CLN: Use group_info less (#57598)

Author: rhshadrach

pandas/core/groupby/generic.py

@@ -813,7 +813,7 @@ def value_counts(
  from pandas.core.reshape.merge import get_join_indexers
  from pandas.core.reshape.tile import cut
 
- ids, _ = self._grouper.group_info
+ ids = self._grouper.ids
  val = self.obj._values
 
  index_names = self._grouper.names + [self.obj.name]

pandas/core/groupby/groupby.py

@@ -1228,7 +1228,7 @@ def _concat_objects(
 
  ax = self._selected_obj.index
  if self.dropna:
- labels = self._grouper.group_info[0]
+ labels = self._grouper.ids
  mask = labels != -1
  ax = ax[mask]
 
@@ -1423,7 +1423,7 @@ def _numba_agg_general(
  )
  # Pass group ids to kernel directly if it can handle it
  # (This is faster since it doesn't require a sort)
- ids, _ = self._grouper.group_info
+ ids = self._grouper.ids
  ngroups = self._grouper.ngroups
 
  res_mgr = df._mgr.apply(
@@ -4163,7 +4163,7 @@ def _nth(
  if not dropna:
  mask = self._make_mask_from_positional_indexer(n)
 
- ids, _ = self._grouper.group_info
+ ids = self._grouper.ids
 
  # Drop NA values in grouping
  mask = mask & (ids != -1)
@@ -4503,7 +4503,7 @@ def ngroup(self, ascending: bool = True):
  """
  obj = self._obj_with_exclusions
  index = obj.index
- comp_ids = self._grouper.group_info[0]
+ comp_ids = self._grouper.ids
 
  dtype: type
  if self._grouper.has_dropped_na:
@@ -5382,7 +5382,7 @@ def _mask_selected_obj(self, mask: npt.NDArray[np.bool_]) -> NDFrameT:
  Series or DataFrame
  Filtered _selected_obj.
  """
- ids = self._grouper.group_info[0]
+ ids = self._grouper.ids
  mask = mask & (ids != -1)
  return self._selected_obj[mask]
 

pandas/core/groupby/ops.py

@@ -716,7 +716,7 @@ def groups(self) -> dict[Hashable, Index]:
  @cache_readonly
  def is_monotonic(self) -> bool:
  # return if my group orderings are monotonic
- return Index(self.group_info[0]).is_monotonic_increasing
+ return Index(self.ids).is_monotonic_increasing
 
  @final
  @cache_readonly
@@ -735,8 +735,7 @@ def group_info(self) -> tuple[npt.NDArray[np.intp], int]:
  @cache_readonly
  def codes_info(self) -> npt.NDArray[np.intp]:
  # return the codes of items in original grouped axis
- ids, _ = self.group_info
- return ids
+ return self.ids
 
  @final
  @cache_readonly
@@ -933,9 +932,7 @@ def agg_series(
  def _aggregate_series_pure_python(
  self, obj: Series, func: Callable
  ) -> npt.NDArray[np.object_]:
- _, ngroups = self.group_info
-
- result = np.empty(ngroups, dtype="O")
+ result = np.empty(self.ngroups, dtype="O")
  initialized = False
 
  splitter = self._get_splitter(obj)
@@ -1073,7 +1070,7 @@ def nkeys(self) -> int:
  @cache_readonly
  def codes_info(self) -> npt.NDArray[np.intp]:
  # return the codes of items in original grouped axis
- ids, _ = self.group_info
+ ids = self.ids
  if self.indexer is not None:
  sorter = np.lexsort((ids, self.indexer))
  ids = ids[sorter]
@@ -1133,7 +1130,7 @@ def result_index(self) -> Index:
 
  @cache_readonly
  def codes(self) -> list[npt.NDArray[np.intp]]:
- return [self.group_info[0]]
+ return [self.ids]
 
  @cache_readonly
  def result_index_and_ids(self):
@@ -1150,7 +1147,7 @@ def names(self) -> list[Hashable]:
  @property
  def groupings(self) -> list[grouper.Grouping]:
  lev = self.binlabels
- codes = self.group_info[0]
+ codes = self.ids
  labels = lev.take(codes)
  ping = grouper.Grouping(
  labels, labels, in_axis=False, level=None, uniques=lev._values

pandas/tests/groupby/test_grouping.py

@@ -776,10 +776,10 @@ def test_groupby_empty(self):
  # check group properties
  assert len(gr._grouper.groupings) == 1
  tm.assert_numpy_array_equal(
- gr._grouper.group_info[0], np.array([], dtype=np.dtype(np.intp))
+ gr._grouper.ids, np.array([], dtype=np.dtype(np.intp))
  )
 
- assert gr._grouper.group_info[1] == 0
+ assert gr._grouper.ngroups == 0
 
  # check name
  gb = s.groupby(s)