cleanup code + prep for acceleration
-- grab the output from the golden model and save it in github
-- integrate the uncomitted work I have in virtualbox VM
-- switch from numpy to tensor in entire code
-- try change code to L2 for speedup
-- print results to file
-- cleanup, esp gen_data and value_at_risk
-- add nice comments to clarify what each function does (including list of args, etc as per style of weighter class + create smaller functions as needed
-- check what smoother/weighter was used in first paper
-- create a k nearest neighbor function, use my FAISS question to rename stuff
-- create mahalanobis distance function for clarity
-- benchmark vs julia?
-- faiss for mahalanobis distance search?
-- create mahalanobis distance function for clarity -- benchmark vs julia? -- faiss for mahalanobis distance search?