_iotools.py 文件源码

python
阅读 31 收藏 0 点赞 0 评论 0

项目:lambda-numba 作者: rlhotovy 项目源码 文件源码
def flatten_dtype(ndtype, flatten_base=False):
    """
    Unpack a structured data-type by collapsing nested fields and/or fields
    with a shape.

    Note that the field names are lost.

    Parameters
    ----------
    ndtype : dtype
        The datatype to collapse
    flatten_base : {False, True}, optional
        Whether to transform a field with a shape into several fields or not.

    Examples
    --------
    >>> dt = np.dtype([('name', 'S4'), ('x', float), ('y', float),
    ...                ('block', int, (2, 3))])
    >>> np.lib._iotools.flatten_dtype(dt)
    [dtype('|S4'), dtype('float64'), dtype('float64'), dtype('int32')]
    >>> np.lib._iotools.flatten_dtype(dt, flatten_base=True)
    [dtype('|S4'), dtype('float64'), dtype('float64'), dtype('int32'),
     dtype('int32'), dtype('int32'), dtype('int32'), dtype('int32'),
     dtype('int32')]

    """
    names = ndtype.names
    if names is None:
        if flatten_base:
            return [ndtype.base] * int(np.prod(ndtype.shape))
        return [ndtype.base]
    else:
        types = []
        for field in names:
            info = ndtype.fields[field]
            flat_dt = flatten_dtype(info[0], flatten_base)
            types.extend(flat_dt)
        return types
评论列表
文章目录


问题


面经


文章

微信
公众号

扫码关注公众号