From tameyer at ihug.co.nz Sat Oct 1 04:45:52 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sat, 1 Oct 2005 14:45:52 +1200 Subject: [Spambayes] Problem with Web Interface Advanced Configuration In-Reply-To: <200509300912.36744.vze5bgzj@verizon.net> References: <200509300912.36744.vze5bgzj@verizon.net> Message-ID: > I have just upgraded to Spambayes 1.1a1 POP3 Proxy. sb_server has serious flaws in 1.1a1 and should not be used. You can use 1.0.4, or run from CVS. > Also, I have removed the new hammie.db, etc. from the the 1.1a1 > files that I > extracted from the Gzipped TAR ball The archive should not have included any database files. Are you positive that it did? Where you get the archive from? > and replaced with the existing hammie.db > from the original installation and was disappointed to see that the > application does not realize that the database includes over 15K > trained > messages. How do I pump the .db folders through the training > filters for the > new version to "bring it up to speed" right away? Installing a new version will not overwrite any training, so something else has gone wrong here. BTW, better results are generally found with smaller databases, rather than large ones. has more. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From ravi at netvision.net.il Sat Oct 1 11:35:00 2005 From: ravi at netvision.net.il (Avi Rosenthal) Date: Sat, 01 Oct 2005 11:35:00 +0200 Subject: [Spambayes] Database Recovery Message-ID: <000801c5c66b$650cb8a0$7102a8c0@AVI> I received the following message: DBRunRecoveryError: (-30978, 'DB_RUNRECOVERY: Fatal error, run database recovery -- PANIC: Invalid argument')According to the FAQ file I should delete the database. I was not able to find the databse in order to delete it. UNinstalling and Reinstalling SpamBayes does not help (probably it does not delete the database). I think that a hyperlink for database deletion or a documenting the name of the database is needed. Thank you Avi Rosenthal StrategicTechnologies Consultant Tel. 972-54-4480616 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051001/da1a2fc0/attachment.htm -------------- next part -------------- No virus found in this outgoing message. Checked by AVG Anti-Virus. Version: 7.0.344 / Virus Database: 267.11.9/116 - Release Date: 30/09/2005 From ravi at netvision.net.il Sat Oct 1 11:38:31 2005 From: ravi at netvision.net.il (Avi Rosenthal) Date: Sat, 01 Oct 2005 11:38:31 +0200 Subject: [Spambayes] Database Recovery Message-ID: <003e01c5c66b$e26e0ab0$7102a8c0@AVI> I received your automated answer. I already looked for answer in the FAQ file and did not find. Avi Rosenthal StrategicTechnologies Consultant Tel. 972-54-4480616 ----- Original Message ----- From: Avi Rosenthal To: spambayes at python.org Sent: Saturday, October 01, 2005 11:35 AM Subject: Database Recovery I am using Outlook Express as an e-mail client. I received the following message: DBRunRecoveryError: (-30978, 'DB_RUNRECOVERY: Fatal error, run database recovery -- PANIC: Invalid argument')According to the FAQ file I should delete the database. I was not able to find the databse in order to delete it. UNinstalling and Reinstalling SpamBayes does not help (probably it does not delete the database). I think that a hyperlink for database deletion or a documenting the name of the database is needed. Thank you Avi Rosenthal StrategicTechnologies Consultant Tel. 972-54-4480616 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051001/ebcf81a0/attachment.html -------------- next part -------------- No virus found in this outgoing message. Checked by AVG Anti-Virus. Version: 7.0.344 / Virus Database: 267.11.9/116 - Release Date: 30/09/2005 From kirebrow at yahoo.com Sat Oct 1 12:03:44 2005 From: kirebrow at yahoo.com (Erik Brown) Date: Sat, 1 Oct 2005 05:03:44 -0500 Subject: [Spambayes] Using spamcounts.py In-Reply-To: Message-ID: <20051001090445.JJXV27562.ibm59aec.bellsouth.net@ENLIGHTENED> Tony, I ran across this message on the forums a few years back: http://mail.python.org/pipermail/spambayes/2003-December/010005.html and I want to try the same thing to analyze all of my tokens. For some reason, when I use spamcounts.py -r '.*' to export to CVS I get an error message below. (I'm running the outlook addin from source.) How do I specify a path? exec codeObject in __main__.__dict__ File "F:\!Programs\SpamBayes From Source\spambayes\contrib\spamcounts.py", line 27, in ? from spambayes.Options import options, get_pathname_option ImportError: No module named spambayes.Options >>> Erik Brown From vze5bgzj at verizon.net Sat Oct 1 12:31:16 2005 From: vze5bgzj at verizon.net (vze5bgzj@verizon.net) Date: Sat, 1 Oct 2005 06:31:16 -0400 Subject: [Spambayes] ham, Re: Problem with Web Interface Advanced Configuration In-Reply-To: References: <200509300912.36744.vze5bgzj@verizon.net> Message-ID: <200510010631.17120.vze5bgzj@verizon.net> On Friday 30 September 2005 22:45, you wrote: > > I have just upgraded to Spambayes 1.1a1 POP3 Proxy. > > sb_server has serious flaws in 1.1a1 and should not be used. You can > use 1.0.4, or run from CVS. > OK, and thanks for that > > Also, I have removed the new hammie.db, etc. from the the 1.1a1 > > files that I > > extracted from the Gzipped TAR ball > > The archive should not have included any database files. Are you > positive that it did? I saved the zipped TAR ball and just looked at it again. I was wrong, there is no hammie.db, though there is a hammie.py, etc. > Where you get the archive from? From the SPAMBayes site. > > > and replaced with the existing hammie.db > > from the original installation and was disappointed to see that the > > application does not realize that the database includes over 15K > > trained > > messages. How do I pump the .db folders through the training > > filters for the > > new version to "bring it up to speed" right away? > > Installing a new version will not overwrite any training, so > something else has gone wrong here. The system seems to be working OK, though the UI still reads that only approx 130 emails have been classified. This read figure is wrong since, as I mentioned, the database contains far more records. But I will install 1.0.4 as per your suggestion above. > BTW, better results are > generally found with smaller databases, rather than large ones. > has more. OK, I will check this TrainingIdeas URL out. Thanks! Mike > > =Tony.Meyer From vze5bgzj at verizon.net Sat Oct 1 13:35:58 2005 From: vze5bgzj at verizon.net (vze5bgzj@verizon.net) Date: Sat, 1 Oct 2005 07:35:58 -0400 Subject: [Spambayes] Can't start the application Message-ID: <200510010735.58228.vze5bgzj@verizon.net> Hi. Are there upgrade docs available for this application? Pursuant to Tony's comment, I have downloaded spambayes-1.0.4 and am trying to get rid of spambayes-1.1a1. I now have two directories, spambayes-1.1a1 (a) and spambayes-1.0.4 (b). I have kept (a) unless/until I verify that (b) works. Now, neither application will load python scripts/sb_server.py -b (SCRIPT) When I try shutting down the application from the UI and running (SCRIPT) from (b) I receive the following error message: Traceback (most recent call last): File "scripts/sb_server.py", line 991, in ? run() File "scripts/sb_server.py", line 985, in run start() File "scripts/sb_server.py", line 922, in start main(state.servers, state.proxyPorts, state.uiPort, state.launchUI) File "scripts/sb_server.py", line 900, in main proxyUI = ProxyUserInterface(state, _recreateState) File "/usr/lib/python2.4/site-packages/spambayes/ProxyUI.py", line 168, in __init__ proxy_state.lang_manager, AttributeError: State instance has no attribute 'lang_manager' I have checked permissions, they appear to be fine or at least identical to the permissions in (a). When I try running (SCRIPT) from (a), I receive an error message that the Version cannot be established. When I run python Version.py from the spambayes subdirectory, I receive nonsensical information (as compared to running the same command from Version.py from the spambayes subdiretory of (b)). HELP! Our LAN is now out of commission and no one can check mail. Thanks Mike From vze5bgzj at verizon.net Sat Oct 1 14:16:32 2005 From: vze5bgzj at verizon.net (vze5bgzj@verizon.net) Date: Sat, 1 Oct 2005 08:16:32 -0400 Subject: [Spambayes] Problem is fixed Message-ID: <200510010816.32096.vze5bgzj@verizon.net> Hi. I found a note from Tony to another person who had experienced the problem and have now fixed it with --force. Regards Mike From kirebrow at yahoo.com Sat Oct 1 17:52:29 2005 From: kirebrow at yahoo.com (Erik Brown) Date: Sat, 1 Oct 2005 10:52:29 -0500 Subject: [Spambayes] Using spamcounts.py In-Reply-To: <20051001090445.JJXV27562.ibm59aec.bellsouth.net@ENLIGHTENED> Message-ID: <20051001145232.PWWM3080.ibm63aec.bellsouth.net@ENLIGHTENED> Better question. How does one currently export their db into a cvs format as to sort in Excel? Thanks! Erik Brown -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Erik Brown Sent: Saturday, October 01, 2005 5:04 AM To: 'Tony Meyer' Cc: spambayes at python.org Subject: [Spambayes] Using spamcounts.py Tony, I ran across this message on the forums a few years back: http://mail.python.org/pipermail/spambayes/2003-December/010005.html and I want to try the same thing to analyze all of my tokens. For some reason, when I use spamcounts.py -r '.*' to export to CVS I get an error message below. (I'm running the outlook addin from source.) How do I specify a path? exec codeObject in __main__.__dict__ File "F:\!Programs\SpamBayes From Source\spambayes\contrib\spamcounts.py", line 27, in ? from spambayes.Options import options, get_pathname_option ImportError: No module named spambayes.Options >>> Erik Brown _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From FreeMJ at HotPop.com Sun Oct 2 20:53:20 2005 From: FreeMJ at HotPop.com (FreeMJ@HotPop.com) Date: Sun, 2 Oct 2005 11:53:20 -0700 Subject: [Spambayes] SpamBayes to Handle Embedded Images Message-ID: <20051002185310.C4C811931381@smtp-2.hotpop.com> Back in April, Tony Meyer posted that he was receiving a lot of image-based spam. I too am having nothing but trouble with embedded images: - Daily adds for fake Rolex watches - Daily stock tips - TONS of drugs for sale. This style of Spam contains an image at the top, followed by a bunch of totally unrelated text that has been copied from some kind of random composition. I have very large Spam & Ham folders, that I've successfully trained SpamBayes with. It's only these image-based adverts that sneak by EVERY DAY. Something really needs to be done about this type of Spam within SpamBayes. Are any other Spam engines able to handle this stuff, by scanning the image for text, or something? -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051002/e803addc/attachment.htm From wsy at merl.com Sun Oct 2 21:20:23 2005 From: wsy at merl.com (wsy) Date: Sun, 2 Oct 2005 15:20:23 -0400 Subject: [Spambayes] SpamBayes to Handle Embedded Images In-Reply-To: <20051002185310.C4C811931381@smtp-2.hotpop.com> (FreeMJ@hotpop.com) References: <20051002185310.C4C811931381@smtp-2.hotpop.com> Message-ID: <200510021920.j92JKMg4008596@spoo.merl.com> From: Back in April, Tony Meyer posted that he was receiving a lot of image-based spam. I too am having nothing but trouble with embedded images: - Daily adds for fake Rolex watches - Daily stock tips - TONS of drugs for sale. This style of Spam contains an image at the top, followed by a bunch of totally unrelated text that has been copied from some kind of random composition. I have very large Spam & Ham folders, that I've successfully trained SpamBayes with. It's only these image-based adverts that sneak by EVERY DAY. Something really needs to be done about this type of Spam within SpamBayes. Are any other Spam engines able to handle this stuff, by scanning the image for text, or something? I'm not having trouble with it, because nobody sends me gifs or jpgs in the mail. Thus, any that appear are almost certainly spam. Do you have people sending you a lot of images that _aren't_ spam? If not, then train the images as spam. It won't matter if the images can be decoded or not; just establish a liklihood that any image at all means it's a spam. I'm using CRM114, but it shouldn't matter what engine you use, at least in the near term, as long as you don't get a lot of images otherwise. -Bill Yerazunis From HerbM at learnquick.com Sun Oct 2 21:43:07 2005 From: HerbM at learnquick.com (Herb Martin) Date: Sun, 2 Oct 2005 14:43:07 -0500 Subject: [Spambayes] SpamBayes to Handle Embedded Images In-Reply-To: <20051002185310.C4C811931381@smtp-2.hotpop.com> Message-ID: Back in April, Tony Meyer posted that he was receiving a lot of image-based spam. I too am having nothing but trouble with embedded images: - Daily adds for fake Rolex watches - Daily stock tips - TONS of drugs for sale. This style of Spam contains an image at the top, followed by a bunch of totally unrelated text that has been copied from some kind of random composition. I have very large Spam & Ham folders, that I've successfully trained SpamBayes with. It's only these image-based adverts that sneak by EVERY DAY. Mostly my SpamBayes catches ALL of these when anything gets this far... Something really needs to be done about this type of Spam within SpamBayes. Are any other Spam engines able to handle this stuff, by scanning the image for text, or something? Sure, there are others (as well a SpamBayes if you just keep training EVERY ONE of them) but most of the others are either commercial (i.e., cost money) OR they run on the Server (SpamAssassin, greylistd, and other filters.) There has been talk about filters which would explicitly do OCR or some other type of image content detection but I don't (personally) know of any that are working/available/effective right now. Such would also likely be "resource (CPU) intensive". FWIW, greylisting on the server knocks down practically all of this junk and SpamAssassin catches the rest. The VERY occasional item that slips through our server is caught by SpamBayes. (Defense in depth is our key to ZERO spam -- with practically everything REJECTED, not bounced, at the server during SMTP connect time.) And some of us DO WISH to get graphical email -- picture of my grand kid(s) frequently arrive this way. -- Herb Martin _____ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of FreeMJ at hotpop.com Sent: Sunday, October 02, 2005 1:53 PM To: spambayes at python.org Subject: [Spambayes] SpamBayes to Handle Embedded Images -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051002/82a85b71/attachment.html From FreeMJ at HotPop.com Mon Oct 3 01:01:03 2005 From: FreeMJ at HotPop.com (FreeMJ@HotPop.com) Date: Sun, 2 Oct 2005 16:01:03 -0700 Subject: [Spambayes] SpamBayes to Handle Embedded Images In-Reply-To: <200510021920.j92JKMg4008596@spoo.merl.com> Message-ID: <20051002230051.7151C193ECCC@smtp-2.hotpop.com> Bill, I DO get a lot of HTML based e-mail with images and photos from credible sources. I feel I shouldn't have to "throw the baby out with the bath water". Searching Google and Google News for "Viagra and Rolex" reveals that this image-based Spam is a HUGE problem/loophole! -----Original Message----- From: wsy [mailto:wsy at merl.com] Sent: Sunday, October 02, 2005 12:20 PM To: FreeMJ at hotpop.com Cc: spambayes at python.org Subject: Re: [Spambayes] SpamBayes to Handle Embedded Images From: Back in April, Tony Meyer posted that he was receiving a lot of image-based spam. I too am having nothing but trouble with embedded images: - Daily adds for fake Rolex watches - Daily stock tips - TONS of drugs for sale. This style of Spam contains an image at the top, followed by a bunch of totally unrelated text that has been copied from some kind of random composition. I have very large Spam & Ham folders, that I've successfully trained SpamBayes with. It's only these image-based adverts that sneak by EVERY DAY. Something really needs to be done about this type of Spam within SpamBayes. Are any other Spam engines able to handle this stuff, by scanning the image for text, or something? I'm not having trouble with it, because nobody sends me gifs or jpgs in the mail. Thus, any that appear are almost certainly spam. Do you have people sending you a lot of images that _aren't_ spam? If not, then train the images as spam. It won't matter if the images can be decoded or not; just establish a liklihood that any image at all means it's a spam. I'm using CRM114, but it shouldn't matter what engine you use, at least in the near term, as long as you don't get a lot of images otherwise. -Bill Yerazunis From FreeMJ at HotPop.com Mon Oct 3 01:43:36 2005 From: FreeMJ at HotPop.com (FreeMJ@HotPop.com) Date: Sun, 2 Oct 2005 16:43:36 -0700 Subject: [Spambayes] SpamBayes to Handle Embedded Images In-Reply-To: Message-ID: <20051002234321.571C6193F553@smtp-2.hotpop.com> Herb, OCR is probably the only sure-fire way to nail this scourge. As far as being resource intensive, like most other people with always-on broadband access now, my e-mail just trickles in a little at a time. And many/most PCs are powerful enough to stream video now-a-days; they really shouldn't have a problem with it being added as a feature. It's a lot more disruptive to manage these by hand, if you ask me. And an OCR feature could allow itself to be disabled, if it ended up being a performance problem for someone. It's gotta be done. Now that these spammers have found an easy way to trick these engines to be digging through meaningless text, there'll be no slowing them without OCR. I'm getting more and more of this style of Spam. Easy to install/use programs like SpamBayes have to keep up with the times, or they'll die on the vine. Years ago, when we mostly exchanged text-based e-mail, it wasn't an issue. But now, nearly all of the e-mail I receive is HTML; and lots of it has images. I'm ONLY using SpamBayes with Outlook 2003 (at home, where I'm having all the trouble). I love the easy button-based re-training! And I don't really care for the idea of having to add, train, and administer another layer. Other than a miraculous OCR feature showing up in SpamBayes soon, I'm out of ideas for a simple way of managing this type of mail on my home PC. (Very frustrating). Thanks, FMJ _____ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Herb Martin Sent: Sunday, October 02, 2005 12:43 PM To: spambayes at python.org Subject: Re: [Spambayes] SpamBayes to Handle Embedded Images Back in April, Tony Meyer posted that he was receiving a lot of image-based spam. I too am having nothing but trouble with embedded images: - Daily adds for fake Rolex watches - Daily stock tips - TONS of drugs for sale. This style of Spam contains an image at the top, followed by a bunch of totally unrelated text that has been copied from some kind of random composition. I have very large Spam & Ham folders, that I've successfully trained SpamBayes with. It's only these image-based adverts that sneak by EVERY DAY. Mostly my SpamBayes catches ALL of these when anything gets this far... Something really needs to be done about this type of Spam within SpamBayes. Are any other Spam engines able to handle this stuff, by scanning the image for text, or something? Sure, there are others (as well a SpamBayes if you just keep training EVERY ONE of them) but most of the others are either commercial (i.e., cost money) OR they run on the Server (SpamAssassin, greylistd, and other filters.) There has been talk about filters which would explicitly do OCR or some other type of image content detection but I don't (personally) know of any that are working/available/effective right now. Such would also likely be "resource (CPU) intensive". FWIW, greylisting on the server knocks down practically all of this junk and SpamAssassin catches the rest. The VERY occasional item that slips through our server is caught by SpamBayes. (Defense in depth is our key to ZERO spam -- with practically everything REJECTED, not bounced, at the server during SMTP connect time.) And some of us DO WISH to get graphical email -- picture of my grand kid(s) frequently arrive this way. -- Herb Martin _____ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of FreeMJ at hotpop.com Sent: Sunday, October 02, 2005 1:53 PM To: spambayes at python.org Subject: [Spambayes] SpamBayes to Handle Embedded Images -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051002/546f3be4/attachment.html From vincent+spambayes at zweije.nl.eu.org Mon Oct 3 09:55:40 2005 From: vincent+spambayes at zweije.nl.eu.org (Vincent Zweije) Date: Mon, 3 Oct 2005 09:55:40 +0200 Subject: [Spambayes] Inspecting images (was: SpamBayes to Handle Embedded Images) In-Reply-To: <20051002234321.571C6193F553@smtp-2.hotpop.com> References: <20051002234321.571C6193F553@smtp-2.hotpop.com> Message-ID: <20051003075540.GA27153@love.zweije.nl.eu.org> On Sun, Oct 02, 2005 at 04:43:36PM -0700, FreeMJ at HotPop.com wrote: || Other than a miraculous OCR feature showing up in SpamBayes soon, I'm out || of ideas for a simple way of managing this type of mail on my home PC. Hmm... if anyone is going to work on this, do it the Bayesian way. Don't try to recognise text, just recognize patterns in the image. Just like spambayes doesn't understand language, just recognizes words (and a little of their context). Would be a lovely research project, I'm sure. Say, how do those photocopy machines decide and refuse when a bank note is being copied? Ciao. Vincent. -- Vincent Zweije | "If you're flamed in a group you | don't read, does anybody get burnt?" [Xhost should be taken out and shot] | -- Paul Tomblin on a.s.r. From wsy at merl.com Mon Oct 3 13:42:23 2005 From: wsy at merl.com (wsy) Date: Mon, 3 Oct 2005 07:42:23 -0400 Subject: [Spambayes] Inspecting images (was: SpamBayes to Handle Embedded Images) In-Reply-To: <20051003075540.GA27153@love.zweije.nl.eu.org> (message from Vincent Zweije on Mon, 3 Oct 2005 09:55:40 +0200) References: <20051002234321.571C6193F553@smtp-2.hotpop.com> <20051003075540.GA27153@love.zweije.nl.eu.org> Message-ID: <200510031142.j93BgNxY010015@spoo.merl.com> From: Vincent Zweije [...] Say, how do those photocopy machines decide and refuse when a bank note is being copied? There's a five-circles "constellation" that means "this is currency, do not copy". It's the ratios of the distances that matter, not the orientation, so spinning the note (or the design) around won't change anything. In Euro notes, it's the little H-shaped constellations, with little circles at the tips. In US money, (only in the 20's and up so far, but will be inserted in lower bills as they are redesigned) it's in the dollar numbers themselves. Look on a 20; you'll see a field of -many- "20" texts scattered sorta randomly. It's not random. The position of the 0's form the same "constellation" as is obvious on the EU notes. -Bill Yerazunis From jsp at PKC.com Mon Oct 3 15:31:35 2005 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 3 Oct 2005 09:31:35 -0400 Subject: [Spambayes] Inspecting images (was: SpamBayes to Handle EmbeddedImages) Message-ID: <16E2027582CDB74180896CDB4B8CC1F9F1566E@PKCVT01.pkc.com> Of course, whatever the approach, the images must be fetched, which often means letting the spammer know that you've received (and seemingly viewed) their message, which encourages more messages. If such a feature were to be added, it should be disabled by default. > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Vincent Zweije > Sent: Monday, October 03, 2005 3:56 AM > To: spambayes at python.org > Subject: [Spambayes] Inspecting images (was: SpamBayes to > Handle EmbeddedImages) > > On Sun, Oct 02, 2005 at 04:43:36PM -0700, FreeMJ at HotPop.com wrote: > > || Other than a miraculous OCR feature showing up in > SpamBayes soon, I'm out > || of ideas for a simple way of managing this type of mail > on my home PC. > > Hmm... if anyone is going to work on this, do it the Bayesian way. > Don't try to recognise text, just recognize patterns in the image. > Just like spambayes doesn't understand language, just recognizes words > (and a little of their context). > > Would be a lovely research project, I'm sure. > > Say, how do those photocopy machines decide and refuse when a > bank note > is being copied? > > Ciao. > Vincent. > -- > > Vincent Zweije | "If you're flamed in a > group you > | don't read, does > anybody get burnt?" > [Xhost should be taken out and shot] | -- Paul > Tomblin on a.s.r. > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html > From jsp at PKC.com Mon Oct 3 15:38:19 2005 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 3 Oct 2005 09:38:19 -0400 Subject: [Spambayes] SpamBayes to Handle Embedded Images Message-ID: <16E2027582CDB74180896CDB4B8CC1F9F1566F@PKCVT01.pkc.com> Large databases are not necessarily better. You might get better results by retraining from scratch. It's easy and doesn't take long to get good results. ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of FreeMJ at hotpop.com Sent: Sunday, October 02, 2005 2:53 PM To: spambayes at python.org Subject: [Spambayes] SpamBayes to Handle Embedded Images Back in April, Tony Meyer posted that he was receiving a lot of image-based spam. I too am having nothing but trouble with embedded images: - Daily adds for fake Rolex watches - Daily stock tips - TONS of drugs for sale. This style of Spam contains an image at the top, followed by a bunch of totally unrelated text that has been copied from some kind of random composition. I have very large Spam & Ham folders, that I've successfully trained SpamBayes with. It's only these image-based adverts that sneak by EVERY DAY. Something really needs to be done about this type of Spam within SpamBayes. Are any other Spam engines able to handle this stuff, by scanning the image for text, or something? -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051003/a385cd84/attachment.htm From vincent+spambayes at zweije.nl.eu.org Mon Oct 3 15:39:46 2005 From: vincent+spambayes at zweije.nl.eu.org (Vincent Zweije) Date: Mon, 3 Oct 2005 15:39:46 +0200 Subject: [Spambayes] Inspecting images (was: SpamBayes to Handle EmbeddedImages) In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F9F1566E@PKCVT01.pkc.com> References: <16E2027582CDB74180896CDB4B8CC1F9F1566E@PKCVT01.pkc.com> Message-ID: <20051003133946.GA765@love.zweije.nl.eu.org> On Mon, Oct 03, 2005 at 09:31:35AM -0400, Jesse Pelton wrote: || Of course, whatever the approach, the images must be fetched, which || often means letting the spammer know that you've received (and seemingly || viewed) their message, which encourages more messages. If such a || feature were to be added, it should be disabled by default. Bah. Good point, given that, as I suppose, most images are not in the spam itself. I never bother to check, as I don't view images in mutt. Ciao. Vincent. From grundy at comcast.net Mon Oct 3 16:31:04 2005 From: grundy at comcast.net (Eric Grundlehner) Date: Mon, 3 Oct 2005 10:31:04 -0400 Subject: [Spambayes] Spambayes crashes Outlook 2003 - tried everything Message-ID: <20051003143114.55CDA1E401D@bag.python.org> XP SP2 with Outlook 2003 using 2 POP Accounts Spam Bayes 1.04 was using an old version prior Spambayes was working fine for 2 years. Computer was infected with spyware, ran the usuall adaware, hijackthis, spybot Outlook 2003 disabled spambayes. I re-enabled and it crashes and disables. I removed the preference file, try to enable it, still crashed Re-registered the add in - Crashed still Removed the toolbar - Crashed Deleted training .db - Crashed Removed Spam Bayes completely. All .ini and all .db Reinstalled 1.04, crashed on open Removed 1.04, installed 1.11 crashed on open Is there anything I'm missing? I have tried everything. I also REPAIRED OUTLOOK to its DEFAULTS Thanks, Eric -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051003/8681ee69/attachment.html From rcoe at CambridgeMA.GOV Mon Oct 3 16:35:45 2005 From: rcoe at CambridgeMA.GOV (Coe, Bob) Date: Mon, 3 Oct 2005 10:35:45 -0400 Subject: [Spambayes] Inspecting images (was: SpamBayes to HandleEmbeddedImages) Message-ID: <42393C9DA7930245AB540667607F4F5005242EE4@SPIKE.city> > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Vincent Zweije > Sent: Monday, October 03, 2005 9:40 AM > To: spambayes at python.org > Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to > HandleEmbeddedImages) > > > On Mon, Oct 03, 2005 at 09:31:35AM -0400, Jesse Pelton wrote: > > || Of course, whatever the approach, the images must be fetched, > || which often means letting the spammer know that you've received > || (and seemingly viewed) their message, which encourages more > || messages. If such a feature were to be added, it should be > || disabled by default. > > Bah. Good point, given that, as I suppose, most images are > not in the spam itself. I never bother to check, as I don't > view images in mutt. But not retrieving the image may not do any harm. Recognizing spamlike patterns in an encoded image is a hard problem, while classifying the image's URL as spamlike is easy. (If the spammer wants you to see the image, he can't disguise the URL very much.) I'd guess that working with URLs only would give better results. Bob From HerbM at learnquick.com Mon Oct 3 18:06:19 2005 From: HerbM at learnquick.com (Herb Martin) Date: Mon, 3 Oct 2005 11:06:19 -0500 Subject: [Spambayes] Inspecting images (was: SpamBayes to HandleEmbeddedImages) In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F9F1566E@PKCVT01.pkc.com> Message-ID: > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Jesse Pelton > Sent: Monday, October 03, 2005 8:32 AM > To: Vincent Zweije; spambayes at python.org > Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to > HandleEmbeddedImages) > > Of course, whatever the approach, the images must be fetched, > which often means letting the spammer know that you've > received (and seemingly > viewed) their message, which encourages more messages. If > such a feature were to be added, it should be disabled by default. > This is probably a completely different type of message we have been discussing. Those messages that use links to web based storage usually (almost always) provide enough info for the Statistical filters to determine their spamminess. The ones that are truly hard are those with the image embedded directly into the mail as a direct attachment. These latter do not give away their receipt when showing the message and are generally harder, but not impossible, to statistically filter. Greylisting will stop the large majority of them -- DNS blacklists can stop most of them too. -- Herb Martin, MCT, MCSD, MCSE, MVP HerbM at LearnQuick.Com http://LearnQuick.Com 512 388 7339 -or- 1 800 MCSE PRO Accelerated MCSE in a Week Seminars From anne at booksbyme.us Mon Oct 3 18:56:23 2005 From: anne at booksbyme.us (M. Anne Clark) Date: Mon, 3 Oct 2005 12:56:23 -0400 Subject: [Spambayes] IMPORTANT QUESTION Message-ID: <000801c5c83b$664d1300$021919ac@Revanne> Why did my tool bar items for SpamBayes disappear? IS there a way to HELP train mine? It sure isn't learning very well. For example; Is there a way to give it certain words like Cialis, meds, mortgage, etc. so it dumps anything containing those into the Junk folder?! (I can't find answers to those ?s in your FAQ, AND I'm not familiar with all the software jargon, either. A simple answer would be most appreciated.) Anne Zoe Clark - WRITER & AUTHOR! Rev. M. Anne Clark Wedding of Souls Officiant for Weddings in VT and NH www.weddingofsouls.com Super Annie, American Nanny... for peaceful parenting! -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051003/057814b3/attachment.htm From jsp at PKC.com Mon Oct 3 21:11:27 2005 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 3 Oct 2005 15:11:27 -0400 Subject: [Spambayes] IMPORTANT QUESTION Message-ID: <16E2027582CDB74180896CDB4B8CC1F9F15675@PKCVT01.pkc.com> Have you tried the suggestions in http://spambayes.sourceforge.net/faq.html#the-recover-from-spam-button-n o-longer-appears? As for training, the recommended (simplest and typically most effective) approach is the obvious one: when SpamBayes puts something in the Unsure folder or misclassifies a message (thinks it's spam when it's not or vice versa), use the "Delete as Spam" or "Recover as Spam" button as appropriate to train SpamBayes. People typically find that classification improves rapidly; training on ten or so messages often leads to good results. If you're not getting good results, it may be worth discarding the training database and starting over. There's no way to tell SpamBayes that certain words only occur in spam. The process of scoring messages as ham or spam works by looking at how often the words in a message appear in other messages that you have indicated are spam and/or ham. This tends to work better than simple black-and-white filtering. For instance, to use your example, if a friend writes to tell that she's buying a house and looking for a recommendation for bank to get a mortgage from, filtering only on mortgage would mean that message is discarded. SpamBayes would look at every word in the message, and if you've done a good job of training, it would probably decide that the message is not spam. Another example: I get lots of messages discussing Cialis, meds, mortgages, etc, and the spam is almost all correctly classified as such, but your message got through, because SpamBayes was able to determine that the despite the presence of these "spammy" terms, your message actually wasn't spam. (That's pretty cool, when you think about it!) ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of M. Anne Clark Sent: Monday, October 03, 2005 12:56 PM To: spambayes at python.org Subject: [Spambayes] IMPORTANT QUESTION Why did my tool bar items for SpamBayes disappear? IS there a way to HELP train mine? It sure isn't learning very well. For example; Is there a way to give it certain words like Cialis, meds, mortgage, etc. so it dumps anything containing those into the Junk folder?! (I can't find answers to those ?s in your FAQ, AND I'm not familiar with all the software jargon, either. A simple answer would be most appreciated.) Anne Zoe Clark - WRITER & AUTHOR! Rev. M. Anne Clark Wedding of Souls Officiant for Weddings in VT and NH www.weddingofsouls.com Super Annie, American Nanny... for peaceful parenting! -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051003/62d0ba37/attachment.htm From kirebrow at yahoo.com Tue Oct 4 00:49:25 2005 From: kirebrow at yahoo.com (Erik Brown) Date: Mon, 3 Oct 2005 17:49:25 -0500 Subject: [Spambayes] SpamBayes to Handle Embedded Images In-Reply-To: <20051002234321.571C6193F553@smtp-2.hotpop.com> Message-ID: <20051003214927.MWBP9927.ibm69aec.bellsouth.net@ENLIGHTENED> FMJ, You need to experiment with the following config options. I do not have a problem whatsoever with embedded images. They usually link to a site and it gets all of the related tokens. Try for yourself and report back: [Classifier] # Generate both unigrams (words) and bigrams (pairs of words). However, # extending an idea originally from Gary Robinson, the message is # 'tiled' into non-overlapping unigrams and bigrams, approximating the # strongest outcome over all possible tilings. Note that to really test # this option you need to retrain with it on, so that your database # includes the bigrams - if you subsequently turn it off, these tokens # will have no effect. This option will at least double your database # size given the same training data, and will probably at least triple # it. You may also wish to increase the max_discriminators (maximum # number of extreme words) option if you enable this option, perhaps # doubling or quadrupling it. It's not yet clear. Bigrams create many # more hapaxes, and that seems to increase the brittleness of minimalist # training regimes; increasing max_discriminators may help to soften # that effect. OTOH, max_discriminators defaults to 150 in part because # that makes it easy to prove that the chi-squared math is immune from # numeric problems. Increase it too much, and insane results will # eventually result (including fatal floating-point exceptions on some # boxes). This option is experimental, and may be removed in a future # release. We would appreciate feedback about it if you use it - email # spambayes at python.org with your comments and results. x-use_bigrams: True [Tokenizer] # This non-default option is very effective # at nailing Asian spam with little training and small database burden. # It should probably be exposed via the GUI, as it's not appropriate # for people who get "high-bit ham". Asian spam is nailed with this # False too, but it requires more training and a larger database, since # a sufficient variety of "8bit%" and "skip" metatokens take longer to # learn about than strings of question marks. replace_nonascii_chars: True # It's helpful for Tim . record_header_absence: True # Recognize 'www.python.org' or ftp.python.org as URLs instead of just # long words. x-fancy_url_recognition: True # Note whether url contains non-standard port or user/password elements. x-pick_apart_urls: True basic_header_tokenize: True basic_header_skip: date x-.* domainkey-signature list-.* check_octets: True mine_received_headers: True summarize_email_prefixes: True summarize_email_suffixes: True skip_max_word_size: 50 [URLRetriever] # So that SpamBayes doesn't need to retrieve the same URL over and over # again, it stores local copies of the text at the end of the URL. This # is the directory that will be used for those copies. x-cache_directory: url-cache # This is the number of days that local cached copies of the text at the # URLs will be stored for. x-cache_expiry_days: 31 # To try and speed things up, and to avoid following unique URLS, if # this option is enabled, SpamBayes will convert the URL to as basic a # form it we can. All directory information is removed and the domain is # reduced to the two (or three for those with a country TLD) top-most # elements. For example, # http://www.massey.ac.nz/~tameyer/index.html?you=me would become # http://massey.ac.nz and http://id.example.com would become # http://example.com This should have two beneficial effects: o It's # unlikely that any information could be contained in this 'base' url # that could identify the user (unless they have a *lot* of domains). o # Many urls (both spam and ham) will strip down into the same 'base' # url. Since we have a limited form of caching, this means that a lot # fewer urls will have to be retrieved. However, this does mean that if # the 'base' url is hammy and the full is spammy, or vice-versa, that # the slurp will give back the wrong information. Whether or not this is # the case would have to be determined by testing. x-only_slurp_base: True # If this option is enabled, when a message normally scores in the # 'unsure' range, and has fewer tokens than the maximum looked at, and # contains URLs, then the text at those URLs is obtained and tokenized. # If those tokens result in the message moving to a score outside the # 'unsure' range, then they are added to the tokens for the message. # This should be particularly effective for messages that contain only a # single URL and no other text. x-slurp_urls: True # It may be that what is hammy/spammy for you in email isn't from # webpages. You can then set this option (to "web:", for example), and # effectively create an independent (sub)database for tokens derived # from parsing web pages. # "x-web_prefix" is a string value that defines a prefix to be added to tokens # generated from a slurped URL. This would be used if you wanted the tokens # generated from a web page to be separate from the tokens generated from the # body of an email message. For example, the config setting # "x-web_prefix:web:" would generate a token "spambayes" if it appears in an # email and "web:spambayes" if it appears in a slurped URL. x-web_prefix:web: Erik Brown _____ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of FreeMJ at HotPop.com Sent: Sunday, October 02, 2005 6:44 PM To: 'Herb Martin' Cc: spambayes at python.org Subject: Re: [Spambayes] SpamBayes to Handle Embedded Images Herb, OCR is probably the only sure-fire way to nail this scourge. As far as being resource intensive, like most other people with always-on broadband access now, my e-mail just trickles in a little at a time. And many/most PCs are powerful enough to stream video now-a-days; they really shouldn't have a problem with it being added as a feature. It's a lot more disruptive to manage these by hand, if you ask me. And an OCR feature could allow itself to be disabled, if it ended up being a performance problem for someone. It's gotta be done. Now that these spammers have found an easy way to trick these engines to be digging through meaningless text, there'll be no slowing them without OCR. I'm getting more and more of this style of Spam. Easy to install/use programs like SpamBayes have to keep up with the times, or they'll die on the vine. Years ago, when we mostly exchanged text-based e-mail, it wasn't an issue. But now, nearly all of the e-mail I receive is HTML; and lots of it has images. I'm ONLY using SpamBayes with Outlook 2003 (at home, where I'm having all the trouble). I love the easy button-based re-training! And I don't really care for the idea of having to add, train, and administer another layer. Other than a miraculous OCR feature showing up in SpamBayes soon, I'm out of ideas for a simple way of managing this type of mail on my home PC. (Very frustrating). Thanks, FMJ _____ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Herb Martin Sent: Sunday, October 02, 2005 12:43 PM To: spambayes at python.org Subject: Re: [Spambayes] SpamBayes to Handle Embedded Images Back in April, Tony Meyer posted that he was receiving a lot of image-based spam. I too am having nothing but trouble with embedded images: - Daily adds for fake Rolex watches - Daily stock tips - TONS of drugs for sale. This style of Spam contains an image at the top, followed by a bunch of totally unrelated text that has been copied from some kind of random composition. I have very large Spam & Ham folders, that I've successfully trained SpamBayes with. It's only these image-based adverts that sneak by EVERY DAY. Mostly my SpamBayes catches ALL of these when anything gets this far... Something really needs to be done about this type of Spam within SpamBayes. Are any other Spam engines able to handle this stuff, by scanning the image for text, or something? Sure, there are others (as well a SpamBayes if you just keep training EVERY ONE of them) but most of the others are either commercial (i.e., cost money) OR they run on the Server (SpamAssassin, greylistd, and other filters.) There has been talk about filters which would explicitly do OCR or some other type of image content detection but I don't (personally) know of any that are working/available/effective right now. Such would also likely be "resource (CPU) intensive". FWIW, greylisting on the server knocks down practically all of this junk and SpamAssassin catches the rest. The VERY occasional item that slips through our server is caught by SpamBayes. (Defense in depth is our key to ZERO spam -- with practically everything REJECTED, not bounced, at the server during SMTP connect time.) And some of us DO WISH to get graphical email -- picture of my grand kid(s) frequently arrive this way. -- Herb Martin _____ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of FreeMJ at hotpop.com Sent: Sunday, October 02, 2005 1:53 PM To: spambayes at python.org Subject: [Spambayes] SpamBayes to Handle Embedded Images -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051003/7eea4efe/attachment-0001.htm From tim.peters at gmail.com Tue Oct 4 03:50:46 2005 From: tim.peters at gmail.com (Tim Peters) Date: Mon, 3 Oct 2005 21:50:46 -0400 Subject: [Spambayes] E-Mail ID #319042 [PayPal phish crap] In-Reply-To: References: <1f7befae05092608331ee73666@mail.gmail.com> Message-ID: <1f7befae0510031850v613dbac2h3d96e2f3b88e8ce0@mail.gmail.com> [Tim Peters] >> A way to get what you want is turn this into a moderated >> list, with all postings held for moderator review. ... [Herb Martin] > I was (of course) mostly just venting and offering a > hint to others that this referenced message was "just > another phish" but I do have a method that might work, > and I would probably be willing to be ONE of the moderators: I let this sit for a while so you could see for yourself the rush of volunteers for such a job ;-) > When I ran a large lists my settings included the > following (on Lyris so other lists servers may not > quite have this feature): > > All NEW posters were on "N moderated review" where > N was a reasonably low integer. > (not publicized, it remained undocumented to users) > > After N moderated APPROVALS Lyris removed the moderation > block on that user. > > This practically eliminated the "drive by spam" to the > list -- and even idiots who posted personally but could > never seem to read or even come close to understanding > the list rules did not interfere with the list.... This list is run via GNU Mailman, which doesn't have such an option. That's a technical detail. The real problem is that it wouldn't work anyway: there's rarely an extended discussion on this particular list. It's mostly one- or two-shot postings, containing questions from users who won't post again. IOW, most initial postings here would fall into your "N moderated review" category. Most people who _answer_ questions here frequently answer, and probably wouldn't care if posting were wholly restricted to members. But this list really exists for the benefit of those who just have a question or two; discussions about development make more sense on the related spambayes-dev list. > With a few moderators (and an appropriate web interface) > approval for new users -- or even past abuses -- can be > quite swift. > > I will/would volunteer to be one of several moderators > in such a scheme. If "several" can be reduced to "one", the job is yours ;-) From jon.cohen at interfold.com Tue Oct 4 04:25:45 2005 From: jon.cohen at interfold.com (Jonathan Cohen) Date: Mon, 3 Oct 2005 20:25:45 -0600 Subject: [Spambayes] uninstall Message-ID: Dear Spam-Bayes, How do I uninstall the Spam-Bayes program? Jonathan Cohen From HerbM at learnquick.com Tue Oct 4 05:27:23 2005 From: HerbM at learnquick.com (Herb Martin) Date: Mon, 3 Oct 2005 22:27:23 -0500 Subject: [Spambayes] E-Mail ID #319042 [PayPal phish crap] In-Reply-To: <1f7befae0510031850v613dbac2h3d96e2f3b88e8ce0@mail.gmail.com> Message-ID: > > I will/would volunteer to be one of several moderators in such a > > scheme. > > If "several" can be reduced to "one", the job is yours ;-) Doesn't matter if the list doesn't support it. You can get volunteers if you enable it and ask for the help, but the point about most people are one shot posters is the real issue. They come on, ask a question, solve their problem and disappear. -- Herb Martin From jsp at PKC.com Tue Oct 4 14:15:49 2005 From: jsp at PKC.com (Jesse Pelton) Date: Tue, 4 Oct 2005 08:15:49 -0400 Subject: [Spambayes] uninstall Message-ID: <16E2027582CDB74180896CDB4B8CC1F9F15676@PKCVT01.pkc.com> It looks like you're running running Outlook, presumably with the SpamBayes plug-in. If this is the case, please see the FAQ: http://spambayes.sourceforge.net/faq.html#how-do-i-uninstall-the-plug-in . > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Jonathan Cohen > Sent: Monday, October 03, 2005 10:26 PM > To: spambayes at python.org > Cc: Jonathan A. Cohen > Subject: [Spambayes] uninstall > > Dear Spam-Bayes, > > How do I uninstall the Spam-Bayes program? From jsp at PKC.com Tue Oct 4 16:05:21 2005 From: jsp at PKC.com (Jesse Pelton) Date: Tue, 4 Oct 2005 10:05:21 -0400 Subject: [Spambayes] IMPORTANT QUESTION Message-ID: <16E2027582CDB74180896CDB4B8CC1F9F15677@PKCVT01.pkc.com> I'm sending a copy of this message to the SpamBayes list so you'll get the benefit of the experience of everyone who subscribes. I'm just another user; I try to help out on the list so the developers can focus on development. I haven't had this particular problem, so my experience is of limited use to you. That said, one thing that I know happens sometimes is that Outlook decides that it should disable SpamBayes. Go to Outlook's Help menu, select "About Microsoft Office Outlook," and click the "Disabled Items..." button. If SpamBayes is listed, re-enable it. The SpamBayes Manager dialog is only accessible from the SpamBayes toolbar button, so until you get the toolbar back, you won't be able to get to the dialog. Let's take one problem at a time, and deal with the training issue once you've got the toolbar back. ________________________________ From: M. Anne Clark [mailto:anne at booksbyme.us] Sent: Monday, October 03, 2005 4:18 PM To: Jesse Pelton Subject: RE: [Spambayes] IMPORTANT QUESTION Thanks for your reply, However I just went to that site and the space for those buttons is still there, but they're not. I don't know what they mean -- because both my DELETE AS SPAM and RECOVER FROM SPAM buttons are gone. And-- I don't know how to open up the Spam Bayes Manager Dialogue, i.e. don't know where it is etc. I also don't know how to discard the training database. Is there a way I can call you and get a "talk thru" to solve my problems? Thanks! Anne -----Original Message----- From: Jesse Pelton [mailto:jsp at PKC.com] Sent: Monday, October 03, 2005 2:11 PM To: anne at booksbyme.us; spambayes at python.org Subject: RE: [Spambayes] IMPORTANT QUESTION Have you tried the suggestions in http://spambayes.sourceforge.net/faq.html#the-recover-from-spam-button-n o-longer-appears? As for training, the recommended (simplest and typically most effective) approach is the obvious one: when SpamBayes puts something in the Unsure folder or misclassifies a message (thinks it's spam when it's not or vice versa), use the "Delete as Spam" or "Recover as Spm" button as appropriate to train SpamBayes. People typically find that classification improves rapidly; training on ten or so messages often leads to good results. If you're not getting good results, it may be worth discarding the training database and starting over. There's no way to tell SpamBayes that certain words only occur in spam. The process of scoring messages as ham or spam works by looking at how often the words in a message appear in other messages that you have indicated are spam and/or ham. This tends to work better than simple black-and-white filtering. For instance, to use your example, if a friend writes to tell that she's buying a house and looking for a recommendation for bank to get a mortgage from, filtering only on mortgage would mean that message is discarded. SpamBayes would look at every word in the message, and if you've done a good job of training, it would probably decide that the message is not spam. Another example: I get lots of messages discussing Cialis, meds, mortgages, etc, and the spam is almost all correctly classified as such, but your message got through, because SpamBayes was able to determine that the despite the presence of these "spammy" terms, your message actually wasn't spam. (That's pretty cool, when you think about it!) ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of M. Anne Clark Sent: Monday, October 03, 2005 12:56 PM To: spambayes at python.org Subject: [Spambayes] IMPORTANT QUESTION Why did my tool bar items for SpamBayes disappear? IS there a way to HELP train mine? It sure isn't learning very well. For example; Is there a way to give it certain words like Cialis, meds, mortgage, etc. so it dumps anything containing those into the Junk folder?! (I can't find answers to those ?s in your FAQ, AND I'm not familiar with all the software jargon, either. A simple answer would be most appreciated.) Anne Zoe Clark - WRITER & AUTHOR! Rev. M. Anne Clark Wedding of Souls Officiant for Weddings in VT and NH www.weddingofsouls.com Super Annie, American Nanny... for peaceful parenting! -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051004/d5cfca10/attachment.htm From KRFinkbeiner at dow.com Tue Oct 4 16:33:27 2005 From: KRFinkbeiner at dow.com (Finkbeiner, Karin (KR)) Date: Tue, 4 Oct 2005 10:33:27 -0400 Subject: [Spambayes] Export Restrictions for SpamBayes Anti-span Client software Message-ID: We have some questions regarding using your SpamBayes Anti-span Client software. Can you confirm if there are any Export Restrictions for this software? Or if this software as an ECCN# or Export Control Classification Number? We're trying to determine if we can legally distribute this sw product outside US without going against any government export restrictions. ______________________________ Karin Finkbeiner I/S Contract Management Team Software Contracts The Dow Chemical Company 2040 Dow Center Midland, MI 48674 Ph: 989-636-8595 Fax: 989-636-9389 kfinkbeiner at dow.com From tim.peters at gmail.com Tue Oct 4 16:56:50 2005 From: tim.peters at gmail.com (Tim Peters) Date: Tue, 4 Oct 2005 10:56:50 -0400 Subject: [Spambayes] Export Restrictions for SpamBayes Anti-span Client software In-Reply-To: References: Message-ID: <1f7befae0510040756w79850bb6x8b1615c1a97804fd@mail.gmail.com> [Finkbeiner, Karin (KR)] |> We have some questions regarding using your SpamBayes Anti-span > Client software. SpamBayes comes in several versions, and I don't know which one you're thinking about here. > Can you confirm if there are any Export Restrictions for this software? Not that we know of, but nobody has asked the Bureau of Industry and Security for a classification. Your company can ask them for a SpamBayes classification, if your company has interest in doing so. The SpamBayes developers are unpaid volunteers, and I doubt they have interest in volunteering time to drive that process. If your company wants to pursue it, we'll gladly cooperate (answer technical questions about the software). > Or if this software as an ECCN# or Export Control Classification Number? It does not. If you're talking about a version of SpamBayes that includes the Python programming language, Python's ECCN is 5D002. My best _guess_ is that this would be a suitable classification for SpamBayes too, although I am not a lawyer and have only a very shallow understanding of ECCN requirements. > We're trying to determine if we can legally distribute this sw product outside > US without going against any government export restrictions. I'm sure you understand that we can't give legal advice in any case. From LDRothman at dow.com Tue Oct 4 21:46:10 2005 From: LDRothman at dow.com (Rothman, Dave (LD)) Date: Tue, 4 Oct 2005 14:46:10 -0500 Subject: [Spambayes] Filtering doesn't start automatically in "Connected" mode Message-ID: <506FBA663A5A434BA571F48033D01DDF597190@USMDLMDOWX004.dow.com> I'm using SpamBayes with Outlook 2002. It used to work just fine, but now message filtering does not start automatically when I connect to the server. If I start SpamBayes Manager, select the Advanced tab and change the position of the slider for Processing start delay, SpamBayes will automatically filter any new messages, but I must initiate filtering to filter any messages already in the Inbox. Message filtering is automatic when I'm running Outlook in off-line mode. I'm using a company-standard configuration PC. Others who use SpamBayes aren't seeing this problem. Removing and re-installing SpamBayes doesn't fix my problem. Thoughts? Thanks, Dave Rothman Scientist, Core R&D The Dow Chemical Company From bob at 1776.com Wed Oct 5 04:01:46 2005 From: bob at 1776.com (Robert K. Coe) Date: Tue, 4 Oct 2005 22:01:46 -0400 Subject: [Spambayes] Export Restrictions for SpamBayes Anti-span Clientsoftware In-Reply-To: <1f7befae0510040756w79850bb6x8b1615c1a97804fd@mail.gmail.com> Message-ID: <007101c5c950$c0abd320$0301a8c0@CambridgeMA.GOV> Am I missing something? I'm not a lawyer either, but a couple of points seem pretty clear. The most obvious is that Spambayes is already in use all over the world. If Karin's company's foreign subsidiaries want it, they can download it off the Python website, can't they? Beyond that, wasn't Spambayes developed largely outside the U.S. anyway? We have Australians and New Zealanders and Frenchmen working on it and users of many nationalities offering advice and assistance. What, exactly, would the U.S. government think it could restrict? Even the colossal arrogance of the Bush administration may not reach that far. Bob > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Tim Peters > Sent: Tuesday, October 04, 2005 10:57 AM > To: Finkbeiner, Karin (KR) > Cc: spambayes at python.org > Subject: Re: [Spambayes] Export Restrictions for SpamBayes > Anti-span Clientsoftware > > > [Finkbeiner, Karin (KR)] > > We have some questions regarding using your SpamBayes Anti-span > > Client software. > > SpamBayes comes in several versions, and I don't know which > one you're thinking about here. > > > Can you confirm if there are any Export Restrictions for this > > software? > > Not that we know of, but nobody has asked the Bureau of > Industry and Security for a classification. Your company can > ask them for a SpamBayes classification, if your company has > interest in doing so. > The SpamBayes developers are unpaid volunteers, and I doubt > they have interest in volunteering time to drive that > process. If your company wants to pursue it, we'll gladly > cooperate (answer technical questions about the software). > > > Or if this software as an ECCN# or Export Control Classification > > Number? > > It does not. If you're talking about a version of SpamBayes > that includes the Python programming language, Python's ECCN > is 5D002. My best _guess_ is that this would be a suitable > classification for SpamBayes too, although I am not a lawyer > and have only a very shallow understanding of ECCN requirements. > > > We're trying to determine if we can legally distribute this sw product > > outside US without going against any government export restrictions. > > I'm sure you understand that we can't give legal advice in any case. From tameyer at ihug.co.nz Wed Oct 5 07:02:08 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Wed, 5 Oct 2005 18:02:08 +1300 Subject: [Spambayes] Using spamcounts.py In-Reply-To: <20051001145232.PWWM3080.ibm63aec.bellsouth.net@ENLIGHTENED> References: <20051001145232.PWWM3080.ibm63aec.bellsouth.net@ENLIGHTENED> Message-ID: > How does one currently export their db into a cvs format > as to sort in Excel? Via this simple three step process (you may be able to skip step 1 and 2): 1. Get and install Python 2. Get a copy of the SpamBayes source distribution. 3. In a command prompt, go to the top directory in the expanded distribution (the one with the README) and enter: python scripts\sb_dbexpimp.py -e -f .\hammie.csv (Replace .\hammie.csv with whatever name you want the CSV file to have). If sb_dbexpimp.py doesn't find your database, you can tell it where it is: python scripts\sb_dbexpimp.py -e -f .\hammie.csv -o "Storage:persistent_storage_file:C:\Path to\my\database.db" =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Wed Oct 5 07:02:39 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Wed, 5 Oct 2005 18:02:39 +1300 Subject: [Spambayes] IMPORTANT QUESTION In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F9F15677@PKCVT01.pkc.com> References: <16E2027582CDB74180896CDB4B8CC1F9F15677@PKCVT01.pkc.com> Message-ID: <67F673FE-215F-4A90-976E-54909D0868D5@ihug.co.nz> >> Thanks for your reply, However I just went to that site and the >> space for those buttons is still there, but they're not. I don't >> know what they mean -- because both my DELETE AS SPAM and RECOVER >> FROM SPAM buttons are gone. > > That said, one thing that I know happens sometimes is that Outlook > decides that it should disable SpamBayes. Go to Outlook's Help > menu, select "About Microsoft Office Outlook," and click the > "Disabled Items..." button. If SpamBayes is listed, re-enable it. If this isn't the problem, it's worth also trying the suggestions in the troubleshooting guide. A copy is installed with SpamBayes, or you can read it online at: >> I also don't know how to discard the training database. Once the toolbar is fixed, all you need to do is click the SpamBayes button on the toolar, then choose SpamBayes Manager, then go to the Training tab and do the training from there, ensuring that you tick the "Rebuild entire database" box. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Wed Oct 5 07:07:06 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Wed, 5 Oct 2005 18:07:06 +1300 Subject: [Spambayes] Database Recovery In-Reply-To: <003e01c5c66b$e26e0ab0$7102a8c0@AVI> References: <003e01c5c66b$e26e0ab0$7102a8c0@AVI> Message-ID: <6AC40BE7-3902-4C5A-9E8A-C9DC66A00B22@ihug.co.nz> >> I received the following message: DBRunRecoveryError: (-30978, >> 'DB_RUNRECOVERY: Fatal error, run database recovery -- PANIC: >> Invalid argument') >> According to the FAQ file I should delete the database. >> I was not able to find the databse in order to delete it. The configuration page of the web interface tells you where it is. The most likely place is C:\Documents and Settings\{username} \Application Data\SpamBayes\hammie.db but it will vary depending on which version of Windows you are using and how it is set up. >> I think that a hyperlink for database deletion or a documenting >> the name of the database is needed. > > I received your automated answer. > I already looked for answer in the FAQ file and did not find. It's there, but it's not simple to find, since it's in the answer to other questions. This FAQ tells you what to do about that <0.5 wink>: =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Wed Oct 5 07:11:42 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Wed, 5 Oct 2005 18:11:42 +1300 Subject: [Spambayes] SpamBayes to Handle Embedded Images In-Reply-To: <20051002185310.C4C811931381@smtp-2.hotpop.com> References: <20051002185310.C4C811931381@smtp-2.hotpop.com> Message-ID: > Back in April, Tony Meyer posted that he was receiving a lot of > image-based spam. Are you sure? I did a quick search through the April archives, and I don't find anything that says that. I do receive it, but it's not a problem for me, and I do receive messages from friends/family that's little or nothing more than images. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Wed Oct 5 07:24:01 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Wed, 5 Oct 2005 18:24:01 +1300 Subject: [Spambayes] Inspecting images (was: SpamBayes to Handle Embedded Images) In-Reply-To: <20051003075540.GA27153@love.zweije.nl.eu.org> References: <20051002234321.571C6193F553@smtp-2.hotpop.com> <20051003075540.GA27153@love.zweije.nl.eu.org> Message-ID: >> Other than a miraculous OCR feature showing up in SpamBayes soon, >> I'm out >> of ideas for a simple way of managing this type of mail on my home >> PC. > > Hmm... if anyone is going to work on this, do it the Bayesian way. > Don't try to recognise text, just recognize patterns in the image. > Just like spambayes doesn't understand language, just recognizes words > (and a little of their context). FWIW, I suspect that this may be quite effective. Techniques like this are used in image processing already - for example, the Viola- Jones method of detecting patterns (e.g. faces) in an image uses a cascade of haar-like classifiers: essentially, a whole lot of tiny little classifiers that look at tiny parts of the image (which are all automatically generated via training, not specified as rules). If only there was more time in the day ... :) =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Wed Oct 5 07:02:39 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Wed, 5 Oct 2005 18:02:39 +1300 Subject: [Spambayes] IMPORTANT QUESTION In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F9F15677@PKCVT01.pkc.com> References: <16E2027582CDB74180896CDB4B8CC1F9F15677@PKCVT01.pkc.com> Message-ID: <67F673FE-215F-4A90-976E-54909D0868D5@ihug.co.nz> >> Thanks for your reply, However I just went to that site and the >> space for those buttons is still there, but they're not. I don't >> know what they mean -- because both my DELETE AS SPAM and RECOVER >> FROM SPAM buttons are gone. > > That said, one thing that I know happens sometimes is that Outlook > decides that it should disable SpamBayes. Go to Outlook's Help > menu, select "About Microsoft Office Outlook," and click the > "Disabled Items..." button. If SpamBayes is listed, re-enable it. If this isn't the problem, it's worth also trying the suggestions in the troubleshooting guide. A copy is installed with SpamBayes, or you can read it online at: >> I also don't know how to discard the training database. Once the toolbar is fixed, all you need to do is click the SpamBayes button on the toolar, then choose SpamBayes Manager, then go to the Training tab and do the training from there, ensuring that you tick the "Rebuild entire database" box. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From FreeMJ at HotPop.com Wed Oct 5 07:49:21 2005 From: FreeMJ at HotPop.com (FreeMJ@HotPop.com) Date: Tue, 4 Oct 2005 22:49:21 -0700 Subject: [Spambayes] SpamBayes to Handle Embedded Images In-Reply-To: Message-ID: <20051005054906.F1E271968FCD@smtp-2.hotpop.com> Tony, Sorry, my mistake. I found your clipped reply to Xesdeeni: http://mail.python.org/pipermail/spambayes/2005-April/016639.html I thought it was an issue you were having too. FMJ -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Tony Meyer Sent: Tuesday, October 04, 2005 10:12 PM To: Cc: spambayes at python.org Subject: Re: [Spambayes] SpamBayes to Handle Embedded Images > Back in April, Tony Meyer posted that he was receiving a lot of > image-based spam. Are you sure? I did a quick search through the April archives, and I don't find anything that says that. I do receive it, but it's not a problem for me, and I do receive messages from friends/family that's little or nothing more than images. