ENH: Enhancement for spss kwargs

doc/source/whatsnew/v2.2.0.rst

@@ -871,7 +871,8 @@ I/O
 - Bug in :func:`read_csv` with ``engine="pyarrow"`` where ``usecols`` wasn't working with a CSV with no headers (:issue:`54459`)
 - Bug in :func:`read_excel`, with ``engine="xlrd"`` (``xls`` files) erroring when the file contains ``NaN`` or ``Inf`` (:issue:`54564`)
 - Bug in :func:`read_json` not handling dtype conversion properly if ``infer_string`` is set (:issue:`56195`)
-- Bug in :meth:`DataFrame.to_excel`, with ``OdsWriter`` (``ods`` files) writing Boolean/string value (:issue:`54994`)
+- Bug in :func:`read_spss` where kwargs were not passed to pyreadstat (:issue:`56356`)
+- Bug in :meth:`DataFrame.to_excel`, with ``OdsWriter`` (``ods`` files) writing boolean/string value (:issue:`54994`)
 - Bug in :meth:`DataFrame.to_hdf` and :func:`read_hdf` with ``datetime64`` dtypes with non-nanosecond resolution failing to round-trip correctly (:issue:`55622`)
 - Bug in :meth:`DataFrame.to_stata` raising for extension dtypes (:issue:`54671`)
 - Bug in :meth:`~pandas.read_excel` with ``engine="odf"`` (``ods`` files) when a string cell contains an annotation (:issue:`55200`)

pandas/io/spss.py

@@ -24,6 +24,7 @@ def read_spss(
     usecols: Sequence[str] | None = None,
     convert_categoricals: bool = True,
     dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
+    **kwargs: dict,
 ) -> DataFrame:
     """
     Load an SPSS file from the file path, returning a DataFrame.
@@ -46,6 +47,8 @@ def read_spss(
           DataFrame.
 
         .. versionadded:: 2.0
+    kwargs : dict, optional
+        Additional keyword arguments passed to :func:`pyreadstat.read_sav`.
 
     Returns
     -------
@@ -64,7 +67,10 @@ def read_spss(
         usecols = list(usecols)  # pyreadstat requires a list
 
     df, metadata = pyreadstat.read_sav(
-        stringify_path(path), usecols=usecols, apply_value_formats=convert_categoricals
+        stringify_path(path),
+        usecols=usecols,
+        apply_value_formats=convert_categoricals,
+        **kwargs,
     )
     df.attrs = metadata.__dict__
     if dtype_backend is not lib.no_default:

pandas/tests/io/test_spss.py

@@ -65,6 +65,22 @@ def test_spss_labelled_str(datapath):
     tm.assert_frame_equal(df, expected)
 
 
+@pytest.mark.filterwarnings("ignore::pandas.errors.ChainedAssignmentError")
+@pytest.mark.filterwarnings("ignore:ChainedAssignmentError:FutureWarning")
+def test_spss_kwargs(datapath):
+    # test file from the Haven project (https://haven.tidyverse.org/)
+    # Licence at LICENSES/HAVEN_LICENSE, LICENSES/HAVEN_MIT
+    fname = datapath("io", "data", "spss", "labelled-str.sav")
+
+    df = pd.read_spss(fname, convert_categoricals=True, row_limit=1)
+    expected = pd.DataFrame({"gender": ["Male"]}, dtype="category")
+    tm.assert_frame_equal(df, expected)
+
+    df = pd.read_spss(fname, convert_categoricals=False, row_offset=1)
+    expected = pd.DataFrame({"gender": ["F"]})
+    tm.assert_frame_equal(df, expected)
+
+
 @pytest.mark.filterwarnings("ignore::pandas.errors.ChainedAssignmentError")
 @pytest.mark.filterwarnings("ignore:ChainedAssignmentError:FutureWarning")
 def test_spss_umlauts(datapath):