Skip to content

REF: hide ArrayManager implementation details from GroupBy #41086

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 3 commits into from
Apr 30, 2021
Merged

REF: hide ArrayManager implementation details from GroupBy #41086

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
77eb2d2
REF: hide ArrayManager implementation details from GroupBy
jbrockmendel Apr 21, 2021
4e85874
Merge branch 'master' into ref-gr
jbrockmendel Apr 30, 2021
d6aba61
Merge branch 'master' into ref-gr
jbrockmendel Apr 30, 2021
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
15 changes: 1 addition & 14 deletions pandas/core/groupby/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,6 @@
all_indexes_same,
)
import pandas.core.indexes.base as ibase
from pandas.core.internals import ArrayManager
from pandas.core.series import Series
from pandas.core.util.numba_ import maybe_use_numba

Expand Down Expand Up @@ -1103,17 +1102,11 @@ def _cython_agg_general(
if numeric_only:
data = data.get_numeric_data(copy=False)

using_array_manager = isinstance(data, ArrayManager)

def cast_agg_result(result: ArrayLike, values: ArrayLike) -> ArrayLike:
# see if we can cast the values to the desired dtype
# this may not be the original dtype

if (
not using_array_manager
and isinstance(result.dtype, np.dtype)
and result.ndim == 1
):
if isinstance(result.dtype, np.dtype) and result.ndim == 1:
# We went through a SeriesGroupByPath and need to reshape
# GH#32223 includes case with IntegerArray values
# We only get here with values.dtype == object
Expand Down Expand Up @@ -1794,8 +1787,6 @@ def count(self) -> DataFrame:
ids, _, ngroups = self.grouper.group_info
mask = ids != -1

using_array_manager = isinstance(data, ArrayManager)

def hfunc(bvalues: ArrayLike) -> ArrayLike:
# TODO(2DEA): reshape would not be necessary with 2D EAs
if bvalues.ndim == 1:
Expand All @@ -1805,10 +1796,6 @@ def hfunc(bvalues: ArrayLike) -> ArrayLike:
masked = mask & ~isna(bvalues)

counted = lib.count_level_2d(masked, labels=ids, max_bin=ngroups, axis=1)
if using_array_manager:
# count_level_2d return (1, N) array for single column
# -> extract 1D array
counted = counted[0, :]
return counted

new_mgr = data.grouped_reduce(hfunc)
Expand Down
8 changes: 8 additions & 0 deletions pandas/core/internals/array_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -932,12 +932,20 @@ def grouped_reduce(self: T, func: Callable, ignore_failures: bool = False) -> T:
result_indices: list[int] = []

for i, arr in enumerate(self.arrays):
# grouped_reduce functions all expect 2D arrays
arr = ensure_block_shape(arr, ndim=2)
try:
res = func(arr)
except (TypeError, NotImplementedError):
if not ignore_failures:
raise
continue

if res.ndim == 2:
# reverse of ensure_block_shape
assert res.shape[0] == 1
res = res[0]

result_arrays.append(res)
result_indices.append(i)

Expand Down