Backport PR #51571 on branch 2.0.x (ENH: DataFrame.fillna making deep copy for dict arg) (#51636)

Backport PR #51571: ENH: DataFrame.fillna making deep copy for dict arg

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

Author: meeseeksmachine

pandas/core/generic.py

@@ -6876,8 +6876,10 @@ def fillna(
                         "with dict/Series column "
                         "by column"
                     )
-
-                result = self if inplace else self.copy()
+                if using_copy_on_write():
+                    result = self.copy(deep=None)
+                else:
+                    result = self if inplace else self.copy()
                 is_dict = isinstance(downcast, dict)
                 for k, v in value.items():
                     if k not in result:
@@ -6931,8 +6933,10 @@ def fillna(
                                     result.iloc[:, loc] = res_loc
                                 else:
                                     result.isetitem(loc, res_loc)
-
-                return result if not inplace else None
+                if inplace:
+                    return self._update_inplace(result)
+                else:
+                    return result
 
             elif not is_list_like(value):
                 if axis == 1:

pandas/tests/copy_view/test_interp_fillna.py

@@ -180,6 +180,21 @@ def test_fillna(using_copy_on_write):
     tm.assert_frame_equal(df_orig, df)
 
 
+def test_fillna_dict(using_copy_on_write):
+    df = DataFrame({"a": [1.5, np.nan], "b": 1})
+    df_orig = df.copy()
+
+    df2 = df.fillna({"a": 100.5})
+    if using_copy_on_write:
+        assert np.shares_memory(get_array(df, "b"), get_array(df2, "b"))
+        assert not np.shares_memory(get_array(df, "a"), get_array(df2, "a"))
+    else:
+        assert not np.shares_memory(get_array(df, "b"), get_array(df2, "b"))
+
+    df2.iloc[0, 1] = 100
+    tm.assert_frame_equal(df_orig, df)
+
+
 @pytest.mark.parametrize("downcast", [None, False])
 def test_fillna_inplace(using_copy_on_write, downcast):
     df = DataFrame({"a": [1.5, np.nan], "b": 1})

pandas/tests/extension/json/test_json.py

@@ -301,6 +301,18 @@ def test_searchsorted(self, data_for_sorting):
     def test_equals(self, data, na_value, as_series):
         super().test_equals(data, na_value, as_series)
 
+    def test_fillna_copy_frame(self, data_missing, using_copy_on_write):
+        arr = data_missing.take([1, 1])
+        df = pd.DataFrame({"A": arr})
+
+        filled_val = df.iloc[0, 0]
+        result = df.fillna(filled_val)
+
+        if using_copy_on_write:
+            assert df.A.values is result.A.values
+        else:
+            assert df.A.values is not result.A.values
+
 
 class TestCasting(BaseJSON, base.BaseCastingTests):
     @pytest.mark.xfail(reason="failing on np.array(self, dtype=str)")