Backport PR #51834: CoW: Set copy=False in internal usages of Series/DataFrame constructors (#52012)

CoW: Set copy=False in internal usages of Series/DataFrame constructors (#51834)

(cherry picked from commit c98b7c8)

Co-authored-by: Patrick Hoefler <61934744+phofl@users.noreply.github.com>

Author: jorisvandenbossche

pandas/core/frame.py

@@ -1592,16 +1592,21 @@ def dot(self, other: AnyArrayLike | DataFrame) -> DataFrame | Series:
 
         if isinstance(other, DataFrame):
             return self._constructor(
-                np.dot(lvals, rvals), index=left.index, columns=other.columns
+                np.dot(lvals, rvals),
+                index=left.index,
+                columns=other.columns,
+                copy=False,
             )
         elif isinstance(other, Series):
-            return self._constructor_sliced(np.dot(lvals, rvals), index=left.index)
+            return self._constructor_sliced(
+                np.dot(lvals, rvals), index=left.index, copy=False
+            )
         elif isinstance(rvals, (np.ndarray, Index)):
             result = np.dot(lvals, rvals)
             if result.ndim == 2:
-                return self._constructor(result, index=left.index)
+                return self._constructor(result, index=left.index, copy=False)
             else:
-                return self._constructor_sliced(result, index=left.index)
+                return self._constructor_sliced(result, index=left.index, copy=False)
         else:  # pragma: no cover
             raise TypeError(f"unsupported type: {type(other)}")
 
@@ -3571,9 +3576,15 @@ def transpose(self, *args, copy: bool = False) -> DataFrame:
 
         else:
             new_arr = self.values.T
-            if copy:
+            if copy and not using_copy_on_write():
                 new_arr = new_arr.copy()
-            result = self._constructor(new_arr, index=self.columns, columns=self.index)
+            result = self._constructor(
+                new_arr,
+                index=self.columns,
+                columns=self.index,
+                # We already made a copy (more than one block)
+                copy=False,
+            )
 
         return result.__finalize__(self, method="transpose")
 
@@ -3795,7 +3806,7 @@ def _getitem_multilevel(self, key):
             else:
                 new_values = self._values[:, loc]
                 result = self._constructor(
-                    new_values, index=self.index, columns=result_columns
+                    new_values, index=self.index, columns=result_columns, copy=False
                 )
                 if using_copy_on_write() and isinstance(loc, slice):
                     result._mgr.add_references(self._mgr)  # type: ignore[arg-type]
@@ -4029,7 +4040,7 @@ def _setitem_frame(self, key, value):
         if isinstance(key, np.ndarray):
             if key.shape != self.shape:
                 raise ValueError("Array conditional must be same shape as self")
-            key = self._constructor(key, **self._construct_axes_dict())
+            key = self._constructor(key, **self._construct_axes_dict(), copy=False)
 
         if key.size and not all(is_bool_dtype(dtype) for dtype in key.dtypes):
             raise TypeError(
@@ -4939,7 +4950,9 @@ def _reindex_multi(
             #  condition more specific.
             indexer = row_indexer, col_indexer
             new_values = take_2d_multi(self.values, indexer, fill_value=fill_value)
-            return self._constructor(new_values, index=new_index, columns=new_columns)
+            return self._constructor(
+                new_values, index=new_index, columns=new_columns, copy=False
+            )
         else:
             return self._reindex_with_indexers(
                 {0: [new_index, row_indexer], 1: [new_columns, col_indexer]},
@@ -10060,7 +10073,7 @@ def corr(
                 f"'{method}' was supplied"
             )
 
-        result = self._constructor(correl, index=idx, columns=cols)
+        result = self._constructor(correl, index=idx, columns=cols, copy=False)
         return result.__finalize__(self, method="corr")
 
     def cov(
@@ -10191,7 +10204,7 @@ def cov(
         else:
             base_cov = libalgos.nancorr(mat, cov=True, minp=min_periods)
 
-        result = self._constructor(base_cov, index=idx, columns=cols)
+        result = self._constructor(base_cov, index=idx, columns=cols, copy=False)
         return result.__finalize__(self, method="cov")
 
     def corrwith(
@@ -10304,7 +10317,9 @@ def c(x):
                 return nanops.nancorr(x[0], x[1], method=method)
 
             correl = self._constructor_sliced(
-                map(c, zip(left.values.T, right.values.T)), index=left.columns
+                map(c, zip(left.values.T, right.values.T)),
+                index=left.columns,
+                copy=False,
             )
 
         else:
@@ -10415,7 +10430,7 @@ def count(self, axis: Axis = 0, numeric_only: bool = False):
                 series_counts = notna(frame).sum(axis=axis)
                 counts = series_counts._values
                 result = self._constructor_sliced(
-                    counts, index=frame._get_agg_axis(axis)
+                    counts, index=frame._get_agg_axis(axis), copy=False
                 )
 
         return result.astype("int64").__finalize__(self, method="count")
@@ -10524,7 +10539,7 @@ def _reduce_axis1(self, name: str, func, skipna: bool) -> Series:
             middle = func(arr, axis=0, skipna=skipna)
             result = ufunc(result, middle)
 
