Merge branch 'main' into state-machine

* main: (26 commits)
  [pre-commit.ci] pre-commit autoupdate (pydata#8900)
  Bump the actions group with 1 update (pydata#8896)
  New empty whatsnew entry (pydata#8899)
  Update reference to 'Weighted quantile estimators' (pydata#8898)
  2024.03.0: Add whats-new (pydata#8891)
  Add typing to test_groupby.py (pydata#8890)
  Avoid in-place multiplication of a large value to an array with small integer dtype (pydata#8867)
  Check for aligned chunks when writing to existing variables (pydata#8459)
  Add dt.date to plottable types (pydata#8873)
  Optimize writes to existing Zarr stores. (pydata#8875)
  Allow multidimensional variable with same name as dim when constructing dataset via coords (pydata#8886)
  Don't allow overwriting indexes with region writes (pydata#8877)
  Migrate datatree.py module into xarray.core. (pydata#8789)
  warn and return bytes undecoded in case of UnicodeDecodeError in h5netcdf-backend (pydata#8874)
  groupby: Dispatch quantile to flox. (pydata#8720)
  Opt out of auto creating index variables (pydata#8711)
  Update docs on view / copies (pydata#8744)
  Handle .oindex and .vindex for the PandasMultiIndexingAdapter and PandasIndexingAdapter (pydata#8869)
  numpy 2.0 copy-keyword and trapz vs trapezoid (pydata#8865)
  upstream-dev CI: Fix interp and cumtrapz (pydata#8861)
  ...

Author: dcherian

.github/workflows/ci-additional.yaml

@@ -127,7 +127,7 @@ jobs:
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report xarray/
 
       - name: Upload mypy coverage to Codecov
-        uses: codecov/[email protected].0
+        uses: codecov/[email protected].1
         with:
           file: mypy_report/cobertura.xml
           flags: mypy
@@ -181,7 +181,7 @@ jobs:
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report xarray/
 
       - name: Upload mypy coverage to Codecov
-        uses: codecov/[email protected].0
+        uses: codecov/[email protected].1
         with:
           file: mypy_report/cobertura.xml
           flags: mypy39
@@ -242,7 +242,7 @@ jobs:
           python -m pyright xarray/
 
       - name: Upload pyright coverage to Codecov
-        uses: codecov/[email protected].0
+        uses: codecov/[email protected].1
         with:
           file: pyright_report/cobertura.xml
           flags: pyright
@@ -301,7 +301,7 @@ jobs:
           python -m pyright xarray/
 
       - name: Upload pyright coverage to Codecov
-        uses: codecov/[email protected].0
+        uses: codecov/[email protected].1
         with:
           file: pyright_report/cobertura.xml
           flags: pyright39

.github/workflows/ci.yaml

@@ -151,7 +151,7 @@ jobs:
           path: pytest.xml
 
       - name: Upload code coverage to Codecov
-        uses: codecov/[email protected].0
+        uses: codecov/[email protected].1
         with:
           file: ./coverage.xml
           flags: unittests

.github/workflows/upstream-dev-ci.yaml

@@ -143,7 +143,7 @@ jobs:
         run: |
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report
       - name: Upload mypy coverage to Codecov
-        uses: codecov/[email protected].0
+        uses: codecov/[email protected].1
         with:
           file: mypy_report/cobertura.xml
           flags: mypy

.pre-commit-config.yaml

@@ -13,24 +13,24 @@ repos:
       - id: mixed-line-ending
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: 'v0.2.0'
+    rev: 'v0.3.4'
     hooks:
       - id: ruff
         args: ["--fix", "--show-fixes"]
   # https://github.com/python/black#version-control-integration
   - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 24.1.1
+    rev: 24.3.0
     hooks:
       - id: black-jupyter
   - repo: https://github.com/keewis/blackdoc
     rev: v0.3.9
     hooks:
       - id: blackdoc
         exclude: "generate_aggregations.py"
-        additional_dependencies: ["black==24.1.1"]
+        additional_dependencies: ["black==24.3.0"]
       - id: blackdoc-autoupdate-black
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.8.0
+    rev: v1.9.0
     hooks:
       - id: mypy
         # Copied from setup.cfg

doc/user-guide/indexing.rst

@@ -748,7 +748,7 @@ Whether array indexing returns a view or a copy of the underlying
 data depends on the nature of the labels.
 
