diff --git a/doc/source/whatsnew/v2.2.0.rst b/doc/source/whatsnew/v2.2.0.rst index 2b436bc5d1855..b138e91b41661 100644 --- a/doc/source/whatsnew/v2.2.0.rst +++ b/doc/source/whatsnew/v2.2.0.rst @@ -789,6 +789,7 @@ Numeric - Bug in :meth:`Series.__floordiv__` and :meth:`Series.__truediv__` for :class:`ArrowDtype` with integral dtypes raising for large divisors (:issue:`56706`) - Bug in :meth:`Series.__floordiv__` for :class:`ArrowDtype` with integral dtypes raising for large values (:issue:`56645`) - Bug in :meth:`Series.pow` not filling missing values correctly (:issue:`55512`) +- Bug in :meth:`Series.replace` and :meth:`DataFrame.replace` matching float ``0.0`` with ``False`` and vice versa (:issue:`55398`) Conversion ^^^^^^^^^^ diff --git a/pandas/core/missing.py b/pandas/core/missing.py index 5dd9aaf5fbb4a..ff45662d0bdc8 100644 --- a/pandas/core/missing.py +++ b/pandas/core/missing.py @@ -31,6 +31,7 @@ from pandas.core.dtypes.cast import infer_dtype_from from pandas.core.dtypes.common import ( is_array_like, + is_bool_dtype, is_numeric_dtype, is_numeric_v_string_like, is_object_dtype, @@ -100,21 +101,34 @@ def mask_missing(arr: ArrayLike, values_to_mask) -> npt.NDArray[np.bool_]: # GH 21977 mask = np.zeros(arr.shape, dtype=bool) - for x in nonna: - if is_numeric_v_string_like(arr, x): - # GH#29553 prevent numpy deprecation warnings - pass - else: - if potential_na: - new_mask = np.zeros(arr.shape, dtype=np.bool_) - new_mask[arr_mask] = arr[arr_mask] == x + if ( + is_numeric_dtype(arr.dtype) + and not is_bool_dtype(arr.dtype) + and is_bool_dtype(nonna.dtype) + ): + pass + elif ( + is_bool_dtype(arr.dtype) + and is_numeric_dtype(nonna.dtype) + and not is_bool_dtype(nonna.dtype) + ): + pass + else: + for x in nonna: + if is_numeric_v_string_like(arr, x): + # GH#29553 prevent numpy deprecation warnings + pass else: - new_mask = arr == x - - if not isinstance(new_mask, np.ndarray): - # usually BooleanArray - new_mask = new_mask.to_numpy(dtype=bool, na_value=False) - mask |= new_mask + if potential_na: + new_mask = np.zeros(arr.shape, dtype=np.bool_) + new_mask[arr_mask] = arr[arr_mask] == x + else: + new_mask = arr == x + + if not isinstance(new_mask, np.ndarray): + # usually BooleanArray + new_mask = new_mask.to_numpy(dtype=bool, na_value=False) + mask |= new_mask if na_mask.any(): mask |= isna(arr) diff --git a/pandas/tests/series/methods/test_replace.py b/pandas/tests/series/methods/test_replace.py index 4330153c186ca..b0f4e233ba5eb 100644 --- a/pandas/tests/series/methods/test_replace.py +++ b/pandas/tests/series/methods/test_replace.py @@ -799,3 +799,15 @@ def test_replace_numeric_column_with_na(self, val): ser.replace(to_replace=1, value=pd.NA, inplace=True) tm.assert_series_equal(ser, expected) + + def test_replace_ea_float_with_bool(self): + # GH#55398 + ser = pd.Series([0.0], dtype="Float64") + expected = ser.copy() + result = ser.replace(False, 1.0) + tm.assert_series_equal(result, expected) + + ser = pd.Series([False], dtype="boolean") + expected = ser.copy() + result = ser.replace(0.0, True) + tm.assert_series_equal(result, expected)