From: timm@cs.pdx.edu   
      
   so i've been writing a PRISM/INDUCT clone that   
   finds attribute ranges of interest, removes   
   all instances with those ranges, then repeats   
   on the remaining data.   
      
   i had a "good idea" of keeping indexes attribute values   
   for each instance and incrementally updating those   
   indexes when i removed some data.   
      
   this has proven to be surprisingly complex so i was   
   wondering if anyone had a view on good data structures   
   for the internals of a rule covering algorithm?   
      
   tim menzies   
   http://menzies.us   
      
   [ comp.ai is moderated.  To submit, just post and be patient, or if ]   
   [ that fails mail your article to , and ]   
   [ ask your news administrator to fix the problems with your system. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)