updates for pandas v2.2 and xarray v2024.02

CHANGELOG.rst

@@ -34,6 +34,8 @@ Internal Changes
 
 - Start testing the minimum versions of required dependencies (`#398 <https://github.com/MESMER-group/mesmer/pull/398>`_).
   By `Mathias Hauser`_.
+- Restore compatibility with pandas version v2.2 and xarray version v2024.02 (`#404 <https://github.com/MESMER-group/mesmer/pull/404>`_).
+  By `Mathias Hauser`_.
 
 
 v0.10.0 - 2024.01.04

mesmer/core/_data.py

@@ -3,6 +3,8 @@
 
 import pandas as pd
 import pooch
+import xarray as xr
+from packaging.version import Version
 
 import mesmer
 
@@ -36,18 +38,19 @@ def _load_aod_obs(*, version, resample):
 
     df = pd.read_csv(
         filename,
-        delim_whitespace=True,
+        sep=r"\s+",
         skiprows=11,
         names=("year", "month", "aod"),
-        parse_dates=[["year", "month"]],
-        date_format={"year_month": "%Y %m"},
-        index_col="year_month",
+        dtype={"year": str, "month": str},
     )
 
-    aod = df.to_xarray().rename(year_month="time").aod
+    time = pd.to_datetime(df.year + df.month, format="%Y%m")
+
+    aod = xr.DataArray(df.aod.values, coords={"time": time}, name="aod")
 
     if resample:
-        aod = aod.resample(time="A").mean()
+        freq = "YE" if Version(xr.__version__) >= Version("2024.02") else "A"
+        aod = aod.resample(time=freq).mean()
 
     return aod
 

tests/unit/test_data.py

@@ -1,6 +1,7 @@
 import numpy as np
 import pandas as pd
 import xarray as xr
+from packaging.version import Version
 
 from mesmer.core._data import load_stratospheric_aerosol_optical_depth_obs
 
@@ -9,7 +10,9 @@ def test_load_stratospheric_aerosol_optical_depth_data():
 
     aod = load_stratospheric_aerosol_optical_depth_obs(version="2022", resample=True)
 
-    time = pd.date_range("1850", "2023", freq="A")
+    freq = "YE" if Version(pd.__version__) >= Version("2.2") else "A"
+
+    time = pd.date_range("1850", "2023", freq=freq)
     time = xr.DataArray(time, dims="time", coords={"time": time})
 
     xr.testing.assert_equal(aod.time, time)

tests/unit/test_utils.py

@@ -1,5 +1,4 @@
 import numpy as np
-import pandas as pd
 import pytest
 import xarray as xr
 from packaging.version import Version
@@ -196,29 +195,15 @@ def test_check_dataarray_form_shape():
 
 
 def _get_time(*args, **kwargs):
-    # TODO: use xr.date_range once requiring xarray >= v0.21
 
     calendar = kwargs.pop("calendar", "standard")
     freq = kwargs.pop("freq", None)
 
     # translate freq strings
-    pandas_calendars = ["standard", "gregorian"]
-    if freq:
-        if calendar not in pandas_calendars and Version(xr.__version__) < Version(
-            "2023.11"
-        ):
-            freq = freq.replace("Y", "A").replace("ME", "M")
-        if calendar in pandas_calendars and Version(pd.__version__) < Version("2.2"):
-            freq = freq.replace("Y", "A").replace("ME", "M")
-
-    if Version(xr.__version__) >= Version("0.21"):
-        time = xr.date_range(*args, calendar=calendar, freq=freq, **kwargs)
-    else:
-
-        if calendar == "standard":
-            time = pd.date_range(*args, freq=freq, **kwargs)
-        else:
-            time = xr.cftime_range(*args, calendar=calendar, freq=freq, **kwargs)
+    if freq and Version(xr.__version__) < Version("2024.02"):
+        freq = freq.replace("YE", "A").replace("ME", "M")
+
+    time = xr.date_range(*args, calendar=calendar, freq=freq, **kwargs)
 
     return xr.DataArray(time, dims="time")
 
@@ -228,14 +213,14 @@ def _get_time(*args, **kwargs):
 )
 def test_assert_annual_data(calendar):
 
-    time = _get_time("2000", "2005", freq="Y", calendar=calendar)
+    time = _get_time("2000", "2005", freq="YE", calendar=calendar)
 
     # no error
     mesmer.core.utils._assert_annual_data(time)
 
 
 @pytest.mark.parametrize("calendar", ["standard", "gregorian", "365_day"])
-@pytest.mark.parametrize("freq", ["2Y", "ME"])
+@pytest.mark.parametrize("freq", ["2YE", "ME"])
 def test_assert_annual_data_wrong_freq(calendar, freq):
 
     time = _get_time("2000", periods=5, freq=freq, calendar=calendar)
@@ -248,7 +233,7 @@ def test_assert_annual_data_wrong_freq(calendar, freq):
 
 def test_assert_annual_data_unkown_freq():
 
-    time1 = _get_time("2000", periods=2, freq="Y")
+    time1 = _get_time("2000", periods=2, freq="YE")
     time2 = _get_time("2002", periods=3, freq="ME")
     time = xr.concat([time1, time2], dim="time")