Merge branch 'main' into groupby-shuffle

* main:
  Revise (pydata#9366)
  Fix rechunking to a frequency with empty bins. (pydata#9364)
  whats-new entry for dropping python 3.9 (pydata#9359)
  drop support for `python=3.9` (pydata#8937)
  Revise (pydata#9357)
  try to fix scheduled hypothesis test (pydata#9358)

.github/workflows/ci-additional.yaml

@@ -139,15 +139,15 @@ jobs:
           fail_ci_if_error: false
 
   mypy39:
-    name: Mypy 3.9
+    name: Mypy 3.10
     runs-on: "ubuntu-latest"
     needs: detect-ci-trigger
     defaults:
       run:
         shell: bash -l {0}
     env:
       CONDA_ENV_FILE: ci/requirements/environment.yml
-      PYTHON_VERSION: "3.9"
+      PYTHON_VERSION: "3.10"
 
     steps:
       - uses: actions/checkout@v4
@@ -254,7 +254,7 @@ jobs:
           fail_ci_if_error: false
 
   pyright39:
-    name: Pyright 3.9
+    name: Pyright 3.10
     runs-on: "ubuntu-latest"
     needs: detect-ci-trigger
     if: |
@@ -267,7 +267,7 @@ jobs:
         shell: bash -l {0}
     env:
       CONDA_ENV_FILE: ci/requirements/environment.yml
-      PYTHON_VERSION: "3.9"
+      PYTHON_VERSION: "3.10"
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/ci.yaml

@@ -47,15 +47,15 @@ jobs:
       matrix:
         os: ["ubuntu-latest", "macos-latest", "windows-latest"]
         # Bookend python versions
-        python-version: ["3.9",  "3.12"]
+        python-version: ["3.10", "3.12"]
         env: [""]
         include:
           # Minimum python version:
           - env: "bare-minimum"
-            python-version: "3.9"
+            python-version: "3.10"
             os: ubuntu-latest
           - env: "min-all-deps"
-            python-version: "3.9"
+            python-version: "3.10"
             os: ubuntu-latest
           # Latest python version:
           - env: "all-but-dask"

.github/workflows/hypothesis.yaml

@@ -20,7 +20,7 @@ jobs:
     runs-on: ubuntu-latest
     if: |
       github.repository == 'pydata/xarray'
-      && (github.event_name == 'push' || github.event_name == 'pull_request')
+      && (github.event_name == 'push' || github.event_name == 'pull_request' || github.event_name == 'schedule')
     outputs:
       triggered: ${{ steps.detect-trigger.outputs.trigger-found }}
     steps:

ci/requirements/bare-minimum.yml

@@ -3,7 +3,7 @@ channels:
   - conda-forge
   - nodefaults
 dependencies:
-  - python=3.9
+  - python=3.10
   - coveralls
   - pip
   - pytest

ci/requirements/min-all-deps.yml

@@ -7,7 +7,7 @@ dependencies:
   # Run ci/min_deps_check.py to verify that this file respects the policy.
   # When upgrading python, numpy, or pandas, must also change
   # doc/user-guide/installing.rst, doc/user-guide/plotting.rst and setup.py.
-  - python=3.9
+  - python=3.10
   - array-api-strict=1.0  # dependency for testing the array api compat
   - boto3=1.26
   - bottleneck=1.3

doc/getting-started-guide/installing.rst

@@ -6,7 +6,7 @@ Installation
 Required dependencies
 ---------------------
 
-- Python (3.9 or later)
+- Python (3.10 or later)
 - `numpy <https://www.numpy.org/>`__ (1.23 or later)
 - `packaging <https://packaging.pypa.io/en/latest/#>`__ (23.1 or later)
 - `pandas <https://pandas.pydata.org/>`__ (2.0 or later)

doc/user-guide/computation.rst

@@ -482,7 +482,7 @@ every 2 points along ``x`` dimension,
 
     da.coarsen(time=7, x=2).mean()
 
