REF: share _reduce method (#44737)

Author: jbrockmendel

pandas/core/arrays/_mixins.py

@@ -339,14 +339,6 @@ def fillna(
     # ------------------------------------------------------------------------
     # Reductions
 
-    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
-        meth = getattr(self, name, None)
-        if meth:
-            return meth(skipna=skipna, **kwargs)
-        else:
-            msg = f"'{type(self).__name__}' does not implement reduction '{name}'"
-            raise TypeError(msg)
-
     def _wrap_reduction_result(self, axis: int | None, result):
         if axis is None or self.ndim == 1:
             return self._box_func(result)

pandas/core/arrays/base.py

@@ -1352,7 +1352,13 @@ def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
         ------
         TypeError : subclass does not define reductions
         """
-        raise TypeError(f"cannot perform {name} with type {self.dtype}")
+        meth = getattr(self, name, None)
+        if meth is None:
+            raise TypeError(
+                f"'{type(self).__name__}' with dtype {self.dtype} "
+                f"does not support reduction '{name}'"
+            )
+        return meth(skipna=skipna, **kwargs)
 
     # https://github.com/python/typeshed/issues/2148#issuecomment-520783318
     # Incompatible types in assignment (expression has type "None", base class

pandas/core/arrays/sparse/array.py

@@ -1363,13 +1363,6 @@ def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
         else:
             arr = self.dropna()
 
-        # we don't support these kwargs.
-        # They should only be present when called via pandas, so do it here.
-        # instead of in `any` / `all` (which will raise if they're present,
-        # thanks to nv.validate
-        kwargs.pop("filter_type", None)
-        kwargs.pop("numeric_only", None)
-        kwargs.pop("op", None)
         return getattr(arr, name)(**kwargs)
 
     def all(self, axis=None, *args, **kwargs):

pandas/core/arrays/string_arrow.py

@@ -335,12 +335,6 @@ def _as_pandas_scalar(self, arrow_scalar: pa.Scalar):
         else:
             return scalar
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
-        if name in ["min", "max"]:
-            return getattr(self, name)(skipna=skipna)
-
-        raise TypeError(f"Cannot perform reduction '{name}' with string dtype")
-
     @property
     def nbytes(self) -> int:
         """

pandas/tests/arrays/categorical/test_operators.py

@@ -371,17 +371,15 @@ def test_numeric_like_ops(self):
         # min/max)
         s = df["value_group"]
         for op in ["kurt", "skew", "var", "std", "mean", "sum", "median"]:
-            msg = f"'Categorical' does not implement reduction '{op}'"
+            msg = f"does not support reduction '{op}'"
             with pytest.raises(TypeError, match=msg):
                 getattr(s, op)(numeric_only=False)
 
         # mad technically works because it takes always the numeric data
 
         # numpy ops
         s = Series(Categorical([1, 2, 3, 4]))
-        with pytest.raises(
-            TypeError, match="'Categorical' does not implement reduction 'sum'"
-        ):
+        with pytest.raises(TypeError, match="does not support reduction 'sum'"):
             np.sum(s)
 
         # numeric ops on a Series

pandas/tests/arrays/string_/test_string.py

@@ -345,7 +345,7 @@ def test_reduce(skipna, dtype):
 def test_min_max(method, skipna, dtype, request):
     if dtype.storage == "pyarrow":
         reason = "'ArrowStringArray' object has no attribute 'max'"
-        mark = pytest.mark.xfail(raises=AttributeError, reason=reason)
+        mark = pytest.mark.xfail(raises=TypeError, reason=reason)
         request.node.add_marker(mark)
 
     arr = pd.Series(["a", "b", "c", None], dtype=dtype)
@@ -362,12 +362,10 @@ def test_min_max(method, skipna, dtype, request):
 def test_min_max_numpy(method, box, dtype, request):
     if dtype.storage == "pyarrow":
         if box is pd.array:
-            raises = TypeError
             reason = "'<=' not supported between instances of 'str' and 'NoneType'"
         else:
-            raises = AttributeError
             reason = "'ArrowStringArray' object has no attribute 'max'"
-        mark = pytest.mark.xfail(raises=raises, reason=reason)
+        mark = pytest.mark.xfail(raises=TypeError, reason=reason)
         request.node.add_marker(mark)
 
     arr = box(["a", "b", "c", None], dtype=dtype)

pandas/tests/arrays/test_datetimelike.py

@@ -246,7 +246,7 @@ def test_reduce_invalid(self):
         data = np.arange(10, dtype="i8") * 24 * 3600 * 10 ** 9
         arr = self.array_cls(data, freq="D")
 
