Skip to content

ASV: reduce overall run time for GroupByMethods benchmarks #44604

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
Nov 25, 2021
Merged

ASV: reduce overall run time for GroupByMethods benchmarks #44604

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
48c6ce6
ASV: reduce overall run time for GroupByMethods benchmarks
jorisvandenbossche Nov 24, 2021
41c810d
ngroups=20 for all describe
jorisvandenbossche Nov 25, 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
13 changes: 8 additions & 5 deletions asv_bench/benchmarks/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -443,7 +443,7 @@ class GroupByMethods:
"var",
],
["direct", "transformation"],
[1, 2, 5, 10],
[1, 5],
]

def setup(self, dtype, method, application, ncols):
Expand All @@ -455,6 +455,7 @@ def setup(self, dtype, method, application, ncols):
raise NotImplementedError

if application == "transformation" and method in [
"describe",
"head",
"tail",
"unique",
Expand All @@ -464,7 +465,12 @@ def setup(self, dtype, method, application, ncols):
# DataFrameGroupBy doesn't have these methods
raise NotImplementedError

ngroups = 1000
if method == "describe":
ngroups = 20
elif method in ["mad", "skew"]:
ngroups = 100
else:
ngroups = 1000
size = ngroups * 2
rng = np.arange(ngroups).reshape(-1, 1)
rng = np.broadcast_to(rng, (len(rng), ncols))
Expand All @@ -491,9 +497,6 @@ def setup(self, dtype, method, application, ncols):
cols = cols[0]

if application == "transformation":
if method == "describe":
raise NotImplementedError

self.as_group_method = lambda: df.groupby("key")[cols].transform(method)
self.as_field_method = lambda: df.groupby(cols)["key"].transform(method)
else:
Expand Down