-:py:meth:`~xarray.DataArray.coarsen` raises an ``ValueError`` if the data
+:py:meth:`~xarray.DataArray.coarsen` raises a ``ValueError`` if the data
 length is not a multiple of the corresponding window size.
 You can choose ``boundary='trim'`` or ``boundary='pad'`` options for trimming
 the excess entries or padding ``nan`` to insufficient entries,

doc/user-guide/groupby.rst

@@ -276,7 +276,7 @@ is identical to
 
     ds.groupby(x=UniqueGrouper())
 
-; and
+and
 
 .. code-block:: python
 

doc/whats-new.rst

@@ -26,6 +26,7 @@ New Features
 
 Breaking changes
 ~~~~~~~~~~~~~~~~
+- Support for ``python 3.9`` has been dropped (:pull:`8937`)
 
 
 Deprecations
@@ -35,6 +36,8 @@ Deprecations
 Bug fixes
 ~~~~~~~~~
 
+- Fix bug with rechunking to a frequency when some periods contain no data (:issue:`9360`).
+  By `Deepak Cherian <https://github.com/dcherian>`_.
 - Fix bug causing `DataTree.from_dict` to be sensitive to insertion order (:issue:`9276`, :pull:`9292`).
   By `Tom Nicholas <https://github.com/TomNicholas>`_.
 - Fix resampling error with monthly, quarterly, or yearly frequencies with

pyproject.toml

@@ -9,7 +9,6 @@ classifiers = [
   "Intended Audience :: Science/Research",
   "Programming Language :: Python",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
@@ -20,7 +19,7 @@ dynamic = ["version"]
 license = {text = "Apache-2.0"}
 name = "xarray"
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 
 dependencies = [
   "numpy>=1.23",
@@ -242,7 +241,7 @@ extend-exclude = [
   "doc",
   "_typed_ops.pyi",
 ]
-target-version = "py39"
+target-version = "py310"
 
 [tool.ruff.lint]
 # E402: module level import not at top of file
@@ -255,6 +254,7 @@ ignore = [
   "E402",
   "E501",
   "E731",
+  "UP007"
 ]
 select = [
   "F", # Pyflakes

xarray/backends/api.py

@@ -1,14 +1,20 @@
 from __future__ import annotations
 
 import os
-from collections.abc import Hashable, Iterable, Mapping, MutableMapping, Sequence
+from collections.abc import (
+    Callable,
+    Hashable,
+    Iterable,
+    Mapping,
+    MutableMapping,
+    Sequence,
+)
 from functools import partial
 from io import BytesIO
 from numbers import Number
 from typing import (
     TYPE_CHECKING,
     Any,
-    Callable,
     Final,
     Literal,
     Union,
@@ -358,7 +364,7 @@ def _dataset_from_backend_dataset(
     from_array_kwargs,
     **extra_tokens,
 ):
-    if not isinstance(chunks, (int, dict)) and chunks not in {None, "auto"}:
+    if not isinstance(chunks, int | dict) and chunks not in {None, "auto"}:
         raise ValueError(
             f"chunks must be an int, dict, 'auto', or None. Instead found {chunks}."
         )
@@ -385,7 +391,7 @@ def _dataset_from_backend_dataset(
     if "source" not in ds.encoding:
         path = getattr(filename_or_obj, "path", filename_or_obj)
 
-        if isinstance(path, (str, os.PathLike)):
+        if isinstance(path, str | os.PathLike):
             ds.encoding["source"] = _normalize_path(path)
 
     return ds
@@ -1042,7 +1048,7 @@ def open_mfdataset(
         raise OSError("no files to open")
 
     if combine == "nested":
-        if isinstance(concat_dim, (str, DataArray)) or concat_dim is None:
+        if isinstance(concat_dim, str | DataArray) or concat_dim is None:
             concat_dim = [concat_dim]  # type: ignore[assignment]
 
         # This creates a flat list which is easier to iterate over, whilst

xarray/backends/h5netcdf_.py

@@ -109,7 +109,7 @@ class H5NetCDFStore(WritableCFDataStore):
     def __init__(self, manager, group=None, mode=None, lock=HDF5_LOCK, autoclose=False):
         import h5netcdf
 
