CoW: Remove a few copy=False statements (#57346)

Author: phofl

pandas/core/apply.py

@@ -1361,7 +1361,7 @@ def infer_to_same_shape(self, results: ResType, res_index: Index) -> DataFrame:
         result.index = res_index
 
         # infer dtypes
-        result = result.infer_objects(copy=False)
+        result = result.infer_objects()
 
         return result
 
@@ -1873,7 +1873,7 @@ def relabel_result(
         # assign the new user-provided "named aggregation" as index names, and reindex
         # it based on the whole user-provided names.
         s.index = reordered_indexes[idx : idx + len(fun)]
-        reordered_result_in_dict[col] = s.reindex(columns, copy=False)
+        reordered_result_in_dict[col] = s.reindex(columns)
         idx = idx + len(fun)
     return reordered_result_in_dict
 

pandas/core/computation/align.py

@@ -134,7 +134,7 @@ def _align_core(terms):
                         w, category=PerformanceWarning, stacklevel=find_stack_level()
                     )
 
-                obj = ti.reindex(reindexer, axis=axis, copy=False)
+                obj = ti.reindex(reindexer, axis=axis)
                 terms[i].update(obj)
 
         terms[i].update(terms[i].value.values)

pandas/core/groupby/generic.py

@@ -1648,7 +1648,7 @@ def _wrap_applied_output(
                 res_index = self._grouper.result_index
 
             result = self.obj._constructor(index=res_index, columns=data.columns)
-            result = result.astype(data.dtypes, copy=False)
+            result = result.astype(data.dtypes)
             return result
 
         # GH12824
@@ -1815,7 +1815,7 @@ def _transform_general(self, func, engine, engine_kwargs, *args, **kwargs):
 
         concat_index = obj.columns
         concatenated = concat(applied, axis=0, verify_integrity=False)
-        concatenated = concatenated.reindex(concat_index, axis=1, copy=False)
+        concatenated = concatenated.reindex(concat_index, axis=1)
         return self._set_result_index_ordered(concatenated)
 
     __examples_dataframe_doc = dedent(

pandas/core/groupby/groupby.py

@@ -1241,7 +1241,7 @@ def _concat_objects(
                 indexer, _ = result.index.get_indexer_non_unique(target)
                 result = result.take(indexer, axis=0)
             else:
-                result = result.reindex(ax, axis=0, copy=False)
+                result = result.reindex(ax, axis=0)
 
         else:
             result = concat(values, axis=0)
@@ -1269,18 +1269,18 @@ def _set_result_index_ordered(
 
         if self._grouper.is_monotonic and not self._grouper.has_dropped_na:
             # shortcut if we have an already ordered grouper
-            result = result.set_axis(index, axis=0, copy=False)
+            result = result.set_axis(index, axis=0)
             return result
 
         # row order is scrambled => sort the rows by position in original index
         original_positions = Index(self._grouper.result_ilocs)
-        result = result.set_axis(original_positions, axis=0, copy=False)
+        result = result.set_axis(original_positions, axis=0)
         result = result.sort_index(axis=0)
         if self._grouper.has_dropped_na:
             # Add back in any missing rows due to dropna - index here is integral
             # with values referring to the row of the input so can use RangeIndex
             result = result.reindex(RangeIndex(len(index)), axis=0)
-        result = result.set_axis(index, axis=0, copy=False)
+        result = result.set_axis(index, axis=0)
 
         return result
 
@@ -1913,7 +1913,7 @@ def _wrap_transform_fast_result(self, result: NDFrameT) -> NDFrameT:
 
         # for each col, reshape to size of original frame by take operation
         ids = self._grouper.ids
-        result = result.reindex(self._grouper.result_index, axis=0, copy=False)
+        result = result.reindex(self._grouper.result_index, axis=0)
 
         if self.obj.ndim == 1:
             # i.e. SeriesGroupBy

pandas/core/indexing.py

@@ -2280,7 +2280,7 @@ def _setitem_with_indexer_missing(self, indexer, value):
             has_dtype = hasattr(value, "dtype")
             if isinstance(value, ABCSeries):
                 # append a Series
-                value = value.reindex(index=self.obj.columns, copy=True)
+                value = value.reindex(index=self.obj.columns)
                 value.name = indexer
             elif isinstance(value, dict):
                 value = Series(
@@ -2310,7 +2310,7 @@ def _setitem_with_indexer_missing(self, indexer, value):
                 if not has_dtype:
                     # i.e. if we already had a Series or ndarray, keep that
                     #  dtype.  But if we had a list or dict, then do inference
-                    df = df.infer_objects(copy=False)
+                    df = df.infer_objects()
                 self.obj._mgr = df._mgr
             else:
                 self.obj._mgr = self.obj._append(value)._mgr
@@ -2383,7 +2383,8 @@ def ravel(i):
             # we have a frame, with multiple indexers on both axes; and a
             # series, so need to broadcast (see GH5206)
             if sum_aligners == self.ndim and all(is_sequence(_) for _ in indexer):
-                ser_values = ser.reindex(obj.axes[0][indexer[0]], copy=True)._values
+                # TODO(CoW): copy shouldn't be needed here
+                ser_values = ser.reindex(obj.axes[0][indexer[0]]).copy()._values
 
