Concurrent_AP.py 文件源码

def set_preference(data, chunk_size):
    """Return the median of the distribution of pairwise L2 Euclidean distances 
        between samples (the rows of 'data') as the default preference parameter
        for Affinity Propagation clustering.

    Parameters
    ----------
    data : array of shape (N_samples, N_features)
        The data-set submitted for Affinity Propagation clustering.

    chunk_size : int
        The size of random subsamples from the data-set whose similarity
        matrix is computed. The resulting median of the distribution of 
        pairwise distances between the data-points selected as part of a
        given subsample is stored into a list of medians. 

    Returns
    -------
    preference : float
        The preference parameter for Affinity Propagation clustering is computed
        as the median of the list of median pairwise distances between the data-points
        selected as part of each of 15 rounds of random subsampling.
    """

    N_samples, N_features = data.shape

    rng = np.arange(0, N_samples, dtype = int)
    medians = []

    for i in xrange(15):
        selected_samples = np.random.choice(N_samples, size = chunk_size, replace = False)
        samples = data[selected_samples, :]

        S = - euclidean_distances(samples, data, squared = True)

        n = chunk_size * N_samples - (chunk_size * (chunk_size + 1) / 2)

        rows = np.zeros(0, dtype = int)
        for i in xrange(chunk_size):
            rows = np.append(rows, np.full(N_samples - i, i, dtype = int))

        cols = np.zeros(0, dtype = int)
        for i in xrange(chunk_size):
            cols = np.append(cols, np.delete(rng, selected_samples[:i+1]))

        triu_indices = tuple((rows, cols))

        preference = np.median(S, overwrite_input = True)
        medians.append(preference)

        del S

        if i % 4 == 3:
            gc.collect()       

    preference = np.median(medians)

    return preference