Address latest pandas-related upstream test failures (#9081)

* Address pandas-related upstream test failures

* Address more warnings

* Don't lose coverage for pandas < 3

* Address one more warning

* Fix accidental change from MS to ME

* Use datetime64[ns] arrays

* Switch to @pytest.mark.filterwarnings

Author: spencerkclark

xarray/coding/cftime_offsets.py

@@ -77,13 +77,21 @@
     from xarray.core.types import InclusiveOptions, SideOptions
 
 
+def _nanosecond_precision_timestamp(*args, **kwargs):
+    # As of pandas version 3.0, pd.to_datetime(Timestamp(...)) will try to
+    # infer the appropriate datetime precision. Until xarray supports
+    # non-nanosecond precision times, we will use this constructor wrapper to
+    # explicitly create nanosecond-precision Timestamp objects.
+    return pd.Timestamp(*args, **kwargs).as_unit("ns")
+
+
 def get_date_type(calendar, use_cftime=True):
     """Return the cftime date type for a given calendar name."""
     if cftime is None:
         raise ImportError("cftime is required for dates with non-standard calendars")
     else:
         if _is_standard_calendar(calendar) and not use_cftime:
-            return pd.Timestamp
+            return _nanosecond_precision_timestamp
 
         calendars = {
             "noleap": cftime.DatetimeNoLeap,

xarray/tests/test_backends.py

@@ -529,7 +529,7 @@ def test_roundtrip_string_encoded_characters(self) -> None:
             assert actual["x"].encoding["_Encoding"] == "ascii"
 
     def test_roundtrip_numpy_datetime_data(self) -> None:
-        times = pd.to_datetime(["2000-01-01", "2000-01-02", "NaT"])
+        times = pd.to_datetime(["2000-01-01", "2000-01-02", "NaT"], unit="ns")
         expected = Dataset({"t": ("t", times), "t0": times[0]})
         kwargs = {"encoding": {"t0": {"units": "days since 1950-01-01"}}}
         with self.roundtrip(expected, save_kwargs=kwargs) as actual:

xarray/tests/test_coding_times.py

@@ -538,11 +538,14 @@ def test_infer_datetime_units(freq, units) -> None:
     ["dates", "expected"],
     [
         (
-            pd.to_datetime(["1900-01-01", "1900-01-02", "NaT"]),
+            pd.to_datetime(["1900-01-01", "1900-01-02", "NaT"], unit="ns"),
             "days since 1900-01-01 00:00:00",
         ),
-        (pd.to_datetime(["NaT", "1900-01-01"]), "days since 1900-01-01 00:00:00"),
-        (pd.to_datetime(["NaT"]), "days since 1970-01-01 00:00:00"),
+        (
+            pd.to_datetime(["NaT", "1900-01-01"], unit="ns"),
+            "days since 1900-01-01 00:00:00",
+        ),
+        (pd.to_datetime(["NaT"], unit="ns"), "days since 1970-01-01 00:00:00"),
     ],
 )
 def test_infer_datetime_units_with_NaT(dates, expected) -> None:

xarray/tests/test_combine.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-from datetime import datetime
 from itertools import product
 
 import numpy as np
@@ -229,8 +228,12 @@ def test_lexicographic_sort_string_coords(self):
         assert concat_dims == ["simulation"]
 
     def test_datetime_coords(self):
-        ds0 = Dataset({"time": [datetime(2000, 3, 6), datetime(2001, 3, 7)]})
-        ds1 = Dataset({"time": [datetime(1999, 1, 1), datetime(1999, 2, 4)]})
+        ds0 = Dataset(
+            {"time": np.array(["2000-03-06", "2000-03-07"], dtype="datetime64[ns]")}
+        )
+        ds1 = Dataset(
+            {"time": np.array(["1999-01-01", "1999-02-04"], dtype="datetime64[ns]")}
+        )
 
         expected = {(0,): ds1, (1,): ds0}
         actual, concat_dims = _infer_concat_order_from_coords([ds0, ds1])

xarray/tests/test_dataarray.py

@@ -3642,6 +3642,7 @@ def test_to_and_from_dict(
         actual_no_data = da.to_dict(data=False, encoding=encoding)
         assert expected_no_data == actual_no_data
 
