Skip to content

PERF: avoid unnecessary cast in Groupby.std with Float64 #51021

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
Jan 27, 2023
Merged

PERF: avoid unnecessary cast in Groupby.std with Float64 #51021

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
24 changes: 15 additions & 9 deletions pandas/core/groupby/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2097,20 +2097,26 @@ def std(
f"numeric_only={numeric_only} and dtype {self.obj.dtype}"
)

def _preprocessing(values):
if isinstance(values, BaseMaskedArray):
return values._data, None
return values, None

def _postprocessing(
vals, inference, nullable: bool = False, mask=None
vals, inference, nullable: bool = False, result_mask=None
) -> ArrayLike:
if nullable:
if mask.ndim == 2:
mask = mask[:, 0]
return FloatingArray(np.sqrt(vals), mask.view(np.bool_))
if result_mask.ndim == 2:
result_mask = result_mask[:, 0]
return FloatingArray(np.sqrt(vals), result_mask.view(np.bool_))
return np.sqrt(vals)

result = self._get_cythonized_result(
libgroupby.group_var,
cython_dtype=np.dtype(np.float64),
numeric_only=numeric_only,
needs_counts=True,
pre_processing=_preprocessing,
post_processing=_postprocessing,
ddof=ddof,
how="std",
Expand Down Expand Up @@ -3720,7 +3726,7 @@ def blk_func(values: ArrayLike) -> ArrayLike:
inferences = None

if needs_counts:
counts = np.zeros(self.ngroups, dtype=np.int64)
counts = np.zeros(ngroups, dtype=np.int64)
func = partial(func, counts=counts)

vals = values
Expand All @@ -3742,11 +3748,11 @@ def blk_func(values: ArrayLike) -> ArrayLike:
is_nullable = isinstance(values, BaseMaskedArray)
func = partial(func, nullable=is_nullable)

else:
elif isinstance(values, BaseMaskedArray):
result_mask = np.zeros(result.shape, dtype=np.bool_)
func = partial(func, result_mask=result_mask)

func(**kwargs) # Call func to modify indexer values in place
func(**kwargs) # Call func to modify result in place

if values.ndim == 1:
assert result.shape[1] == 1, result.shape
Expand All @@ -3755,8 +3761,8 @@ def blk_func(values: ArrayLike) -> ArrayLike:
if post_processing:
pp_kwargs: dict[str, bool | np.ndarray] = {}
pp_kwargs["nullable"] = isinstance(values, BaseMaskedArray)
if how == "std":
pp_kwargs["mask"] = result_mask
if how == "std" and pp_kwargs["nullable"]:
pp_kwargs["result_mask"] = result_mask

result = post_processing(result, inferences, **pp_kwargs)

Expand Down