Skip to content

REF: don't call libalgos.groupsort_indexer directly for simple argsort usage #40105

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 27, 2021
Merged

REF: don't call libalgos.groupsort_indexer directly for simple argsort usage #40105

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions pandas/core/indexes/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,6 +148,7 @@
from pandas.core.ops.invalid import make_invalid_op
from pandas.core.sorting import (
ensure_key_mapped,
get_group_index_sorter,
nargsort,
)
from pandas.core.strings import StringMethods
Expand Down Expand Up @@ -4098,9 +4099,7 @@ def _get_leaf_sorter(labels):
return np.empty(0, dtype="int64")

if len(labels) == 1:
lab = ensure_int64(labels[0])
sorter, _ = libalgos.groupsort_indexer(lab, 1 + lab.max())
return sorter
return get_group_index_sorter(labels[0])

# find indexers of beginning of each set of
# same-key labels w.r.t all but last level
Expand Down
5 changes: 2 additions & 3 deletions pandas/core/reshape/reshape.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@

import numpy as np

import pandas._libs.algos as libalgos
import pandas._libs.reshape as libreshape
from pandas._libs.sparse import IntIndex
from pandas._typing import Dtype
Expand Down Expand Up @@ -42,6 +41,7 @@
decons_obs_group_ids,
get_compressed_ids,
get_group_index,
get_group_index_sorter,
)


Expand Down Expand Up @@ -139,8 +139,7 @@ def _indexer_and_to_sort(self):
comp_index, obs_ids = get_compressed_ids(to_sort, sizes)
ngroups = len(obs_ids)

indexer = libalgos.groupsort_indexer(comp_index, ngroups)[0]
indexer = ensure_platform_int(indexer)
indexer = get_group_index_sorter(comp_index, ngroups)

return indexer, to_sort

Expand Down
6 changes: 5 additions & 1 deletion pandas/core/sorting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -567,7 +567,9 @@ def get_indexer_dict(
# sorting levels...cleverly?


def get_group_index_sorter(group_index, ngroups: int):
def get_group_index_sorter(
group_index: np.ndarray, ngroups: int | None = None
) -> np.ndarray:
"""
algos.groupsort_indexer implements `counting sort` and it is at least
O(ngroups), where
Expand All @@ -581,6 +583,8 @@ def get_group_index_sorter(group_index, ngroups: int):
groupby operations. e.g. consider:
df.groupby(key)[col].transform('first')
"""
if ngroups is None:
ngroups = 1 + group_index.max()
count = len(group_index)
alpha = 0.0 # taking complexities literally; there may be
beta = 1.0 # some room for fine-tuning these parameters
Expand Down