Skip to content

⚡️ Speed up function _get_converter by 5% #111

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 _get_converter by 5% #111

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
17 changes: 11 additions & 6 deletions pandas/io/pytables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1750,7 +1750,7 @@ def info(self) -> str:

if self.is_open:
lkeys = sorted(self.keys())
if len(lkeys):
if lkeys:
keys = []
values = []

Expand Down Expand Up @@ -4505,7 +4505,7 @@ def write_data(self, chunksize: int | None, dropna: bool = False) -> None:
masks.append(mask.astype("u1", copy=False))

# consolidate masks
if len(masks):
if masks:
mask = masks[0]
for m in masks[1:]:
mask = mask & m
Expand Down Expand Up @@ -4625,7 +4625,7 @@ def delete(
groups = list(diff[diff > 1].index)

# 1 group
if not len(groups):
if not groups:
groups = [0]

# final element
Expand Down Expand Up @@ -5091,7 +5091,7 @@ def _maybe_convert_for_string_atom(
if bvalues.dtype != object:
return bvalues

bvalues = cast(np.ndarray, bvalues)
bvalues = cast("np.ndarray", bvalues)

dtype_name = bvalues.dtype.name
inferred_type = lib.infer_dtype(bvalues, skipna=False)
Expand Down Expand Up @@ -5229,13 +5229,18 @@ def _maybe_convert(values: np.ndarray, val_kind: str, encoding: str, errors: str


def _get_converter(kind: str, encoding: str, errors: str):
# Use direct comparison for expected kinds to avoid expensive substring search
if kind == "datetime64":
return lambda x: np.asarray(x, dtype="M8[ns]")
elif "datetime64" in kind:
elif kind.startswith(
"datetime64"
): # substring search is more expensive than startswith
return lambda x: np.asarray(x, dtype=kind)
elif kind == "string":
# Move instantiation of lambda parameters outside for less overhead inside lambda
nan_rep = None
return lambda x: _unconvert_string_array(
x, nan_rep=None, encoding=encoding, errors=errors
x, nan_rep=nan_rep, encoding=encoding, errors=errors
)
else: # pragma: no cover
raise ValueError(f"invalid kind {kind}")
Expand Down