ENH: support datetime64, datetime64tz in nanops.mean, nanops.median

pandas/core/frame.py

@@ -7575,6 +7575,19 @@ def _count_level(self, level, axis=0, numeric_only=False):
     def _reduce(
         self, op, name, axis=0, skipna=True, numeric_only=None, filter_type=None, **kwds
     ):
+
+        dtype_is_dt = self.dtypes.apply(lambda x: x.kind == "M")
+        if numeric_only is None and name in ["mean", "median"] and dtype_is_dt.any():
+            warnings.warn(
+                "DataFrame.mean and DataFrame.median with numeric_only=None "
+                "will include datetime64 and datetime64tz columns in a "
+                "future version.",
+                FutureWarning,
+                stacklevel=3,
+            )
+            cols = self.columns[~dtype_is_dt]
+            self = self[cols]
+
         if axis is None and filter_type == "bool":
             labels = None
             constructor = None
@@ -7614,8 +7627,10 @@ def _get_data(axis_matters):
                     # TODO: combine with hasattr(result, 'dtype') further down
                     # hard since we don't have `values` down there.
                     result = np.bool_(result)
-            except TypeError:
+            except (TypeError, ValueError):
                 # e.g. in nanops trying to convert strs to float
+                # TODO: the ValueError is raised in trying to convert str
+                #  to float, should we make that a TypError?
 
                 # try by-column first
                 if filter_type is None and axis == 0:

pandas/core/nanops.py

@@ -29,7 +29,6 @@
     is_timedelta64_dtype,
     pandas_dtype,
 )
-from pandas.core.dtypes.dtypes import DatetimeTZDtype
 from pandas.core.dtypes.missing import isna, na_value_for_dtype, notna
 
 bn = import_optional_dependency("bottleneck", raise_on_missing=False, on_version="warn")
@@ -494,7 +493,6 @@ def nansum(values, axis=None, skipna=True, min_count=0, mask=None):
     return _wrap_results(the_sum, dtype)
 
 
-@disallow("M8", DatetimeTZDtype)
 @bottleneck_switch()
 def nanmean(values, axis=None, skipna=True, mask=None):
     """
@@ -552,7 +550,6 @@ def nanmean(values, axis=None, skipna=True, mask=None):
     return _wrap_results(the_mean, dtype)
 
 
-@disallow("M8")
 @bottleneck_switch()
 def nanmedian(values, axis=None, skipna=True, mask=None):
     """
@@ -585,8 +582,12 @@ def get_median(x):
         return np.nanmedian(x[mask])
 
     values, mask, dtype, dtype_max, _ = _get_values(values, skipna, mask=mask)
-    if not is_float_dtype(values):
-        values = values.astype("f8")
+    if not is_float_dtype(values.dtype):
+        try:
+            values = values.astype("f8")
+        except ValueError:
+            # e.g. "could not convert string to float: 'a'"
+            raise TypeError
         if mask is not None:
             values[mask] = np.nan
 

pandas/tests/frame/test_analytics.py

@@ -66,12 +66,15 @@ def assert_stat_op_calc(
     f = getattr(frame, opname)
 
     if check_dates:
+        expected_warning = FutureWarning if opname in ["mean", "median"] else None
         df = DataFrame({"b": date_range("1/1/2001", periods=2)})
-        result = getattr(df, opname)()
+        with tm.assert_produces_warning(expected_warning):
+            result = getattr(df, opname)()
         assert isinstance(result, Series)
 
         df["a"] = range(len(df))
-        result = getattr(df, opname)()
+        with tm.assert_produces_warning(expected_warning):
+            result = getattr(df, opname)()
         assert isinstance(result, Series)
         assert len(result)
 
@@ -1062,7 +1065,8 @@ def test_nunique(self):
     def test_mean_mixed_datetime_numeric(self, tz):
         # https://github.com/pandas-dev/pandas/issues/24752
         df = pd.DataFrame({"A": [1, 1], "B": [pd.Timestamp("2000", tz=tz)] * 2})
-        result = df.mean()
+        with tm.assert_produces_warning(FutureWarning):
+            result = df.mean()
         expected = pd.Series([1.0], index=["A"])
         tm.assert_series_equal(result, expected)
 
@@ -1072,7 +1076,8 @@ def test_mean_excludeds_datetimes(self, tz):
         # Our long-term desired behavior is unclear, but the behavior in
         # 0.24.0rc1 was buggy.
         df = pd.DataFrame({"A": [pd.Timestamp("2000", tz=tz)] * 2})
-        result = df.mean()
+        with tm.assert_produces_warning(FutureWarning):
+            result = df.mean()
         expected = pd.Series()
         tm.assert_series_equal(result, expected)
 
@@ -1458,7 +1463,9 @@ def test_mean_datetimelike(self):
         expected = pd.Series({"A": 1.0})
         tm.assert_series_equal(result, expected)
 
-        result = df.mean()
+        with tm.assert_produces_warning(FutureWarning):
+            # in the future datetime columns will be included
+            result = df.mean()
         expected = pd.Series({"A": 1.0, "C": df.loc[1, "C"]})
         tm.assert_series_equal(result, expected)
 

pandas/tests/test_nanops.py

@@ -985,7 +985,6 @@ def prng(self):
 
 class TestDatetime64NaNOps:
     @pytest.mark.parametrize("tz", [None, "UTC"])
-    @pytest.mark.xfail(reason="disabled")
     # Enabling mean changes the behavior of DataFrame.mean
     # See https://github.com/pandas-dev/pandas/issues/24752
     def test_nanmean(self, tz):