-        res_ser = self._constructor_sliced(result, index=self.index)
+        res_ser = self._constructor_sliced(result, index=self.index, copy=False)
         return res_ser
 
     def nunique(self, axis: Axis = 0, dropna: bool = True) -> Series:
@@ -11206,6 +11221,7 @@ def isin(self, values: Series | DataFrame | Sequence | Mapping) -> DataFrame:
                 ).reshape(self.shape),
                 self.index,
                 self.columns,
+                copy=False,
             )
         return result.__finalize__(self, method="isin")
 

pandas/core/generic.py

@@ -779,6 +779,8 @@ def swapaxes(
         return self._constructor(
             new_values,
             *new_axes,
+            # The no-copy case for CoW is handled above
+            copy=False,
         ).__finalize__(self, method="swapaxes")
 
     @final
@@ -9629,7 +9631,7 @@ def _where(
                 cond = np.asanyarray(cond)
             if cond.shape != self.shape:
                 raise ValueError("Array conditional must be same shape as self")
-            cond = self._constructor(cond, **self._construct_axes_dict())
+            cond = self._constructor(cond, **self._construct_axes_dict(), copy=False)
 
         # make sure we are boolean
         fill_value = bool(inplace)
@@ -9704,7 +9706,9 @@ def _where(
 
             # we are the same shape, so create an actual object for alignment
             else:
-                other = self._constructor(other, **self._construct_axes_dict())
+                other = self._constructor(
+                    other, **self._construct_axes_dict(), copy=False
+                )
 
         if axis is None:
             axis = 0

pandas/core/series.py

@@ -840,7 +840,7 @@ def view(self, dtype: Dtype | None = None) -> Series:
         # self.array instead of self._values so we piggyback on PandasArray
         #  implementation
         res_values = self.array.view(dtype)
-        res_ser = self._constructor(res_values, index=self.index)
+        res_ser = self._constructor(res_values, index=self.index, copy=False)
         if isinstance(res_ser._mgr, SingleBlockManager) and using_copy_on_write():
             blk = res_ser._mgr._block
             blk.refs = cast("BlockValuesRefs", self._references)
@@ -1073,7 +1073,7 @@ def _get_values_tuple(self, key: tuple):
 
         # If key is contained, would have returned by now
         indexer, new_index = self.index.get_loc_level(key)
-        new_ser = self._constructor(self._values[indexer], index=new_index)
+        new_ser = self._constructor(self._values[indexer], index=new_index, copy=False)
         if using_copy_on_write() and isinstance(indexer, slice):
             new_ser._mgr.add_references(self._mgr)  # type: ignore[arg-type]
         return new_ser.__finalize__(self)
@@ -1113,7 +1113,9 @@ def _get_value(self, label, takeable: bool = False):
 
             new_index = mi[loc]
             new_index = maybe_droplevels(new_index, label)
-            new_ser = self._constructor(new_values, index=new_index, name=self.name)
+            new_ser = self._constructor(
+                new_values, index=new_index, name=self.name, copy=False
+            )
             if using_copy_on_write() and isinstance(loc, slice):
                 new_ser._mgr.add_references(self._mgr)  # type: ignore[arg-type]
             return new_ser.__finalize__(self)
@@ -1413,7 +1415,7 @@ def repeat(self, repeats: int | Sequence[int], axis: None = None) -> Series:
         nv.validate_repeat((), {"axis": axis})
         new_index = self.index.repeat(repeats)
         new_values = self._values.repeat(repeats)
-        return self._constructor(new_values, index=new_index).__finalize__(
+        return self._constructor(new_values, index=new_index, copy=False).__finalize__(
             self, method="repeat"
         )
 
@@ -1579,7 +1581,7 @@ def reset_index(
                 self.index = new_index
             else:
                 return self._constructor(
-                    self._values.copy(), index=new_index
+                    self._values.copy(), index=new_index, copy=False
                 ).__finalize__(self, method="reset_index")
         elif inplace:
             raise TypeError(
@@ -2101,7 +2103,7 @@ def mode(self, dropna: bool = True) -> Series:
 
