Backport PR #42579: BUG: DataFrame.copy not consolidating (#42679)

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

Author: meeseeksmachine

doc/source/whatsnew/v1.3.1.rst

@@ -37,7 +37,7 @@ Bug fixes
 ~~~~~~~~~
 - Fixed bug in :meth:`DataFrame.transpose` dropping values when the DataFrame had an Extension Array dtype and a duplicate index (:issue:`42380`)
 - Fixed bug in :meth:`DataFrame.to_xml` raising ``KeyError`` when called with ``index=False`` and an offset index (:issue:`42458`)
--
+- Fixed bug in :meth:`DataFrame.copy` failing to consolidate blocks in the result (:issue:`42579`)
 
 .. ---------------------------------------------------------------------------
 

pandas/core/internals/managers.py

@@ -594,6 +594,9 @@ def copy_func(ax):
 
         res = self.apply("copy", deep=deep)
         res.axes = new_axes
+
+        if deep:
+            res._consolidate_inplace()
         return res
 
     def consolidate(self: T) -> T:

pandas/core/reshape/reshape.py

@@ -399,7 +399,8 @@ def _unstack_multiple(data, clocs, fill_value=None):
 
             return result
 
-        dummy = data.copy()
+        # GH#42579 deep=False to avoid consolidating
+        dummy = data.copy(deep=False)
         dummy.index = dummy_index
 
         unstacked = dummy.unstack("__placeholder__", fill_value=fill_value)

pandas/tests/frame/methods/test_copy.py

@@ -1,5 +1,8 @@
+import numpy as np
 import pytest
 
+import pandas.util._test_decorators as td
+
 from pandas import DataFrame
 import pandas._testing as tm
 
@@ -41,3 +44,20 @@ def test_copy(self, float_frame, float_string_frame):
         # copy objects
         copy = float_string_frame.copy()
         assert copy._mgr is not float_string_frame._mgr
+
+    @td.skip_array_manager_invalid_test
+    def test_copy_consolidates(self):
+        # GH#42477
+        df = DataFrame(
+            {
+                "a": np.random.randint(0, 100, size=55),
+                "b": np.random.randint(0, 100, size=55),
+            }
+        )
+
+        for i in range(0, 10):
+            df.loc[:, f"n_{i}"] = np.random.randint(0, 100, size=55)
+
+        assert len(df._mgr.blocks) == 11
+        result = df.copy()
+        assert len(result._mgr.blocks) == 1

pandas/tests/internals/test_internals.py

@@ -461,6 +461,9 @@ def test_copy(self, mgr):
                 # DatetimeTZBlock has DatetimeIndex values
                 assert cp_blk.values._data.base is blk.values._data.base
 
+        # copy(deep=True) consolidates, so the block-wise assertions will
+        #  fail is mgr is not consolidated
+        mgr._consolidate_inplace()
         cp = mgr.copy(deep=True)
         for blk, cp_blk in zip(mgr.blocks, cp.blocks):