Backport PR pandas-dev#57758: BUG: DataFrame Interchange Protocol errors on Boolean columns

Author: MarcoGorelli

doc/source/whatsnew/v2.2.2.rst

@@ -22,6 +22,7 @@ Fixed regressions
 
 Bug fixes
 ~~~~~~~~~
+- :meth:`DataFrame.__dataframe__` was producing incorrect data buffers when the column's type was nullable boolean (:issue:`55332`)
 - :meth:`DataFrame.__dataframe__` was showing bytemask instead of bitmask for ``'string[pyarrow]'`` validity buffer (:issue:`57762`)
 - :meth:`DataFrame.__dataframe__` was showing non-null validity buffer (instead of ``None``) ``'string[pyarrow]'`` without missing values (:issue:`57761`)
 

pandas/core/interchange/utils.py

@@ -144,6 +144,9 @@ def dtype_to_arrow_c_fmt(dtype: DtypeObj) -> str:
     elif isinstance(dtype, DatetimeTZDtype):
         return ArrowCTypes.TIMESTAMP.format(resolution=dtype.unit[0], tz=dtype.tz)
 
+    elif isinstance(dtype, pd.BooleanDtype):
+        return ArrowCTypes.BOOL
+
     raise NotImplementedError(
         f"Conversion of {dtype} to Arrow C format string is not implemented."
     )

pandas/tests/interchange/test_impl.py

@@ -470,6 +470,7 @@ def test_non_str_names_w_duplicates():
         ),
         ([1.0, 2.25, None], "Float32", "float32"),
         ([1.0, 2.25, None], "Float32[pyarrow]", "float32"),
+        ([True, False, None], "boolean", "bool"),
         ([True, False, None], "boolean[pyarrow]", "bool"),
         (["much ado", "about", None], "string[pyarrow_numpy]", "large_string"),
         (["much ado", "about", None], "string[pyarrow]", "large_string"),
@@ -532,6 +533,7 @@ def test_pandas_nullable_with_missing_values(
         ),
         ([1.0, 2.25, 5.0], "Float32", "float32"),
         ([1.0, 2.25, 5.0], "Float32[pyarrow]", "float32"),
+        ([True, False, False], "boolean", "bool"),
         ([True, False, False], "boolean[pyarrow]", "bool"),
         (["much ado", "about", "nothing"], "string[pyarrow_numpy]", "large_string"),
         (["much ado", "about", "nothing"], "string[pyarrow]", "large_string"),