BUG: wide_to_long with string columns (#57089)

Author: mroeschke

doc/source/whatsnew/v2.2.1.rst

@@ -16,6 +16,7 @@ Fixed regressions
 - Fixed memory leak in :func:`read_csv` (:issue:`57039`)
 - Fixed performance regression in :meth:`Series.combine_first` (:issue:`55845`)
 - Fixed regression in :func:`merge_ordered` raising ``TypeError`` for ``fill_method="ffill"`` and ``how="left"`` (:issue:`57010`)
+- Fixed regression in :func:`wide_to_long` raising an ``AttributeError`` for string columns (:issue:`57066`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` ignoring the ``skipna`` argument (:issue:`57040`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` where values containing the minimum or maximum value for the dtype could produce incorrect results (:issue:`57040`)
 - Fixed regression in :meth:`Series.pct_change` raising a ``ValueError`` for an empty :class:`Series` (:issue:`57056`)

pandas/core/reshape/melt.py

@@ -458,8 +458,7 @@ def wide_to_long(
 
  def get_var_names(df, stub: str, sep: str, suffix: str):
  regex = rf"^{re.escape(stub)}{re.escape(sep)}{suffix}$"
- pattern = re.compile(regex)
- return df.columns[df.columns.str.match(pattern)]
+ return df.columns[df.columns.str.match(regex)]
 
  def melt_stub(df, stub: str, i, j, value_vars, sep: str):
  newdf = melt(

pandas/core/strings/accessor.py

@@ -1332,14 +1332,14 @@ def contains(
  return self._wrap_result(result, fill_value=na, returns_string=False)
 
  @forbid_nonstring_types(["bytes"])
- def match(self, pat, case: bool = True, flags: int = 0, na=None):
+ def match(self, pat: str, case: bool = True, flags: int = 0, na=None):
  """
  Determine if each string starts with a match of a regular expression.
 
  Parameters
  ----------
  pat : str
- Character sequence or regular expression.
+ Character sequence.
  case : bool, default True
  If True, case sensitive.
  flags : int, default 0 (no flags)

pandas/tests/reshape/test_melt.py

@@ -1217,3 +1217,33 @@ def test_missing_stubname(self, dtype):
  new_level = expected.index.levels[0].astype(dtype)
  expected.index = expected.index.set_levels(new_level, level=0)
  tm.assert_frame_equal(result, expected)
+
+
+def test_wide_to_long_pyarrow_string_columns():
+ # GH 57066
+ pytest.importorskip("pyarrow")
+ df = DataFrame(
+ {
+ "ID": {0: 1},
+ "R_test1": {0: 1},
+ "R_test2": {0: 1},
+ "R_test3": {0: 2},
+ "D": {0: 1},
+ }
+ )
+ df.columns = df.columns.astype("string[pyarrow_numpy]")
+ result = wide_to_long(
+ df, stubnames="R", i="ID", j="UNPIVOTED", sep="_", suffix=".*"
+ )
+ expected = DataFrame(
+ [[1, 1], [1, 1], [1, 2]],
+ columns=Index(["D", "R"], dtype=object),
+ index=pd.MultiIndex.from_arrays(
+ [
+ [1, 1, 1],
+ Index(["test1", "test2", "test3"], dtype="string[pyarrow_numpy]"),
+ ],
+ names=["ID", "UNPIVOTED"],
+ ),
+ )
+ tm.assert_frame_equal(result, expected)