REF: de-duplicate Block.diff, remove axis kwd (pandas-dev#53807)

* REF: remove axis keyword from internal diff methods

* De-duplicate diff

Author: jbrockmendel

pandas/core/algorithms.py

@@ -1441,8 +1441,8 @@ def diff(arr, n: int, axis: AxisInt = 0):
         arr = arr.to_numpy()
         dtype = arr.dtype
 
-    if not isinstance(dtype, np.dtype):
-        # i.e ExtensionDtype
+    if not isinstance(arr, np.ndarray):
+        # i.e ExtensionArray
         if hasattr(arr, f"__{op.__name__}__"):
             if axis != 0:
                 raise ValueError(f"cannot diff {type(arr).__name__} on axis={axis}")

pandas/core/frame.py

@@ -9479,7 +9479,7 @@ def diff(self, periods: int = 1, axis: Axis = 0) -> DataFrame:
             # With periods=0 this is equivalent to a diff with axis=0
             axis = 0
 
-        new_data = self._mgr.diff(n=periods, axis=axis)
+        new_data = self._mgr.diff(n=periods)
         return self._constructor(new_data).__finalize__(self, "diff")
 
     # ----------------------------------------------------------------------

pandas/core/internals/array_manager.py

@@ -353,9 +353,9 @@ def putmask(self, mask, new, align: bool = True) -> Self:
             new=new,
         )
 
-    def diff(self, n: int, axis: AxisInt) -> Self:
-        assert self.ndim == 2 and axis == 0  # caller ensures
-        return self.apply(algos.diff, n=n, axis=axis)
+    def diff(self, n: int) -> Self:
+        assert self.ndim == 2  # caller ensures
+        return self.apply(algos.diff, n=n)
 
     def interpolate(self, **kwargs) -> Self:
         return self.apply_with_block("interpolate", swap_axis=False, **kwargs)

pandas/core/internals/blocks.py

@@ -1426,10 +1426,12 @@ def interpolate(
         nb = self.make_block_same_class(data, refs=refs)
         return nb._maybe_downcast([nb], downcast, using_cow)
 
-    def diff(self, n: int, axis: AxisInt = 1) -> list[Block]:
+    @final
+    def diff(self, n: int) -> list[Block]:
         """return block for the diff of the values"""
-        # only reached with ndim == 2 and axis == 1
-        new_values = algos.diff(self.values, n, axis=axis)
+        # only reached with ndim == 2
+        # TODO(EA2D): transpose will be unnecessary with 2D EAs
+        new_values = algos.diff(self.values.T, n, axis=0).T
         return [self.make_block(values=new_values)]
 
     def shift(
@@ -2067,12 +2069,6 @@ def slice_block_rows(self, slicer: slice) -> Self:
         new_values = self.values[slicer]
         return type(self)(new_values, self._mgr_locs, ndim=self.ndim, refs=self.refs)
 
-    def diff(self, n: int, axis: AxisInt = 1) -> list[Block]:
-        # only reached with ndim == 2 and axis == 1
-        # TODO(EA2D): Can share with NDArrayBackedExtensionBlock
-        new_values = algos.diff(self.values, n, axis=0)
-        return [self.make_block(values=new_values)]
-
     def shift(
         self, periods: int, axis: AxisInt = 0, fill_value: Any = None
     ) -> list[Block]:
@@ -2191,32 +2187,6 @@ def is_view(self) -> bool:
         # check the ndarray values of the DatetimeIndex values
         return self.values._ndarray.base is not None
 
-    def diff(self, n: int, axis: AxisInt = 0) -> list[Block]:
-        """
-        1st discrete difference.
-
-        Parameters
-        ----------
-        n : int
-            Number of periods to diff.
-        axis : int, default 0
-            Axis to diff upon.
-
-        Returns
-        -------
-        A list with a new Block.
-
-        Notes
-        -----
-        The arguments here are mimicking shift so they are called correctly
-        by apply.
-        """
-        # only reached with ndim == 2 and axis == 1
-        values = self.values
-
-        new_values = values - values.shift(n, axis=axis)
-        return [self.make_block(new_values)]
-
     def shift(
         self, periods: int, axis: AxisInt = 0, fill_value: Any = None
     ) -> list[Block]:

pandas/core/internals/managers.py

@@ -411,10 +411,9 @@ def putmask(self, mask, new, align: bool = True) -> Self:
             using_cow=using_copy_on_write(),
         )
 
-    def diff(self, n: int, axis: AxisInt) -> Self:
-        # only reached with self.ndim == 2 and axis == 1
-        axis = self._normalize_axis(axis)
-        return self.apply("diff", n=n, axis=axis)
+    def diff(self, n: int) -> Self:
+        # only reached with self.ndim == 2
+        return self.apply("diff", n=n)
 
     def interpolate(self, inplace: bool, **kwargs) -> Self:
         return self.apply(