information_process.py 文件源码

def extract_probs(label, x):
    """calculate the probabilities of the given data and labels p(x), p(y) and (y|x)"""
    pys = np.sum(label, axis=0) / float(label.shape[0])
    b = np.ascontiguousarray(x).view(np.dtype((np.void, x.dtype.itemsize * x.shape[1])))
    unique_array, unique_indices, unique_inverse_x, unique_counts = \
        np.unique(b, return_index=True, return_inverse=True, return_counts=True)
    unique_a = x[unique_indices]
    b1 = np.ascontiguousarray(unique_a).view(np.dtype((np.void, unique_a.dtype.itemsize * unique_a.shape[1])))
    pxs = unique_counts / float(np.sum(unique_counts))
    p_y_given_x = []
    for i in range(0, len(unique_array)):
        indexs = unique_inverse_x == i
        py_x_current = np.mean(label[indexs, :], axis=0)
        p_y_given_x.append(py_x_current)
    p_y_given_x = np.array(p_y_given_x).T
    b_y = np.ascontiguousarray(label).view(np.dtype((np.void, label.dtype.itemsize * label.shape[1])))
    unique_array_y, unique_indices_y, unique_inverse_y, unique_counts_y = \
        np.unique(b_y, return_index=True, return_inverse=True, return_counts=True)
    pys1 = unique_counts_y / float(np.sum(unique_counts_y))
    return pys, pys1, p_y_given_x, b1, b, unique_a, unique_inverse_x, unique_inverse_y, pxs