CoW: Add warning for replace with inplace (#56060)

Author: phofl

pandas/core/generic.py

@@ -100,6 +100,7 @@
     SettingWithCopyError,
     SettingWithCopyWarning,
     _chained_assignment_method_msg,
+    _chained_assignment_warning_method_msg,
 )
 from pandas.util._decorators import (
     deprecate_nonkeyword_arguments,
@@ -7773,6 +7774,22 @@ def replace(
                         ChainedAssignmentError,
                         stacklevel=2,
                     )
+            elif not PYPY and not using_copy_on_write():
+                ctr = sys.getrefcount(self)
+                ref_count = REF_COUNT
+                if isinstance(self, ABCSeries) and hasattr(self, "_cacher"):
+                    # in non-CoW mode, chained Series access will populate the
+                    # `_item_cache` which results in an increased ref count not below
+                    # the threshold, while we still need to warn. We detect this case
+                    # of a Series derived from a DataFrame through the presence of
+                    # `_cacher`
+                    ref_count += 1
+                if ctr <= ref_count:
+                    warnings.warn(
+                        _chained_assignment_warning_method_msg,
+                        FutureWarning,
+                        stacklevel=2,
+                    )
 
         if not is_bool(regex) and to_replace is not None:
             raise ValueError("'to_replace' must be 'None' if 'regex' is not a bool")

pandas/errors/__init__.py

@@ -503,6 +503,19 @@ class ChainedAssignmentError(Warning):
 )
 
 
+_chained_assignment_warning_method_msg = (
+    "A value is trying to be set on a copy of a DataFrame or Series "
+    "through chained assignment using an inplace method.\n"
+    "The behavior will change in pandas 3.0. This inplace method will "
+    "never work because the intermediate object on which we are setting "
+    "values always behaves as a copy.\n\n"
+    "For example, when doing 'df[col].method(value, inplace=True)', try "
+    "using 'df.method({col: value}, inplace=True)' or "
+    "df[col] = df[col].method(value) instead, to perform "
+    "the operation inplace on the original object.\n\n"
+)
+
+
 class NumExprClobberingError(NameError):
     """
     Exception raised when trying to use a built-in numexpr name as a variable name.

pandas/tests/copy_view/test_replace.py

@@ -4,6 +4,7 @@
 from pandas import (
     Categorical,
     DataFrame,
+    option_context,
 )
 import pandas._testing as tm
 from pandas.tests.copy_view.util import get_array
@@ -395,6 +396,17 @@ def test_replace_chained_assignment(using_copy_on_write):
         with tm.raises_chained_assignment_error():
             df[["a"]].replace(1, 100, inplace=True)
         tm.assert_frame_equal(df, df_orig)
+    else:
+        with tm.assert_produces_warning(FutureWarning, match="inplace method"):
+            with option_context("mode.chained_assignment", None):
+                df[["a"]].replace(1, 100, inplace=True)
+
+        with tm.assert_produces_warning(FutureWarning, match="inplace method"):
+            with option_context("mode.chained_assignment", None):
+                df[df.a > 5].replace(1, 100, inplace=True)
+
+        with tm.assert_produces_warning(FutureWarning, match="inplace method"):
+            df["a"].replace(1, 100, inplace=True)
 
 
 def test_replace_listlike(using_copy_on_write):

scripts/validate_unwanted_patterns.py

@@ -50,6 +50,7 @@
     "_global_config",
     "_chained_assignment_msg",
     "_chained_assignment_method_msg",
+    "_chained_assignment_warning_method_msg",
     "_version_meson",
     # The numba extensions need this to mock the iloc object
     "_iLocIndexer",