Bump dependencies incl pandas>=2 (#8968)

* Bump dependencies incl `pandas>=2`

* fix whats-new

* fix whats-new again

* clean up test

* bump h5py and hdf5

* Skip hdf5

* one more cleanup

Author: dcherian

ci/requirements/bare-minimum.yml

@@ -12,5 +12,5 @@ dependencies:
   - pytest-xdist
   - pytest-timeout
   - numpy=1.23
-  - packaging=22.0
-  - pandas=1.5
+  - packaging=23.1
+  - pandas=2.0

ci/requirements/min-all-deps.yml

@@ -9,13 +9,13 @@ dependencies:
   # doc/user-guide/installing.rst, doc/user-guide/plotting.rst and setup.py.
   - python=3.9
   - array-api-strict=1.0  # dependency for testing the array api compat
-  - boto3=1.24
+  - boto3=1.26
   - bottleneck=1.3
   - cartopy=0.21
   - cftime=1.6
   - coveralls
-  - dask-core=2022.12
-  - distributed=2022.12
+  - dask-core=2023.4
+  - distributed=2023.4
   # Flox > 0.8 has a bug with numbagg versions
   # It will require numbagg > 0.6
   # so we should just skip that series eventually
@@ -25,24 +25,24 @@ dependencies:
   # h5py and hdf5 tend to cause conflicts
   # for e.g. hdf5 1.12 conflicts with h5py=3.1
   # prioritize bumping other packages instead
-  - h5py=3.7
+  - h5py=3.8
   - hdf5=1.12
   - hypothesis
   - iris=3.4
   - lxml=4.9  # Optional dep of pydap
-  - matplotlib-base=3.6
+  - matplotlib-base=3.7
   - nc-time-axis=1.4
   # netcdf follows a 1.major.minor[.patch] convention
   # (see https://github.com/Unidata/netcdf4-python/issues/1090)
   - netcdf4=1.6.0
   - numba=0.56
   - numbagg=0.2.1
   - numpy=1.23
-  - packaging=22.0
-  - pandas=1.5
+  - packaging=23.1
+  - pandas=2.0
   - pint=0.22
   - pip
-  - pydap=3.3
+  - pydap=3.4
   - pytest
   - pytest-cov
   - pytest-env
@@ -51,7 +51,7 @@ dependencies:
   - rasterio=1.3
   - scipy=1.10
   - seaborn=0.12
-  - sparse=0.13
+  - sparse=0.14
   - toolz=0.12
-  - typing_extensions=4.4
-  - zarr=2.13
+  - typing_extensions=4.5
+  - zarr=2.14

doc/whats-new.rst

@@ -35,6 +35,23 @@ Breaking changes
 - The PyNIO backend has been deleted (:issue:`4491`, :pull:`7301`).
   By `Deepak Cherian <https://github.com/dcherian>`_.
 
+- The minimum versions of some dependencies were changed, in particular our minimum supported pandas version is now Pandas 2.
+
+  ===================== =========  =======
+   Package                    Old      New
+  ===================== =========  =======
+   dask-core              2022.12   2023.4
+   distributed            2022.12   2023.4
+   h5py                       3.7      3.8
+   matplotlib-base            3.6      3.7
+   packaging                 22.0     23.1
+   pandas                     1.5      2.0
+   pydap                      3.3      3.4
+   sparse                    0.13     0.14
+   typing_extensions          4.4      4.5
+   zarr                      2.13     2.14
+  ===================== =========  =======
+
 
