which distance to check correrlation with?

[xmangaz]

Knowledge_Persistence/compute_distance_bet_neg_graphs_extended.py

Line 216 in 703417b

'distances': dists

Hi,,

With this output, two dists are given. which ones will be the correct measure correlation against ranking metrics?? Or is it weighted?

THanks :)

[ansonb]

Hello,

Thanks for your interest in our work.

With the two distances, I guess you are referring to the 0 and 1 dimensional PD distances. Empirically we have found the 0 dim PD (the first distance) to give better results. So you could try with using the first element of "dists".

Thanks