-        if isinstance(manager, (h5netcdf.File, h5netcdf.Group)):
+        if isinstance(manager, h5netcdf.File | h5netcdf.Group):
             if group is None:
                 root, group = find_root_and_group(manager)
             else:
@@ -374,7 +374,7 @@ def guess_can_open(
         if magic_number is not None:
             return magic_number.startswith(b"\211HDF\r\n\032\n")
 
-        if isinstance(filename_or_obj, (str, os.PathLike)):
+        if isinstance(filename_or_obj, str | os.PathLike):
             _, ext = os.path.splitext(filename_or_obj)
             return ext in {".nc", ".nc4", ".cdf"}
 

xarray/backends/lru_cache.py

@@ -2,8 +2,8 @@
 
 import threading
 from collections import OrderedDict
-from collections.abc import Iterator, MutableMapping
-from typing import Any, Callable, TypeVar
+from collections.abc import Callable, Iterator, MutableMapping
+from typing import Any, TypeVar
 
 K = TypeVar("K")
 V = TypeVar("V")

xarray/backends/netCDF4_.py

@@ -615,7 +615,7 @@ def guess_can_open(
             # netcdf 3 or HDF5
             return magic_number.startswith((b"CDF", b"\211HDF\r\n\032\n"))
 
-        if isinstance(filename_or_obj, (str, os.PathLike)):
+        if isinstance(filename_or_obj, str | os.PathLike):
             _, ext = os.path.splitext(filename_or_obj)
             return ext in {".nc", ".nc4", ".cdf"}
 

xarray/backends/plugins.py

@@ -3,22 +3,17 @@
 import functools
 import inspect
 import itertools
-import sys
 import warnings
+from collections.abc import Callable
 from importlib.metadata import entry_points
-from typing import TYPE_CHECKING, Any, Callable
+from typing import TYPE_CHECKING, Any
 
 from xarray.backends.common import BACKEND_ENTRYPOINTS, BackendEntrypoint
 from xarray.core.utils import module_available
 
 if TYPE_CHECKING:
     import os
-    from importlib.metadata import EntryPoint
-
-    if sys.version_info >= (3, 10):
-        from importlib.metadata import EntryPoints
-    else:
-        EntryPoints = list[EntryPoint]
+    from importlib.metadata import EntryPoint, EntryPoints
     from io import BufferedIOBase
 
     from xarray.backends.common import AbstractDataStore
@@ -129,13 +124,8 @@ def list_engines() -> dict[str, BackendEntrypoint]:
     -----
     This function lives in the backends namespace (``engs=xr.backends.list_engines()``).
     If available, more information is available about each backend via ``engs["eng_name"]``.
-
-    # New selection mechanism introduced with Python 3.10. See GH6514.
     """
-    if sys.version_info >= (3, 10):
-        entrypoints = entry_points(group="xarray.backends")
-    else:
-        entrypoints = entry_points().get("xarray.backends", [])
+    entrypoints = entry_points(group="xarray.backends")
     return build_engines(entrypoints)
 
 

xarray/backends/scipy_.py

@@ -299,7 +299,7 @@ def guess_can_open(
         if magic_number is not None:
             return magic_number.startswith(b"CDF")
 
-        if isinstance(filename_or_obj, (str, os.PathLike)):
+        if isinstance(filename_or_obj, str | os.PathLike):
             _, ext = os.path.splitext(filename_or_obj)
             return ext in {".nc", ".nc4", ".cdf", ".gz"}
 

xarray/backends/zarr.py

@@ -1140,7 +1140,7 @@ def guess_can_open(
         self,
         filename_or_obj: str | os.PathLike[Any] | BufferedIOBase | AbstractDataStore,
     ) -> bool:
-        if isinstance(filename_or_obj, (str, os.PathLike)):
+        if isinstance(filename_or_obj, str | os.PathLike):
             _, ext = os.path.splitext(filename_or_obj)
             return ext in {".zarr"}
 

xarray/coding/calendar_ops.py

@@ -362,7 +362,7 @@ def interp_calendar(source, target, dim="time"):
     """
     from xarray.core.dataarray import DataArray
 
