From cda38abc9f6929a04f15b2ea7ed8a5a0960e609c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mateusz=20Sok=C3=B3=C5=82?= Date: Thu, 31 Aug 2023 11:30:09 +0200 Subject: [PATCH] MAINT: Refactor recarray access --- pandas/core/dtypes/missing.py | 6 ++++-- pandas/core/frame.py | 6 +++--- pandas/core/internals/construction.py | 2 +- pandas/io/stata.py | 4 ++-- pandas/tests/frame/constructors/test_from_records.py | 2 +- pandas/tests/frame/methods/test_to_records.py | 2 +- 6 files changed, 12 insertions(+), 10 deletions(-) diff --git a/pandas/core/dtypes/missing.py b/pandas/core/dtypes/missing.py index de99f828d604f..7117e34b23ca4 100644 --- a/pandas/core/dtypes/missing.py +++ b/pandas/core/dtypes/missing.py @@ -285,7 +285,7 @@ def _isna_array(values: ArrayLike, inf_as_na: bool = False): # "Union[ndarray[Any, Any], ExtensionArraySupportsAnyAll]", variable has # type "ndarray[Any, dtype[bool_]]") result = values.isna() # type: ignore[assignment] - elif isinstance(values, np.recarray): + elif isinstance(values, np.rec.recarray): # GH 48526 result = _isna_recarray_dtype(values, inf_as_na=inf_as_na) elif is_string_or_object_np_dtype(values.dtype): @@ -332,7 +332,9 @@ def _has_record_inf_value(record_as_array: np.ndarray) -> np.bool_: return np.any(is_inf_in_record) -def _isna_recarray_dtype(values: np.recarray, inf_as_na: bool) -> npt.NDArray[np.bool_]: +def _isna_recarray_dtype( + values: np.rec.recarray, inf_as_na: bool +) -> npt.NDArray[np.bool_]: result = np.zeros(values.shape, dtype=bool) for i, record in enumerate(values): record_as_array = np.array(record.tolist()) diff --git a/pandas/core/frame.py b/pandas/core/frame.py index 282ecdcf31939..6fae6273be998 100644 --- a/pandas/core/frame.py +++ b/pandas/core/frame.py @@ -2412,7 +2412,7 @@ def maybe_reorder( def to_records( self, index: bool = True, column_dtypes=None, index_dtypes=None - ) -> np.recarray: + ) -> np.rec.recarray: """ Convert DataFrame to a NumPy record array. @@ -2437,7 +2437,7 @@ def to_records( Returns ------- - numpy.recarray + numpy.rec.recarray NumPy ndarray with the DataFrame labels as fields and each row of the DataFrame as entries. @@ -2445,7 +2445,7 @@ def to_records( -------- DataFrame.from_records: Convert structured or record ndarray to DataFrame. - numpy.recarray: An ndarray that allows field access using + numpy.rec.recarray: An ndarray that allows field access using attributes, analogous to typed columns in a spreadsheet. diff --git a/pandas/core/internals/construction.py b/pandas/core/internals/construction.py index 5c8873d4324e0..3b9e546a99b32 100644 --- a/pandas/core/internals/construction.py +++ b/pandas/core/internals/construction.py @@ -159,7 +159,7 @@ def arrays_to_mgr( def rec_array_to_mgr( - data: np.recarray | np.ndarray, + data: np.rec.recarray | np.ndarray, index, columns, dtype: DtypeObj | None, diff --git a/pandas/io/stata.py b/pandas/io/stata.py index c5648a022d4a9..7f19e62f40774 100644 --- a/pandas/io/stata.py +++ b/pandas/io/stata.py @@ -2963,7 +2963,7 @@ def _convert_strls(self, data: DataFrame) -> DataFrame: """No-op, future compatibility""" return data - def _prepare_data(self) -> np.recarray: + def _prepare_data(self) -> np.rec.recarray: data = self.data typlist = self.typlist convert_dates = self._convert_dates @@ -2995,7 +2995,7 @@ def _prepare_data(self) -> np.recarray: return data.to_records(index=False, column_dtypes=dtypes) - def _write_data(self, records: np.recarray) -> None: + def _write_data(self, records: np.rec.recarray) -> None: self._write_bytes(records.tobytes()) @staticmethod diff --git a/pandas/tests/frame/constructors/test_from_records.py b/pandas/tests/frame/constructors/test_from_records.py index 59dca5055f170..7dffa7bb242d5 100644 --- a/pandas/tests/frame/constructors/test_from_records.py +++ b/pandas/tests/frame/constructors/test_from_records.py @@ -93,7 +93,7 @@ def test_from_records_sequencelike(self): tup.extend(b.iloc[i].values) tuples.append(tuple(tup)) - recarray = np.array(tuples, dtype=dtypes).view(np.recarray) + recarray = np.array(tuples, dtype=dtypes).view(np.rec.recarray) recarray2 = df.to_records() lists = [list(x) for x in tuples] diff --git a/pandas/tests/frame/methods/test_to_records.py b/pandas/tests/frame/methods/test_to_records.py index e18f236d40804..fa8c4e4811ea6 100644 --- a/pandas/tests/frame/methods/test_to_records.py +++ b/pandas/tests/frame/methods/test_to_records.py @@ -391,7 +391,7 @@ def test_to_records_dtype(self, kwargs, expected): # see GH#18146 df = DataFrame({"A": [1, 2], "B": [0.2, 1.5], "C": ["a", "bc"]}) - if not isinstance(expected, np.recarray): + if not isinstance(expected, np.rec.recarray): with pytest.raises(expected[0], match=expected[1]): df.to_records(**kwargs) else: