Backport PR #51659 on branch 2.0.x (ENH: Improve replace lazy copy for categoricals) (#51699)

Backport PR #51659: ENH: Improve replace lazy copy for categoricals

Co-authored-by: Patrick Hoefler <[email protected]>

Author: meeseeksmachine

pandas/core/internals/blocks.py

@@ -701,8 +701,7 @@ def replace_list(
             # TODO: avoid special-casing
             # GH49404
             if using_cow and inplace:
-                # TODO(CoW): Optimize
-                blk = self.copy()
+                blk = self.copy(deep=self.refs.has_reference())
             else:
                 blk = self if inplace else self.copy()
             values = cast(Categorical, blk.values)

pandas/tests/copy_view/test_replace.py

@@ -112,6 +112,38 @@ def test_replace_to_replace_wrong_dtype(using_copy_on_write):
         assert not np.shares_memory(get_array(df, "b"), get_array(df2, "b"))
 
 
+def test_replace_list_categorical(using_copy_on_write):
+    df = DataFrame({"a": ["a", "b", "c"]}, dtype="category")
+    arr = get_array(df, "a")
+    df.replace(["c"], value="a", inplace=True)
+    assert np.shares_memory(arr.codes, get_array(df, "a").codes)
+    if using_copy_on_write:
+        assert df._mgr._has_no_reference(0)
+
+    df_orig = df.copy()
+    df2 = df.replace(["b"], value="a")
+    assert not np.shares_memory(arr.codes, get_array(df2, "a").codes)
+
+    tm.assert_frame_equal(df, df_orig)
+
+
+def test_replace_list_inplace_refs_categorical(using_copy_on_write):
+    df = DataFrame({"a": ["a", "b", "c"]}, dtype="category")
+    view = df[:]
+    df_orig = df.copy()
+    df.replace(["c"], value="a", inplace=True)
+    if using_copy_on_write:
+        assert not np.shares_memory(
+            get_array(view, "a").codes, get_array(df, "a").codes
+        )
+        tm.assert_frame_equal(df_orig, view)
+    else:
+        # This could be inplace
+        assert not np.shares_memory(
+            get_array(view, "a").codes, get_array(df, "a").codes
+        )
+
+
 @pytest.mark.parametrize("to_replace", [1.5, [1.5], []])
 def test_replace_inplace(using_copy_on_write, to_replace):
     df = DataFrame({"a": [1.5, 2, 3]})