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From tameyer at ihug.co.nz Wed Oct 5 07:48:58 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Wed, 5 Oct 2005 18:48:58 +1300 Subject: [Spambayes] Using spamcounts.py In-Reply-To: <20051001090445.JJXV27562.ibm59aec.bellsouth.net@ENLIGHTENED> References: <20051001090445.JJXV27562.ibm59aec.bellsouth.net@ENLIGHTENED> Message-ID: > I ran across this message on the forums a few years back: > http://mail.python.org/pipermail/spambayes/2003-December/010005.html > and I want to try the same thing to analyze all of my tokens. > > For some reason, when I use spamcounts.py -r '.*' to export to CVS > I get an > error message below. (I'm running the outlook addin from source.) > How do I > specify a path? > > exec codeObject in __main__.__dict__ > File "F:\!Programs\SpamBayes From Source\spambayes\contrib > \spamcounts.py", > line 27, in ? > from spambayes.Options import options, get_pathname_option > ImportError: No module named spambayes.Options I know you're planning on using sb_dbexpimp.py instead, but in case you're still curious or someone looks through the archives for an answer to this: You need to tell Python where the SpamBayes package is. There are three ways to do this, any of which will work: 1. Run "python setup.py install" in the top-level spambayes directory. This will install the spambayes package in the Python Lib \site-packages directory. 2. Set the environment variable PYTHONPATH to include the path to the spambayes top-level directory. Something like 'set PYTHONPATH="F: \!Programs\SpamBayes From Source\spambayes"' (no single-quotes). 3. Run the script from the spambayes top-level directory (e.g. "python contrib\spamcounts.py"). Python will look in the current directory for the package. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From Carol.Knowles.1 at uni.massey.ac.nz Wed Oct 5 07:58:15 2005 From: Carol.Knowles.1 at uni.massey.ac.nz (Carol Knowles) Date: Wed, 5 Oct 2005 18:58:15 +1300 Subject: [Spambayes] Help to download spambays Message-ID: <01ab01c5c971$c71a6390$7ded7b82@massey.ac.nz> I want to download free spambays but cannot understand your website on how to do it.Can you help please? Thanks very much Carol -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051005/94b492d4/attachment.html From kirebrow at yahoo.com Wed Oct 5 09:24:41 2005 From: kirebrow at yahoo.com (Erik Brown) Date: Wed, 5 Oct 2005 02:24:41 -0500 Subject: [Spambayes] Help to download spambays In-Reply-To: <01ab01c5c971$c71a6390$7ded7b82@massey.ac.nz> Message-ID: <20051005062442.ZIJS14361.ibm68aec.bellsouth.net@ENLIGHTENED> Carol, Please see http://spambayes.sourceforge.net/download.html Erik Brown _____ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Carol Knowles Sent: Wednesday, October 05, 2005 12:58 AM To: spambayes at python.org Subject: [Spambayes] Help to download spambays I want to download free spambays but cannot understand your website on how to do it.Can you help please? Thanks very much Carol -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051005/cc5b3b73/attachment.htm From kirebrow at yahoo.com Wed Oct 5 09:24:53 2005 From: kirebrow at yahoo.com (Erik Brown) Date: Wed, 5 Oct 2005 02:24:53 -0500 Subject: [Spambayes] Using spamcounts.py In-Reply-To: Message-ID: <20051005062455.ZIJZ14361.ibm68aec.bellsouth.net@ENLIGHTENED> Tony, Thanks for this info! Erik Brown -----Original Message----- From: Tony Meyer [mailto:tameyer at ihug.co.nz] Sent: Wednesday, October 05, 2005 12:49 AM To: Erik Brown Cc: spambayes at python.org Subject: Re: Using spamcounts.py > I ran across this message on the forums a few years back: > http://mail.python.org/pipermail/spambayes/2003-December/010005.html > and I want to try the same thing to analyze all of my tokens. > > For some reason, when I use spamcounts.py -r '.*' to export to CVS > I get an > error message below. (I'm running the outlook addin from source.) > How do I > specify a path? > > exec codeObject in __main__.__dict__ > File "F:\!Programs\SpamBayes From Source\spambayes\contrib > \spamcounts.py", > line 27, in ? > from spambayes.Options import options, get_pathname_option > ImportError: No module named spambayes.Options I know you're planning on using sb_dbexpimp.py instead, but in case you're still curious or someone looks through the archives for an answer to this: You need to tell Python where the SpamBayes package is. There are three ways to do this, any of which will work: 1. Run "python setup.py install" in the top-level spambayes directory. This will install the spambayes package in the Python Lib \site-packages directory. 2. Set the environment variable PYTHONPATH to include the path to the spambayes top-level directory. Something like 'set PYTHONPATH="F: \!Programs\SpamBayes From Source\spambayes"' (no single-quotes). 3. Run the script from the spambayes top-level directory (e.g. "python contrib\spamcounts.py"). Python will look in the current directory for the package. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Wed Oct 5 11:29:19 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Wed, 5 Oct 2005 22:29:19 +1300 Subject: [Spambayes] Question relating to Microsoft Plug-in In-Reply-To: References: Message-ID: > Is there a way to control the order in which SpamBayes processes > incoming messages vs. . when my Outlook rules process a message? > Ideally I would like to guarantee my Outlook rules process incoming > messages prior to SpamBayes. I have set the delay to 10 secs on > SpamBayes, but this does not always appear to work. This is meant to work (and is the reason for that setting). Are you finding that Outlook takes more than 10 seconds to process a message? Or do you mean something else when you say that it doesn't always work? =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From kirebrow at yahoo.com Wed Oct 5 13:11:13 2005 From: kirebrow at yahoo.com (Erik Brown) Date: Wed, 5 Oct 2005 06:11:13 -0500 Subject: [Spambayes] Bit of help on adding another statistic = ) In-Reply-To: Message-ID: <20051005101115.IAGU9927.ibm69aec.bellsouth.net@ENLIGHTENED> Tony, I am doing some real life testing and the statistics help tremendously. I plan on giving my results soon. I tried to hack the Stats.py to display in larger font below the spam savings the total number of messages classified - the total number of messages classified incorrectly. Just for kicks, I am providing a screen shot of what I'm trying to accomplish. My current numbers after 860 messages classified is only 2 misclassified. So the number would be 100 - 0.2326 = 99.7674. http://www.pleasebuymyproducts.com/files/spambayes-statistics.gif The number on the screen shot indicates what I am trying to do. Can you provide me the code so that I can hack my local copy perhaps? Thanks! Erik Brown From jgilmour at globalnet.co.uk Wed Oct 5 17:30:14 2005 From: jgilmour at globalnet.co.uk (James Gilmour) Date: Wed, 5 Oct 2005 16:30:14 +0100 Subject: [Spambayes] SpamBayes says "Something screwey" Message-ID: <000401c5c9c1$af0a8320$0200a8c0@u2amd> Dear Friends Quite suddenly SpamBayes has stopped working properly. When all else failed, I uninstalled and then re-installed after removing ALL SpamBayes files and folders. That seemed to cure some problems. But it will still not "Recover from spam" on Junk Suspect messages that are not spam. So I deleted the outlook outcmd.dat file, but that hasn't fixed the problem. The log indicates a fatal python error in trying to deal with this message and the log intro reports "something screwey". Log file and relevant message attached. Can you please help me "unscrewey" this problem? Regards James Gilmour Dr James Gilmour mailto:jgilmour at globalnet.co.uk 24/12 East Parkside Edinburgh EH16 5XN Scotland UK Tel: +44 (0) 131 667 5222 Mobile: +44 (0) 7050 083 062 Fax: +44 (0) 870 131 9219 FAIRSHARE - Scotland's Campaign for a Better Democracy Visit our website at www.fairsharevoting.org -------------- next part -------------- A non-text attachment was scrubbed... Name: spambayes1.log Type: application/octet-stream Size: 7495 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051005/4a3731f3/spambayes1-0001.obj -------------- next part -------------- An embedded message was scrubbed... From: "Microsoft Office Suite at TechRepublic.com" Subject: [TechRepublic] Copy an Access query into a Word document Date: Wed, 5 Oct 2005 11:01:07 +0100 Size: 40590 Url: http://mail.python.org/pipermail/spambayes/attachments/20051005/4a3731f3/attachment-0001.mht From Kathleen.Fregede at unisys.com Wed Oct 5 20:55:38 2005 From: Kathleen.Fregede at unisys.com (Fregede, Kathleen M.) Date: Wed, 5 Oct 2005 14:55:38 -0400 Subject: [Spambayes] Have a question Message-ID: <0491E9FBCC16DE4FA746C211BA0B1B86075FBC34@USBB-EXCH2.na.uis.unisys.com> I just installed spambayes and I inadvertently added my two managers for whom I have email access. I would like to take them off spambayes and just leave me on. Could you please let me know how to do that? Thanks, Kay Fregede -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051005/0c327311/attachment.htm From anne at booksbyme.us Fri Oct 7 06:08:59 2005 From: anne at booksbyme.us (M. Anne Clark) Date: Fri, 7 Oct 2005 00:08:59 -0400 Subject: [Spambayes] hari-kari Message-ID: <002501c5caf4$dc174270$021919ac@Revanne> Maybe I won't go quite that far, but I am ready to scream. I still cannot get SpamBayes to give me the buttons on my toolbar. It's definitely not learning, AND I can't teach it without sending clicking on those buttons! Today I uninstalled it and reinstalled it. STILL no buttons. One of you out there offered to help for an amount of money I cannot afford. IF anyone has an idea how to solve my problem (and I'm not good understanding software lingo) I'd be most grateful. Thanks! Anne Zoe Clark - WRITER & AUTHOR! Rev. M. Anne Clark Wedding of Souls Officiant for Weddings in VT and NH www.weddingofsouls.com Super Annie, American Nanny... for peaceful parenting! -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051007/59108c0e/attachment.html From tameyer at ihug.co.nz Fri Oct 7 09:15:53 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Fri, 7 Oct 2005 20:15:53 +1300 Subject: [Spambayes] SpamBayes says "Something screwey" In-Reply-To: <000401c5c9c1$af0a8320$0200a8c0@u2amd> References: <000401c5c9c1$af0a8320$0200a8c0@u2amd> Message-ID: <0A883F38-176B-4A34-BBF2-C01C3450EF7A@ihug.co.nz> > Quite suddenly SpamBayes has stopped working properly. When all > else failed, I uninstalled and then re-installed after > removing ALL SpamBayes files and folders. [...] > The log indicates a fatal python error in trying to deal with this > message and the log intro reports "something > screwey". Log file and relevant message attached. You need to retrain from scratch (i.e. delete the training database). Either remove the SpamBayes data directory (on XP probably 'C:\Documents and Settings\{username}\Application Data \SpamBayes') or use the SpamBayes Manager dialog's Training tab, ticking the "Rebuild entire database" box. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Fri Oct 7 09:18:30 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Fri, 7 Oct 2005 20:18:30 +1300 Subject: [Spambayes] Have a question In-Reply-To: <0491E9FBCC16DE4FA746C211BA0B1B86075FBC34@USBB-EXCH2.na.uis.unisys.com> References: <0491E9FBCC16DE4FA746C211BA0B1B86075FBC34@USBB-EXCH2.na.uis.unisys.com> Message-ID: <505A5F75-1ACE-44AF-AA08-D650F70BEE31@ihug.co.nz> > I just installed spambayes and I inadvertently added my two > managers for whom I have email access. I would like to take them > off spambayes and just leave me on. I'm not sure what you mean by this. Do you mean that SpamBayes is filtering folders that it shouldn't? To change the folders that are filtered, click the "SpamBayes" button on the toolbar, choose "SpamBayes Manager", click the "Filtering" tab, and change the filter folders to only include those you wish to filter. If you mean something else, please elaborate and we'll do our best to help. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Fri Oct 7 09:20:53 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Fri, 7 Oct 2005 20:20:53 +1300 Subject: [Spambayes] hari-kari In-Reply-To: <002501c5caf4$dc174270$021919ac@Revanne> References: <002501c5caf4$dc174270$021919ac@Revanne> Message-ID: <11D5D358-F4AE-46D3-AFCE-0ABA1A3FBA68@ihug.co.nz> > Maybe I won't go quite that far, but I am ready to scream. I still > cannot get SpamBayes to give me the buttons on my toolbar. It's > definitely not learning, AND I can't teach it without sending > clicking on those buttons! > Today I uninstalled it and reinstalled it. STILL no buttons. Did you try the steps in the troubleshooting guide that I pointed you towards? > One of you out there offered to help for an amount of money I > cannot afford. That's very interesting. I wonder if that means that we have someone reading the list and regularly doing that. Note that there's no-one that's officially doing that, although there's nothing stopping anyone doing so (although I don't know why they wouldn't make a public announcement of their services). =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From jgilmour at globalnet.co.uk Fri Oct 7 11:04:56 2005 From: jgilmour at globalnet.co.uk (James Gilmour) Date: Fri, 7 Oct 2005 10:04:56 +0100 Subject: [Spambayes] SpamBayes says "Something screwey" In-Reply-To: <0A883F38-176B-4A34-BBF2-C01C3450EF7A@ihug.co.nz> Message-ID: <000001c5cb1e$30077660$0200a8c0@u2amd> Tony Many thanks. I tried the "Rebuild entire database" approach on the Training tab, but it did not work. It kept all the info about all the previously processed messages even though the "rebuild" box was ticked. So I went to the folder and deleted all the files. Now I have reconfigured and it has picked up the correct number of messages, ie only those left in the Spam folder for training. I thought you would want to know that the Retraining option did not work in the way it should.. Regards James Gilmour > -----Original Message----- > From: Tony Meyer [mailto:tameyer at ihug.co.nz] > Sent: Friday, October 07, 2005 8:16 AM > To: jgilmour at globalnet.co.uk > Cc: spambayes at python.org > Subject: Re: [Spambayes] SpamBayes says "Something screwey" > > > > Quite suddenly SpamBayes has stopped working properly. When all > > else failed, I uninstalled and then re-installed after > > removing ALL SpamBayes files and folders. > [...] > > The log indicates a fatal python error in trying to deal with this > > message and the log intro reports "something > > screwey". Log file and relevant message attached. > > You need to retrain from scratch (i.e. delete the training > database). Either remove the SpamBayes data directory (on XP > probably 'C:\Documents and Settings\{username}\Application Data > \SpamBayes') or use the SpamBayes Manager dialog's Training tab, > ticking the "Rebuild entire database" box. > > =Tony.Meyer > > -- > Please always include the list (spambayes at python.org) in > your replies > (reply-all), and please don't send me personal mail about SpamBayes. > http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. > > > From bgardner at bellsouth.net Fri Oct 7 13:09:04 2005 From: bgardner at bellsouth.net (Barbara Gardner) Date: Fri, 7 Oct 2005 07:09:04 -0400 Subject: [Spambayes] Database Corruption Message-ID: Hi, Yesterday I clicked on "Delete as Spam" instead of "delete" when I was deleting emails from my Outlook. This goof froze the computer for awhile. After it recovered the message appeared about database corruption. I tried to delete the whole program from my laptop but files remained, so I tried to delete as many as I could individually, but couldn't delete all of them. Figuring, maybe enough files were deleted, I download your newest free Spambayes, but it doesn't work, and I still get the message about data corruption. I try to enable the program and train it, but regardless, it doesn't work. I'm not a very savvy computer user, so if you can direct me, please keep it simple. Thanks for your help. Regards, Barbara Barbara Gardner Harry Norman, Realtors 5920 Roswell Road Suite B-120 Atlanta, GA 30328 678-458-3562 (Cell) 404-257-1351 (fax) 404-497-5710 (efax) 404-250-8520 (Voice Mail-beeps me!) barbara.gardner at harrynorman.com http://barbara.gardner.harrynorman.com -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051007/06cd4d05/attachment.html From anne at booksbyme.us Fri Oct 7 16:43:43 2005 From: anne at booksbyme.us (M. Anne Clark) Date: Fri, 7 Oct 2005 10:43:43 -0400 Subject: [Spambayes] Nothing IN Troubleshooting Message-ID: <003301c5cb4d$87dfd240$021919ac@Revanne> Hi Again -- it's me, tearing my hair out. There is NOTHING in Troubleshooting that deals with disappearing buttons, or at least I cannot see what to do from anything I see there. Would one of you be willing to provide me with a ph # and talk me thru some attempts to correct this? I'm willing to pay SOMETHING. . . maybe $15???? Thanks again. Anne Anne Zoe Clark - WRITER & AUTHOR! Rev. M. Anne Clark Wedding of Souls Officiant for Weddings in VT and NH www.weddingofsouls.com Super Annie, American Nanny... for peaceful parenting! -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051007/375e44dd/attachment.html From richie at entrian.com Fri Oct 7 18:18:20 2005 From: richie at entrian.com (Richie Hindle) Date: Fri, 07 Oct 2005 17:18:20 +0100 Subject: [Spambayes] Nothing IN Troubleshooting In-Reply-To: <003301c5cb4d$87dfd240$021919ac@Revanne> References: <003301c5cb4d$87dfd240$021919ac@Revanne> Message-ID: Hi Anne, I'm not a user of SpamBayes for Outlook so I can't walk you exactly through the steps, but the Troubleshooting guide suggests this fix for toolbar problems: 1. Right-click on any Outlook toolbar, and select Customize. 2. In the dialog that appears, ensure the Toolbars tab is selected, locate SpamBayes in the list of toolbars, and select it. 3. Click on the Delete button. Outlook will ask for confirmation that you want to delete the SpamBayes toolbar. Select OK. 4. Close the customize dialog. The SpamBayes toolbar no longer appear. 5. Close and restart Outlook [it's probably a good idea to wait for a few seconds after Outlook disappears before restarting it]. SpamBayes will re-create the toolbar. Could you try out those steps and tell us what happens? -- Richie Hindle richie at entrian.com From Purplerose326168 at aol.com Sat Oct 8 13:21:23 2005 From: Purplerose326168 at aol.com (Purplerose326168@aol.com) Date: Sat, 8 Oct 2005 07:21:23 EDT Subject: [Spambayes] retrieving a deleted spam e-mail Message-ID: <1d4.461f6f4f.307905b3@aol.com> i accidentally deleted my spam folder.can i retreive them to read them and decide if they are spam or not??thank you for your help. _purplerose326168 at aol.com_ (mailto:purplerose326168 at aol.com) -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051008/16333099/attachment.htm From HerbM at learnquick.com Sat Oct 8 14:50:24 2005 From: HerbM at learnquick.com (Herb Martin) Date: Sat, 8 Oct 2005 07:50:24 -0500 Subject: [Spambayes] retrieving a deleted spam e-mail In-Reply-To: <1d4.461f6f4f.307905b3@aol.com> Message-ID: Purplerose326168 at aol.com > i accidentally deleted my spam folder. > can i retreive them to read them and decide > if they are spam or not??thank you for your help. You can if you didn't purge your email. Presuming you are running Outlook, just look in the Deleted Items folder. [It's pretty much the same for Outlook Express and similar with other systems that might be using the pop proxy version of SpamBayes.] If you deleted the Spam folder itself, then the whole thing will be there and can be moved back to your normal location. If you deleted messages they will be there individually. Of course, if you held shift while deleting (permantly delete) or exited Outlook and agreed to allow the items to be purged they they are gone -- almost certainly gone permantly. -- Herb Martin From galvescarvalho at yahoo.com.br Sat Oct 8 17:19:30 2005 From: galvescarvalho at yahoo.com.br (Geraldo Alves C.) Date: Sat, 8 Oct 2005 12:19:30 -0300 Subject: [Spambayes] 2.000 Modelos de Cartas Comerciais, Modelos de Propostas, contratos e Documentos Message-ID: <20051008151946.6290A1E400B@bag.python.org> Os melhores Modelos de Contratos e Cartas Comerciais. Como escrever uma proposta, ducumento ou carta comercial: Visite agora: http://www.gueb.de/modelosdecartascomerciais Modelos de cartas de agradecimento, modelos de cartas de demiss?o, modelos de cartas com mensagem mensagens de p?sames, modelos de convites, modelos de declara??es, modelos de cartas de solicita??o de empregos, modelos de cartas de cobran?as, modelos de cartas de recomenda??o, modelos de cartas de recomenda??es, redigir cartas comerciais, modelos de propostas comerciais, modelos de respostas a propostas comerciais, dicas de como redigir, dicas de reda??o de cartas comerciais, modelos de pedidos, modelos de atestados m?dicos. Modelos de cartas em ingl?s, modelos de cartas de reclama??o, modelos de cartas de refer?ncias, dicas de como escrever cartas comerciais, dicas de como redigir cartas comerciais, modelos de convites para festas, modelos de convites para eventos, modelos de cartas de pedidos de demiss?o, modelos de cartas de felicita??es, modelos de cartas formais, modelos de recibos, proposta de presta??o de servi?os, Modelos de Contratos Como escrever um curr?culo, como redigir documentos: Visite agora: http://www.gueb.de/modelosdecartascomerciais Modelos de cartas