diff --git a/doc/source/whatsnew/v2.2.0.rst b/doc/source/whatsnew/v2.2.0.rst index 9a9ac769a4893..2018c8936ee3c 100644 --- a/doc/source/whatsnew/v2.2.0.rst +++ b/doc/source/whatsnew/v2.2.0.rst @@ -934,6 +934,7 @@ Other - Bug in :func:`cut` and :func:`qcut` with ``datetime64`` dtype values with non-nanosecond units incorrectly returning nanosecond-unit bins (:issue:`56101`) - Bug in :func:`cut` incorrectly allowing cutting of timezone-aware datetimes with timezone-naive bins (:issue:`54964`) - Bug in :func:`infer_freq` and :meth:`DatetimeIndex.inferred_freq` with weekly frequencies and non-nanosecond resolutions (:issue:`55609`) +- Bug in :func:`pd.api.interchange.from_dataframe` where it raised ``NotImplementedError`` when handling empty string columns (:issue:`56703`) - Bug in :meth:`DataFrame.apply` where passing ``raw=True`` ignored ``args`` passed to the applied function (:issue:`55009`) - Bug in :meth:`DataFrame.from_dict` which would always sort the rows of the created :class:`DataFrame`. (:issue:`55683`) - Bug in :meth:`DataFrame.sort_index` when passing ``axis="columns"`` and ``ignore_index=True`` raising a ``ValueError`` (:issue:`56478`) @@ -942,7 +943,6 @@ Other - Bug in the error message when assigning an empty :class:`DataFrame` to a column (:issue:`55956`) - Bug when time-like strings were being cast to :class:`ArrowDtype` with ``pyarrow.time64`` type (:issue:`56463`) - .. --------------------------------------------------------------------------- .. _whatsnew_220.contributors: diff --git a/pandas/core/interchange/column.py b/pandas/core/interchange/column.py index 7f524d6823f30..ee1b5cd34a7f7 100644 --- a/pandas/core/interchange/column.py +++ b/pandas/core/interchange/column.py @@ -116,7 +116,7 @@ def dtype(self) -> tuple[DtypeKind, int, str, str]: Endianness.NATIVE, ) elif is_string_dtype(dtype): - if infer_dtype(self._col) == "string": + if infer_dtype(self._col) in ("string", "empty"): return ( DtypeKind.STRING, 8, diff --git a/pandas/tests/interchange/test_impl.py b/pandas/tests/interchange/test_impl.py index 4ba6eb8464261..2bc488fbb1dd1 100644 --- a/pandas/tests/interchange/test_impl.py +++ b/pandas/tests/interchange/test_impl.py @@ -355,6 +355,14 @@ def test_interchange_from_corrected_buffer_dtypes(monkeypatch) -> None: pd.api.interchange.from_dataframe(df) +def test_empty_string_column(): + # https://github.com/pandas-dev/pandas/issues/56703 + df = pd.DataFrame({"a": []}, dtype=str) + df2 = df.__dataframe__() + result = pd.api.interchange.from_dataframe(df2) + tm.assert_frame_equal(df, result) + + def test_large_string(): # GH#56702 pytest.importorskip("pyarrow")