Merge branch 'main' into flox-preserve-dtype

* main: (26 commits)
  Forbid modifying names of DataTree objects with parents (pydata#9494)
  DAS-2155 - Merge datatree documentation into main docs. (pydata#9033)
  Make illegal path-like variable names when constructing a DataTree from a Dataset (pydata#9378)
  Ensure TreeNode doesn't copy in-place (pydata#9482)
  `open_groups` for zarr backends (pydata#9469)
  Update pyproject.toml (pydata#9484)
  New whatsnew section (pydata#9483)
  Release notes for v2024.09.0 (pydata#9480)
  Fix `DataTree.coords.__setitem__` by adding `DataTreeCoordinates` class (pydata#9451)
  Rename DataTree's "ds" and "data" to "dataset" (pydata#9476)
  Update DataTree repr to indicate inheritance (pydata#9470)
  Bump pypa/gh-action-pypi-publish in the actions group (pydata#9460)
  Repo checker (pydata#9450)
  Add days_in_year and decimal_year to dt accessor (pydata#9105)
  remove parent argument from DataTree.__init__ (pydata#9465)
  Fix inheritance in DataTree.copy() (pydata#9457)
  Implement `DataTree.__delitem__` (pydata#9453)
  Add ASV for datatree.from_dict (pydata#9459)
  Make the first argument in DataTree.from_dict positional only (pydata#9446)
  Fix typos across the code, doc and comments (pydata#9443)
  ...

Author: dcherian

.github/workflows/ci-additional.yaml

@@ -81,8 +81,7 @@ jobs:
           #
           # If dependencies emit warnings we can't do anything about, add ignores to
           # `xarray/tests/__init__.py`.
-          # [MHS, 01/25/2024] Skip datatree_ documentation remove after #8572
-          python -m pytest --doctest-modules xarray --ignore xarray/tests --ignore xarray/datatree_ -Werror
+          python -m pytest --doctest-modules xarray --ignore xarray/tests -Werror
 
   mypy:
     name: Mypy

.github/workflows/pypi-release.yaml

@@ -88,7 +88,7 @@ jobs:
           path: dist
       - name: Publish package to TestPyPI
         if: github.event_name == 'push'
-        uses: pypa/gh-action-pypi-publish@v1.10.0
+        uses: pypa/gh-action-pypi-publish@v1.10.1
         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/gh-action-pypi-publish@v1.10.0
+        uses: pypa/gh-action-pypi-publish@v1.10.1
         with:
           verbose: true

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 # https://pre-commit.com/
 ci:
     autoupdate_schedule: monthly
-exclude: 'xarray/datatree_.*'
+    autoupdate_commit_msg: 'Update pre-commit hooks'
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.6.0

MANIFEST.in

@@ -7,8 +7,6 @@
 import pandas as pd
 
 import xarray as xr
-from xarray.backends.api import open_datatree
-from xarray.core.datatree import DataTree
 
 from . import _skip_slow, parameterized, randint, randn, requires_dask
 
@@ -556,7 +554,7 @@ def make_datatree(self, nchildren=10):
             for group in range(self.nchildren)
         }
         dtree = root | nested_tree1 | nested_tree2 | nested_tree3
-        self.dtree = DataTree.from_dict(dtree)
+        self.dtree = xr.DataTree.from_dict(dtree)
 
 
 class IOReadDataTreeNetCDF4(IONestedDataTree):
@@ -574,10 +572,10 @@ def setup(self):
         dtree.to_netcdf(filepath=self.filepath)
 
     def time_load_datatree_netcdf4(self):
-        open_datatree(self.filepath, engine="netcdf4").load()
+        xr.open_datatree(self.filepath, engine="netcdf4").load()
 
     def time_open_datatree_netcdf4(self):
-        open_datatree(self.filepath, engine="netcdf4")
+        xr.open_datatree(self.filepath, engine="netcdf4")
 
 
 class IOWriteNetCDFDask:
@@ -724,7 +722,7 @@ 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/dataset_io.py

@@ -0,0 +1,15 @@
+import xarray as xr
+from xarray.core.datatree import DataTree
+
+
+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}": xr.Dataset({"a": 1}) for i in range(100)}
+
+    def time_from_dict_few(self):
+        DataTree.from_dict(self.d_few)
+
+    def time_from_dict_many(self):
+        DataTree.from_dict(self.d_many)

asv_bench/benchmarks/datatree.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/groupby.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(

asv_bench/benchmarks/rolling.py

@@ -11,6 +11,6 @@ dependencies:
   - pytest-env
   - pytest-xdist
   - pytest-timeout
-  - numpy=1.23
+  - numpy=1.24
   - packaging=23.1
-  - pandas=2.0
+  - pandas=2.1

ci/requirements/bare-minimum.yml

@@ -39,7 +39,8 @@ dependencies:
   - sphinx-copybutton
   - sphinx-design
   - sphinx-inline-tabs
-  - sphinx>=5.0
+  - sphinx>=5.0,<7.0 # https://github.com/executablebooks/sphinx-book-theme/issues/749
+  - sphinxcontrib-srclinks
   - sphinx-remove-toctrees
   - sphinxext-opengraph
   - sphinxext-rediraffe