(Continuing per @avsm’s suggestion): what’s everyone doing this week?
I’ve just finished a cleanup of some simple clustering code (namely k-means, k-medoids and aggregative clustering). I expect that these implementations are slower than python or R ones, since the latter are essentially wrapping C code. It’s not on opam yet, as it’s not thoroughly tested (I used it on smallish datasets). Here’s the code: https://github.com/igarnier/clustering