Function sanitize_array

pandas/core/construction.py:531–688

Sanitize input data to an ndarray or ExtensionArray, copy if specified, coerce to the dtype if specified. Parameters ---------- data : Any index : Index or None, default None dtype : np.dtype, ExtensionDtype, or None, default None copy : bool, default False allo

(
    data,
    index: Index | None,
    dtype: DtypeObj | None = None,
    copy: bool = False,
    *,
    allow_2d: bool = False,
)

def sanitize_array(
    data,
    index: Index | None,
    dtype: DtypeObj | None = None,
    copy: bool = False,
    *,
    allow_2d: bool = False,
) -> ArrayLike:
    """
    Sanitize input data to an ndarray or ExtensionArray, copy if specified,
    coerce to the dtype if specified.

    Parameters
    ----------
    data : Any
    index : Index or None, default None
    dtype : np.dtype, ExtensionDtype, or None, default None
    copy : bool, default False
    allow_2d : bool, default False
        If False, raise if we have a 2D Arraylike.

    Returns
    -------
    np.ndarray or ExtensionArray
    """
    original_dtype = dtype
    if isinstance(data, ma.MaskedArray):
        data = sanitize_masked_array(data)

    if isinstance(dtype, NumpyEADtype):
        # Avoid ending up with a NumpyExtensionArray
        dtype = dtype.numpy_dtype

    infer_object = not isinstance(data, (ABCIndex, ABCSeries))

    # extract ndarray or ExtensionArray, ensure we have no NumpyExtensionArray
    data = extract_array(data, extract_numpy=True, extract_range=True)

    if isinstance(data, np.ndarray) and data.ndim == 0:
        if dtype is None:
            dtype = data.dtype
        data = lib.item_from_zerodim(data)
    elif isinstance(data, range):
        # GH#16804
        data = range_to_ndarray(data)
        copy = False

    if not is_list_like(data):
        if index is None:
            raise ValueError("index must be specified when data is not list-like")
        if isinstance(data, str) and using_string_dtype() and original_dtype is None:
            from pandas.core.arrays.string_ import StringDtype

            dtype = StringDtype(na_value=np.nan)
        data = construct_1d_arraylike_from_scalar(data, len(index), dtype)

        return data