
         from dask.delayed import Delayed
     except ImportError:
-        Delayed = None  # type: ignore
+        Delayed = None  # type: ignore[assignment, misc]
     from io import BufferedIOBase
 
     from xarray.backends.common import BackendEntrypoint
@@ -1113,7 +1113,7 @@ def open_mfdataset(
             list(combined_ids_paths.keys()),
             list(combined_ids_paths.values()),
         )
-    elif combine == "by_coords" and concat_dim is not None:
+    elif concat_dim is not None:
         raise ValueError(
             "When combine='by_coords', passing a value for `concat_dim` has no "
             "effect. To manually combine along a specific dimension you should "
@@ -1432,7 +1432,7 @@ def to_netcdf(
             store.sync()
             return target.getvalue()
     finally:
-        if not multifile and compute:
+        if not multifile and compute:  # type: ignore[redundant-expr]
             store.close()
 
     if not compute:
@@ -1585,8 +1585,9 @@ def save_mfdataset(
                 multifile=True,
                 **kwargs,
             )
-            for ds, path, group in zip(datasets, paths, groups)
-        ]
+            for ds, path, group in zip(datasets, paths, groups, strict=True)
+        ],
+        strict=True,
     )
 
     try:
@@ -1600,7 +1601,10 @@ def save_mfdataset(
         import dask
 
         return dask.delayed(
-            [dask.delayed(_finalize_store)(w, s) for w, s in zip(writes, stores)]
+            [
+                dask.delayed(_finalize_store)(w, s)
+                for w, s in zip(writes, stores, strict=True)
+            ]
         )
 
 

xarray/backends/common.py

@@ -431,7 +431,7 @@ def set_dimensions(self, variables, unlimited_dims=None):
         for v in unlimited_dims:  # put unlimited_dims first
             dims[v] = None
         for v in variables.values():
-            dims.update(dict(zip(v.dims, v.shape)))
+            dims.update(dict(zip(v.dims, v.shape, strict=True)))
 
         for dim, length in dims.items():
             if dim in existing_dims and length != existing_dims[dim]:

xarray/backends/file_manager.py

@@ -276,7 +276,7 @@ def __getstate__(self):
     def __setstate__(self, state) -> None:
         """Restore from a pickle."""
         opener, args, mode, kwargs, lock, manager_id = state
-        self.__init__(  # type: ignore
+        self.__init__(  # type: ignore[misc]
             opener, *args, mode=mode, kwargs=kwargs, lock=lock, manager_id=manager_id
         )
 

xarray/backends/h5netcdf_.py

@@ -208,7 +208,9 @@ def open_store_variable(self, name, var):
             "shuffle": var.shuffle,
         }
         if var.chunks:
-            encoding["preferred_chunks"] = dict(zip(var.dimensions, var.chunks))
+            encoding["preferred_chunks"] = dict(
+                zip(var.dimensions, var.chunks, strict=True)
+            )
         # Convert h5py-style compression options to NetCDF4-Python
         # style, if possible
         if var.compression == "gzip":

xarray/backends/netCDF4_.py

@@ -278,7 +278,9 @@ def _extract_nc4_variable_encoding(
         chunksizes = encoding["chunksizes"]
         chunks_too_big = any(
             c > d and dim not in unlimited_dims
-            for c, d, dim in zip(chunksizes, variable.shape, variable.dims)
+            for c, d, dim in zip(
+                chunksizes, variable.shape, variable.dims, strict=False
+            )
         )
         has_original_shape = "original_shape" in encoding
         changed_shape = (
@@ -446,7 +448,9 @@ def open_store_variable(self, name: str, var):
             else:
                 encoding["contiguous"] = False
                 encoding["chunksizes"] = tuple(chunking)
-                encoding["preferred_chunks"] = dict(zip(var.dimensions, chunking))
+                encoding["preferred_chunks"] = dict(
+                    zip(var.dimensions, chunking, strict=True)
+                )
         # TODO: figure out how to round-trip "endian-ness" without raising
         # warnings from netCDF4
         # encoding['endian'] = var.endian()

xarray/backends/plugins.py

@@ -199,7 +199,7 @@ def get_backend(engine: str | type[BackendEntrypoint]) -> BackendEntrypoint:
                 "https://docs.xarray.dev/en/stable/getting-started-guide/installing.html"
             )
         backend = engines[engine]
-    elif isinstance(engine, type) and issubclass(engine, BackendEntrypoint):
+    elif issubclass(engine, BackendEntrypoint):
         backend = engine()
     else:
         raise TypeError(