 For positional (integer)
-indexing, xarray follows the same rules as NumPy:
+indexing, xarray follows the same `rules`_ as NumPy:
 
 * Positional indexing with only integers and slices returns a view.
 * Positional indexing with arrays or lists returns a copy.
@@ -765,8 +765,10 @@ Whether data is a copy or a view is more predictable in xarray than in pandas, s
 unlike pandas, xarray does not produce `SettingWithCopy warnings`_. However, you
 should still avoid assignment with chained indexing.
 
-.. _SettingWithCopy warnings: https://pandas.pydata.org/pandas-docs/stable/indexing.html#returning-a-view-versus-a-copy
+Note that other operations (such as :py:meth:`~xarray.DataArray.values`) may also return views rather than copies.
 
+.. _SettingWithCopy warnings: https://pandas.pydata.org/pandas-docs/stable/indexing.html#returning-a-view-versus-a-copy
+.. _rules: https://numpy.org/doc/stable/user/basics.copies.html
 
 .. _multi-level indexing:
 

doc/whats-new.rst

@@ -15,32 +15,65 @@ What's New
     np.random.seed(123456)
 
 
-.. _whats-new.2024.03.0:
+.. _whats-new.2024.04.0:
 
-v2024.03.0 (unreleased)
+v2024.04.0 (unreleased)
 -----------------------
 
 New Features
 ~~~~~~~~~~~~
 
+
+Breaking changes
+~~~~~~~~~~~~~~~~
+
+
+Bug fixes
+~~~~~~~~~
+
+
+Internal Changes
+~~~~~~~~~~~~~~~~
+
+
+.. _whats-new.2024.03.0:
+
+v2024.03.0 (Mar 29, 2024)
+-------------------------
+
+This release brings performance improvements for grouped and resampled quantile calculations, CF decoding improvements,
+minor optimizations to distributed Zarr writes, and compatibility fixes for Numpy 2.0 and Pandas 3.0.
+
+Thanks to the 18 contributors to this release:
+Anderson Banihirwe, Christoph Hasse, Deepak Cherian, Etienne Schalk, Justus Magin, Kai Mühlbauer, Kevin Schwarzwald, Mark Harfouche, Martin, Matt Savoie, Maximilian Roos, Ray Bell, Roberto Chang, Spencer Clark, Tom Nicholas, crusaderky, owenlittlejohns, saschahofmann
+
+New Features
+~~~~~~~~~~~~
+- Partial writes to existing chunks with ``region`` or ``append_dim`` will now raise an error
+  (unless ``safe_chunks=False``); previously an error would only be raised on
+  new variables. (:pull:`8459`, :issue:`8371`, :issue:`8882`)
+  By `Maximilian Roos <https://github.com/max-sixty>`_.
+- Grouped and resampling quantile calculations now use the vectorized algorithm in ``flox>=0.9.4`` if present.
+  By `Deepak Cherian <https://github.com/dcherian>`_.
 - Do not broadcast in arithmetic operations when global option ``arithmetic_broadcast=False``
   (:issue:`6806`, :pull:`8784`).
   By `Etienne Schalk <https://github.com/etienneschalk>`_ and `Deepak Cherian <https://github.com/dcherian>`_.
 - Add the ``.oindex`` property to Explicitly Indexed Arrays for orthogonal indexing functionality. (:issue:`8238`, :pull:`8750`)
   By `Anderson Banihirwe <https://github.com/andersy005>`_.
-
 - Add the ``.vindex`` property to Explicitly Indexed Arrays for vectorized indexing functionality. (:issue:`8238`, :pull:`8780`)
   By `Anderson Banihirwe <https://github.com/andersy005>`_.
-
 - Expand use of ``.oindex`` and ``.vindex`` properties. (:pull: `8790`)
   By `Anderson Banihirwe <https://github.com/andersy005>`_ and `Deepak Cherian <https://github.com/dcherian>`_.
+- Allow creating :py:class:`xr.Coordinates` objects with no indexes (:pull:`8711`)
+  By `Benoit Bovy <https://github.com/benbovy>`_ and `Tom Nicholas
+  <https://github.com/TomNicholas>`_.
+- Enable plotting of ``datetime.dates``. (:issue:`8866`, :pull:`8873`)
+  By `Sascha Hofmann <https://github.com/saschahofmann>`_.
 
 Breaking changes
 ~~~~~~~~~~~~~~~~
-
-
-Deprecations
-~~~~~~~~~~~~
+- Don't allow overwriting index variables with ``to_zarr`` region writes. (:issue:`8589`, :pull:`8876`).
+  By `Deepak Cherian <https://github.com/dcherian>`_.
 
