Skip to content

ASV: Add benchmarks for groupby with multiple categories #56030

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
Nov 18, 2023
Merged

ASV: Add benchmarks for groupby with multiple categories #56030

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
45 changes: 45 additions & 0 deletions asv_bench/benchmarks/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -802,6 +802,51 @@ def time_groupby_extra_cat_nosort(self, observed):
self.df_extra_cat.groupby("a", observed=observed, sort=False)["b"].count()


class MultipleCategories:
def setup(self):
N = 10**3
arr = np.random.random(N)
data = {
"a1": Categorical(np.random.randint(10000, size=N)),
"a2": Categorical(np.random.randint(10000, size=N)),
"b": arr,
}
self.df = DataFrame(data)
data = {
"a1": Categorical(np.random.randint(10000, size=N), ordered=True),
"a2": Categorical(np.random.randint(10000, size=N), ordered=True),
"b": arr,
}
self.df_ordered = DataFrame(data)
data = {
"a1": Categorical(np.random.randint(100, size=N), categories=np.arange(N)),
"a2": Categorical(np.random.randint(100, size=N), categories=np.arange(N)),
"b": arr,
}
self.df_extra_cat = DataFrame(data)

def time_groupby_sort(self):
self.df.groupby(["a1", "a2"], observed=False)["b"].count()

def time_groupby_nosort(self):
self.df.groupby(["a1", "a2"], observed=False, sort=False)["b"].count()

def time_groupby_ordered_sort(self):
self.df_ordered.groupby(["a1", "a2"], observed=False)["b"].count()

def time_groupby_ordered_nosort(self):
self.df_ordered.groupby(["a1", "a2"], observed=False, sort=False)["b"].count()

def time_groupby_extra_cat_sort(self):
self.df_extra_cat.groupby(["a1", "a2"], observed=False)["b"].count()

def time_groupby_extra_cat_nosort(self):
self.df_extra_cat.groupby(["a1", "a2"], observed=False, sort=False)["b"].count()

def time_groupby_transform(self):
self.df_extra_cat.groupby(["a1", "a2"], observed=False)["b"].cumsum()


class Datelike:
# GH 14338
params = ["period_range", "date_range", "date_range_tz"]
Expand Down