+    @pytest.mark.filterwarnings("ignore:Converting non-nanosecond")
     def test_to_and_from_dict_with_time_dim(self) -> None:
         x = np.random.randn(10, 3)
         t = pd.date_range("20130101", periods=10)
@@ -3650,6 +3651,7 @@ def test_to_and_from_dict_with_time_dim(self) -> None:
         roundtripped = DataArray.from_dict(da.to_dict())
         assert_identical(da, roundtripped)
 
+    @pytest.mark.filterwarnings("ignore:Converting non-nanosecond")
     def test_to_and_from_dict_with_nan_nat(self) -> None:
         y = np.random.randn(10, 3)
         y[2] = np.nan

xarray/tests/test_groupby.py

@@ -139,8 +139,7 @@ def test_groupby_da_datetime() -> None:
     times = pd.date_range("2000-01-01", periods=4)
     foo = xr.DataArray([1, 2, 3, 4], coords=dict(time=times), dims="time")
     # create test index
-    dd = times.to_pydatetime()
-    reference_dates = [dd[0], dd[2]]
+    reference_dates = [times[0], times[2]]
     labels = reference_dates[0:1] * 2 + reference_dates[1:2] * 2
     ind = xr.DataArray(
         labels, coords=dict(time=times), dims="time", name="reference_date"
@@ -1881,7 +1880,7 @@ def test_resample_first(self) -> None:
         array = Dataset({"time": times})["time"]
         actual = array.resample(time="1D").last()
         expected_times = pd.to_datetime(
-            ["2000-01-01T18", "2000-01-02T18", "2000-01-03T06"]
+            ["2000-01-01T18", "2000-01-02T18", "2000-01-03T06"], unit="ns"
         )
         expected = DataArray(expected_times, [("time", times[::4])], name="time")
         assert_identical(expected, actual)

xarray/tests/test_plot.py

@@ -5,7 +5,7 @@
 import math
 from collections.abc import Generator, Hashable
 from copy import copy
-from datetime import date, datetime, timedelta
+from datetime import date, timedelta
 from typing import Any, Callable, Literal
 
 import numpy as np
@@ -2912,9 +2912,8 @@ def setUp(self) -> None:
         """
         month = np.arange(1, 13, 1)
         data = np.sin(2 * np.pi * month / 12.0)
-
-        darray = DataArray(data, dims=["time"])
-        darray.coords["time"] = np.array([datetime(2017, m, 1) for m in month])
+        times = pd.date_range(start="2017-01-01", freq="MS", periods=12)
+        darray = DataArray(data, dims=["time"], coords=[times])
 
         self.darray = darray
 

xarray/tests/test_variable.py

@@ -36,6 +36,7 @@
     assert_equal,
     assert_identical,
     assert_no_warnings,
+    has_pandas_3,
     raise_if_dask_computes,
     requires_bottleneck,
     requires_cupy,
@@ -252,6 +253,7 @@ def test_0d_object_array_with_list(self):
         assert_array_equal(x[0].data, listarray.squeeze())
         assert_array_equal(x.squeeze().data, listarray.squeeze())
 
+    @pytest.mark.filterwarnings("ignore:Converting non-nanosecond")
     def test_index_and_concat_datetime(self):
         # regression test for #125
         date_range = pd.date_range("2011-09-01", periods=10)
@@ -2942,8 +2944,8 @@ def test_from_pint_wrapping_dask(self, Var):
         (np.array([np.datetime64("2000-01-01", "ns")]), False),
         (np.array([np.datetime64("2000-01-01", "s")]), True),
         (pd.date_range("2000", periods=1), False),
-        (datetime(2000, 1, 1), False),
-        (np.array([datetime(2000, 1, 1)]), False),
+        (datetime(2000, 1, 1), has_pandas_3),
+        (np.array([datetime(2000, 1, 1)]), has_pandas_3),
         (pd.date_range("2000", periods=1, tz=pytz.timezone("America/New_York")), False),
         (
             pd.Series(