I have a label matrix A, another label matrix B:
A = [1 1 1 2 3 3 1 1 2 2 3 3 4 1 2 2 3 3 4 4 5 5 5 5]B = [10 10 12 12 12 11 10 10 12 12 11 11 14 14 12 11 11 11 14 14 7 7 7 12]
how can I compute a mapping matrix C such that C(A) is most similar to B. Each C(i) should take the major element of B(A==i). For example,
C = [10 12 11 14 7]% means
% for B(A==1), most elements are 10.
% for B(A==2), most elements are 12.
% for B(A==3), most elements are 11.
% for B(A==4), most elements are 14.
% for B(A==5), most elements are 7.
Best Answer