-    if isinstance(target, (pd.DatetimeIndex, CFTimeIndex)):
+    if isinstance(target, pd.DatetimeIndex | CFTimeIndex):
         target = DataArray(target, dims=(dim,), name=dim)
 
     if not _contains_datetime_like_objects(

xarray/coding/cftime_offsets.py

@@ -220,7 +220,7 @@ def _next_higher_resolution(self) -> Tick:
         raise ValueError("Could not convert to integer offset at any resolution")
 
     def __mul__(self, other: int | float) -> Tick:
-        if not isinstance(other, (int, float)):
+        if not isinstance(other, int | float):
             return NotImplemented
         if isinstance(other, float):
             n = other * self.n
@@ -805,7 +805,7 @@ def to_cftime_datetime(date_str_or_date, calendar=None):
         return date
     elif isinstance(date_str_or_date, cftime.datetime):
         return date_str_or_date
-    elif isinstance(date_str_or_date, (datetime, pd.Timestamp)):
+    elif isinstance(date_str_or_date, datetime | pd.Timestamp):
         return cftime.DatetimeProlepticGregorian(*date_str_or_date.timetuple())
     else:
         raise TypeError(
@@ -1409,7 +1409,7 @@ def date_range_like(source, calendar, use_cftime=None):
     from xarray.coding.frequencies import infer_freq
     from xarray.core.dataarray import DataArray
 
-    if not isinstance(source, (pd.DatetimeIndex, CFTimeIndex)) and (
+    if not isinstance(source, pd.DatetimeIndex | CFTimeIndex) and (
         isinstance(source, DataArray)
         and (source.ndim != 1)
         or not _contains_datetime_like_objects(source.variable)
@@ -1458,7 +1458,7 @@ def date_range_like(source, calendar, use_cftime=None):
 
     # For the cases where the source ends on the end of the month, we expect the same in the new calendar.
     if source_end.day == source_end.daysinmonth and isinstance(
-        freq_as_offset, (YearEnd, QuarterEnd, MonthEnd, Day)
+        freq_as_offset, YearEnd | QuarterEnd | MonthEnd | Day
     ):
         end = end.replace(day=end.daysinmonth)
 

xarray/coding/cftimeindex.py

@@ -566,7 +566,7 @@ def shift(  # type: ignore[override]  # freq is typed Any, we are more precise
         if isinstance(freq, timedelta):
             return self + periods * freq
 
-        if isinstance(freq, (str, BaseCFTimeOffset)):
+        if isinstance(freq, str | BaseCFTimeOffset):
             from xarray.coding.cftime_offsets import to_offset
 
             return self + periods * to_offset(freq)

xarray/coding/frequencies.py

@@ -82,7 +82,7 @@ def infer_freq(index):
     from xarray.core.dataarray import DataArray
     from xarray.core.variable import Variable
 
-    if isinstance(index, (DataArray, pd.Series)):
+    if isinstance(index, DataArray | pd.Series):
         if index.ndim != 1:
             raise ValueError("'index' must be 1D")
         elif not _contains_datetime_like_objects(Variable("dim", index)):

xarray/coding/times.py

@@ -2,10 +2,10 @@
 
 import re
 import warnings
-from collections.abc import Hashable
+from collections.abc import Callable, Hashable
 from datetime import datetime, timedelta
 from functools import partial
-from typing import Callable, Literal, Union, cast
+from typing import Literal, Union, cast
 
 import numpy as np
 import pandas as pd

xarray/coding/variables.py

@@ -3,9 +3,9 @@
 from __future__ import annotations
 
 import warnings
-from collections.abc import Hashable, MutableMapping
+from collections.abc import Callable, Hashable, MutableMapping
 from functools import partial
-from typing import TYPE_CHECKING, Any, Callable, Union
+from typing import TYPE_CHECKING, Any, Union
 
 import numpy as np
 import pandas as pd