I applied 3 classifiers and I want to apply soft voting manually not by sklearn, in addition, I have 4 labels.
for example, I have 4 labels (L1, L2, L3, L4), each label has two classes(0/1):
class label: L1 L2 L3 L4
predict vlaues for classifier 1: 0.5 0.2 0.7 0.3
predict vlaues for classifier 2: 0.3 0.4 0.2 0.6
predict vlaues for classifier 3: 0.7 0.8 0.1 0.9
I want to apply soft voting manually (by equations) for multi-label, not for multi-class. note: we assign equal weights to all classifiers: w1=1, w2=1, w3=1, and to make a decision for the classifier, if the value >=0.5 then the predicted label is 1 and if the value <0.5 then the predict label is 0.
