You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
71 lines
2.1 KiB
71 lines
2.1 KiB
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
from pandas._libs import lib
|
|
from pandas.compat._optional import import_optional_dependency
|
|
from pandas.util._validators import check_dtype_backend
|
|
|
|
from pandas.core.dtypes.inference import is_list_like
|
|
|
|
from pandas.io.common import stringify_path
|
|
|
|
if TYPE_CHECKING:
|
|
from collections.abc import Sequence
|
|
from pathlib import Path
|
|
|
|
from pandas._typing import DtypeBackend
|
|
|
|
from pandas import DataFrame
|
|
|
|
|
|
def read_spss(
|
|
path: str | Path,
|
|
usecols: Sequence[str] | None = None,
|
|
convert_categoricals: bool = True,
|
|
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
|
|
) -> DataFrame:
|
|
"""
|
|
Load an SPSS file from the file path, returning a DataFrame.
|
|
|
|
Parameters
|
|
----------
|
|
path : str or Path
|
|
File path.
|
|
usecols : list-like, optional
|
|
Return a subset of the columns. If None, return all columns.
|
|
convert_categoricals : bool, default is True
|
|
Convert categorical columns into pd.Categorical.
|
|
dtype_backend : {'numpy_nullable', 'pyarrow'}, default 'numpy_nullable'
|
|
Back-end data type applied to the resultant :class:`DataFrame`
|
|
(still experimental). Behaviour is as follows:
|
|
|
|
* ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame`
|
|
(default).
|
|
* ``"pyarrow"``: returns pyarrow-backed nullable :class:`ArrowDtype`
|
|
DataFrame.
|
|
|
|
.. versionadded:: 2.0
|
|
|
|
Returns
|
|
-------
|
|
DataFrame
|
|
|
|
Examples
|
|
--------
|
|
>>> df = pd.read_spss("spss_data.sav") # doctest: +SKIP
|
|
"""
|
|
pyreadstat = import_optional_dependency("pyreadstat")
|
|
check_dtype_backend(dtype_backend)
|
|
|
|
if usecols is not None:
|
|
if not is_list_like(usecols):
|
|
raise TypeError("usecols must be list-like.")
|
|
usecols = list(usecols) # pyreadstat requires a list
|
|
|
|
df, _ = pyreadstat.read_sav(
|
|
stringify_path(path), usecols=usecols, apply_value_formats=convert_categoricals
|
|
)
|
|
if dtype_backend is not lib.no_default:
|
|
df = df.convert_dtypes(dtype_backend=dtype_backend)
|
|
return df
|
|
|