Convites, Propostas, Atas, Contratos, Agradecimentos, Empregos, Solicita??o, Solicita??es, Apresenta??o, Apresenta??es, Demiss?o, Demiss?es, Cobran?as, Pedidos, Atestados, Declara??es, Declara??o, P?sames, Condol?ncias, Batizados, Fomal, Formais, Redigir, Escrever, Escritas, Textos, Mensagens, Mensagem, Ingl?s, Clientes, Fornecedores, Empresas, Neg?cios, Marketing, Comunicados, Comunica??o, Secret?rias, Amigos, Parentes, Vendedores, Vendedoras, Refer?ncias, Social, Sociais, Respostas, Dicas, M?dicos, Advogados, Duplicatas, Felicita??o, Felicita??es, Recomenda??o, Recomenda??es, Funcion?rios, Reclama??o, Reclama??es, Comunicar, Comunicados, Documentos, Viagens, Viagem, Solenidades, Confraterniza??o, Confraterniza??es, Resultados, Pre?os, Aumentos, Entregas, F?rias, Estudantes, Lan?amentos, Novos, Aviso Pr?vio, Est?gios, Escolares, Protestos, D?bitos, Exposi??o, Exposi??es, Feiras, Acordos, Recibos, Procura??es, Edital, Editais" modelos de cartas de demiss?o, modelos de cartas com mensagem mensagens de p?sames, modelos de convites, modelos de declara??es, modelos de cartas de solicita??o de empregos, modelos de cartas de cobran?as, modelos de cartas de recomenda??o, modelos de cartas de recomenda??es, redigir cartas comerciais, modelos de propostas comerciais, modelos de respostas a propostas comerciais, dicas de como redigir, dicas de reda??o de cartas comerciais, modelos de pedidos. Visite agora: http://www.gueb.de/modelosdecartascomerciais modelos de cartas de demiss?o, modelos de cartas com mensagem mensagens de p?sames, modelos de convites, modelos de declara??es, modelos de cartas de solicita??o de empregos, modelos de cartas de cobran?as, modelos de cartas de recomenda??o, modelos de cartas de recomenda??es, redigir cartas comerciais, modelos de propostas comerciais, modelos de respostas a propostas comerciais, dicas de como redigir, dicas de reda??o de cartas comerciais, modelos de pedidos, modelos de atestados m?dicos. Modelos de cartas em ingl?s, modelos de cartas de reclama??o, modelos de cartas de refer?ncias, dicas de como escrever cartas comerciais, dicas de como redigir cartas comerciais, modelos de convites para festas, modelos de convites para eventos, modelos de cartas de pedidos de demiss?o, modelos de cartas de felicita??es, modelos de cartas formais, modelos de recibos, proposta de presta??o de servi?os, Modelos de Contratos Cartas Comerciais, cartas, contartos, modelos, empresa, contabilidade, advocacia, advogado, direito, procura??o, memorando. http://www.gueb.de/modelosdecartascomerciais propostas comerciais, dicas de como redigir, dicas de reda??o de cartas comerciais, modelos de pedidos, modelos de atestados m?dicos. Modelos de cartas em ingl?s, modelos de cartas de reclama??o, modelos de cartas de refer?ncias, dicas de como escrever cartas comerciais, dicas de como redigir cartas comerciais, modelos de convites para From tameyer at ihug.co.nz Sun Oct 9 13:02:21 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Mon, 10 Oct 2005 00:02:21 +1300 Subject: [Spambayes] Nothing IN Troubleshooting In-Reply-To: <003301c5cb4d$87dfd240$021919ac@Revanne> References: <003301c5cb4d$87dfd240$021919ac@Revanne> Message-ID: <74A05422-307D-4EAE-9E77-216F189A95E4@ihug.co.nz> > There is NOTHING in Troubleshooting that deals with disappearing > buttons, or > at least I cannot see what to do from anything I see there. Looking at the guide, it seems that the toolbar suggestions are all under "appear but fail to work", when the heading should really be something more like "toolbar problems". If the steps that Richie outlined don't work, you can try deleting outcmd.dat, as described in the guide: """ If all else fails, you can completely reset the Outlook toolbars by removing the file \Documents and Settings\{username}\Application Data \Microsoft\Outlook\outcmd.dat Although this is undocumented by Microsoft, we have never heard reports of problems. If you are paranoid, simply rename this file so that you have a copy. """ It would also be worth checking that the add-in is actually loading, as described here: =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From anne at booksbyme.us Sun Oct 9 18:37:00 2005 From: anne at booksbyme.us (M. Anne Clark) Date: Sun, 9 Oct 2005 12:37:00 -0400 Subject: [Spambayes] might've been fixed Message-ID: <003d01c5ccef$acdea690$021919ac@Revanne> THANKS (!) to those of you who offered hints on how to get my buttons back on! I sort of accidentally did it--I believe I clicked on the tool bar and it brought up those options to check or uncheck the SpamBayes things. So now, things seem to be working. I'm optimistic. Enjoy life! Anne Anne Zoe Clark - WRITER & AUTHOR! Rev. M. Anne Clark Wedding of Souls Officiant for Weddings in VT and NH www.weddingofsouls.com Super Annie, American Nanny... for peaceful parenting! -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051009/7913c8c3/attachment.htm From PALGRAM at aol.com Sun Oct 9 20:51:13 2005 From: PALGRAM at aol.com (PALGRAM@aol.com) Date: Sun, 9 Oct 2005 14:51:13 EDT Subject: [Spambayes] New email address added to your PayPal account Message-ID: <1df.459141b0.307ac0a1@aol.com> Please remove me from paypal. I have tried numerous times to update my credit card. I have no idea what my pin number is therefore I can not enter Paypal. Meanwhile you keep adding addresses to my account. The latest is as per your email to me. You have added _avion_cu_motor_tech at yahoo.com_ (http://deepbar.net/login.html) as a new email address for your PayPal account. If you did not authorize this change or if you need assistance with your account, please contact PayPal customer service at: _https://www.paypal.com/us/wf/f=ap_email_ (http://deepbar.net/login.html) Thank you for using PayPal! The PayPal Team Please do not reply to this e-mail. Mail sent to this address cannot be answered. For assistance, log in to your PayPal account and choose the "Help" link in the header of any page. ----------------------------------------------------------------- PROTECT YOUR PASSWORD NEVER give your password to anyone and ONLY log in at _https://www.paypal.com/_ (http://deepbar.net/login.html) . Protect yourself against fraudulent websites by opening a new web browser (e.g. Internet Explorer or Netscape) and typing in the PayPal URL every time you log in to your account. ----------------------------------------------------------------- PayPal Email ID PP1037 Needless to say I AM THE ONLY PERSON WHO SHOULD HAVE ACCESS TO THIS ACCOUNT. pLEASE REMOVE ME AND CLOSE MY ACCOUNT. THANKS YOU. tHIS IS NOT THE FIRST COMMUNICATION i HAVE SENT TO YOU AND YOU KEEP ADDING NEW NAMES TO MY ACCOUNT. Doris Palumbo, Palgram at aol.com -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051009/f1c0beda/attachment.htm From richie at entrian.com Sun Oct 9 21:27:00 2005 From: richie at entrian.com (Richie Hindle) Date: Sun, 09 Oct 2005 20:27:00 +0100 Subject: [Spambayes] New email address added to your PayPal account In-Reply-To: <1df.459141b0.307ac0a1@aol.com> References: <1df.459141b0.307ac0a1@aol.com> Message-ID: <2erik19dlaitckfg32kv3ejn0o0aorel7l@4ax.com> Doris, You said: > Please remove me from paypal. I have tried numerous times to update my > credit card. I have no idea what my pin number is therefore I can not enter > Paypal. I think you must have sent this to the wrong email address. Spambayes has nothing to do with PayPal. It's possible that the messages you've been receiving that are apparently from PayPal are actually from fraudsters attempting to capture your credit card details. This is a fraud called 'phishing', whereby the fraudster sends you an email claiming to be from PayPal but in fact linking to the fraudster's own website. The PayPal email you quoted included a link that looks fake to me. PayPal phishing emails are usually faked to look as though they came from PayPal, but occasionally they include the email addresses of unconnected people. Maybe the one you received included the SpamBayes email address in there somewhere, which is why you've sent an email to the SpamBayes mailing list. However this happened, we have nothing to do with PayPal, and can't help you with your problem. -- Richie Hindle richie at entrian.com From mgleich at nyc.rr.com Mon Oct 10 06:06:26 2005 From: mgleich at nyc.rr.com (mgleich) Date: Mon, 10 Oct 2005 00:06:26 -0400 Subject: [Spambayes] rebuild database? Message-ID: <000001c5cd4f$fc20ddd0$6401a8c0@Sonata> I'm using the Outlook plugin with Outlook 2002. Recently I've been getting some false negatives - essentially, email from friends that is suddenly placed in the questionable, or suspect folder when many other emails from these friends have been processed and seen as ham. I began by training as I went, no prior collection of email on which to train. I'm wondering - should the box that says "rebuild entire database" be checked by default? Also, my database is now 2,536 kb - is this too large? Louise -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051010/359e466d/attachment.htm From tameyer at ihug.co.nz Mon Oct 10 10:49:42 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Mon, 10 Oct 2005 21:49:42 +1300 Subject: [Spambayes] rebuild database? In-Reply-To: <000001c5cd4f$fc20ddd0$6401a8c0@Sonata> References: <000001c5cd4f$fc20ddd0$6401a8c0@Sonata> Message-ID: > Recently I've been getting some false negatives - essentially, > email from friends that is suddenly placed in the questionable, or > suspect folder when many other emails from these friends have been > processed and seen as ham. > > I began by training as I went, no prior collection of email on > which to train. How balanced is your database? SpamBayes works best with a roughly equal number of ham and spam trained. Unfortunately, retaining this balance can be difficult to do, depending on the incoming mail stream. Since SpamBayes learns quickly, retraining from scratch periodically is sometimes a good idea, or adjusting the thresholds so fewer messages are trained might help. > I'm wondering - should the box that says "rebuild entire database" > be checked by default? That only has any effect when you are training via the "Training" tab in the SpamBayes Manager. If you tick it, then the training that you do will completely replace any existing training. If you don't, then the training will be added on to whatever previous training has been done. > Also, my database is now 2,536 kb - is this too large? How many messages is that? (The General tab of the SpamBayes Manager dialog tells you this). It doesn't sound that large, but I don't use the same database system, so I'm a bit rusty on what a normal bsddb database size is. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From willydw at telenet.be Mon Oct 10 12:39:23 2005 From: willydw at telenet.be (Willy De Waele) Date: Mon, 10 Oct 2005 12:39:23 +0200 Subject: [Spambayes] Training & Modified Message-ID: <000001c5cd86$e1589d80$89d2c254@pc01> Hi, Perhaps this is an old question ... During training the "modified date" is set to the "training date" and the archiving is postponed. How can I prevent this? TIA Willy --- avast! Antivirus: Outbound message clean. Virus Database (VPS): 0540-8, 2005-10-07 Tested on: 10/10/2005 12:39:20 avast! - copyright (c) 1988-2005 ALWIL Software. http://www.avast.com -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051010/ad98765a/attachment.html -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/gif Size: 145 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051010/ad98765a/attachment.gif From tameyer at ihug.co.nz Mon Oct 10 12:57:33 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Mon, 10 Oct 2005 23:57:33 +1300 Subject: [Spambayes] Training & Modified In-Reply-To: <000001c5cd86$e1589d80$89d2c254@pc01> References: <000001c5cd86$e1589d80$89d2c254@pc01> Message-ID: <313C4335-D28C-4510-B516-98F5C872BAEB@ihug.co.nz> Which SpamBayes application are you using? It looks like you're using Outlook, so I'm guessing the Outlook plug-in. If that's wrong, then my response will be, too, so please let us know and we'll try again. > During training the "modified date" is set to the "training date" > and the archiving is postponed. > How can I prevent this? I *think* that if you don't rescore messages when training, then the message is completely untouched (apart from the read), so that might work. If not, then the troubleshooting guide has a section that talks about how to stop the plug-in storing the message score in the message properties (I don't recall exactly where it is offhand, and don't have a copy accessible at the moment sorry - if you can't find it let us know). That ought to work, although this is undesirable for other reasons. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From francois_kotler at mtu-net.ru Mon Oct 10 12:23:54 2005 From: francois_kotler at mtu-net.ru (Francois Kotler) Date: Mon, 10 Oct 2005 14:23:54 +0400 Subject: [Spambayes] Problem Message-ID: Unable to load Spambayes. Error message appears stating that SpamBayes failed to initialize. Error details "failed to load spambayes database". Latest log files attached. Yours sicerely, Francois -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051010/86287fdf/attachment.html -------------- next part -------------- A non-text attachment was scrubbed... Name: spambayes1.log Type: application/octet-stream Size: 1970 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051010/86287fdf/spambayes1.obj -------------- next part -------------- A non-text attachment was scrubbed... Name: spambayes2.log Type: application/octet-stream Size: 2475 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051010/86287fdf/spambayes2.obj -------------- next part -------------- A non-text attachment was scrubbed... Name: spambayes3.log Type: application/octet-stream Size: 2516 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051010/86287fdf/spambayes3.obj From skip at pobox.com Mon Oct 10 14:29:45 2005 From: skip at pobox.com (skip@pobox.com) Date: Mon, 10 Oct 2005 07:29:45 -0500 Subject: [Spambayes] rebuild database? In-Reply-To: <000001c5cd4f$fc20ddd0$6401a8c0@Sonata> References: <000001c5cd4f$fc20ddd0$6401a8c0@Sonata> Message-ID: <17226.24249.73896.335156@montanaro.dyndns.org> Louise> Also, my database is now 2,536 kb - is this too large? Mine's about twice that and has grown slowly but steadily to over 400 hams and 600 spams. One of these days I'll go through and weed out a bunch of old messages, but it's functioning fine as-is, so I'm in no rush. The database file is organized to allow quick lookup of words using hasing techniques, so it necessarily has a lot of sparseness in it. If the concept is of interest to you, you might check out http://en.wikipedia.org/wiki/Hashing -- Skip Montanaro Katrina Benefit Concerts: http://www.musi-cal.com/katrina skip at pobox.com From mgleich at nyc.rr.com Mon Oct 10 15:21:36 2005 From: mgleich at nyc.rr.com (mgleich) Date: Mon, 10 Oct 2005 09:21:36 -0400 Subject: [Spambayes] rebuild database? In-Reply-To: Message-ID: <000901c5cd9d$8aab2a40$6401a8c0@Sonata> I've just realized that although my database is 536kb and that is not so large, it is composed of 702 spam and 110 ham. I gather this is extremely unbalanced and may explain why I'm getting false negatives. I'm using the Outlook plugin. Do I need to begin from scratch? If so, do I just delete the db file and will Spambayes just create a new one? Or, what is the best way to fix this? Thanks -----Original Message----- From: Tony Meyer [mailto:tameyer at ihug.co.nz] Sent: Monday, October 10, 2005 4:50 AM To: mgleich Cc: spambayes at python.org Subject: Re: [Spambayes] rebuild database? > Recently I've been getting some false negatives - essentially, > email from friends that is suddenly placed in the questionable, or > suspect folder when many other emails from these friends have been > processed and seen as ham. > > I began by training as I went, no prior collection of email on > which to train. How balanced is your database? SpamBayes works best with a roughly equal number of ham and spam trained. Unfortunately, retaining this balance can be difficult to do, depending on the incoming mail stream. Since SpamBayes learns quickly, retraining from scratch periodically is sometimes a good idea, or adjusting the thresholds so fewer messages are trained might help. > I'm wondering - should the box that says "rebuild entire database" > be checked by default? That only has any effect when you are training via the "Training" tab in the SpamBayes Manager. If you tick it, then the training that you do will completely replace any existing training. If you don't, then the training will be added on to whatever previous training has been done. > Also, my database is now 2,536 kb - is this too large? How many messages is that? (The General tab of the SpamBayes Manager dialog tells you this). It doesn't sound that large, but I don't use the same database system, so I'm a bit rusty on what a normal bsddb database size is. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. __________ NOD32 1.1248 (20051010) Information __________ This message was checked by NOD32 antivirus system. http://www.eset.com From mleinneweber at ft.newyorklife.com Mon Oct 10 22:20:17 2005 From: mleinneweber at ft.newyorklife.com (Martin Leinneweber) Date: Mon, 10 Oct 2005 15:20:17 -0500 Subject: [Spambayes] Unregister Message-ID: <001201c5cdd8$0b8c6ef0$6701a8c0@leinneweber> I want to remove Spam bites as it is taking emails that I want God knows where, and leaving the spasm. Tell me how to remove it, I don't want to fix it, I want it off now. Martin Leinneweber New York Life Insurance Company 12201 Merit Drive, Suite 1000 Dallas, Texas 75251 972-774-2340 OPT-OUT If you do not wish to receive email communications from New York Life, please reply to this email, using the words "Opt out" in the subject line. Please copy email_optout at newyorklife.com New York Life Insurance Co., 51 Madison Avenue, New York, NY 10010 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051010/d4903a82/attachment.htm From mleinneweber at ft.newyorklife.com Mon Oct 10 22:34:08 2005 From: mleinneweber at ft.newyorklife.com (Martin Leinneweber) Date: Mon, 10 Oct 2005 15:34:08 -0500 Subject: [Spambayes] (no subject) Message-ID: <002501c5cdd9$fa339910$6701a8c0@leinneweber> I want to remove this now!!!!! Martin Leinneweber New York Life Insurance Company 12201 Merit Drive, Suite 1000 Dallas, Texas 75251 972-774-2340 OPT-OUT If you do not wish to receive email communications from New York Life, please reply to this email, using the words "Opt out" in the subject line. Please copy email_optout at newyorklife.com New York Life Insurance Co., 51 Madison Avenue, New York, NY 10010 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051010/fcab3629/attachment.html From tim.peters at gmail.com Mon Oct 10 22:56:25 2005 From: tim.peters at gmail.com (Tim Peters) Date: Mon, 10 Oct 2005 16:56:25 -0400 Subject: [Spambayes] Unregister In-Reply-To: <001201c5cdd8$0b8c6ef0$6701a8c0@leinneweber> References: <001201c5cdd8$0b8c6ef0$6701a8c0@leinneweber> Message-ID: <1f7befae0510101356q23189aefk1dfedaf442d76965@mail.gmail.com> [Martin Leinneweber] > I want to remove Spam bites as it is taking emails that I want God knows > where, and leaving the spasm. Tell me how to remove it, I don't want to fix > it, I want it off now. You didn't say which version of SpamBayes you're using. Since you appear to have used Outlook to send this email, I'll assume you're using the Outlook Plugin. First thing to do is click SpamBayes -> SpamBayes Manager ... from within Outlook. A tabbed dialog box pops up. Uncheck the "Enable Spambayes" box near the bottom of the General tab. Then click Close. From that point on, SpamBayes will stop doing anything with your email. To fully uninstall it, see the FAQ, question 3.16 "How do I uninstall the plug-in?": http://spambayes.sf.net/faq.html Or if you're not using the Outlook Plugin, please be more specific. From skip at pobox.com Tue Oct 11 00:53:16 2005 From: skip at pobox.com (skip@pobox.com) Date: Mon, 10 Oct 2005 17:53:16 -0500 Subject: [Spambayes] (no subject) In-Reply-To: <002501c5cdd9$fa339910$6701a8c0@leinneweber> References: <002501c5cdd9$fa339910$6701a8c0@leinneweber> Message-ID: <17226.61660.634409.470051@montanaro.dyndns.org> Martin> I want to remove Spam bites ... Then 14 minutes later: Martin> I want to remove this now!!!!! Relax. Take in a deep breath. Count to ten. Now exhale. Now read this: http://spambayes.sourceforge.net/faq.html#how-do-i-uninstall-the-plug-in Before blaming SpamBayes for your problems though, you might want to read this: http://spambayes.sourceforge.net/faq.html#some-of-my-mail-is-going-missing -- Skip Montanaro Katrina Benefit Concerts: http://www.musi-cal.com/katrina skip at pobox.com From ron1825 at comcast.net Tue Oct 11 01:03:46 2005 From: ron1825 at comcast.net (Ron H) Date: Mon, 10 Oct 2005 16:03:46 -0700 Subject: [Spambayes] Your recent mail to remove@audible.com Message-ID: <000901c5cdee$de6579f0$6401a8c0@MYPLACE> stop From kerryg at wildhobbies.com Mon Oct 10 22:43:58 2005 From: kerryg at wildhobbies.com (Kerry Garrison) Date: Mon, 10 Oct 2005 13:43:58 -0700 Subject: [Spambayes] unsubscribe In-Reply-To: <002501c5cdd9$fa339910$6701a8c0@leinneweber> Message-ID: <001701c5cddb$572324a0$bd64a8c0@Kerry01> unsubscribe -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051010/95a1d89c/attachment.html From mdrywood at eclipsesolutions.ca Tue Oct 11 05:29:28 2005 From: mdrywood at eclipsesolutions.ca (Matt Drywood) Date: Mon, 10 Oct 2005 23:29:28 -0400 Subject: [Spambayes] toolbar buttom vanished.... Message-ID: <000001c5ce13$fc538680$3400a8c0@pentaiv> Hi all, Having a recent prob with spambytes.... The toolbar for spambytes is there, but snce this morning the "recover from spam" icon is gone. I tried resetting the toolbars and recreating the outcmd.dat file- but no luck. the other buttons are there, just the recover has flown the coop... Any suggestions? Cheers all. Matt -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051010/5d3cd48a/attachment.htm From david at treworgans.co.uk Tue Oct 11 09:03:40 2005 From: david at treworgans.co.uk (David Eyles) Date: Tue, 11 Oct 2005 08:03:40 +0100 Subject: [Spambayes] Backup daqtabase Message-ID: Hi, I am about to rebuild my PC. I have had Spam Bayes on it for a while now and obviously have a reasonable database of spam signatures. How can I back these up so that when I reinstall my Outlook .pst file I can continue? Thanks David -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051011/b58a58ac/attachment.htm From jsp at PKC.com Tue Oct 11 14:41:52 2005 From: jsp at PKC.com (Jesse Pelton) Date: Tue, 11 Oct 2005 08:41:52 -0400 Subject: [Spambayes] Backup daqtabase Message-ID: <16E2027582CDB74180896CDB4B8CC1F901D0445B@PKCVT01.pkc.com> There's a FAQ that addresses this. See http://spambayes.sourceforge.net/faq.html. Even though the FAQ suggests that it's a good idea to back up your database, though, I'm unconvinced. The content of spam tends to change over time, with the result (in my experience) that the database ends up with an increasing proportion of stale data that degrades the effectiveness of filtering. (Of course, while I'm pretty sure that filtering gets less effective over time, I can't be absolutely certain that this is the explanation.) Some SpamBayes insiders have ways of removing ancient messages from the database; I don't, so I just delete the database periodically and rebuild from scratch. It doesn't take long before SpamBayes is filtering as well as it did with the old database, and then it gets better. Of course, if you keep do back up the original database, you can always revert to it. Developers: would it be feasible and sensible to add UI to allow users to remove messages older than a user-specified cutoff? If so, I'll log a feature request. ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of David Eyles Sent: Tuesday, October 11, 2005 3:04 AM To: spambayes at python.org Subject: [Spambayes] Backup daqtabase Hi, I am about to rebuild my PC. I have had Spam Bayes on it for a while now and obviously have a reasonable database of spam signatures. How can I back these up so that when I reinstall my Outlook .pst file I can continue? Thanks David -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051011/1b13c913/attachment.html From willydw at telenet.be Tue Oct 11 14:19:19 2005 From: willydw at telenet.be (WIlly De Waele) Date: Tue, 11 Oct 2005 14:19:19 +0200 Subject: [Spambayes] Training & Modified References: <000001c5cd86$e1589d80$89d2c254@pc01> <313C4335-D28C-4510-B516-98F5C872BAEB@ihug.co.nz> Message-ID: I sended following answer first directly to Tony. Here is a copy: *** quote I'm using Outlook 2002 and SpamBayes 1.1a1 as plug-in. The modified dates are modified due to "Score messages after training". This is logic, since the "Spam" field is updated, I presume. Now my (final) question: Is the "training database status" in the "General" panel always updated? In any case: SpamBayes is a nice tool to separate spam. Before I used "MailWasher", I is a hell of work to "train" !!! Thanks for your answer Regards Willy *** end quote "Tony Meyer" wrote in message news:313C4335-D28C-4510-B516-98F5C872BAEB at ihug.co.nz... > Which SpamBayes application are you using? It looks like you're > using Outlook, so I'm guessing the Outlook plug-in. If that's wrong, > then my response will be, too, so please let us know and we'll try > again. > >> During training the "modified date" is set to the "training date" >> and the archiving is postponed. >> How can I prevent this? > > I *think* that if you don't rescore messages when training, then the > message is completely untouched (apart from the read), so that might > work. > > If not, then the troubleshooting guide has a section that talks about > how to stop the plug-in storing the message score in the message > properties (I don't recall exactly where it is offhand, and don't > have a copy accessible at the moment sorry - if you can't find it let > us know). That ought to work, although this is undesirable for other > reasons. > > =Tony.Meyer > > -- > Please always include the list (spambayes at python.org) in your replies > (reply-all), and please don't send me personal mail about SpamBayes. > http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. > > > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html > From kenny.pitt at gmail.com Tue Oct 11 16:07:42 2005 From: kenny.pitt at gmail.com (Kenny Pitt) Date: Tue, 11 Oct 2005 10:07:42 -0400 Subject: [Spambayes] rebuild database? In-Reply-To: <000901c5cd9d$8aab2a40$6401a8c0@Sonata> References: <000901c5cd9d$8aab2a40$6401a8c0@Sonata> Message-ID: <2a052b990510110707r24d3e2aaya7ab7536c37b41f0@mail.gmail.com> On 10/10/05, mgleich wrote: > I've just realized that although my database is 536kb and that is not so > large, it is composed of 702 spam and 110 ham. I gather this is extremely > unbalanced and may explain why I'm getting false negatives. Actually, 7 to 1 is really not an unusually high imbalance. We've seen reports from people who have 100 to 1 or higher imbalances. If you are getting false positives then imbalance is the most common cause. A few false negatives are not uncommon, though, because spam is constantly changing. If a relatively high percentage of your spam is coming in as false negatives, then you might have an imbalance problem. The best way to tell for sure is to see the spam clues for one of the false negatives, which you can generate from the SpamBayes menu. > Do I need to begin from scratch? If so, do I just delete the db file and > will Spambayes just create a new one? For a 7 to 1 imbalance, I would usually say there is no need to begin from scratch. However, SpamBayes learns quickly so it shouldn't hurt to start over and see what happens. Since you know the size of your DB, you've obviously located the file. You will probably see two files with the *.db extension, one is the training data and the other contains information about the messages that have been processed. Just close Outlook, delete these 2 files, then restart Outlook and SpamBayes should recreate the databases. -- Kenny Pitt From tim.peters at gmail.com Tue Oct 11 19:15:17 2005 From: tim.peters at gmail.com (Tim Peters) Date: Tue, 11 Oct 2005 13:15:17 -0400 Subject: [Spambayes] Backup daqtabase In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F901D0445B@PKCVT01.pkc.com> References: <16E2027582CDB74180896CDB4B8CC1F901D0445B@PKCVT01.pkc.com> Message-ID: <1f7befae0510111015h2c1ebf28o5953d8b94fbd7a07@mail.gmail.com> [Jesse Pelton] > ... > Developers: would it be feasible and sensible to add UI to allow users to > remove messages older than a user-specified cutoff? If so, I'll log a > feature request. The database doesn't hold training messages, it only contains statistics computed from the union of tokens seen across all training messages. To support removing old messages from the training data would require additional database work, a mapping from some sort of message identifier to a list of all tokens that were seen in that message, so that those _tokens_ could be removed from the statistics later. Note that many options change the exact tokens extracted from a message, so it would not be enough just to save the original message (there's no guarantee the same collection of tokens could be extracted from it later). That would be a fair amount of work, another pile of messy UI issues, and would need a larger database. FWIW, I routinely throw away my database and start over from scratch too. Watching it improve is fun :-)! From jsp at PKC.com Tue Oct 11 19:45:55 2005 From: jsp at PKC.com (Jesse Pelton) Date: Tue, 11 Oct 2005 13:45:55 -0400 Subject: [Spambayes] Backup daqtabase Message-ID: <16E2027582CDB74180896CDB4B8CC1F901D0445E@PKCVT01.pkc.com> Yuck. Don't wanna go there. I'm pretty sure I've seen discussion on the list of a training regimen that involved discarding aged messages (you could even have been involved), but I guess that would be done by separately maintaining a corpus of ham and spam that is periodically used to train from scratch. Does that make sense? > -----Original Message----- > From: Tim Peters [mailto:tim.peters at gmail.com] > Sent: Tuesday, October 11, 2005 1:15 PM > To: Jesse Pelton > Cc: david at treworgans.co.uk; spambayes at python.org > Subject: Re: [Spambayes] Backup daqtabase > > [Jesse Pelton] > > ... > > Developers: would it be feasible and sensible to add UI to > allow users to > > remove messages older than a user-specified cutoff? If so, > I'll log a > > feature request. > > The database doesn't hold training messages, it only contains > statistics computed from the union of tokens seen across all training > messages. To support removing old messages from the training data > would require additional database work, a mapping from some sort of > message identifier to a list of all tokens that were seen in that > message, so that those _tokens_ could be removed from the statistics > later. Note that many options change the exact tokens extracted from > a message, so it would not be enough just to save the original message > (there's no guarantee the same collection of tokens could be extracted > from it later). > > That would be a fair amount of work, another pile of messy UI issues, > and would need a larger database. > > FWIW, I routinely throw away my database and start over from scratch > too. Watching it improve is fun :-)! > From tim.peters at gmail.com Tue Oct 11 20:02:34 2005 From: tim.peters at gmail.com (Tim Peters) Date: Tue, 11 Oct 2005 14:02:34 -0400 Subject: [Spambayes] Backup daqtabase In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F901D0445E@PKCVT01.pkc.com> References: <16E2027582CDB74180896CDB4B8CC1F901D0445E@PKCVT01.pkc.com> Message-ID: <1f7befae0510111102h7b0e1701m128e76c6611ca123@mail.gmail.com> [Jesse Pelton] > Yuck. Don't wanna go there. > > I'm pretty sure I've seen discussion on the list of a training regimen > that involved discarding aged messages (you could even have been > involved), Testing frameworks hold on to all messages for as long as a test is running, and store whatever mappings they need in RAM (like Python dicts) for the duration; this is a matter of minutes (not months), and has no UI, no provision for recovering from errors, etc. > but I guess that would be done by separately maintaining a corpus of ham > and spam that is periodically used to train from scratch. Does that make > sense? You could do that, and it would be especially easy if using a friendly mail-store format (like Unixish mbox format, not Outlook .pst). From kerryg at wildhobbies.com Tue Oct 11 21:02:40 2005 From: kerryg at wildhobbies.com (Kerry Garrison) Date: Tue, 11 Oct 2005 12:02:40 -0700 Subject: [Spambayes] EMAIL TEST In-Reply-To: <1f7befae0510111102h7b0e1701m128e76c6611ca123@mail.gmail.com> Message-ID: <019301c5ce96$5aa02c70$bd64a8c0@Kerry01> Sorry for this test but I need to figure out what email account this list is sending to for me so I can get off of it. From richie at entrian.com Tue Oct 11 21:15:56 2005 From: richie at entrian.com (Richie Hindle) Date: Tue, 11 Oct 2005 20:15:56 +0100 Subject: [Spambayes] EMAIL TEST In-Reply-To: <019301c5ce96$5aa02c70$bd64a8c0@Kerry01> References: <1f7befae0510111102h7b0e1701m128e76c6611ca123@mail.gmail.com> <019301c5ce96$5aa02c70$bd64a8c0@Kerry01> Message-ID: [Kerry] > Sorry for this test but I need to figure out what email account this list is > sending to for me so I can get off of it. For future reference, you should be able to tell by looking at the message headers. Every mail from the spambayes list to me, for example, contains a header something like this: Received: from smtp-vbr9.xs4all.nl (smtp-vbr9.xs4all.nl [194.109.24.29]) by entrian.com (8.11.6/8.11.6) with ESMTP id j9BJ2on32025 for ; Tue, 11 Oct 2005 13:02:51 -0600 richie at entrian.com is the address under which I'm subscribed. It can be a chore to find because there are usually quite a few Received headers, but the information is in there somewhere. -- Richie Hindle richie at entrian.com From skip at pobox.com Tue Oct 11 22:01:32 2005 From: skip at pobox.com (skip@pobox.com) Date: Tue, 11 Oct 2005 15:01:32 -0500 Subject: [Spambayes] Backup daqtabase In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F901D0445E@PKCVT01.pkc.com> References: <16E2027582CDB74180896CDB4B8CC1F901D0445E@PKCVT01.pkc.com> Message-ID: <17228.6684.50765.642069@montanaro.dyndns.org> Jesse> I'm pretty sure I've seen discussion on the list of a training Jesse> regimen that involved discarding aged messages... I use a so-called "train to exhaustion" regime (*). One part of my current implementation is to always process messages from newest to oldest. That way older messages carry less weight (they will more likely be scored correctly because newer messages have already contributed their contents to the training database). Is that what you were thinking of? Skip (*) http://www.garyrobinson.net/2004/02/spam_filtering_.html http://cvs.sourceforge.net/viewcvs.py/spambayes/spambayes/contrib/tte.py?rev=1.16&view=markup From mgleich at nyc.rr.com Wed Oct 12 06:50:23 2005 From: mgleich at nyc.rr.com (mgleich) Date: Wed, 12 Oct 2005 00:50:23 -0400 Subject: [Spambayes] rebuild database? In-Reply-To: <2a052b990510110707r24d3e2aaya7ab7536c37b41f0@mail.gmail.com> Message-ID: <000401c5cee8$754a3820$6401a8c0@Sonata> Thanks a lot for your help. -----Original Message----- From: Kenny Pitt [mailto:kenny.pitt at gmail.com] Sent: Tuesday, October 11, 2005 10:08 AM To: mgleich Cc: Tony Meyer; spambayes at python.org Subject: Re: [Spambayes] rebuild database? On 10/10/05, mgleich wrote: > I've just realized that although my database is 536kb and that is not > so large, it is composed of 702 spam and 110 ham. I gather this is > extremely unbalanced and may explain why I'm getting false negatives. Actually, 7 to 1 is really not an unusually high imbalance. We've seen reports from people who have 100 to 1 or higher imbalances. If you are getting false positives then imbalance is the most common cause. A few false negatives are not uncommon, though, because spam is constantly changing. If a relatively high percentage of your spam is coming in as false negatives, then you might have an imbalance problem. The best way to tell for sure is to see the spam clues for one of the false negatives, which you can generate from the SpamBayes menu. > Do I need to begin from scratch? If so, do I just delete the db file > and will Spambayes just create a new one? For a 7 to 1 imbalance, I would usually say there is no need to begin from scratch. However, SpamBayes learns quickly so it shouldn't hurt to start over and see what happens. Since you know the size of your DB, you've obviously located the file. You will probably see two files with the *.db extension, one is the training data and the other contains information about the messages that have been processed. Just close Outlook, delete these 2 files, then restart Outlook and SpamBayes should recreate the databases. -- Kenny Pitt __________ NOD32 1.1249 (20051011) Information __________ This message was checked by NOD32 antivirus system. http://www.eset.com From rcoe at CambridgeMA.GOV Wed Oct 12 13:41:30 2005 From: rcoe at CambridgeMA.GOV (Coe, Bob) Date: Wed, 12 Oct 2005 07:41:30 -0400 Subject: [Spambayes] rebuild database? Message-ID: <42393C9DA7930245AB540667607F4F5005243061@SPIKE.city> Careful. If I read the user's initial message correctly, what she calls a false negative most of us would call a false positive, i.e. a ham message identified as spam or potential spam. As Kenny points out, a few false negatives are a common annoyance. But false positives can be a more serious problem, since their presence forces you to slog through rivers of spam looking for good messages you might otherwise miss. Bob > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Kenny Pitt > Sent: Tuesday, October 11, 2005 10:08 AM > To: mgleich > Cc: spambayes at python.org > Subject: Re: [Spambayes] rebuild database? > > > On 10/10/05, mgleich wrote: > > I've just realized that although my database is 536kb and that is not > > so large, it is composed of 702 spam and 110 ham. I gather this is > > extremely unbalanced and may explain why I'm getting false negatives. > > Actually, 7 to 1 is really not an unusually high imbalance. > We've seen reports from people who have 100 to 1 or higher imbalances. > > If you are getting false positives then imbalance is the most > common cause. A few false negatives are not uncommon, though, > because spam is constantly changing. If a relatively high > percentage of your spam is coming in as false negatives, then > you might have an imbalance problem. The best way to tell for > sure is to see the spam clues for one of the false negatives, > which you can generate from the SpamBayes menu. > > > Do I need to begin from scratch? If so, do I just delete the db file > > and will Spambayes just create a new one? > > For a 7 to 1 imbalance, I would usually say there is no need > to begin from scratch. However, SpamBayes learns quickly so > it shouldn't hurt to start over and see what happens. Since > you know the size of your DB, you've obviously located the > file. You will probably see two files with the *.db > extension, one is the training data and the other contains > information about the messages that have been processed. Just > close Outlook, delete these 2 files, then restart Outlook and > SpamBayes should recreate the databases. From jsp at PKC.com Wed Oct 12 15:26:23 2005 From: jsp at PKC.com (Jesse Pelton) Date: Wed, 12 Oct 2005 09:26:23 -0400 Subject: [Spambayes] Backup daqtabase Message-ID: <16E2027582CDB74180896CDB4B8CC1F901D04461@PKCVT01.pkc.com> That's probably it. My recollection is hazy at best; this may indicate that I failed to pay sufficiently close attention as I read, which likely also led to misunderstanding the message. > -----Original Message----- > From: skip at pobox.com [mailto:skip at pobox.com] > Sent: Tuesday, October 11, 2005 4:02 PM > To: Jesse Pelton > Cc: Tim Peters; spambayes at python.org; david at treworgans.co.uk > Subject: Re: [Spambayes] Backup daqtabase > > > Jesse> I'm pretty sure I've seen discussion on the list > of a training > Jesse> regimen that involved discarding aged messages... > > I use a so-called "train to exhaustion" regime (*). One part > of my current > implementation is to always process messages from newest to > oldest. That > way older messages carry less weight (they will more likely be scored > correctly because newer messages have already contributed > their contents to > the training database). Is that what you were thinking of? > > Skip > > (*) http://www.garyrobinson.net/2004/02/spam_filtering_.html > > http://cvs.sourceforge.net/viewcvs.py/spambayes/spambayes/cont > rib/tte.py?rev=1.16&view=markup > > From philipp.schaefer at kochan.de Wed Oct 12 16:29:47 2005 From: philipp.schaefer at kochan.de (Philipp Schaefer) Date: Wed, 12 Oct 2005 16:29:47 +0200 Subject: [Spambayes] help: strange files in c:\ directory - from SpamBayes? Message-ID: <200510121429.j9CETiC7031198@mx.kochan.de> Hi! I'm new to the list, working in Germany in a design company. I use SpamBayes now for quite a time and it's the best spam filtering tool I know. Problem: All spam is put into strange files in my "root" (C:\) like: s2cc s2cc.1 s2h4 ... (see screen shot attached - haven't found any hint if attachements are allowed on this list. Sorry, if not...) when I open the file, it's just the mil in plain text with all headers tec. This adds up to hundreds of files, I have to delete them manually... The files from the current session are locked - I can only access the files from older days. SpamBayes itself works perfect and handles mail as expected. My Question: Is SpamBayes causing this? Or do I have another problem? Tahnk you very much for any hint! Best! /philipp My system: OS: Windows XP SP2 Addin Binary Version 1.0.4 log file: ******************** Warning: option experimental_ham_spam_imbalance_adjustment in section Classifier is deprecated Loaded bayes database from 'C:\Dokumente und Einstellungen\Philipp Schaefer\Anwendungsdaten\SpamBayes\default_bayes_database.db' Loaded message database from 'C:\Dokumente und Einstellungen\Philipp Schaefer\Anwendungsdaten\SpamBayes\default_message_database.db' Bayes database initialized with 1363 spam and 685 good messages SpamBayes Outlook Addin Binary Version 1.0.4 (March 2005) starting (with engine SpamBayes Engine Version 0.3 (January 2004)) on Windows 5.1.2600 (Service Pack 2) using Python 2.3.5 (#62, Feb 8 2005, 16:23:02) [MSC v.1200 32 bit (Intel)] SpamBayes: Watching (for filtering) in 'Pers?nliche Ordner/Posteingang' SpamBayes: Watching (for incremental training) in 'Pers?nliche Ordner/Junk-E-Mail' Processing missed spam in folder 'Posteingang' by starting a timer FAILED to add the toolbar item 'SpamBayesCommand.Manager' - (-2147352567, 'Ausnahmefehler aufgetreten.', (0, None, None, None, 0, -2147467259), None) The above toolbar message is common - recreating the toolbar... FAILED to add the toolbar item 'SpamBayesCommand.Manager' - (-2147352567, 'Ausnahmefehler aufgetreten.', (0, None, 'Mitglied nicht gefunden.', None, 0, -2147467259), None) The above toolbar message is common - recreating the toolbar... Message 'openBC: Sie haben eine neue Nachricht von Sybille Steidinger' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' FAILED to add the toolbar item 'SpamBayesCommand.Manager' - (-2147352567, 'Ausnahmefehler aufgetreten.', (0, None, 'Mitglied nicht gefunden.', None, 0, -2147467259), None) The above toolbar message is common - recreating the toolbar... Message '#18701 AWO Abnahme & Abschluss' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'RE: Krankenversicherung' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Re: #18701 AWO Abnahme & Abschluss' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'openBC: Sie haben eine neue Nachricht von Johannes F. Woll' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Re: #18701 AWO Abnahme & Abschluss' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Re: #18701 AWO Abnahme & Abschluss' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' FAILED to add the toolbar item 'SpamBayesCommand.Manager' - (-2147352567, 'Ausnahmefehler aufgetreten.', (0, None, 'Mitglied nicht gefunden.', None, 0, -2147467259), None) The above toolbar message is common - recreating the toolbar... Message 'Abwesenheitsnotiz: Layouts / Projektplan Relaunch Mariaberer Heime e.V.' