PERF: Return RangeIndex columns in str.extract when possible

doc/source/whatsnew/v3.0.0.rst

@@ -175,7 +175,7 @@ Performance improvements
 - Performance improvement in :meth:`RangeIndex.append` when appending the same index (:issue:`57252`)
 - Performance improvement in :meth:`RangeIndex.take` returning a :class:`RangeIndex` instead of a :class:`Index` when possible. (:issue:`57445`)
 - Performance improvement in indexing operations for string dtypes (:issue:`56997`)
--
+- :meth:`Series.str.extract` returns a :class:`RangeIndex` columns instead of an :class:`Index` column when possible (:issue:`?``)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_300.bug_fixes:

pandas/core/strings/accessor.py

@@ -3557,7 +3557,7 @@ def _get_single_group_name(regex: re.Pattern) -> Hashable:
         return None
 
 
-def _get_group_names(regex: re.Pattern) -> list[Hashable]:
+def _get_group_names(regex: re.Pattern) -> list[Hashable] | range:
     """
     Get named groups from compiled regex.
 
@@ -3571,8 +3571,15 @@ def _get_group_names(regex: re.Pattern) -> list[Hashable]:
     -------
     list of column labels
     """
+    rng = range(regex.groups)
     names = {v: k for k, v in regex.groupindex.items()}
-    return [names.get(1 + i, i) for i in range(regex.groups)]
+    if not names:
+        return rng
+    result: list[Hashable] = [names.get(1 + i, i) for i in rng]
+    arr = np.array(result)
+    if arr.dtype.kind == "i" and lib.is_range_indexer(arr, len(arr)):
+        return rng
+    return result
 
 
 def str_extractall(arr, pat, flags: int = 0) -> DataFrame:

pandas/tests/strings/test_extract.py

@@ -563,13 +563,13 @@ def test_extractall_no_matches(data, names, any_string_dtype):
 
     # one un-named group.
     result = s.str.extractall("(z)")
-    expected = DataFrame(columns=[0], index=expected_index, dtype=any_string_dtype)
-    tm.assert_frame_equal(result, expected)
+    expected = DataFrame(columns=range(1), index=expected_index, dtype=any_string_dtype)
+    tm.assert_frame_equal(result, expected, check_column_type=True)
 
     # two un-named groups.
     result = s.str.extractall("(z)(z)")
-    expected = DataFrame(columns=[0, 1], index=expected_index, dtype=any_string_dtype)
-    tm.assert_frame_equal(result, expected)
+    expected = DataFrame(columns=range(2), index=expected_index, dtype=any_string_dtype)
+    tm.assert_frame_equal(result, expected, check_column_type=True)
 
     # one named group.
     result = s.str.extractall("(?P<first>z)")