we really need to check code for metrics in terms of "sample_weights" and normalization. #1138
Open
Description
should be carefully read, but also unit tested in terms of behavior.
maybe test sse1(w1) + sse2(w2) = sse2(w)
{{ message }}
should be carefully read, but also unit tested in terms of behavior.
maybe test sse1(w1) + sse2(w2) = sse2(w)