information_process.py 文件源码

def calc_information_sampling(data, bins, pys1, pxs, label, b, b1, len_unique_a, p_YgX, unique_inverse_x,
                              unique_inverse_y, calc_DKL=False):
    bins = bins.astype(np.float32)
    num_of_bins = bins.shape[0]
    # bins = stats.mstats.mquantiles(np.squeeze(data.reshape(1, -1)), np.linspace(0,1, num=num_of_bins))
    # hist, bin_edges = np.histogram(np.squeeze(data.reshape(1, -1)), normed=True)
    digitized = bins[np.digitize(np.squeeze(data.reshape(1, -1)), bins) - 1].reshape(len(data), -1)
    b2 = np.ascontiguousarray(digitized).view(
        np.dtype((np.void, digitized.dtype.itemsize * digitized.shape[1])))
    unique_array, unique_inverse_t, unique_counts = \
        np.unique(b2, return_index=False, return_inverse=True, return_counts=True)
    p_ts = unique_counts / float(sum(unique_counts))
    PXs, PYs = np.asarray(pxs).T, np.asarray(pys1).T
    if calc_DKL:
        pxy_given_T = np.array(
            [calc_probs(i, unique_inverse_t, label, b, b1, len_unique_a) for i in range(0, len(unique_array))]
        )
        p_XgT = np.vstack(pxy_given_T[:, 0])
        p_YgT = pxy_given_T[:, 1]
        p_YgT = np.vstack(p_YgT).T
        DKL_YgX_YgT = np.sum([inf_ut.KL(c_p_YgX, p_YgT.T) for c_p_YgX in p_YgX.T], axis=0)
        H_Xgt = np.nansum(p_XgT * np.log2(p_XgT), axis=1)
    local_IXT, local_ITY = calc_information_from_mat(PXs, PYs, p_ts, digitized, unique_inverse_x, unique_inverse_y,
                                                     unique_array)
    return local_IXT, local_ITY