I wrote up a quick blog post on my first experiences with the GaussianMixtures.jl package by @davidavdav. My main alternative would be an R implementation, hence the benchmark is comparing 2 R with 2 julia implementations. Julia outperforms R (surprise? ). Comments most welcome!
wow, the R code is a monster compared to the julia bit
yes. well, I couldn’t claim that’s the best possible R code, but I couldn’t figure out how to do the
repeat without this
spread function. There may be better ways. Also, to be fair, I had another 3 lines of not shown julia code defining the