utils.py 文件源码

def estimate_rank(data, tol='auto', return_singular=False,
                  norm=True, copy=None):
    """Helper to estimate the rank of data

    This function will normalize the rows of the data (typically
    channels or vertices) such that non-zero singular values
    should be close to one.

    Parameters
    ----------
    data : array
        Data to estimate the rank of (should be 2-dimensional).
    tol : float | str
        Tolerance for singular values to consider non-zero in
        calculating the rank. The singular values are calculated
        in this method such that independent data are expected to
        have singular value around one. Can be 'auto' to use the
        same thresholding as ``scipy.linalg.orth``.
    return_singular : bool
        If True, also return the singular values that were used
        to determine the rank.
    norm : bool
        If True, data will be scaled by their estimated row-wise norm.
        Else data are assumed to be scaled. Defaults to True.
    copy : bool
        This parameter has been deprecated and will be removed in 0.13.
        It is ignored in 0.12.

    Returns
    -------
    rank : int
        Estimated rank of the data.
    s : array
        If return_singular is True, the singular values that were
        thresholded to determine the rank are also returned.
    """
    if copy is not None:
        warn('copy is deprecated and ignored. It will be removed in 0.13.')
    data = data.copy()  # operate on a copy
    if norm is True:
        norms = _compute_row_norms(data)
        data /= norms[:, np.newaxis]
    s = linalg.svd(data, compute_uv=False, overwrite_a=True)
    if isinstance(tol, string_types):
        if tol != 'auto':
            raise ValueError('tol must be "auto" or float')
        eps = np.finfo(float).eps
        tol = np.max(data.shape) * np.amax(s) * eps
    tol = float(tol)
    rank = np.sum(s > tol)
    if return_singular is True:
        return rank, s
    else:
        return rank