metrics.py 文件源码

def sigma_gak(dataset, n_samples=100, random_state=None):
    """Compute sigma value to be used for GAK.

    This method was originally presented in [1]_.

    Parameters
    ----------
    dataset
        A dataset of time series
    n_samples : int (default: 100)
        Number of samples on which median distance should be estimated
    random_state : integer or numpy.RandomState or None (default: None)
        The generator used to draw the samples. If an integer is given, it fixes the seed. Defaults to the global
        numpy random number generator.

    Returns
    -------
    float
        Suggested bandwidth (:math:`\\sigma`) for the Global Alignment kernel

    Example
    -------
    >>> dataset = [[1, 2, 2, 3], [1., 2., 3., 4.]]
    >>> sigma_gak(dataset=dataset, n_samples=200, random_state=0)  # doctest: +ELLIPSIS
    2.0...

    See Also
    --------
    gak : Compute Global Alignment kernel
    cdist_gak : Compute cross-similarity matrix using Global Alignment kernel

    References
    ----------
    .. [1] M. Cuturi, "Fast global alignment kernels," ICML 2011.
    """
    random_state = check_random_state(random_state)
    dataset = to_time_series_dataset(dataset)
    n_ts, sz, d = dataset.shape
    if n_ts * sz < n_samples:
        replace = True
    else:
        replace = False
    sample_indices = random_state.choice(n_ts * sz, size=n_samples, replace=replace)
    dists = pdist(dataset.reshape((-1, d))[sample_indices], metric="euclidean")
    return numpy.median(dists) * numpy.sqrt(sz)