naresh1318 / diagnosispredictor Goto Github PK

Hello, I got a new result after running the codes on my computer about the dense_fully_connected.py, the deep_dense_fully_connected.py and the lstm.py in Predictor_tfidf.

• When calculate the confusion matrix, it raise the 'UndefinedMetricWarning: No negative samples in y_true, false positive value should be meaningless' .
• Besides, the scores of other evaluation indicators are different from the uploaded socres.

So, have you ever had such a problem? Why are the results different from the uploaded ones? and would you like to give the links if you published any relevant papers?

I would appreciate if you can give me some explanations about my questions.

Does this implement multi - label neural network with binary relevance (BR) and label powerset (LP) ?