         # Ensure index is type stable (should always use int index)
         return self._constructor(
-            res_values, index=range(len(res_values)), name=self.name
+            res_values, index=range(len(res_values)), name=self.name, copy=False
         )
 
     def unique(self) -> ArrayLike:  # pylint: disable=useless-parent-delegation
@@ -2365,7 +2367,7 @@ def duplicated(self, keep: DropKeep = "first") -> Series:
         dtype: bool
         """
         res = self._duplicated(keep=keep)
-        result = self._constructor(res, index=self.index)
+        result = self._constructor(res, index=self.index, copy=False)
         return result.__finalize__(self, method="duplicated")
 
     def idxmin(self, axis: Axis = 0, skipna: bool = True, *args, **kwargs) -> Hashable:
@@ -2543,7 +2545,7 @@ def round(self, decimals: int = 0, *args, **kwargs) -> Series:
         """
         nv.validate_round(args, kwargs)
         result = self._values.round(decimals)
-        result = self._constructor(result, index=self.index).__finalize__(
+        result = self._constructor(result, index=self.index, copy=False).__finalize__(
             self, method="round"
         )
 
@@ -2844,7 +2846,7 @@ def diff(self, periods: int = 1) -> Series:
         {examples}
         """
         result = algorithms.diff(self._values, periods)
-        return self._constructor(result, index=self.index).__finalize__(
+        return self._constructor(result, index=self.index, copy=False).__finalize__(
             self, method="diff"
         )
 
@@ -2962,7 +2964,7 @@ def dot(self, other: AnyArrayLike) -> Series | np.ndarray:
 
         if isinstance(other, ABCDataFrame):
             return self._constructor(
-                np.dot(lvals, rvals), index=other.columns
+                np.dot(lvals, rvals), index=other.columns, copy=False
             ).__finalize__(self, method="dot")
         elif isinstance(other, Series):
             return np.dot(lvals, rvals)
@@ -3264,7 +3266,7 @@ def combine(
         # try_float=False is to match agg_series
         npvalues = lib.maybe_convert_objects(new_values, try_float=False)
         res_values = maybe_cast_pointwise_result(npvalues, self.dtype, same_dtype=False)
-        return self._constructor(res_values, index=new_index, name=new_name)
+        return self._constructor(res_values, index=new_index, name=new_name, copy=False)
 
     def combine_first(self, other) -> Series:
         """
@@ -3615,7 +3617,7 @@ def sort_values(
             return self.copy(deep=None)
 
         result = self._constructor(
-            self._values[sorted_index], index=self.index[sorted_index]
+            self._values[sorted_index], index=self.index[sorted_index], copy=False
         )
 
         if ignore_index:
@@ -3863,7 +3865,9 @@ def argsort(
         else:
             result = np.argsort(values, kind=kind)
 
-        res = self._constructor(result, index=self.index, name=self.name, dtype=np.intp)
+        res = self._constructor(
+            result, index=self.index, name=self.name, dtype=np.intp, copy=False
+        )
         return res.__finalize__(self, method="argsort")
 
     def nlargest(
@@ -4238,7 +4242,7 @@ def explode(self, ignore_index: bool = False) -> Series:
         else:
             index = self.index.repeat(counts)
 
-        return self._constructor(values, index=index, name=self.name)
+        return self._constructor(values, index=index, name=self.name, copy=False)
 
     def unstack(self, level: IndexLabel = -1, fill_value: Hashable = None) -> DataFrame:
         """
@@ -4369,7 +4373,7 @@ def map(
         dtype: object
         """
         new_values = self._map_values(arg, na_action=na_action)
-        return self._constructor(new_values, index=self.index).__finalize__(
+        return self._constructor(new_values, index=self.index, copy=False).__finalize__(
             self, method="map"
         )
 
@@ -4663,7 +4667,7 @@ def _reindex_indexer(
         new_values = algorithms.take_nd(
             self._values, indexer, allow_fill=True, fill_value=None
         )
-        return self._constructor(new_values, index=new_index)
+        return self._constructor(new_values, index=new_index, copy=False)
 
     def _needs_reindex_multi(self, axes, method, level) -> bool:
         """
@@ -5378,7 +5382,7 @@ def isin(self, values) -> Series:
         dtype: bool
         """
         result = algorithms.isin(self._values, values)
-        return self._constructor(result, index=self.index).__finalize__(
+        return self._constructor(result, index=self.index, copy=False).__finalize__(
             self, method="isin"
         )