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' FAILED to add the toolbar item 'SpamBayesCommand.Manager' - (-2147352567, 'Ausnahmefehler aufgetreten.', (0, None, 'Mitglied nicht gefunden.', None, 0, -2147467259), None) The above toolbar message is common - recreating the toolbar... Message 'Zugesagt: Raumplanung neue Struktur' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'AW: #18701 AWO Abnahme & Abschluss' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Your Daily Dilbert' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Antons Geburtstags Geschenk' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Mobil-Content und -Werbung auf dem Weg in den Massenmarkt - iBusiness Daily Edition vom 12.10.05' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Unternehmen wollen in EMail- und Chatloesungen investieren - iBusiness Weekly Edition vom 12.10.05' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Weltmeister vs China' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Herr Sch?tze/CAL' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Eine Erg?nzung unter "Logo"' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Current version is 1.04, latest is 1.04. Message 'Tony's Blog: Guy Kawasaki -- Rule No. 3: Jump to the Next Curve' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Cancelling wizard Saving configuration -> C:\Dokumente und Einstellungen\Philipp Schaefer\Anwendungsdaten\SpamBayes\Outlook - IMAP.ini SpamBayes: Watching (for filtering) in 'Pers?nliche Ordner/Posteingang' SpamBayes: Watching (for incremental training) in 'Pers?nliche Ordner/Junk-E-Mail' Saving configuration -> C:\Dokumente und Einstellungen\Philipp Schaefer\Anwendungsdaten\SpamBayes\Outlook - IMAP.ini Message 'Your confirmation is required to join the SpamBayes mailing list' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Message 'Welcome to the "SpamBayes" mailing list (Digest mode)' in 'Pers?nliche Ordner/Posteingang' had a Spam classification of 'No' Saving configuration -> C:\Dokumente und Einstellungen\Philipp Schaefer\Anwendungsdaten\SpamBayes\Outlook - IMAP.ini SpamBayes: Watching (for filtering) in 'Pers?nliche Ordner/Posteingang' SpamBayes: Watching (for incremental training) in 'Pers?nliche Ordner/Junk-E-Mail' Saving configuration -> C:\Dokumente und Einstellungen\Philipp Schaefer\Anwendungsdaten\SpamBayes\Outlook - IMAP.ini SpamBayes: Watching (for filtering) in 'Pers?nliche Ordner/Posteingang' SpamBayes: Watching (for incremental training) in 'Pers?nliche Ordner/Junk-E-Mail' ******************** -- /Philipp Schaefer Karl-Theodor-Str. 104 / 80796 Munich / Germany +49 (0)89 32 66 77 04 / +49 (0)172 812 75 61 mail at philipp-schaefer.de / www.philipp-schaefer.de -------------- next part -------------- A non-text attachment was scrubbed... Name: problem.jpg Type: image/jpeg Size: 115844 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051012/8f0a2707/problem-0001.jpg From tameyer at ihug.co.nz Thu Oct 13 05:39:45 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Thu, 13 Oct 2005 16:39:45 +1300 Subject: [Spambayes] help: strange files in c:\ directory - from SpamBayes? In-Reply-To: <200510121429.j9CETiC7031198@mx.kochan.de> References: <200510121429.j9CETiC7031198@mx.kochan.de> Message-ID: > All spam is put into strange files in my "root" (C:\) like: > s2cc > s2cc.1 > s2h4 > ... [...] > when I open the file, it's just the mil in plain text with all > headers tec. [...] > Is SpamBayes causing this? Or do I have another problem? It's definitely not SpamBayes. No idea what it might be, either, sorry. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From mournfulness at jaystrains.com Thu Oct 13 21:24:58 2005 From: mournfulness at jaystrains.com (Leila Akers) Date: Thu, 13 Oct 2005 21:24:58 +0200 (CEST) Subject: [Spambayes] Suitable for All Occasions Message-ID: <10440112396.6668756855@c-67-171-141-203.hsd1.or.comcast.net> want a Rolex? http://Petersen.lzac.com/re/dir/ BRUTE, n. See HUSBAND. Hope is nature's veil for hiding truth's nakedness. Start every day with a smile and get it over with. Moral indignation is jealousy with a halo. A Multitasking Timex Sinclair Science is nothing but trained and organized common sense. To pity distress is but human; to relieve it is Godlike. Dont' play for safety- it's the most dangerous thing in the world. I don't really trust a sane person. From fjskh at telkom.net Fri Oct 14 06:10:32 2005 From: fjskh at telkom.net (FJ Soekahar) Date: Fri, 14 Oct 2005 11:10:32 +0700 Subject: [Spambayes] SpamBayes activation Message-ID: <000e01c5d07a$b3be2e20$c001a8c0@TOSHIBA> Dear Sirs, I have downloaded and installed your Spambayes few days ago. I am currently using two email clients i.e. Outlook Express 6.0 and Eudora 6.2.1.2. will soon use another on Incredimail too. Since I installed the program, I have trained it with 111 spams and 27 hams for both mail clients. But I haven't seen the Spambayes block any spam in may mail clients, same spams keep on coming every day. Does it needs an activation or something? How to do it? I am looking forward to hearing from you in return.. Best regards, FJ Soekahar -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051014/66704923/attachment.htm From mpankow at hot.rr.com Fri Oct 14 20:02:12 2005 From: mpankow at hot.rr.com (Lisa Pankow) Date: Fri, 14 Oct 2005 13:02:12 -0500 Subject: [Spambayes] URGENT-Stalker and Message Boards Message-ID: <200510141802.j9EI2BB3013235@ms-smtp-05-eri0.texas.rr.com> I am currently dealing with an internet stalker and would VERY much appreciate it if you can take down my information in the links below: http://mail.python.org/pipermail/spambayes/2005-August/017709.html http://www.mail-archive.com/spambayes at python.org/msg02247.html http://www.mail-archive.com/spambayes at python.org/msg02248.html If this could be done ASAP, I would be MOST grateful! Thank you, Lisa P. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051014/b17b6b4f/attachment.htm From tim.peters at gmail.com Fri Oct 14 20:20:34 2005 From: tim.peters at gmail.com (Tim Peters) Date: Fri, 14 Oct 2005 14:20:34 -0400 Subject: [Spambayes] URGENT-Stalker and Message Boards In-Reply-To: <200510141802.j9EI2BB3013235@ms-smtp-05-eri0.texas.rr.com> References: <200510141802.j9EI2BB3013235@ms-smtp-05-eri0.texas.rr.com> Message-ID: <1f7befae0510141120t75eaa7ch27f3f209a9568f69@mail.gmail.com> [Lisa Pankow] > I am currently dealing with an internet stalker and would VERY much > appreciate it if you can take down my information in the links below: I'm sorry, but as you've discovered, public mailing lists get duplicated all over the world. In general nothing can be done to remove messages from their archives. For example, there's nothing I can do to change anything in the "official" SpamBayes archives, despite that I'm an administrator for this list: the machine on which the mailing list software runs isn't even in the same country, and I have no access to it. We have no connection of any kind to www.mail-archive.com, or to any other copy you might find. While you found a few copies of your message, there are more; for example, http://article.gmane.org/gmane.mail.spam.spambayes.general/17584 It's not my intent to depress you ;-), but to get across that what you want can't be done. I would if I could. From kerryg at wildhobbies.com Fri Oct 14 20:28:34 2005 From: kerryg at wildhobbies.com (Kerry Garrison) Date: Fri, 14 Oct 2005 11:28:34 -0700 Subject: [Spambayes] UNSUBSCRIBE In-Reply-To: <1f7befae0510141120t75eaa7ch27f3f209a9568f69@mail.gmail.com> Message-ID: <002701c5d0ed$16a89260$a602a8c0@Kerry01> UNSUBSCRIBE PLEASE FOR THE LOVE OF GOD TAKE ME OFF THIS IMPOSSIBLE TO GET OFF OF LIST!!! I HAVE UNSUBSCRIBED MORE TIMES THAN I CAN COUNT AND I STILL GET FREAKING EMAILS - FIX THE SYSTEM SO I CAN STOP GETTING EMAILS BEFORE I SIGN UP EVERY PERSON I DON'T LIKE TO THIS LIST SO THEY CANT EVER GET THEMSELVES OFF OT IT EITHER. From tim.peters at gmail.com Fri Oct 14 20:45:01 2005 From: tim.peters at gmail.com (Tim Peters) Date: Fri, 14 Oct 2005 14:45:01 -0400 Subject: [Spambayes] UNSUBSCRIBE In-Reply-To: <002701c5d0ed$16a89260$a602a8c0@Kerry01> References: <1f7befae0510141120t75eaa7ch27f3f209a9568f69@mail.gmail.com> <002701c5d0ed$16a89260$a602a8c0@Kerry01> Message-ID: <1f7befae0510141145j31bad8e7q4f4a633dac285f87@mail.gmail.com> [Kerry Garrison] > UNSUBSCRIBE > > PLEASE FOR THE LOVE OF GOD TAKE ME OFF THIS IMPOSSIBLE TO > GET OFF OF LIST!!! I checked, and kerryg at wildhobbies.com is not subscribed to this list. You're not getting messages from this list from us, at least not to that address. Is it possible you subscribed using a different address? That someone else is forwarding messages to you? That a corporate email address is subscribed? That someone else has access to your email account and is maliciously subscribing you without your knowledge? > I HAVE UNSUBSCRIBED MORE TIMES THAN I CAN COUNT AND I STILL > GET FREAKING EMAILS - FIX THE SYSTEM As above, there's no evidence I can find that anything is wrong with the system. > SO I CAN STOP GETTING EMAILS BEFORE I SIGN UP EVERY PERSON > I DON'T LIKE TO THIS LIST SO THEY CANT EVER GET THEMSELVES OFF > OT IT EITHER. You're welcome to try ;-) If you do, you'll discover that you cannot subscribe other people to this list. From kirebrow at yahoo.com Fri Oct 14 22:26:20 2005 From: kirebrow at yahoo.com (Erik Brown) Date: Fri, 14 Oct 2005 15:26:20 -0500 Subject: [Spambayes] UNSUBSCRIBE In-Reply-To: <002701c5d0ed$16a89260$a602a8c0@Kerry01> Message-ID: <20051014192623.UOGH12438.ibm63aec.bellsouth.net@ENLIGHTENED> Have you considered training them as spam? Erik Brown -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Kerry Garrison Sent: Friday, October 14, 2005 1:29 PM To: spambayes at python.org Subject: [Spambayes] UNSUBSCRIBE UNSUBSCRIBE PLEASE FOR THE LOVE OF GOD TAKE ME OFF THIS IMPOSSIBLE TO GET OFF OF LIST!!! I HAVE UNSUBSCRIBED MORE TIMES THAN I CAN COUNT AND I STILL GET FREAKING EMAILS - FIX THE SYSTEM SO I CAN STOP GETTING EMAILS BEFORE I SIGN UP EVERY PERSON I DON'T LIKE TO THIS LIST SO THEY CANT EVER GET THEMSELVES OFF OT IT EITHER. _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From mhewitt at web.de Sat Oct 15 11:23:29 2005 From: mhewitt at web.de (Manuel Hewitt) Date: Sat, 15 Oct 2005 11:23:29 +0200 Subject: [Spambayes] Whitelisting for spam reports Message-ID: <1174638287.20051015112329@web.de> Hi i would really like to see a whitelist implemented. Here is why: i report spam to spamcop and sometimes i get replies from the abuse appartments. These replies include almost always the old spam message that i reported. I think it would be good for the detection accuracy of ham/spam if these replies where not entered in the database. One half of these emails consist of spamtokens and the other half not. Doesn't this confuse the filters? I think, it does. I mark these messages as ham, because they are ham. And so i decrease the spam probability of the spam words that were quoted in the mail. I know that WL is not useful as a substitute for good filters in the email client. I filter my friends out before the spam filter does its work. I could also filter out the spamcop reports, but that is not the point. I still don't want these "hybrid" mails entered in the database. As a normal PC user i don't have access to the mailserver, so i can't redirect these messages before they reach my PC. From tameyer at ihug.co.nz Sat Oct 15 13:25:46 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 00:25:46 +1300 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <1174638287.20051015112329@web.de> References: <1174638287.20051015112329@web.de> Message-ID: > i would really like to see a whitelist implemented. Please see FAQ 6.6: > i report spam to spamcop and sometimes i get replies from the abuse > appartments. These replies include almost always the old spam message > that i reported. Any mail client should let you handle these in whatever fashion you like before any rule involving SpamBayes occurs, and there's no reason why you need to train on this. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From mhewitt at web.de Sat Oct 15 15:57:47 2005 From: mhewitt at web.de (Manuel Hewitt) Date: Sat, 15 Oct 2005 15:57:47 +0200 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: References: <1174638287.20051015112329@web.de> Message-ID: <184020248.20051015155747@web.de> > Please see FAQ 6.6: yeah, yeah, i know this >> i report spam to spamcop and sometimes i get replies from the abuse >> appartments. These replies include almost always the old spam message >> that i reported. > Any mail client should let you handle these in whatever fashion you > like before any rule involving SpamBayes occurs, sure, that is not the problem. But before they went through spambayes > and there's no > reason why you need to train on this. So, you say that i should discard any of these messages manually everytime? From rcoe at CambridgeMA.GOV Sat Oct 15 16:18:28 2005 From: rcoe at CambridgeMA.GOV (Coe, Bob) Date: Sat, 15 Oct 2005 10:18:28 -0400 Subject: [Spambayes] UNSUBSCRIBE Message-ID: <42393C9DA7930245AB540667607F4F500524310D@SPIKE.city> I was all set to ignore this whiner totally, but something in your reply puzzles me a little: If you can't subscribe other people to the list, how could someone have subscribed a corporate email address? (I'm assuming you meant a corporate mailing list of which Mr Garrison is a member.) > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Tim Peters > Sent: Friday, October 14, 2005 2:45 PM > To: Kerry Garrison > Cc: spambayes at python.org > Subject: Re: [Spambayes] UNSUBSCRIBE > > > [Kerry Garrison] > > UNSUBSCRIBE > > > > PLEASE FOR THE LOVE OF GOD TAKE ME OFF THIS IMPOSSIBLE TO > > GET OFF OF LIST!!! > > I checked, and kerryg at wildhobbies.com is not subscribed to this list. > You're not getting messages from this list from us, at least > not to that address. Is it possible you subscribed using a > different address? That someone else is forwarding messages > to you? That a corporate email address is subscribed? That > someone else has access to your email account and is > maliciously subscribing you without your knowledge? > > > I HAVE UNSUBSCRIBED MORE TIMES THAN I CAN COUNT AND I STILL GET > > FREAKING EMAILS - FIX THE SYSTEM > > As above, there's no evidence I can find that anything is > wrong with the system. > > > SO I CAN STOP GETTING EMAILS BEFORE I SIGN UP EVERY PERSON > > I DON'T LIKE TO THIS LIST SO THEY CANT EVER GET THEMSELVES > OFF OT IT > > EITHER. > > You're welcome to try ;-) If you do, you'll discover that > you cannot subscribe other people to this list. > _______________________________________________ > SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html > From skip at pobox.com Sat Oct 15 16:19:58 2005 From: skip at pobox.com (skip@pobox.com) Date: Sat, 15 Oct 2005 09:19:58 -0500 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <184020248.20051015155747@web.de> References: <1174638287.20051015112329@web.de> <184020248.20051015155747@web.de> Message-ID: <17233.4110.173622.182488@montanaro.dyndns.org> Manuel> So, you say that i should discard any of these messages manually Manuel> everytime? No, place a filter in your mail user agent's filter configuration that saves these messages off to a mailbox before SpamBayes sees them. Example: I use procmail to filter my email. On my server I generate up to 500 email-based reports each night. I know they are okay, so I have a recipe that saves them off to a file before the recipe that runs SpamBayes: SCORE="sb_bnfilter.py -a 30 -A 250" ... # since I'm filtering on a highly specific subject it's unlikely I will # get any spam in this mailbox :0: * ^Subject.*(fetch-tn|fetchtour|Musi-Cal (Tour Fetch|Notification)|Unmatched CC Venues) tourfetch :0 fw | $SCORE -- Skip Montanaro Katrina Benefit Concerts: http://www.musi-cal.com/katrina skip at pobox.com From richie at entrian.com Sat Oct 15 17:11:29 2005 From: richie at entrian.com (Richie Hindle) Date: Sat, 15 Oct 2005 16:11:29 +0100 Subject: [Spambayes] UNSUBSCRIBE In-Reply-To: <42393C9DA7930245AB540667607F4F500524310D@SPIKE.city> References: <42393C9DA7930245AB540667607F4F500524310D@SPIKE.city> Message-ID: [Bob] > If you can't subscribe other people to the list, > how could someone have subscribed a corporate email address? (I'm > assuming you meant a corporate mailing list of which Mr Garrison is a > member.) When you subscribe a given email address, Mailman will send a confirmation message to that address. You have to then reply to that message, or visit a URL given in it, before your subscription activates. So to be pendantic, Tim should have said "You can't subscribe an address whose email you cannot read." -- Richie Hindle richie at entrian.com From mhewitt at web.de Sat Oct 15 17:41:27 2005 From: mhewitt at web.de (Manuel Hewitt) Date: Sat, 15 Oct 2005 17:41:27 +0200 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <17233.4110.173622.182488@montanaro.dyndns.org> References: <1174638287.20051015112329@web.de> <184020248.20051015155747@web.de> <17233.4110.173622.182488@montanaro.dyndns.org> Message-ID: <1487125319.20051015174127@web.de> Hallo skip, Am Samstag, 15. Oktober 2005 hast du geschrieben: > Manuel> So, you say that i should discard any of these messages manually > Manuel> everytime? > No, place a filter in your mail user agent's filter configuration that > saves these messages off to a mailbox before SpamBayes sees them. As i said, i am a normal user and i use a freemail account. I can't intercept messages on the server before they are delivered to me. I know that this is no problem if i had access to the mailserver, but Spambayes is also for endusers and in this case a whitelist is useful (=read: the only possibility). -- Mit freundlichen Gruessen, Manuel From rcoe at CambridgeMA.GOV Sat Oct 15 18:11:35 2005 From: rcoe at CambridgeMA.GOV (Coe, Bob) Date: Sat, 15 Oct 2005 12:11:35 -0400 Subject: [Spambayes] Whitelisting for spam reports Message-ID: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> The idea isn't to intercept the messages on the server; it's to intercept them on the client before they're dumped into your inbox. The theory is that most mail clients will run their own classification rules on incoming messages before making them available to Spambayes. Outlook doesn't, which is why the Outlook version of Spambayes allows you to delay application of its clasification rules until (one hopes) Outlook is finished. Bob > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Manuel Hewitt > Sent: Saturday, October 15, 2005 11:41 AM > To: spambayes > Subject: Re: [Spambayes] Whitelisting for spam reports > > > Hallo skip, > > Am Samstag, 15. Oktober 2005 hast du geschrieben: > > > Manuel> So, you say that i should discard any of these messages manually > > Manuel> everytime? > > > No, place a filter in your mail user agent's filter configuration that > > saves these messages off to a mailbox before SpamBayes sees them. > > As i said, i am a normal user and i use a freemail account. I > can't intercept messages on the server before they are > delivered to me. I know that this is no problem if i had > access to the mailserver, but Spambayes is also for endusers > and in this case a whitelist is useful (=read: the only possibility). > > -- > Mit freundlichen Gruessen, > Manuel From tim.peters at gmail.com Sat Oct 15 18:21:33 2005 From: tim.peters at gmail.com (Tim Peters) Date: Sat, 15 Oct 2005 12:21:33 -0400 Subject: [Spambayes] UNSUBSCRIBE In-Reply-To: <42393C9DA7930245AB540667607F4F500524310D@SPIKE.city> References: <42393C9DA7930245AB540667607F4F500524310D@SPIKE.city> Message-ID: <1f7befae0510150921y1cfcc68dv4ff1a2fe181d6406@mail.gmail.com> [Coe, Bob] > I was all set to ignore this whiner totally, but something in your reply > puzzles me a little: If you can't subscribe other people to the list, > how could someone have subscribed a corporate email address? (I'm > assuming you meant a corporate mailing list of which Mr Garrison is a > member.) I agree I could have been clearer ;-) RIchie explained one meaning. The one I had in mind is probably what you have in mind there, and seems more common: _someone_ at a company subscribes to a Mailman list with a corporate-internal mailing-list address, and then everyone on that company list gets the Mailman list traffic. Corporate communication being what it is ;-), often the end users have no idea why they're getting this stuff, and harangue the Mailman list owner to get them off. As it turned out, the OP in this case was getting this list's traffic via a generic "info at XYZ.com" subscribed address. Since the conversation wasn't particularly pleasant , I didn't press to find out whether the OP subscribed that address themself, or was a victim of corporate, umm, enthusiasm. From mhewitt at web.de Sat Oct 15 20:41:00 2005 From: mhewitt at web.de (Manuel Hewitt) Date: Sat, 15 Oct 2005 20:41:00 +0200 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> Message-ID: <577481328.20051015204100@web.de> Hallo Bob, Am Samstag, 15. Oktober 2005 hast du geschrieben: > The idea isn't to intercept the messages on the server; it's to > intercept them on the client before they're dumped into your inbox. The > theory is that most mail clients will run their own classification rules > on incoming