Skip to content

⚡️ Speed up function _annual_finder by 11% #97

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

⚡️ Speed up function _annual_finder by 11% #97

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
38 changes: 21 additions & 17 deletions pandas/plotting/_matplotlib/converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@ def wrapper(*args, **kwargs):
with pandas_converters():
return func(*args, **kwargs)

return cast(F, wrapper)
return cast("F", wrapper)


@contextlib.contextmanager
Expand Down Expand Up @@ -466,21 +466,20 @@ def _get_default_annual_spacing(nyears) -> tuple[int, int]:
Returns a default spacing between consecutive ticks for annual data.
"""
if nyears < 11:
(min_spacing, maj_spacing) = (1, 1)
return (1, 1)
elif nyears < 20:
(min_spacing, maj_spacing) = (1, 2)
return (1, 2)
elif nyears < 50:
(min_spacing, maj_spacing) = (1, 5)
return (1, 5)
elif nyears < 100:
(min_spacing, maj_spacing) = (5, 10)
return (5, 10)
elif nyears < 200:
(min_spacing, maj_spacing) = (5, 25)
return (5, 25)
elif nyears < 600:
(min_spacing, maj_spacing) = (10, 50)
return (10, 50)
else:
factor = nyears // 1000 + 1
(min_spacing, maj_spacing) = (factor * 20, factor * 100)
return (min_spacing, maj_spacing)
return (factor * 20, factor * 100)


def _period_break(dates: PeriodIndex, period: str) -> npt.NDArray[np.intp]:
Expand Down Expand Up @@ -879,22 +878,27 @@ def _quarterly_finder(vmin: float, vmax: float, freq: BaseOffset) -> np.ndarray:
@functools.cache
def _annual_finder(vmin: float, vmax: float, freq: BaseOffset) -> np.ndarray:
# Note: small difference here vs other finders in adding 1 to vmax
(vmin, vmax) = (int(vmin), int(vmax + 1))
vmin = int(vmin)
vmax = int(vmax + 1)
span = vmax - vmin + 1

# Precompute arange once and use views for slices wherever possible
dates_ = np.arange(vmin, vmax + 1)
info = np.zeros(
span, dtype=[("val", int), ("maj", bool), ("min", bool), ("fmt", "|S8")]
)
info["val"] = np.arange(vmin, vmax + 1)
info["fmt"] = ""
dates_ = info["val"]
info["val"] = dates_
# "fmt" field pre-fills as empty bytes, so direct assignment unnecessary

min_anndef, maj_anndef = _get_default_annual_spacing(span)

(min_anndef, maj_anndef) = _get_default_annual_spacing(span)
# Use numpy vectorization for fast assignment
major_idx = dates_ % maj_anndef == 0
minor_idx = dates_ % min_anndef == 0
info["maj"][major_idx] = True
info["min"][minor_idx] = True
info["fmt"][major_idx] = "%Y"
# As 'major_idx' and 'minor_idx' are numpy bool arrays, assignment with them is fast
info["maj"] = major_idx
info["min"] = minor_idx
info["fmt"][major_idx] = b"%Y"

return info

Expand Down