Skip to content

[skip-ci] Add benchmarks for groupby math #6390

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 3 commits into from
Mar 21, 2022
Merged

[skip-ci] Add benchmarks for groupby math #6390

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2c786bd
Add benchmarks for groupby math
dcherian Mar 21, 2022
2e7fad2
[skip-ci]
dcherian Mar 21, 2022
d2842b4
[skip-ci] add peakmem benchmarks
dcherian Mar 21, 2022
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
44 changes: 44 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 @@ -16,6 +16,8 @@ def setup(self, *args, **kwargs):
}
)
self.ds2d = self.ds1d.expand_dims(z=10)
self.ds1d_mean = self.ds1d.groupby("b").mean()
self.ds2d_mean = self.ds2d.groupby("b").mean()

@parameterized(["ndim"], [(1, 2)])
def time_init(self, ndim):
Expand All @@ -31,6 +33,18 @@ def time_agg_large_num_groups(self, method, ndim):
ds = getattr(self, f"ds{ndim}d")
getattr(ds.groupby("b"), method)()

def time_groupby_binary_op_1d(self):
self.ds1d - self.ds1d_mean

def time_groupby_binary_op_2d(self):
self.ds2d - self.ds2d_mean

def peakmem_groupby_binary_op_1d(self):
self.ds1d - self.ds1d_mean

def peakmem_groupby_binary_op_2d(self):
self.ds2d - self.ds2d_mean


class GroupByDask(GroupBy):
def setup(self, *args, **kwargs):
Expand All @@ -40,6 +54,8 @@ def setup(self, *args, **kwargs):
self.ds2d = self.ds2d.sel(dim_0=slice(None, None, 2)).chunk(
{"dim_0": 50, "z": 5}
)
self.ds1d_mean = self.ds1d.groupby("b").mean()
self.ds2d_mean = self.ds2d.groupby("b").mean()


class GroupByPandasDataFrame(GroupBy):
Expand All @@ -51,6 +67,13 @@ def setup(self, *args, **kwargs):

super().setup(**kwargs)
self.ds1d = self.ds1d.to_dataframe()
self.ds1d_mean = self.ds1d.groupby("b").mean()

def time_groupby_binary_op_2d(self):
raise NotImplementedError

def peakmem_groupby_binary_op_2d(self):
raise NotImplementedError


class GroupByDaskDataFrame(GroupBy):
Expand All @@ -63,6 +86,13 @@ def setup(self, *args, **kwargs):
requires_dask()
super().setup(**kwargs)
self.ds1d = self.ds1d.chunk({"dim_0": 50}).to_dataframe()
self.ds1d_mean = self.ds1d.groupby("b").mean()

def time_groupby_binary_op_2d(self):
raise NotImplementedError

def peakmem_groupby_binary_op_2d(self):
raise NotImplementedError


class Resample:
Expand All @@ -74,6 +104,8 @@ def setup(self, *args, **kwargs):
coords={"time": pd.date_range("2001-01-01", freq="H", periods=365 * 24)},
)
self.ds2d = self.ds1d.expand_dims(z=10)
self.ds1d_mean = self.ds1d.resample(time="48H").mean()
self.ds2d_mean = self.ds2d.resample(time="48H").mean()

@parameterized(["ndim"], [(1, 2)])
def time_init(self, ndim):
Expand All @@ -89,6 +121,18 @@ def time_agg_large_num_groups(self, method, ndim):
ds = getattr(self, f"ds{ndim}d")
getattr(ds.resample(time="48H"), method)()

def time_groupby_binary_op_1d(self):
self.ds1d - self.ds1d_mean

def time_groupby_binary_op_2d(self):
self.ds2d - self.ds2d_mean

def peakmem_groupby_binary_op_1d(self):
self.ds1d - self.ds1d_mean

def peakmem_groupby_binary_op_2d(self):
self.ds2d - self.ds2d_mean


class ResampleDask(Resample):
def setup(self, *args, **kwargs):
Expand Down