                 # single indexer
                 if len(indexer) > 1 and not multiindex_indexer:

pandas/core/internals/construction.py

@@ -519,11 +519,11 @@ def _homogenize(
     for val in data:
         if isinstance(val, (ABCSeries, Index)):
             if dtype is not None:
-                val = val.astype(dtype, copy=False)
+                val = val.astype(dtype)
             if isinstance(val, ABCSeries) and val.index is not index:
                 # Forces alignment. No need to copy data since we
                 # are putting it into an ndarray later
-                val = val.reindex(index, copy=False)
+                val = val.reindex(index)
             refs.append(val._references)
             val = val._values
         else:

pandas/core/methods/describe.py

@@ -173,7 +173,7 @@ def describe(self, percentiles: Sequence[float] | np.ndarray) -> DataFrame:
 
         col_names = reorder_columns(ldesc)
         d = concat(
-            [x.reindex(col_names, copy=False) for x in ldesc],
+            [x.reindex(col_names) for x in ldesc],
             axis=1,
             sort=False,
         )

pandas/core/reshape/encoding.py

@@ -339,7 +339,7 @@ def get_empty_frame(data) -> DataFrame:
             )
             sparse_series.append(Series(data=sarr, index=index, name=col, copy=False))
 
-        return concat(sparse_series, axis=1, copy=False)
+        return concat(sparse_series, axis=1)
 
     else:
         # ensure ndarray layout is column-major

pandas/core/strings/accessor.py

@@ -661,7 +661,6 @@ def cat(
                 join=(join if join == "inner" else "outer"),
                 keys=range(len(others)),
                 sort=False,
-                copy=False,
             )
             data, others = data.align(others, join=join)
             others = [others[x] for x in others]  # again list of Series

pandas/core/window/ewm.py

@@ -1072,7 +1072,7 @@ def mean(self, *args, update=None, update_times=None, **kwargs):
                 result_kwargs["columns"] = self._selected_obj.columns
             else:
                 result_kwargs["name"] = self._selected_obj.name
-            np_array = self._selected_obj.astype(np.float64, copy=False).to_numpy()
+            np_array = self._selected_obj.astype(np.float64).to_numpy()
         ewma_func = generate_online_numba_ewma_func(
             **get_jit_arguments(self.engine_kwargs)
         )

pandas/core/window/rolling.py

@@ -270,7 +270,7 @@ def _create_data(self, obj: NDFrameT, numeric_only: bool = False) -> NDFrameT:
         """
         # filter out the on from the object
         if self.on is not None and not isinstance(self.on, Index) and obj.ndim == 2:
-            obj = obj.reindex(columns=obj.columns.difference([self.on]), copy=False)
+            obj = obj.reindex(columns=obj.columns.difference([self.on]))
         if obj.ndim > 1 and numeric_only:
             obj = self._make_numeric_only(obj)
         return obj

pandas/io/parsers/base_parser.py

@@ -1354,7 +1354,7 @@ def _isindex(colspec):
             date_cols.update(old_names)
 
     if isinstance(data_dict, DataFrame):
-        data_dict = concat([DataFrame(new_data), data_dict], axis=1, copy=False)
+        data_dict = concat([DataFrame(new_data), data_dict], axis=1)
     else:
         data_dict.update(new_data)
     new_cols.extend(columns)

pandas/plotting/_matplotlib/core.py

@@ -678,7 +678,7 @@ def _compute_plot_data(self) -> None:
 
         # GH16953, infer_objects is needed as fallback, for ``Series``
         # with ``dtype == object``
-        data = data.infer_objects(copy=False)
+        data = data.infer_objects()
         include_type = [np.number, "datetime", "datetimetz", "timedelta"]
 
         # GH23719, allow plotting boolean

pandas/plotting/_matplotlib/hist.py

@@ -94,7 +94,7 @@ def _adjust_bins(self, bins: int | np.ndarray | list[np.ndarray]):
 
     def _calculate_bins(self, data: Series | DataFrame, bins) -> np.ndarray:
         """Calculate bins given data"""
-        nd_values = data.infer_objects(copy=False)._get_numeric_data()
+        nd_values = data.infer_objects()._get_numeric_data()
         values = np.ravel(nd_values)
         values = values[~isna(values)]