-        msg = f"'{type(arr).__name__}' does not implement reduction 'not a method'"
+        msg = "does not support reduction 'not a method'"
         with pytest.raises(TypeError, match=msg):
             arr._reduce("not a method")
 

pandas/tests/extension/base/reduce.py

@@ -29,7 +29,7 @@ def test_reduce_series_numeric(self, data, all_numeric_reductions, skipna):
 
         msg = (
             "[Cc]annot perform|Categorical is not ordered for operation|"
-            "'Categorical' does not implement reduction|"
+            "does not support reduction|"
         )
 
         with pytest.raises(TypeError, match=msg):
@@ -42,7 +42,7 @@ def test_reduce_series_boolean(self, data, all_boolean_reductions, skipna):
 
         msg = (
             "[Cc]annot perform|Categorical is not ordered for operation|"
-            "'Categorical' does not implement reduction|"
+            "does not support reduction|"
         )
 
         with pytest.raises(TypeError, match=msg):

pandas/tests/frame/test_reductions.py

@@ -1507,13 +1507,13 @@ def test_any_all_categorical_dtype_nuisance_column(self, method):
         df = ser.to_frame()
 
         # Double-check the Series behavior is to raise
-        with pytest.raises(TypeError, match="does not implement reduction"):
+        with pytest.raises(TypeError, match="does not support reduction"):
             getattr(ser, method)()
 
-        with pytest.raises(TypeError, match="does not implement reduction"):
+        with pytest.raises(TypeError, match="does not support reduction"):
             getattr(np, method)(ser)
 
-        with pytest.raises(TypeError, match="does not implement reduction"):
+        with pytest.raises(TypeError, match="does not support reduction"):
             getattr(df, method)(bool_only=False)
 
         # With bool_only=None, operating on this column raises and is ignored,
@@ -1537,10 +1537,10 @@ def test_median_categorical_dtype_nuisance_column(self):
         ser = df["A"]
 
         # Double-check the Series behavior is to raise
-        with pytest.raises(TypeError, match="does not implement reduction"):
+        with pytest.raises(TypeError, match="does not support reduction"):
             ser.median()
 
-        with pytest.raises(TypeError, match="does not implement reduction"):
+        with pytest.raises(TypeError, match="does not support reduction"):
             df.median(numeric_only=False)
 
         with tm.assert_produces_warning(
@@ -1553,7 +1553,7 @@ def test_median_categorical_dtype_nuisance_column(self):
         # same thing, but with an additional non-categorical column
         df["B"] = df["A"].astype(int)
 
-        with pytest.raises(TypeError, match="does not implement reduction"):
+        with pytest.raises(TypeError, match="does not support reduction"):
             df.median(numeric_only=False)
 
         with tm.assert_produces_warning(

pandas/tests/groupby/test_groupby.py

@@ -869,7 +869,7 @@ def test_omit_nuisance(df):
 
     # won't work with axis = 1
     grouped = df.groupby({"A": 0, "C": 0, "D": 1, "E": 1}, axis=1)
-    msg = "'DatetimeArray' does not implement reduction 'sum'"
+    msg = "does not support reduction 'sum'"
     with pytest.raises(TypeError, match=msg):
         grouped.agg(lambda x: x.sum(0, numeric_only=False))
 
@@ -1931,7 +1931,7 @@ def get_result():
                 # GH#41291
                 # datetime64 -> prod and sum are invalid
                 if op == "skew":
-                    msg = "'DatetimeArray' does not implement reduction 'skew'"
+                    msg = "does not support reduction 'skew'"
                 else:
                     msg = "datetime64 type does not support"
                 with pytest.raises(TypeError, match=msg):
@@ -1943,9 +1943,9 @@ def get_result():
                 # GH#41291
                 if op == "mad":
                     # mad calls mean, which Categorical doesn't implement
-                    msg = "'Categorical' does not implement reduction 'mean'"
+                    msg = "does not support reduction 'mean'"
                 elif op == "skew":
-                    msg = f"'Categorical' does not implement reduction '{op}'"
+                    msg = f"does not support reduction '{op}'"
                 else:
                     msg = "category type does not support"
                 with pytest.raises(TypeError, match=msg):

pandas/tests/reductions/test_reductions.py

@@ -356,7 +356,7 @@ def test_invalid_td64_reductions(self, opname):
             [
                 f"reduction operation '{opname}' not allowed for this dtype",
                 rf"cannot perform {opname} with type timedelta64\[ns\]",
-                f"'TimedeltaArray' does not implement reduction '{opname}'",
+                f"does not support reduction '{opname}'",
             ]
         )
 
@@ -727,7 +727,7 @@ def test_ops_consistency_on_empty(self, method):
                 [
                     "operation 'var' not allowed",
                     r"cannot perform var with type timedelta64\[ns\]",
-                    "'TimedeltaArray' does not implement reduction 'var'",
+                    "does not support reduction 'var'",
                 ]
             )
             with pytest.raises(TypeError, match=msg):

pandas/tests/reductions/test_stat_reductions.py

@@ -105,7 +105,7 @@ def _check_stat_op(
             # mean, idxmax, idxmin, min, and max are valid for dates
             if name not in ["max", "min", "mean", "median", "std"]:
                 ds = Series(pd.date_range("1/1/2001", periods=10))
-                msg = f"'DatetimeArray' does not implement reduction '{name}'"
+                msg = f"does not support reduction '{name}'"
                 with pytest.raises(TypeError, match=msg):
                     f(ds)