Skip to content

PERF: non-cython groupby.apply #40236

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
Mar 5, 2021
Merged

PERF: non-cython groupby.apply #40236

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
16 changes: 16 additions & 0 deletions pandas/core/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,6 +276,22 @@ def _init_mgr(
mgr = mgr.astype(dtype=dtype)
return mgr

@classmethod
def _from_mgr(cls, mgr: Manager):
"""
Fastpath to create a new DataFrame/Series from just a BlockManager/ArrayManager.

Notes
-----
Skips setting `_flags` attribute; caller is responsible for doing so.
"""
obj = cls.__new__(cls)
object.__setattr__(obj, "_is_copy", None)
object.__setattr__(obj, "_mgr", mgr)
object.__setattr__(obj, "_item_cache", {})
object.__setattr__(obj, "_attrs", {})
return obj

# ----------------------------------------------------------------------
# attrs and flags

Expand Down
14 changes: 12 additions & 2 deletions pandas/core/groupby/ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1013,7 +1013,13 @@ def _chop(self, sdata: Series, slice_obj: slice) -> Series:
# fastpath equivalent to `sdata.iloc[slice_obj]`
mgr = sdata._mgr.get_slice(slice_obj)
# __finalize__ not called here, must be applied by caller if applicable
return sdata._constructor(mgr, name=sdata.name, fastpath=True)

# fastpath equivalent to:
# `return sdata._constructor(mgr, name=sdata.name, fastpath=True)`
obj = type(sdata)._from_mgr(mgr)
object.__setattr__(obj, "_flags", sdata._flags)
object.__setattr__(obj, "_name", sdata._name)
return obj


class FrameSplitter(DataSplitter):
Expand All @@ -1030,7 +1036,11 @@ def _chop(self, sdata: DataFrame, slice_obj: slice) -> DataFrame:
# return sdata.iloc[:, slice_obj]
mgr = sdata._mgr.get_slice(slice_obj, axis=1 - self.axis)
# __finalize__ not called here, must be applied by caller if applicable
return sdata._constructor(mgr)

# fastpath equivalent to `return sdata._constructor(mgr)`
obj = type(sdata)._from_mgr(mgr)
object.__setattr__(obj, "_flags", sdata._flags)
return obj


def get_splitter(
Expand Down