 
 Bug fixes
@@ -57,16 +90,29 @@ Bug fixes
   `CFMaskCoder`/`CFScaleOffsetCoder` (:issue:`2304`, :issue:`5597`,
   :issue:`7691`, :pull:`8713`, see also discussion in :pull:`7654`).
   By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
-
-Documentation
-~~~~~~~~~~~~~
-
+- Do not cast `_FillValue`/`missing_value` in `CFMaskCoder` if `_Unsigned` is provided
+  (:issue:`8844`, :pull:`8852`).
+- Adapt handling of copy keyword argument for numpy >= 2.0dev
+  (:issue:`8844`, :pull:`8851`, :pull:`8865`).
+  By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
+- Import trapz/trapezoid depending on numpy version
+  (:issue:`8844`, :pull:`8865`).
+  By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
+- Warn and return bytes undecoded in case of UnicodeDecodeError in h5netcdf-backend
+  (:issue:`5563`, :pull:`8874`).
+  By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
+- Fix bug incorrectly disallowing creation of a dataset with a multidimensional coordinate variable with the same name as one of its dims.
+  (:issue:`8884`, :pull:`8886`)
+  By `Tom Nicholas <https://github.com/TomNicholas>`_.
 
 Internal Changes
 ~~~~~~~~~~~~~~~~
 - Migrates ``treenode`` functionality into ``xarray/core`` (:pull:`8757`)
   By `Matt Savoie <https://github.com/flamingbear>`_ and `Tom Nicholas
   <https://github.com/TomNicholas>`_.
+- Migrates ``datatree`` functionality into ``xarray/core``. (:pull: `8789`)
+  By `Owen Littlejohns <https://github.com/owenlittlejohns>`_, `Matt Savoie
+  <https://github.com/flamingbear>`_ and `Tom Nicholas <https://github.com/TomNicholas>`_.
 
 
 .. _whats-new.2024.02.0:

pyproject.toml

@@ -171,7 +171,6 @@ module = [
   "xarray.tests.test_dask",
   "xarray.tests.test_dataarray",
   "xarray.tests.test_duck_array_ops",
-  "xarray.tests.test_groupby",
   "xarray.tests.test_indexing",
   "xarray.tests.test_merge",
   "xarray.tests.test_missing",

xarray/backends/api.py

@@ -69,7 +69,7 @@
     T_NetcdfTypes = Literal[
         "NETCDF4", "NETCDF4_CLASSIC", "NETCDF3_64BIT", "NETCDF3_CLASSIC"
     ]
-    from xarray.datatree_.datatree import DataTree
+    from xarray.core.datatree import DataTree
 
 DATAARRAY_NAME = "__xarray_dataarray_name__"
 DATAARRAY_VARIABLE = "__xarray_dataarray_variable__"
@@ -1562,24 +1562,19 @@ def _auto_detect_regions(ds, region, open_kwargs):
     return region
 
 
-def _validate_and_autodetect_region(
-    ds, region, mode, open_kwargs
-) -> tuple[dict[str, slice], bool]:
+def _validate_and_autodetect_region(ds, region, mode, open_kwargs) -> dict[str, slice]:
     if region == "auto":
         region = {dim: "auto" for dim in ds.dims}
 
     if not isinstance(region, dict):
         raise TypeError(f"``region`` must be a dict, got {type(region)}")
 
     if any(v == "auto" for v in region.values()):
-        region_was_autodetected = True
         if mode != "r+":
             raise ValueError(
                 f"``mode`` must be 'r+' when using ``region='auto'``, got {mode}"
             )
         region = _auto_detect_regions(ds, region, open_kwargs)
-    else:
-        region_was_autodetected = False
 
     for k, v in region.items():
         if k not in ds.dims:
@@ -1612,7 +1607,7 @@ def _validate_and_autodetect_region(
             f".drop_vars({non_matching_vars!r})"
