Skip to content

PERF: refactor string construction benchmark #52410

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
Apr 6, 2023
Merged

PERF: refactor string construction benchmark #52410

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e4cb3a9
PERF: refactor string construction benchmark
ngoldbaum Apr 4, 2023
47f9a32
CLN: respond to review comments
ngoldbaum Apr 4, 2023
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
52 changes: 25 additions & 27 deletions asv_bench/benchmarks/strings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,33 +25,31 @@ def setup(self, dtype):


class Construction:
params = ["str", "string"]
param_names = ["dtype"]

def setup(self, dtype):
self.series_arr = tm.rands_array(nchars=10, size=10**5)
self.frame_arr = self.series_arr.reshape((50_000, 2)).copy()

# GH37371. Testing construction of string series/frames from ExtensionArrays
self.series_cat_arr = Categorical(self.series_arr)

def time_series_construction(self, dtype):
Series(self.series_arr, dtype=dtype)

def peakmem_series_construction(self, dtype):
Series(self.series_arr, dtype=dtype)

def time_frame_construction(self, dtype):
DataFrame(self.frame_arr, dtype=dtype)

def peakmem_frame_construction(self, dtype):
DataFrame(self.frame_arr, dtype=dtype)

def time_cat_series_construction(self, dtype):
Series(self.series_cat_arr, dtype=dtype)

def peakmem_cat_series_construction(self, dtype):
Series(self.series_cat_arr, dtype=dtype)
params = (
["series", "frame", "categorical_series"],
["str", "string[python]", "string[pyarrow]"],
)
param_names = ["pd_type", "dtype"]
pd_mapping = {"series": Series, "frame": DataFrame, "categorical_series": Series}
dtype_mapping = {"str": "str", "string[python]": object, "string[pyarrow]": object}

def setup(self, pd_type, dtype):
series_arr = tm.rands_array(
nchars=10, size=10**5, dtype=self.dtype_mapping[dtype]
)
if pd_type == "series":
self.arr = series_arr
elif pd_type == "frame":
self.arr = series_arr.reshape((50_000, 2)).copy()
elif pd_type == "categorical_series":
# GH37371. Testing construction of string series/frames from ExtensionArrays
self.arr = Categorical(series_arr)

def time_construction(self, pd_type, dtype):
self.pd_mapping[pd_type](self.arr, dtype=dtype)

def peakmem_construction(self, pd_type, dtype):
self.pd_mapping[pd_type](self.arr, dtype=dtype)


class Methods(Dtypes):
Expand Down