cluster.py 文件源码

def kmean_distance2(x, C):
    """Compute squared euclidian distance to the nearest cluster centre

    Parameters
    ----------
    x : ndarray
        (n, d) array of n d-dimensional points
    C : ndarray
        (k, d) array of k cluster centres

    Returns
    -------
    d2_x : ndarray
        (n,) length array of distances from each x to the nearest centre
    """
    # To save memory we partition the computation
    nsplits = max(1, int(x.shape[0]/distance_partition_size))
    splits = np.array_split(x, nsplits)
    d2_x = np.empty(x.shape[0])
    idx = 0
    for x_i in splits:
        n_i = x_i.shape[0]
        D2_x = scipy.spatial.distance.cdist(x_i, C, metric='sqeuclidean')
        d2_x[idx:idx + n_i] = np.amin(D2_x, axis=1)
        idx += n_i
    return d2_x