cluster.py 文件源码

def compute_weights(x, C):
    """Number of points in x assigned to each centre c in C

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

    Returns
    -------
    weights : ndarray
        (k,) length array giving number of x closest to each c in C
    """
    nsplits = max(1, int(x.shape[0]/distance_partition_size))
    splits = np.array_split(x, nsplits)
    closests = np.empty(x.shape[0], dtype=int)
    idx = 0
    for x_i in splits:
        n_i = x_i.shape[0]
        D2_x = scipy.spatial.distance.cdist(x_i, C, metric='sqeuclidean')
        closests[idx: idx+n_i] = np.argmin(D2_x, axis=1)
        idx += n_i
    weights = np.bincount(closests, minlength=C.shape[0])
    return weights