         )
 
-    return region, region_was_autodetected
+    return region
 
 
 def _validate_datatypes_for_zarr_append(zstore, dataset):
@@ -1784,12 +1779,9 @@ def to_zarr(
             storage_options=storage_options,
             zarr_version=zarr_version,
         )
-        region, region_was_autodetected = _validate_and_autodetect_region(
-            dataset, region, mode, open_kwargs
-        )
-        # drop indices to avoid potential race condition with auto region
-        if region_was_autodetected:
-            dataset = dataset.drop_vars(dataset.indexes)
+        region = _validate_and_autodetect_region(dataset, region, mode, open_kwargs)
+        # can't modify indexed with region writes
+        dataset = dataset.drop_vars(dataset.indexes)
         if append_dim is not None and append_dim in region:
             raise ValueError(
                 f"cannot list the same dimension in both ``append_dim`` and "

xarray/backends/common.py

@@ -23,8 +23,8 @@
     from netCDF4 import Dataset as ncDataset
 
     from xarray.core.dataset import Dataset
+    from xarray.core.datatree import DataTree
     from xarray.core.types import NestedSequence
-    from xarray.datatree_.datatree import DataTree
 
 # Create a logger object, but don't add any handlers. Leave that to user code.
 logger = logging.getLogger(__name__)
@@ -137,8 +137,8 @@ def _open_datatree_netcdf(
     **kwargs,
 ) -> DataTree:
     from xarray.backends.api import open_dataset
+    from xarray.core.datatree import DataTree
     from xarray.core.treenode import NodePath
-    from xarray.datatree_.datatree import DataTree
 
     ds = open_dataset(filename_or_obj, **kwargs)
     tree_root = DataTree.from_dict({"/": ds})

xarray/backends/h5netcdf_.py

@@ -28,6 +28,7 @@
 from xarray.core import indexing
 from xarray.core.utils import (
     FrozenDict,
+    emit_user_level_warning,
     is_remote_uri,
     read_magic_number_from_file,
     try_read_magic_number_from_file_or_path,
@@ -39,7 +40,7 @@
 
     from xarray.backends.common import AbstractDataStore
     from xarray.core.dataset import Dataset
-    from xarray.datatree_.datatree import DataTree
+    from xarray.core.datatree import DataTree
 
 
 class H5NetCDFArrayWrapper(BaseNetCDF4Array):
@@ -58,21 +59,23 @@ def _getitem(self, key):
             return array[key]
 
 
-def maybe_decode_bytes(txt):
-    if isinstance(txt, bytes):
-        return txt.decode("utf-8")
-    else:
-        return txt
-
-
 def _read_attributes(h5netcdf_var):
     # GH451
     # to ensure conventions decoding works properly on Python 3, decode all
     # bytes attributes to strings
     attrs = {}
     for k, v in h5netcdf_var.attrs.items():
         if k not in ["_FillValue", "missing_value"]:
-            v = maybe_decode_bytes(v)
+            if isinstance(v, bytes):
+                try:
+                    v = v.decode("utf-8")
+                except UnicodeDecodeError:
+                    emit_user_level_warning(
+                        f"'utf-8' codec can't decode bytes for attribute "
+                        f"{k!r} of h5netcdf object {h5netcdf_var.name!r}, "
+                        f"returning bytes undecoded.",
+                        UnicodeWarning,
+                    )
         attrs[k] = v
     return attrs