computation of L2_distances

[Bear-kai]

I think the L2_distances in the function _nearest_neighbourcorrect should be computed as follows: dis = pairs[0][i] - pairs[1][i] dis = dis.reshape(dis.size) L2_distances[i] = np.sqrt(dis.dot(dis)) instead of L2_distances[i] = np.sum(np.sqrt(pairs[0][i]**2 - pairs[1][i]**2))

[jinwu07]

Or simply: L2_distances[i] = np.linalg.norm((pairs[0][i]- pairs[1][i]).reshape(-1), ord=2) The original code isn't quite right.