Running NMF in R with Missing (NA) Values ​​in the Matrix

Question

I am looking for a package / if possible - a relatively ready-made solution for NMF (non-negative matrix factorization) in R, which can handle missing (NA) values ​​and not consider them equal to 0.

The goal is to evaluate these missing values ​​through the product of factorization, for a simple recommendation system.

The NMF CRAN package is wonderful, but it seems that it cannot do it (nor its more recent continuation outside CRAN), and I could not find suitable alternative packages ...

Answer 1

NLLM ( https://cran.r-project.org/web/packages/NNLM/index.html ) makes an erroneous imputation value through non-negative matrix factorization in R.

Set the missing matrix values ​​as NA . See vignette for more details.