Backport PR #42317: Revert "REF: move shift logic from BlockManager to DataFrame" (#42321)

Co-authored-by: jbrockmendel <[email protected]>

Author: meeseeksmachine

pandas/core/frame.py

@@ -5285,45 +5285,28 @@ def shift(
         axis = self._get_axis_number(axis)
 
         ncols = len(self.columns)
+        if axis == 1 and periods != 0 and fill_value is lib.no_default and ncols > 0:
+            # We will infer fill_value to match the closest column
 
-        if (
-            axis == 1
-            and periods != 0
-            and ncols > 0
-            and (fill_value is lib.no_default or len(self._mgr.arrays) > 1)
-        ):
-            # Exclude single-array-with-fill_value case so we issue a FutureWarning
-            #  if an integer is passed with datetimelike dtype GH#31971
-            from pandas import concat
+            # Use a column that we know is valid for our column's dtype GH#38434
+            label = self.columns[0]
 
-            # tail: the data that is still in our shifted DataFrame
             if periods > 0:
-                tail = self.iloc[:, :-periods]
-            else:
-                tail = self.iloc[:, -periods:]
-            # pin a simple Index to avoid costly casting
-            tail.columns = range(len(tail.columns))
-
-            if fill_value is not lib.no_default:
-                # GH#35488
-                # TODO(EA2D): with 2D EAs we could construct other directly
-                ser = Series(fill_value, index=self.index)
+                result = self.iloc[:, :-periods]
+                for col in range(min(ncols, abs(periods))):
+                    # TODO(EA2D): doing this in a loop unnecessary with 2D EAs
+                    # Define filler inside loop so we get a copy
+                    filler = self.iloc[:, 0].shift(len(self))
+                    result.insert(0, label, filler, allow_duplicates=True)
             else:
-                # We infer fill_value to match the closest column
-                if periods > 0:
-                    ser = self.iloc[:, 0].shift(len(self))
-                else:
-                    ser = self.iloc[:, -1].shift(len(self))
-
-            width = min(abs(periods), ncols)
-            other = concat([ser] * width, axis=1)
-
-            if periods > 0:
-                result = concat([other, tail], axis=1)
-            else:
-                result = concat([tail, other], axis=1)
+                result = self.iloc[:, -periods:]
+                for col in range(min(ncols, abs(periods))):
+                    # Define filler inside loop so we get a copy
+                    filler = self.iloc[:, -1].shift(len(self))
+                    result.insert(
+                        len(result.columns), label, filler, allow_duplicates=True
+                    )
 
-            result = cast(DataFrame, result)
             result.columns = self.columns.copy()
             return result
 

pandas/core/internals/managers.py

@@ -381,6 +381,25 @@ def shift(self: T, periods: int, axis: int, fill_value) -> T:
         if fill_value is lib.no_default:
             fill_value = None
 
+        if axis == 0 and self.ndim == 2 and self.nblocks > 1:
+            # GH#35488 we need to watch out for multi-block cases
+            # We only get here with fill_value not-lib.no_default
+            ncols = self.shape[0]
+            if periods > 0:
+                indexer = [-1] * periods + list(range(ncols - periods))
+            else:
+                nper = abs(periods)
+                indexer = list(range(nper, ncols)) + [-1] * nper
+            result = self.reindex_indexer(
+                self.items,
+                indexer,
+                axis=0,
+                fill_value=fill_value,
+                allow_dups=True,
+                consolidate=False,
+            )
+            return result
+
         return self.apply("shift", periods=periods, axis=axis, fill_value=fill_value)
 
     def fillna(self: T, value, limit, inplace: bool, downcast) -> T:

pandas/tests/apply/test_frame_transform.py

@@ -39,8 +39,15 @@ def test_transform_ufunc(axis, float_frame, frame_or_series):
 
 
 @pytest.mark.parametrize("op", frame_transform_kernels)
-def test_transform_groupby_kernel(axis, float_frame, op, request):
+def test_transform_groupby_kernel(axis, float_frame, op, using_array_manager, request):
     # GH 35964
+    if using_array_manager and op == "pct_change" and axis in (1, "columns"):
+        # TODO(ArrayManager) shift with axis=1
+        request.node.add_marker(
+            pytest.mark.xfail(
+                reason="shift axis=1 not yet implemented for ArrayManager"
+            )
+        )
 
     args = [0.0] if op == "fillna" else []
     if axis == 0 or axis == "index":