I already cleaned the db to make sure I dont have it broken. Would it be better to turn off the autolearn. Teach sa ham and spam from over 200 messages and then turn back the autolearn?
thx > On Thu, 29 Oct 2015, Martin Gregorie wrote: > >> On Tue, 2015-10-27 at 14:19 -0500, j...@lexoncom.com wrote: >>> I dont use any ham training.Should I scan all my folders with this >>> command: >>> sa-learn --ham --mbox /home/username/mail/foldername >> >> YES - if Bayes never gets trained on ham, how do you expect it to >> recognise the difference between ham and spam? >> >> Bayes won't start to work until it has seen 200 examples of ham and 200 >> examples of spam. > > Again: *vetted* ham and spam. Don't just blindly throw your inbox at it > assuming your inbox is pristine. > >>> "is the bayes-db of this user *realy* used at scan time" >>> how do i check that? >> >> When its working you'll see BAYES_nn rules firing. > > Note BAYES_00 in the report below. The OP is getting ham from *somewhere*. > If he's never manually trained ham then it's probably coming from > autolearn, and depending on other issues that might have poisoned the > database from the start. > >>> example mail sa headers: >>> >>> X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on >>> ip-10-254-37-89.us-west-2.compute.internal >>> X-Spam-Level: *** >>> X-Spam-Status: No, score=3.1 required=5.0 >>> tests=BAYES_00,HTML_MESSAGE, >>> RAZOR2_CF_RANGE_51_100,RAZOR2_CF_RANGE_E8_51_100,RAZOR2_C >>> HECK,SPF_HELO_PASS, >>> SPF_PASS,URIBL_BLOCKED,URIBL_DBL_SPAM autolearn=no >>> autolearn_force=no >>> version=3.4.0 > > -- > John Hardin KA7OHZ http://www.impsec.org/~jhardin/ > jhar...@impsec.org FALaholic #11174 pgpk -a jhar...@impsec.org > key: 0xB8732E79 -- 2D8C 34F4 6411 F507 136C AF76 D822 E6E6 B873 2E79 > ----------------------------------------------------------------------- > ...the Fates notice those who buy chainsaws... > -- www.darwinawards.com > ----------------------------------------------------------------------- > Tomorrow: Halloween >
