REF: implement NDFrame._from_mgr (pandas-dev#52132)

Author: jbrockmendel

pandas/core/apply.py

@@ -735,7 +735,7 @@ def apply(self) -> DataFrame | Series:
             with np.errstate(all="ignore"):
                 results = self.obj._mgr.apply("apply", func=self.func)
             # _constructor will retain self.index and self.columns
-            return self.obj._constructor(data=results)
+            return self.obj._constructor_from_mgr(results, axes=results.axes)
 
         # broadcasting
         if self.result_type == "broadcast":

pandas/core/arraylike.py

@@ -349,7 +349,7 @@ def _reconstruct(result):
             return result
         if isinstance(result, BlockManager):
             # we went through BlockManager.apply e.g. np.sqrt
-            result = self._constructor(result, **reconstruct_kwargs, copy=False)
+            result = self._constructor_from_mgr(result, axes=result.axes)
         else:
             # we converted an array, lost our axes
             result = self._constructor(

pandas/core/frame.py

@@ -637,8 +637,25 @@ class DataFrame(NDFrame, OpsMixin):
     def _constructor(self) -> Callable[..., DataFrame]:
         return DataFrame
 
+    def _constructor_from_mgr(self, mgr, axes):
+        if self._constructor is DataFrame:
+            # we are pandas.DataFrame (or a subclass that doesn't override _constructor)
+            return self._from_mgr(mgr, axes=axes)
+        else:
+            assert axes is mgr.axes
+            return self._constructor(mgr)
+
     _constructor_sliced: Callable[..., Series] = Series
 
+    def _sliced_from_mgr(self, mgr, axes) -> Series:
+        return Series._from_mgr(mgr, axes)
+
+    def _constructor_sliced_from_mgr(self, mgr, axes):
+        if self._constructor_sliced is Series:
+            return self._sliced_from_mgr(mgr, axes)
+        assert axes is mgr.axes
+        return self._constructor_sliced(mgr)
+
     # ----------------------------------------------------------------------
     # Constructors
 
@@ -3668,9 +3685,9 @@ def _ixs(self, i: int, axis: AxisInt = 0) -> Series:
 
             # if we are a copy, mark as such
             copy = isinstance(new_mgr.array, np.ndarray) and new_mgr.array.base is None
-            result = self._constructor_sliced(new_mgr, name=self.index[i]).__finalize__(
-                self
-            )
+            result = self._constructor_sliced_from_mgr(new_mgr, axes=new_mgr.axes)
+            result._name = self.index[i]
+            result = result.__finalize__(self)
             result._set_is_copy(self, copy=copy)
             return result
 
@@ -3723,7 +3740,7 @@ def _getitem_nocopy(self, key: list):
             copy=False,
             only_slice=True,
         )
-        return self._constructor(new_mgr)
+        return self._constructor_from_mgr(new_mgr, axes=new_mgr.axes)
 
     def __getitem__(self, key):
         check_dict_or_set_indexers(key)
@@ -4259,9 +4276,10 @@ def _box_col_values(self, values: SingleDataManager, loc: int) -> Series:
         # Lookup in columns so that if e.g. a str datetime was passed
         #  we attach the Timestamp object as the name.
         name = self.columns[loc]
-        klass = self._constructor_sliced
         # We get index=self.index bc values is a SingleDataManager
-        return klass(values, name=name, fastpath=True).__finalize__(self)
+        obj = self._constructor_sliced_from_mgr(values, axes=values.axes)
+        obj._name = name
+        return obj.__finalize__(self)
 
     # ----------------------------------------------------------------------
     # Lookup Caching
@@ -4735,7 +4753,7 @@ def predicate(arr: ArrayLike) -> bool:
             return True
 
         mgr = self._mgr._get_data_subset(predicate).copy(deep=None)
-        return type(self)(mgr).__finalize__(self)
+        return self._constructor_from_mgr(mgr, axes=mgr.axes).__finalize__(self)
 
     def insert(
         self,
@@ -5547,7 +5565,7 @@ def shift(
                     fill_value=fill_value,
                     allow_dups=True,
                 )
-                res_df = self._constructor(mgr)
+                res_df = self._constructor_from_mgr(mgr, axes=mgr.axes)
                 return res_df.__finalize__(self, method="shift")
 
         return super().shift(
@@ -6075,7 +6093,8 @@ class    max    type
 
     @doc(NDFrame.isna, klass=_shared_doc_kwargs["klass"])
     def isna(self) -> DataFrame:
-        result = self._constructor(self._mgr.isna(func=isna))
+        res_mgr = self._mgr.isna(func=isna)
+        result = self._constructor_from_mgr(res_mgr, axes=res_mgr.axes)
         return result.__finalize__(self, method="isna")
 
