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

ASV: add benchmarks for DataFrame.xs with a MultiIndex #46233

Merged
merged 2 commits into from
Mar 4, 2022
Merged

ASV: add benchmarks for DataFrame.xs with a MultiIndex #46233

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8353821
add asvs for df.xs with MultiIndex
lukemanley Mar 4, 2022
63570c1
Merge remote-tracking branch 'upstream/main' into multiindex-xs-asvs
lukemanley Mar 4, 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
30 changes: 21 additions & 9 deletions asv_bench/benchmarks/indexing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -204,11 +204,11 @@ class MultiIndexing:
param_names = ["unique_levels"]

def setup(self, unique_levels):
self.ndim = 2
self.nlevels = 2
if unique_levels:
mi = MultiIndex.from_arrays([range(1000000)] * self.ndim)
mi = MultiIndex.from_arrays([range(1000000)] * self.nlevels)
else:
mi = MultiIndex.from_product([range(1000)] * self.ndim)
mi = MultiIndex.from_product([range(1000)] * self.nlevels)
self.df = DataFrame(np.random.randn(len(mi)), index=mi)

self.tgt_slice = slice(200, 800)
Expand All @@ -232,27 +232,27 @@ def time_loc_partial_key_list(self, unique_levels):
def time_loc_partial_key_scalar(self, unique_levels):
self.df.loc[self.tgt_scalar, :]

def time_loc_partial_bool_indexer(self, unique_levels):
def time_loc_partial_key_bool_indexer(self, unique_levels):
self.df.loc[self.tgt_bool_indexer, :]

def time_loc_all_slices(self, unique_levels):
target = tuple([self.tgt_slice] * self.ndim)
target = tuple([self.tgt_slice] * self.nlevels)
self.df.loc[target, :]

def time_loc_all_null_slices(self, unique_levels):
target = tuple([self.tgt_null_slice] * self.ndim)
target = tuple([self.tgt_null_slice] * self.nlevels)
self.df.loc[target, :]

def time_loc_all_lists(self, unique_levels):
target = tuple([self.tgt_list] * self.ndim)
target = tuple([self.tgt_list] * self.nlevels)
self.df.loc[target, :]

def time_loc_all_scalars(self, unique_levels):
target = tuple([self.tgt_scalar] * self.ndim)
target = tuple([self.tgt_scalar] * self.nlevels)
self.df.loc[target, :]

def time_loc_all_bool_indexers(self, unique_levels):
target = tuple([self.tgt_bool_indexer] * self.ndim)
target = tuple([self.tgt_bool_indexer] * self.nlevels)
self.df.loc[target, :]

def time_loc_slice_plus_null_slice(self, unique_levels):
Expand All @@ -263,6 +263,18 @@ def time_loc_null_slice_plus_slice(self, unique_levels):
target = (self.tgt_null_slice, self.tgt_slice)
self.df.loc[target, :]

def time_xs_level_0(self, unique_levels):
target = self.tgt_scalar
self.df.xs(target, level=0)

def time_xs_level_1(self, unique_levels):
target = self.tgt_scalar
self.df.xs(target, level=1)

def time_xs_full_key(self, unique_levels):
target = tuple([self.tgt_scalar] * self.nlevels)
self.df.xs(target)


class IntervalIndexing:
def setup_cache(self):
Expand Down