 Bug fixes
 ~~~~~~~~~

pyproject.toml

@@ -24,8 +24,8 @@ requires-python = ">=3.9"
 
 dependencies = [
   "numpy>=1.23",
-  "packaging>=22",
-  "pandas>=1.5",
+  "packaging>=23.1",
+  "pandas>=2.0",
 ]
 
 [project.optional-dependencies]

xarray/tests/__init__.py

@@ -141,11 +141,6 @@ def _importorskip(
 requires_numbagg_or_bottleneck = pytest.mark.skipif(
     not has_scipy_or_netCDF4, reason="requires scipy or netCDF4"
 )
-# _importorskip does not work for development versions
-has_pandas_version_two = Version(pd.__version__).major >= 2
-requires_pandas_version_two = pytest.mark.skipif(
-    not has_pandas_version_two, reason="requires pandas 2.0.0"
-)
 has_numpy_array_api, requires_numpy_array_api = _importorskip("numpy", "1.26.0")
 has_h5netcdf_ros3, requires_h5netcdf_ros3 = _importorskip("h5netcdf", "1.3.0")
 

xarray/tests/test_dataset.py

@@ -61,7 +61,6 @@
     requires_cupy,
     requires_dask,
     requires_numexpr,
-    requires_pandas_version_two,
     requires_pint,
     requires_scipy,
     requires_sparse,
@@ -3431,7 +3430,6 @@ def test_expand_dims_kwargs_python36plus(self) -> None:
         )
         assert_identical(other_way_expected, other_way)
 
-    @requires_pandas_version_two
     def test_expand_dims_non_nanosecond_conversion(self) -> None:
         # Regression test for https://github.com/pydata/xarray/issues/7493#issuecomment-1953091000
         with pytest.warns(UserWarning, match="non-nanosecond precision"):

xarray/tests/test_groupby.py

@@ -22,7 +22,6 @@
     create_test_data,
     has_cftime,
     has_flox,
-    has_pandas_version_two,
     requires_dask,
     requires_flox,
     requires_scipy,
@@ -93,7 +92,7 @@ def test_groupby_sizes_property(dataset) -> None:
         assert dataset.groupby("x").sizes == dataset.isel(x=1).sizes
     with pytest.warns(UserWarning, match="The `squeeze` kwarg"):
         assert dataset.groupby("y").sizes == dataset.isel(y=1).sizes
-    dataset = dataset.drop("cat")
+    dataset = dataset.drop_vars("cat")
     stacked = dataset.stack({"xy": ("x", "y")})
     with pytest.warns(UserWarning, match="The `squeeze` kwarg"):
         assert stacked.groupby("xy").sizes == stacked.isel(xy=0).sizes
@@ -2172,7 +2171,6 @@ def test_upsample_interpolate_dask(self, chunked_time: bool) -> None:
             # done here due to floating point arithmetic
             assert_allclose(expected, actual, rtol=1e-16)
 
-    @pytest.mark.skipif(has_pandas_version_two, reason="requires pandas < 2.0.0")
     def test_resample_base(self) -> None:
         times = pd.date_range("2000-01-01T02:03:01", freq="6h", periods=10)
         array = DataArray(np.arange(10), [("time", times)])
@@ -2204,11 +2202,10 @@ def test_resample_origin(self) -> None:
         expected = DataArray(array.to_series().resample("24h", origin=origin).mean())
         assert_identical(expected, actual)
 
-    @pytest.mark.skipif(has_pandas_version_two, reason="requires pandas < 2.0.0")
     @pytest.mark.parametrize(
         "loffset",
         [
-            "-12H",
+            "-12h",
             datetime.timedelta(hours=-12),
             pd.Timedelta(hours=-12),
             pd.DateOffset(hours=-12),

xarray/tests/test_variable.py

@@ -36,12 +36,10 @@
     assert_equal,
     assert_identical,
     assert_no_warnings,
-    has_pandas_version_two,
     raise_if_dask_computes,
     requires_bottleneck,
     requires_cupy,
     requires_dask,
-    requires_pandas_version_two,
     requires_pint,
     requires_sparse,
     source_ndarray,
@@ -2645,7 +2643,6 @@ def test_datetime(self):
         assert np.ndarray == type(actual)
         assert np.dtype("datetime64[ns]") == actual.dtype
 
-    @requires_pandas_version_two
     def test_tz_datetime(self) -> None:
         tz = pytz.timezone("America/New_York")
         times_ns = pd.date_range("2000", periods=1, tz=tz)
@@ -2938,7 +2935,7 @@ def test_from_pint_wrapping_dask(self, Var):
 
 
 @pytest.mark.parametrize(
-    ("values", "warns_under_pandas_version_two"),
+    ("values", "warns"),
     [
         (np.datetime64("2000-01-01", "ns"), False),
         (np.datetime64("2000-01-01", "s"), True),
@@ -2957,9 +2954,9 @@ def test_from_pint_wrapping_dask(self, Var):
     ],
     ids=lambda x: f"{x}",
 )
-def test_datetime_conversion_warning(values, warns_under_pandas_version_two) -> None:
+def test_datetime_conversion_warning(values, warns) -> None:
     dims = ["time"] if isinstance(values, (np.ndarray, pd.Index, pd.Series)) else []
-    if warns_under_pandas_version_two and has_pandas_version_two:
+    if warns:
         with pytest.warns(UserWarning, match="non-nanosecond precision datetime"):
             var = Variable(dims, values)
     else:
@@ -2979,7 +2976,6 @@ def test_datetime_conversion_warning(values, warns_under_pandas_version_two) ->
         )
 
 
-@requires_pandas_version_two
 def test_pandas_two_only_datetime_conversion_warnings() -> None:
     # Note these tests rely on pandas features that are only present in pandas
     # 2.0.0 and above, and so for now cannot be parametrized.
@@ -3014,7 +3010,7 @@ def test_pandas_two_only_datetime_conversion_warnings() -> None:
 
 
 @pytest.mark.parametrize(
-    ("values", "warns_under_pandas_version_two"),
+    ("values", "warns"),
     [
         (np.timedelta64(10, "ns"), False),
         (np.timedelta64(10, "s"), True),
@@ -3026,9 +3022,9 @@ def test_pandas_two_only_datetime_conversion_warnings() -> None:
     ],
     ids=lambda x: f"{x}",
 )
-def test_timedelta_conversion_warning(values, warns_under_pandas_version_two) -> None:
+def test_timedelta_conversion_warning(values, warns) -> None:
     dims = ["time"] if isinstance(values, (np.ndarray, pd.Index)) else []
-    if warns_under_pandas_version_two and has_pandas_version_two:
+    if warns:
         with pytest.warns(UserWarning, match="non-nanosecond precision timedelta"):
             var = Variable(dims, values)
     else:
@@ -3039,7 +3035,6 @@ def test_timedelta_conversion_warning(values, warns_under_pandas_version_two) ->
     assert var.dtype == np.dtype("timedelta64[ns]")
 
 
-@requires_pandas_version_two
 def test_pandas_two_only_timedelta_conversion_warning() -> None:
     # Note this test relies on a pandas feature that is only present in pandas
     # 2.0.0 and above, and so for now cannot be parametrized.
@@ -3050,7 +3045,6 @@ def test_pandas_two_only_timedelta_conversion_warning() -> None:
     assert var.dtype == np.dtype("timedelta64[ns]")
 
 
-@requires_pandas_version_two
 @pytest.mark.parametrize(
     ("index", "dtype"),
     [