good. your bayesian watches the body, while stopforumspam inspects usernames, emails and ips. Don't know how much use can it have to instruct your filter with the "terms" present in username and emails of stopforumspam, but I'm happy that at least someone will use the plugin :P
On Thursday, April 4, 2013 12:39:19 AM UTC+2, Ricardo Pedroso wrote: > > On Fri, Mar 29, 2013 at 1:41 AM, Niphlod <[email protected] > <javascript:>>wrote: > >> Here https://github.com/niphlod/w2p_SFS_plugin >> >> Ultra-alpha-Release ... expect bugs, api changes and some other >> intricacies.... >> >> PS: if someone wants to chime in to figure out an algorithm to calculate >> confidence (0-100) based on frequency and last_seen I'm happy to hear its >> thoughs >> > > Hi Niphlod, > > I will take a look for sure, because I'm planning using a bayesian spam > filtering for comments > for a personal blog system that I am, slowly, building. > So I adapt this one https://github.com/jart/redisbayes to be able to use > with DAL. > > I can send you the code right know if you want or just wait until I > release it ;). > > I take this opportunity to ask people to access my testing server where I > have that experimental blog, > and make some comments to see if training/untraining is working. > And also, to see if the system can handle some "real" load. > > http://78.46.172.53:8080/sblog/post/view/first-post-1 > > > Regards, > Ricardo > > -- --- You received this message because you are subscribed to the Google Groups "web2py-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/groups/opt_out.
