Skip to content
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

Add a benchmark to monitor performance for large dataset indexing #9012

Merged
merged 1 commit into from
May 7, 2024
Merged

Add a benchmark to monitor performance for large dataset indexing #9012

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
10 changes: 10 additions & 0 deletions asv_bench/benchmarks/indexing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
nt = 500

basic_indexes = {
"1scalar": {"x": 0},
"1slice": {"x": slice(0, 3)},
"1slice-1scalar": {"x": 0, "y": slice(None, None, 3)},
"2slicess-1scalar": {"x": slice(3, -3, 3), "y": 1, "t": slice(None, -3, 3)},
Expand Down Expand Up @@ -74,6 +75,10 @@ def setup(self, key):
"x_coords": ("x", np.linspace(1.1, 2.1, nx)),
},
)
# Benchmark how indexing is slowed down by adding many scalar variable
# to the dataset
# https://github.com/pydata/xarray/pull/9003
self.ds_large = self.ds.merge({f"extra_var{i}": i for i in range(400)})


class Indexing(Base):
Expand All @@ -89,6 +94,11 @@ def time_indexing_outer(self, key):
def time_indexing_vectorized(self, key):
self.ds.isel(**vectorized_indexes[key]).load()

@parameterized(["key"], [list(basic_indexes.keys())])
def time_indexing_basic_ds_large(self, key):
# https://github.com/pydata/xarray/pull/9003
self.ds_large.isel(**basic_indexes[key]).load()


class Assignment(Base):
@parameterized(["key"], [list(basic_indexes.keys())])
Expand Down