Problem happens when set parameter "mode" = lp

[MingGuangShao]

Hi Maximilian,

I was trying to run your project holographic-embeddings with mode=lp to get the AUC score. At first, I got the error message that

AttributeError: 'PairwiseStochasticTrainer' object has no attribute '_scores'

I only found the '_score' function is belong to the member 'model' of class 'PairwiseStochasticTrainer', so I changed the line 232 of base.py
from

scores = mdl._scores(self.ss, self.ps, self.os)

to

scores = mdl.model._scores(self.ss, self.ps, self.os)

It works now, but I still want to make sure whether it is the right way to do that!
Thank for your kindly help and looking forward to your reply.

Best,
Daye SHAO

[leonardomra]

Hi Maximilian,
I'm also trying to run the project on model "lp". I get the error message:
self.ev_test = self.evaluator(data['test_subs'], data['test_labels']) KeyError: 'test_labels'
and
KeyError: 'valid_labels'
As far as I understood, the dataset should contain two more keys, but they aren't present.
Could you explain what "labels" exactly mean and how it could be fixed? Are "labels" relationships?
Thanks!
Leonardo

[grv1207]

@leonardomra Did you find the exact label ? I'm trying to used labels as 1assuming all edges are true, but that gives me error in AUC curve