On 10/28, Alexandre Boyer wrote: > I understood that. I however need to rescore my ruleset because the setup > I inherited was 1) not updated with sa-update and 2) manually maintained > (with , for example, lot's of perso rules that essentially do the same as > the SA rules added over time).
I don't understand why re-scoring seems like a necessary step to you. One thing I really want you to understand is that the automated main SA re-scoring does not happen unless we have 150,000 spams, and 150,000 hams (non-spams). Because we do not trust the results to be sufficiently accurate / reliable with fewer. If you can get that many hand classified hams and spams together, that's awesome, I envy you, and I think that would be a great idea for your accuracy. However, I doubt it. If you do get re-scoring to work at all, I strongly encourage you to update the wiki. I'm sure that section is particularly in need of love because nobody ever does that. Just create an account on the wiki, and email the dev mailing list to request write access. The age thresholds for re-scoring are: Ham: 6 years (crazy, right? another reason we need more data) Spam: 2 months > As a brutal reset is out of question, I need to do things step by step, > rescoring being one of them prior to have my threshold back to 5 and > sa-update enabled. Taking things step by step sounds reasonable enough. Re-scoring doesn't. > All this being my own private problem, nothing to do with our off topic > exchange :-) Eh, it's some obscure usage, but I still think it's entirely appropriate to discuss here. > Arround 10 corpora. Are those corpora used tu run the SA mass-check on SA > servers or do it also include what I will send one day (my mc logs)? I'll assume you'll find my email which said more on this subject, instead of replying to some of this again. -- "Life is either a daring adventure or it is nothing at all." - Helen Keller http://www.ChaosReigns.com
