Skip to content

⚡️ Speed up function _pad_bytes by 8% #100

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 _pad_bytes by 8% #100

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: 10 additions & 7 deletions pandas/io/stata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1503,7 +1503,7 @@ def _setup_dtype(self) -> np.dtype:
dtypes = [] # Convert struct data types to numpy data type
for i, typ in enumerate(self._typlist):
if typ in self.NUMPY_TYPE_MAP:
typ = cast(str, typ) # only strs in NUMPY_TYPE_MAP
typ = cast("str", typ) # only strs in NUMPY_TYPE_MAP
dtypes.append((f"s{i}", f"{self._byteorder}{self.NUMPY_TYPE_MAP[typ]}"))
else:
dtypes.append((f"s{i}", f"S{typ}"))
Expand Down Expand Up @@ -1832,13 +1832,13 @@ def _do_convert_missing(self, data: DataFrame, convert_missing: bool) -> DataFra
if fmt not in self.OLD_VALID_RANGE:
continue

fmt = cast(str, fmt) # only strs in OLD_VALID_RANGE
fmt = cast("str", fmt) # only strs in OLD_VALID_RANGE
nmin, nmax = self.OLD_VALID_RANGE[fmt]
else:
if fmt not in self.VALID_RANGE:
continue

fmt = cast(str, fmt) # only strs in VALID_RANGE
fmt = cast("str", fmt) # only strs in VALID_RANGE
nmin, nmax = self.VALID_RANGE[fmt]
series = data.iloc[:, i]

Expand Down Expand Up @@ -2174,9 +2174,12 @@ def _pad_bytes(name: AnyStr, length: int) -> AnyStr:
"""
Take a char string and pads it with null bytes until it's length chars.
"""
n_pad = length - len(name)
if n_pad <= 0:
return name
if isinstance(name, bytes):
return name + b"\x00" * (length - len(name))
return name + "\x00" * (length - len(name))
return name + (b"\x00" * n_pad)
return name + ("\x00" * n_pad)


def _convert_datetime_to_stata_type(fmt: str) -> np.dtype:
Expand Down Expand Up @@ -2867,7 +2870,7 @@ def _write_header(
# ds_format - just use 114
self._write_bytes(struct.pack("b", 114))
# byteorder
self._write(byteorder == ">" and "\x01" or "\x02")
self._write((byteorder == ">" and "\x01") or "\x02")
# filetype
self._write("\x01")
# unused
Expand Down Expand Up @@ -3413,7 +3416,7 @@ def _write_header(
# ds_format - 117
bio.write(self._tag(bytes(str(self._dta_version), "utf-8"), "release"))
# byteorder
bio.write(self._tag(byteorder == ">" and "MSF" or "LSF", "byteorder"))
bio.write(self._tag((byteorder == ">" and "MSF") or "LSF", "byteorder"))
# number of vars, 2 bytes in 117 and 118, 4 byte in 119
nvar_type = "H" if self._dta_version <= 118 else "I"
bio.write(self._tag(struct.pack(byteorder + nvar_type, self.nvar), "K"))
Expand Down