You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@spamassassin.apache.org by Ky...@transplace.com on 2005/02/17 00:32:34 UTC
how to read sa-learn --dump output
Could someone help me determine what these fields represent?
0.001 0 48 1108391722 H*M:hpb
0.001 0 48 1108391722 H*M:hpbrm
0.001 0 55 1108391737 H*r:sk:PUBLIC.
0.001 0 56 1108391737 H*F:U*mthomason
0.001 0 57 1108391737 H*F:D*halfpricebooks.com
0.001 0 57 1108391737 H*r:66.250.20
0.013 0 4 1108391715 awfully
0.013 0 4 1108391715 dudes
0.013 0 4 1108391715 hostile
0.013 0 4 1108391722 Someplace
0.013 0 4 1108391737 drinker
0.993 7 0 1107371048 attn
0.993 7 0 1107442179 H*p:D*dartmail.net
0.993 7 0 1107442194 Levitra
0.993 7 0 1107527893 leveraging
1.000 166 0 1108588775 ball
1.000 166 0 1108588775 casualties
1.000 166 0 1108588775 decisive
1.000 166 0 1108588775 impossible
1.000 166 0 1108588775 injuries
1.000 166 0 1108588775 lies
I assume the far left field is the score bayes will apply? Middle maybe
the number of time this token has been encountered in the learning process
(but that doesn't explain the 0's), I don't know the next field, and maybe
the date and then the token?
Could someone clarify this a bit for me?
Thanks,
Kyle Reynolds
972-731-4731
KyleReynolds@Transplace.com
Re: how to read sa-learn --dump output
Posted by Henk van Lingen <he...@cs.uu.nl>.
On Thu, Feb 17, 2005 at 01:41:05PM +0100, Henk van Lingen wrote:
> >
> > spam_probability, #_in_spam, #_in_ham, timestamp, token
>
> How do you produce the tokens in readable form? When I do this, I get:
>
> 1.000 332 1 1108642657 463fa0e5c1
Oke, reading another thread I understand it's being hashed since 3.x.
So I suppose there no way going back to the text :-( ?
Cheers,
--
Henk van Lingen, Systems & Network Administrator (o- -+
Dept. of Computer Science, Utrecht University. /\ |
phone: +31-30-2535278 v_/_
http://henk.vanlingen.net/ http://www.tuxtown.net/netiquette/
Re: how to read sa-learn --dump output
Posted by Henk van Lingen <he...@cs.uu.nl>.
On Wed, Feb 16, 2005 at 07:33:21PM -0500, Theo Van Dinter wrote:
> On Wed, Feb 16, 2005 at 05:32:34PM -0600, KyleReynolds@transplace.com wrote:
> > Could someone help me determine what these fields represent?
> >
> > 0.001 0 48 1108391722 H*M:hpb
> >
> > Could someone clarify this a bit for me?
>
> spam_probability, #_in_spam, #_in_ham, timestamp, token
Hi,
How do you produce the tokens in readable form? When I do this, I get:
adonis:/users/henkvl 538% sa-learn --dump data | sort -nr | head
1.000 332 1 1108642657 463fa0e5c1
1.000 234 2 1108584021 3897973044
1.000 219 2 1108584021 b8fd60299c
1.000 103 0 1108435322 6b5b7358b4
0.999 87 1 1108629105 0537c8cf38
0.999 77 0 1108567242 68bb99bda7
0.999 75 0 1108629105 5c1d162935
0.999 71 2 1108621927 760d79b69d
0.999 68 1 1107940121 4d7c962875
0.999 66 2 1108637074 c77440b295
Cheers,
--
Henk van Lingen, Systems & Network Administrator (o- -+
Dept. of Computer Science, Utrecht University. /\ |
phone: +31-30-2535278 v_/_
http://henk.vanlingen.net/ http://www.tuxtown.net/netiquette/
Re: how to read sa-learn --dump output
Posted by Theo Van Dinter <fe...@kluge.net>.
On Wed, Feb 16, 2005 at 05:32:34PM -0600, KyleReynolds@transplace.com wrote:
> Could someone help me determine what these fields represent?
>
> 0.001 0 48 1108391722 H*M:hpb
>
> Could someone clarify this a bit for me?
spam_probability, #_in_spam, #_in_ham, timestamp, token
--
Randomly Generated Tagline:
Oh my God, someone's trying to kill me! Oh wait, it's for Bart.
-- Homer Simpson
Cape Feare