Using scikit-learn NMF with ONE precomputed basis vector
I am using scikit-learn NMF to decompose a matrix I have to 2-4 bases/factors.
I have only 1 factor which I know/want to anchor, namely I know W(1) and I want to use that knowledge in my factorization process. Is that possible?
I know I can use scikit-learn NMF with a fixed H or W matrix (see this question and answer) in case I have the entire matrix fixed. But what if I only have one basis/factor fixed? Is that technically possible to achieve with this function?
from Recent Questions - Stack Overflow https://ift.tt/3777XMP
https://ift.tt/eA8V8J
Comments
Post a Comment