Skip to content

PERF: faster indexing for non-fastpath groupby ops #34214

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 2 commits into from
May 17, 2020
Merged

PERF: faster indexing for non-fastpath groupby ops #34214

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f97361b
PERF: speedup non-fastpath in groupby ops
jbrockmendel May 16, 2020
f143ed2
PERF: make_block_same_class
jbrockmendel May 16, 2020
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: 10 additions & 5 deletions pandas/core/groupby/ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -952,7 +952,9 @@ def _chop(self, sdata, slice_obj: slice) -> NDFrame:

class SeriesSplitter(DataSplitter):
def _chop(self, sdata: Series, slice_obj: slice) -> Series:
return sdata.iloc[slice_obj]
# fastpath equivalent to `sdata.iloc[slice_obj]`
mgr = sdata._mgr.get_slice(slice_obj)
return type(sdata)(mgr, name=sdata.name, fastpath=True)


class FrameSplitter(DataSplitter):
Expand All @@ -962,10 +964,13 @@ def fast_apply(self, f: F, sdata: FrameOrSeries, names):
return libreduction.apply_frame_axis0(sdata, f, names, starts, ends)

def _chop(self, sdata: DataFrame, slice_obj: slice) -> DataFrame:
if self.axis == 0:
return sdata.iloc[slice_obj]
else:
return sdata.iloc[:, slice_obj]
# Fastpath equivalent to:
# if self.axis == 0:
# return sdata.iloc[slice_obj]
# else:
# return sdata.iloc[:, slice_obj]
mgr = sdata._mgr.get_slice(slice_obj, axis=1 - self.axis)
return type(sdata)(mgr)


def get_splitter(
Expand Down
2 changes: 1 addition & 1 deletion pandas/core/internals/blocks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -251,7 +251,7 @@ def make_block_same_class(self, values, placement=None, ndim=None):
placement = self.mgr_locs
if ndim is None:
ndim = self.ndim
return make_block(values, placement=placement, ndim=ndim, klass=type(self))
return type(self)(values, placement=placement, ndim=ndim)

def __repr__(self) -> str:
# don't want to print out all of the items here
Expand Down