     @doc(NDFrame.isna, klass=_shared_doc_kwargs["klass"])
@@ -6787,7 +6806,7 @@ def sort_values(
                 self._get_block_manager_axis(axis), default_index(len(indexer))
             )
 
-        result = self._constructor(new_data)
+        result = self._constructor_from_mgr(new_data, axes=new_data.axes)
         if inplace:
             return self._update_inplace(result)
         else:
@@ -7481,7 +7500,7 @@ def _dispatch_frame_op(
         if not is_list_like(right):
             # i.e. scalar, faster than checking np.ndim(right) == 0
             bm = self._mgr.apply(array_op, right=right)
-            return self._constructor(bm)
+            return self._constructor_from_mgr(bm, axes=bm.axes)
 
         elif isinstance(right, DataFrame):
             assert self.index.equals(right.index)
@@ -7501,7 +7520,7 @@ def _dispatch_frame_op(
                 right._mgr,  # type: ignore[arg-type]
                 array_op,
             )
-            return self._constructor(bm)
+            return self._constructor_from_mgr(bm, axes=bm.axes)
 
         elif isinstance(right, Series) and axis == 1:
             # axis=1 means we want to operate row-by-row
@@ -9480,7 +9499,8 @@ def diff(self, periods: int = 1, axis: Axis = 0) -> DataFrame:
             axis = 0
 
         new_data = self._mgr.diff(n=periods)
-        return self._constructor(new_data).__finalize__(self, "diff")
+        res_df = self._constructor_from_mgr(new_data, axes=new_data.axes)
+        return res_df.__finalize__(self, "diff")
 
     # ----------------------------------------------------------------------
     # Function application
@@ -10336,12 +10356,13 @@ def _series_round(ser: Series, decimals: int) -> Series:
             # Dispatch to Block.round
             # Argument "decimals" to "round" of "BaseBlockManager" has incompatible
             # type "Union[int, integer[Any]]"; expected "int"
-            return self._constructor(
-                self._mgr.round(
-                    decimals=decimals,  # type: ignore[arg-type]
-                    using_cow=using_copy_on_write(),
-                ),
-            ).__finalize__(self, method="round")
+            new_mgr = self._mgr.round(
+                decimals=decimals,  # type: ignore[arg-type]
+                using_cow=using_copy_on_write(),
+            )
+            return self._constructor_from_mgr(new_mgr, axes=new_mgr.axes).__finalize__(
+                self, method="round"
+            )
         else:
             raise TypeError("decimals must be an integer, a dict-like or a Series")
 
@@ -10893,7 +10914,7 @@ def _get_data() -> DataFrame:
         # After possibly _get_data and transposing, we are now in the
         #  simple case where we can use BlockManager.reduce
         res = df._mgr.reduce(blk_func)
-        out = df._constructor(res).iloc[0]
+        out = df._constructor_from_mgr(res, axes=res.axes).iloc[0]
         if out_dtype is not None:
             out = out.astype(out_dtype)
         elif (df._mgr.get_dtypes() == object).any():
@@ -11507,7 +11528,7 @@ def quantile(
             res = data._mgr.take(indexer[q_idx], verify=False)
             res.axes[1] = q
 
-        result = self._constructor(res)
+        result = self._constructor_from_mgr(res, axes=res.axes)
         return result.__finalize__(self, method="quantile")
 
     def to_timestamp(
@@ -11835,7 +11856,7 @@ def _to_dict_of_blocks(self, copy: bool = True):
         mgr = mgr_to_mgr(mgr, "block")
         mgr = cast(BlockManager, mgr)
         return {
-            k: self._constructor(v).__finalize__(self)
+            k: self._constructor_from_mgr(v, axes=v.axes).__finalize__(self)
             for k, v, in mgr.to_dict(copy=copy).items()
         }