add to BaseGrouper constructor key_dtype_str paramater, correct def result_index_and_ids and def groups

Author: natmokval

pandas/core/groupby/groupby.py

@@ -1012,7 +1012,7 @@ def __iter__(self) -> Iterator[tuple[Hashable, NDFrameT]]:
         # mypy: Argument 1 to "len" has incompatible type "Hashable"; expected "Sized"
         if (
             (is_list_like(level) and len(level) == 1)  # type: ignore[arg-type]
-            or (isinstance(keys, list))
+            or (isinstance(keys, list) and len(keys) == 1)
         ):
             # GH#42795 - when keys is a list, return tuples even when length is 1
             result = (((key,), group) for key, group in result)

pandas/core/groupby/grouper.py

@@ -780,7 +780,9 @@ def get_grouper(
     elif isinstance(key, ops.BaseGrouper):
         return key, frozenset(), obj
 
+    key_dtype_str = False
     if not isinstance(key, list):
+        key_dtype_str = True
         keys = [key]
         match_axis_length = False
     else:
@@ -895,7 +897,6 @@ def is_in_obj(gpr) -> bool:
             if not isinstance(gpr, Grouping)
             else gpr
         )
-
         groupings.append(ping)
 
     if len(groupings) == 0 and len(obj):
@@ -904,7 +905,9 @@ def is_in_obj(gpr) -> bool:
         groupings.append(Grouping(Index([], dtype="int"), np.array([], dtype=np.intp)))
 
     # create the internals grouper
-    grouper = ops.BaseGrouper(group_axis, groupings, sort=sort, dropna=dropna)
+    grouper = ops.BaseGrouper(
+        group_axis, groupings, sort=sort, dropna=dropna, key_dtype_str=key_dtype_str
+    )
     return grouper, frozenset(exclusions), obj
 
 

pandas/core/groupby/ops.py

@@ -584,13 +584,15 @@ def __init__(
         groupings: Sequence[grouper.Grouping],
         sort: bool = True,
         dropna: bool = True,
+        key_dtype_str: bool = True,
     ) -> None:
         assert isinstance(axis, Index), axis
 
         self.axis = axis
         self._groupings: list[grouper.Grouping] = list(groupings)
         self._sort = sort
         self.dropna = dropna
+        self.key_dtype_str = key_dtype_str
 
     @property
     def groupings(self) -> list[grouper.Grouping]:
@@ -640,6 +642,7 @@ def _get_splitter(self, data: NDFrame) -> DataSplitter:
     @cache_readonly
     def indices(self) -> dict[Hashable, npt.NDArray[np.intp]]:
         """dict {group name -> group indices}"""
+
         if len(self.groupings) == 1 and isinstance(self.result_index, CategoricalIndex):
             # This shows unused categories in indices GH#38642
             return self.groupings[0].indices
@@ -703,7 +706,10 @@ def size(self) -> Series:
     @cache_readonly
     def groups(self) -> dict[Hashable, Index]:
         """dict {group name -> group labels}"""
-        if len(self.groupings) == 1 and not isinstance(self.shape, tuple):
+        if len(self.groupings) == 1 and not self.key_dtype_str:
+            result = self.groupings[0].groups
+
+        if self.key_dtype_str and len(self.groupings) == 1:
             return self.groupings[0].groups
         result_index, ids = self.result_index_and_ids
         values = result_index._values
@@ -764,7 +770,7 @@ def result_index_and_ids(self) -> tuple[Index, npt.NDArray[np.intp]]:
             if ping._passed_categorical:
                 levels[k] = level.set_categories(ping._orig_cats)
 
-        if len(self.groupings) == 1:
+        if self.key_dtype_str and len(self.groupings) == 1:
             result_index = levels[0]
             result_index.name = self.names[0]
             ids = ensure_platform_int(self.codes[0])