use mean of min/max years as offset in caclulation of datetime64 mean

pydata · kmuehlbauer · Feb 7, 2025 · Feb 7, 2025 · Feb 7, 2025 · Feb 7, 2025
commit 86f37b1aa430713a607623a8807bd4d55bc8cb3e
diff --git a/xarray/core/duck_array_ops.py b/xarray/core/duck_array_ops.py
@@ -229,7 +229,7 @@
        xp = get_array_namespace(data)
        if xp == np:
            # numpy currently doesn't have a astype:
            return data.astype(dtype, **kwargs)
        return xp.astype(data, dtype, **kwargs)
    return data.astype(dtype, **kwargs)

@@ -549,8 +549,8 @@
 _mean = _create_nan_agg_method("mean", invariant_0d=True)
 
 
-def _datetime_nanmin(array):
-    """nanmin() function for datetime64.
+def _datetime_nanreduce(array, func):
+    """nanreduce() function for datetime64.
 
     Caveats that this function deals with:
 
@@ -562,7 +562,7 @@
     assert dtypes.is_datetime_like(dtype)
     # (NaT).astype(float) does not produce NaN...
     array = where(pandas_isnull(array), np.nan, array.astype(float))
-    array = min(array, skipna=True)
+    array = func(array, skipna=True)
     if isinstance(array, float):
         array = np.array(array)
     # ...but (NaN).astype("M8") does produce NaT
@@ -597,7 +597,7 @@
     # Set offset to minimum if not given
     if offset is None:
         if dtypes.is_datetime_like(array.dtype):
-            offset = _datetime_nanmin(array)
+            offset = _datetime_nanreduce(array, min)
         else:
             offset = min(array)
 
@@ -717,8 +717,11 @@
 
     array = asarray(array)
     if dtypes.is_datetime_like(array.dtype):
-        offset = _datetime_nanmin(array)
-
+        dmin = _datetime_nanreduce(array, min).astype("datetime64[Y]").astype(int)
+        dmax = _datetime_nanreduce(array, max).astype("datetime64[Y]").astype(int)
+        offset = (
+            np.array((dmin + dmax) // 2).astype("datetime64[Y]").astype(array.dtype)
+        )
         # From version 2025.01.2 xarray uses np.datetime64[unit], where unit
         # is one of "s", "ms", "us", "ns".
         # To not have to worry about the resolution, we just convert the output

diff --git a/xarray/tests/test_duck_array_ops.py b/xarray/tests/test_duck_array_ops.py
@@ -481,6 +481,19 @@ def test_cftime_datetime_mean(dask):
     assert_equal(result, expected)
 
 
+@pytest.mark.parametrize("dask", [False, True])
+def test_mean_over_long_spanning_datetime64(dask) -> None:
+    if dask and not has_dask:
+        pytest.skip("requires dask")
+    array = np.array(["1678-01-01", "NaT", "2260-01-01"], dtype="datetime64[ns]")
+    da = DataArray(array, dims=["time"])
+    if dask:
+        da = da.chunk({"time": 2})
+    expected = DataArray(np.array("1969-01-01", dtype="datetime64[ns]"))
+    result = da.mean()
+    assert_equal(result, expected)
+
+
 @requires_cftime
 @requires_dask
 def test_mean_over_non_time_dim_of_dataset_with_dask_backed_cftime_data():