We completed the GA run on the mass check results, then removed the tests in question and ran it again. The results were pretty much as I expected (we're only doing set 0 right now, and the recall dropped from a little over 94% to around 91.5% after removing about 200 tests). So far so good.
The problem we're having now is in trying to get a STATISTICS.txt and 50_scores.cf that reflect the output of the GA (the new scores and stats). We've read the readme's and looked at the code, but can't quite piece it together. We tried a variety of things, including running rewrite-cf-with-new-scores, then another runGA with a command line argument to trigger the [GA Validation Results] part, but none of the results seem correct (the recall number in STATISTICS.txt is much lower than the one that the GA spit out, among other things). The other bigh issue is that the scores in statistics are not updated to reflect the GA results. I'm a little confused by how the correct scores are supposed to find their way into statistics, as the freqs file seems to be created at the beginning of the GA run and then is inserted into the statistics file at the end (and I don't see any place that the scores in freqs get updated to match the scores produced by the GA). Anyway, I'm clearly missing something here. Any help would be appreciated. Bob ------------------------------------------------------- This sf.net email is sponsored by:ThinkGeek Welcome to geek heaven. http://thinkgeek.com/sf _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