messages before making them available to Spambayes. Outlook > doesn't, which is why the Outlook version of Spambayes allows you to > delay application of its clasification rules until (one hopes) Outlook > is finished. Maybe it's my bad english, but i don't understand this. To use Spambayes as a enduser there is only the pop3proxy, the imapfilter and the Outlook plugin. I don't use Outlook or IMAP, so the only possibility is to use the pop3proxy. Every email i get will be processed by Spambayes and i see no way around it. And i esp. don't understand: > The > theory is that most mail clients will run their own classification rules > on incoming messages before making them available to Spambayes. Most email clients can only apply their classification _after_ the emails were available to Spambayes. That is the way i understand the concept of Spambayes. To make it clear: My email client doesn't classify anything. The email client has only to filter the emails according to the classification done by Spambayes. It is no problem to sort the spamcop replies out, because they can be recognized by their email address easily. But that is not the point. The emails still went throught the classification process of Spambayes. I can't train them as spam or ham, because they are ham with spam content inside. This would only reduce the accuracy of the rules. So the only possibility is to discard these messages, but this is annoying because these emails will sometimes be classified as ham, sometimes as spam and mostly as unsure. The only way to handle these kind of emails cleanly without messing the rules is simply to whitelist them. I realize that an average user doesn't need whitelisting, but as soon as get ham emails that are dealing with spam issues, this is an important feature. To comment the FAQ: - as you can see, Spambayes needs in some cases a whitelist. - in my case, spoofing has never been a problem. - ignoring user requests is never a good idea - and, frankly, it isn't hard to code a simple whitelist for a developer that manages to deal with a program like Spambayes The summary of that FAQ answer is simply "No, we don't want a whitelist and we are not going to code one." I'd rather accept this answer instead of the lengthy excuses. From richie at entrian.com Sat Oct 15 21:08:18 2005 From: richie at entrian.com (Richie Hindle) Date: Sat, 15 Oct 2005 20:08:18 +0100 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <577481328.20051015204100@web.de> References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> <577481328.20051015204100@web.de> Message-ID: Manuel, > Maybe it's my bad english, but i don't understand this. Let me try to explain by example. At the moment you use the SpamBayes POP3 proxy to classify your email, and you presumably have a rule set up in your email client to filter spam into a separate folder. For example, my rule looks like this: Where the "X-Spambayes-Classification" header contains "spam", file in folder: "Suspected spam" That rule puts suspected spam into its own folder. (Maybe you're using the Subject: or To: header rather than the "X-Spambayes-Classification" header, but hopefully this is familiar.) What we're suggesting for whitelisting is that you add an additional rule in your email client that looks something like this: Where the "From" header contains "spamcop", file in folder: "Inbox" You give that rule a higher priority than your SpamBayes rule, and the spamcop mail ends up in the "Inbox" folder rather than the "Suspected spam" folder. This *is* whitelisting. All email clients already support it. When, as you say: > The summary of that FAQ answer is simply "No, we don't want a whitelist > and we are not going to code one." you are exactly right, but there is a good reason - you already *have* whitelisting, in the form of the filtering system that you are already using to file away the email that SpamBayes has classified as spam. You're right that you can't meaningfully train on your spamcop replies because they are part spam and part ham, but by overriding your SpamBayes rule with a whitelist rule, it no longer matters what classification SpamBayes gives them. Does that make sense? -- Richie Hindle richie at entrian.com From mhewitt at web.de Sat Oct 15 21:23:53 2005 From: mhewitt at web.de (Manuel Hewitt) Date: Sat, 15 Oct 2005 21:23:53 +0200 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> <577481328.20051015204100@web.de> Message-ID: <18592951.20051015212353@web.de> Hallo Richie, > You give that rule a higher priority than your SpamBayes rule, and the > spamcop mail ends up in the "Inbox" folder rather than the "Suspected > spam" folder. Yes. i know that and i have several filters that overrule the SPAM filter, for friends, online banking, all the normal stuff. But that is not the point i am talking about, see below. > You're right that you can't meaningfully train on your spamcop replies > because they are part spam and part ham, but by overriding your SpamBayes > rule with a whitelist rule, it no longer matters what classification > SpamBayes gives them. Yes, but this way i have always to look on the review page if there is a spamcop reply either in the category ham, in spam or in unsure and have to select "discard". I 'd like to have a possibility to "auto-discard" these emails in Spambayes. I could also call this "ignore list". It is a function that would make reviewing easier for the user. From tameyer at ihug.co.nz Sun Oct 16 00:11:05 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 11:11:05 +1300 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <1487125319.20051015174127@web.de> References: <1174638287.20051015112329@web.de> <184020248.20051015155747@web.de> <17233.4110.173622.182488@montanaro.dyndns.org> <1487125319.20051015174127@web.de> Message-ID: <1D9FDD71-DC5D-49C3-92E9-23EDE27B6D05@ihug.co.nz> >>> So, you say that i should discard any of these messages manually >>> everytime? >> >> No, place a filter in your mail user agent's filter configuration >> that >> saves these messages off to a mailbox before SpamBayes sees them. > > As i said, i am a normal user and i use a freemail account. I can't > intercept messages on the server before they are delivered to me. I > know > that this is no problem if i had access to the mailserver, but > Spambayes > is also for endusers and in this case a whitelist is useful (=read: > the > only possibility). Any mail client lets you filter out messages; you don't have to do this server-side. If you don't want to train on these messages, then don't. If you really want whitelisting, then FAQ 6.6 explains what needs to be done to add it. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 16 00:22:47 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 11:22:47 +1300 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <18592951.20051015212353@web.de> References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> <577481328.20051015204100@web.de> <18592951.20051015212353@web.de> Message-ID: <71FAADCA-6C3F-492F-A110-23BFD78D8DE0@ihug.co.nz> > Yes, but this way i have always to look on the review page if there > is a > spamcop reply either in the category ham, in spam or in unsure and > have > to select "discard". I 'd like to have a possibility to "auto-discard" > these emails in Spambayes. I could also call this "ignore list". > It is a function that would make reviewing easier for the user. This isn't whitelisting, though, it's something else. Even if SpamBayes included whitelisting, there's no reason to think that whitelisted messages would be excluded from the sb_server review page. Assuming that you're training only on any mistakes & unsures, then both ham and spam should be set to default to 'discard' anyway. Is it really that much of a problem to have these in the list when they don't cause any extra work? > To comment the FAQ: > - as you can see, Spambayes needs in some cases a whitelist. There isn't agreement about this. > - ignoring user requests is never a good idea Open-source is a scratch-your-own-itch world. It's not like we have a great deal of time to work on SpamBayes, or that we're getting any financial reward out of doing so. (Having more non-contributing users is in some ways a net negative, because it just adds to the support load). > - and, frankly, it isn't hard to code a simple whitelist for a > developer > that manages to deal with a program like Spambayes So write one and submit a patch. However, you're wrong. Have you read the comments from Mark that are linked to from that FAQ entry? They discuss the difficulty of adding whitelisting (he's talking about adding to the Outlook plug-in, but it mostly all applies to sb_server as well). > The summary of that FAQ answer is simply "No, we don't want a > whitelist > and we are not going to code one." I'd rather accept this answer > instead > of the lengthy excuses. A better summary would be "Whitelisting is a flawed technique and would generally make results worse; since open-source relies on user contributions, and the developers have no interest in adding whitelisting, this is unlikely to be done. If a user wished to supply a patch, it would probably be accepted; however, adding this feature is fairly complicated for these reasons..." =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From mhewitt at web.de Sun Oct 16 00:51:10 2005 From: mhewitt at web.de (Manuel Hewitt) Date: Sun, 16 Oct 2005 00:51:10 +0200 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <71FAADCA-6C3F-492F-A110-23BFD78D8DE0@ihug.co.nz> References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> <577481328.20051015204100@web.de> <18592951.20051015212353@web.de> <71FAADCA-6C3F-492F-A110-23BFD78D8DE0@ihug.co.nz> Message-ID: <689327065.20051016005110@web.de> Hallo Tony, > Assuming that you're training only on any mistakes & unsures, then > both ham and spam should be set to default to 'discard' anyway. Is > it really that much of a problem to have these in the list when they > don't cause any extra work? Well, that does only apply if the assumption is valid. I prefer to always train everything to keep my filter up2date. > Open-source is a scratch-your-own-itch world. It's not like we have > a great deal of time to work on SpamBayes, or that we're getting any > financial reward out of doing so. (Having more non-contributing > users is in some ways a net negative, because it just adds to the > support load). This is your point-of-view. And luckily most OS projects don't think this way. > So write one and submit a patch. However, you're wrong. Have you > read the comments from Mark that are linked to from that FAQ entry? > They discuss the difficulty of adding whitelisting (he's talking > about adding to the Outlook plug-in, but it mostly all applies to > sb_server as well). OK, my fault, i think i overrated the abilities of the developers. From bill.hely at helyholdings.com Sun Oct 16 01:01:54 2005 From: bill.hely at helyholdings.com (Bill Hely) Date: Sun, 16 Oct 2005 09:01:54 +1000 Subject: [Spambayes] Spam target folder restriction Message-ID: QUESTION: Is there a good reason why there is no option to direct spam straight to the Deleted Items folder? It's not as if it is something you could do accidentally, as it has to be intentionally set that way in the SB Manager/Filtering tab. I have to archive all my spam for a few months, but I'm just curious why one is not allowed to do it. - Bill H. -- We take security very seriously. All outgoing mail is certified Virus Free. To boost YOUR security visit The Hacker's Nightmare: http://HackersNightmare.com. Checked by AVG Anti-Virus. Version: 7.0.344 / Virus Database: 267.12.1/135 - Release Date: 15/10/2005 From tameyer at ihug.co.nz Sun Oct 16 01:23:29 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 12:23:29 +1300 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <689327065.20051016005110@web.de> References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> <577481328.20051015204100@web.de> <18592951.20051015212353@web.de> <71FAADCA-6C3F-492F-A110-23BFD78D8DE0@ihug.co.nz> <689327065.20051016005110@web.de> Message-ID: >> Assuming that you're training only on any mistakes & unsures, then >> both ham and spam should be set to default to 'discard' anyway. Is >> it really that much of a problem to have these in the list when they >> don't cause any extra work? > > Well, that does only apply if the assumption is valid. I prefer to > always train everything to keep my filter up2date. Research has shown, in every case, that this will give you inferior results to training on errors & unsures only. >> So write one and submit a patch. However, you're wrong. Have you >> read the comments from Mark that are linked to from that FAQ entry? >> They discuss the difficulty of adding whitelisting (he's talking >> about adding to the Outlook plug-in, but it mostly all applies to >> sb_server as well). > > OK, my fault, i think i overrated the abilities of the developers. Being insulting is certainly not the way to convince people to do something for you. You didn't answer the question - have you read Mark's comments? Do you have solutions for the problems that he outlines? =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 16 01:27:53 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 12:27:53 +1300 Subject: [Spambayes] Spam target folder restriction In-Reply-To: References: Message-ID: <916586CA-193D-44DC-AF67-A0A2701DE10C@ihug.co.nz> > Is there a good reason why there is no option to direct spam > straight to the Deleted Items folder? Yes. See FAQ 3.11: =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 16 01:28:30 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 12:28:30 +1300 Subject: [Spambayes] SpamBayes activation In-Reply-To: <000e01c5d07a$b3be2e20$c001a8c0@TOSHIBA> References: <000e01c5d07a$b3be2e20$c001a8c0@TOSHIBA> Message-ID: > I have downloaded and installed your Spambayes few days ago. > > I am currently using two email clients i.e. Outlook Express 6.0 and > Eudora 6.2.1.2. will soon use another on Incredimail too. > Since I installed the program, I have trained it with 111 spams and > 27 hams for both mail clients. > > But I haven't seen the Spambayes block any spam in may mail > clients, same spams keep on coming every day. > Does it needs an activation or something? How to do it? SpamBayes doesn't block spam, it classifies it so that you can use the classification to do what you want with it in your mail client (e.g. move it to another folder). You need to set up a rule in your mail clients to filter out mail. In Eudora, you can do this by filtering on the "X-Spambayes- Classification" header - if it's "spam", then SpamBayes thinks it's spam, and if it's "unsure", then SpamBayes is unsure, and if it's "ham", then SpamBayes thinks it's ham. You may be also able to get Incredimail to filter on this header, too, I'm not sure. As Outlook Express is such a limited mail client, you can't filter on arbitrary headers, so you have to get SpamBayes to add the classification to the "To" or "Subject" headers, on which you can filter. FAQ 4.21 explains how to do this. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 16 01:30:30 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 12:30:30 +1300 Subject: [Spambayes] Problem In-Reply-To: References: Message-ID: <6643CB72-6153-4C70-99FD-D877FDE1FC85@ihug.co.nz> > Unable to load Spambayes. > > Error message appears stating that SpamBayes failed to initialize. Which version of SpamBayes is this? It appears that it's failing to load the databases because there's a non-ASCII character in the path to them (e.g. your Windows username has a non-ASCII character). I thought that this bug was fixed in 1.0.4 - if you're not using that, then it would be worth upgrading. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 16 01:33:20 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 12:33:20 +1300 Subject: [Spambayes] Database Corruption In-Reply-To: References: Message-ID: <5FC9CE46-133F-4B2D-B25F-98E05D618F02@ihug.co.nz> > Yesterday I clicked on "Delete as Spam" instead of "delete" when I > was deleting emails from my Outlook. This goof froze the computer > for awhile. After it recovered the message appeared about database > corruption. I tried to delete the whole program from my laptop but > files remained, so I tried to delete as many as I could > individually, but couldn't delete all of them. Figuring, maybe > enough files were deleted, I download your newest free Spambayes, > but it doesn't work, and I still get the message about data > corruption. I try to enable the program and train it, but > regardless, it doesn't work. Delete the files "default_bayes_database.db" and "default_messageinfo_database.db" in your data directory, and that should work. Your data directory will differ depending on what version of Windows you're using; if it's Windows XP, then it will probably be: 'C:\Documents and Settings\{username}\Application Data \SpamBayes'. The 'Application Data' directory is hidden by default, so the easiest way to get to it is to show the 'Address Bar' in an explorer window and type in the path, as above (substituting your username in). =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 16 01:35:19 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 16 Oct 2005 12:35:19 +1300 Subject: [Spambayes] toolbar buttom vanished.... In-Reply-To: <000001c5ce13$fc538680$3400a8c0@pentaiv> References: <000001c5ce13$fc538680$3400a8c0@pentaiv> Message-ID: <406AA3F5-FB6E-425D-914D-E8510B46B102@ihug.co.nz> > The toolbar for spambytes is there, but snce this morning the > ?recover from spam? icon is gone. > > I tried resetting the toolbars and recreating the outcmd.dat file- > but no luck. the other buttons are there, just the recover has > flown the coop... Have you tried everything in FAQ 3.15? =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From claude_jones at levitjames.com Sun Oct 16 01:46:04 2005 From: claude_jones at levitjames.com (Claude Jones) Date: Sat, 15 Oct 2005 19:46:04 -0400 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> <689327065.20051016005110@web.de> Message-ID: <200510151946.04865.claude_jones@levitjames.com> On Saturday 15 October 2005 7:23 pm, Tony Meyer wrote: > > OK, my fault, i think i overrated the abilities of the developers. > > Being insulting is certainly not the way to convince people to do > something for you. You didn't answer the question - have you read > Mark's comments? Do you have solutions for the problems that he > outlines? > > =Tony.Meyer Tony: Your patience is a marvel to behold. I belong to many open source lists, but I can't remember encountering such an attitude - it's certainly in violation of the very spirit of the open source movement...what a self centered twit! -- Claude Jones Bluemont, VA, USA From skip at pobox.com Sun Oct 16 03:10:14 2005 From: skip at pobox.com (skip@pobox.com) Date: Sat, 15 Oct 2005 20:10:14 -0500 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <1487125319.20051015174127@web.de> References: <1174638287.20051015112329@web.de> <184020248.20051015155747@web.de> <17233.4110.173622.182488@montanaro.dyndns.org> <1487125319.20051015174127@web.de> Message-ID: <17233.43126.820779.710891@montanaro.dyndns.org> >> No, place a filter in your mail user agent's filter configuration >> that saves these messages off to a mailbox before SpamBayes sees >> them. Manuel> As i said, i am a normal user and i use a freemail account. I Manuel> can't intercept messages on the server before they are delivered Manuel> to me. My procmailrc solution does work on the client end. There's nothing "un-normal" about my setup. It's actually pretty common for Linux/Unix users who have not been seduced by Outlook lookalikes. My mail server delivers the message to my computer where procmail filters the mail in front of me reading it. Can you describe your mail server/mail client/SpamBayes setup? -- Skip Montanaro Katrina Benefit Concerts: http://www.musi-cal.com/katrina skip at pobox.com From Amir_Katz at bmc.com Sun Oct 16 11:25:19 2005 From: Amir_Katz at bmc.com (Katz, Amir) Date: Sun, 16 Oct 2005 11:25:19 +0200 Subject: [Spambayes] Whitelisting for spam reports Message-ID: I think he meant to say "...I overrated the abilities of the developers to withstand people like me" :-) -- Amir -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Claude Jones Sent: Sunday, October 16, 2005 01:46 To: spambayes at python.org Subject: Re: [Spambayes] Whitelisting for spam reports On Saturday 15 October 2005 7:23 pm, Tony Meyer wrote: > > OK, my fault, i think i overrated the abilities of the developers. > > Being insulting is certainly not the way to convince people to do > something for you. You didn't answer the question - have you read > Mark's comments? Do you have solutions for the problems that he > outlines? > > =Tony.Meyer Tony: Your patience is a marvel to behold. I belong to many open source lists, but I can't remember encountering such an attitude - it's certainly in violation of the very spirit of the open source movement...what a self centered twit! -- Claude Jones Bluemont, VA, USA _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From richie at entrian.com Sun Oct 16 15:20:04 2005 From: richie at entrian.com (Richie Hindle) Date: Sun, 16 Oct 2005 14:20:04 +0100 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> <577481328.20051015204100@web.de> <18592951.20051015212353@web.de> <71FAADCA-6C3F-492F-A110-23BFD78D8DE0@ihug.co.nz> <689327065.20051016005110@web.de> Message-ID: <37k4l1lpn64k6otfni0rps09f9f5thdf5v@4ax.com> [Manuel] > I prefer to always train everything to keep my filter up2date. [Tony] > Research has shown, in every case, that this will give you inferior > results to training on errors & unsures only. Whether you train on everything, or only on mistakes and unsures, doesn't make a lot of difference to Manuel's argument. Either way, he needs to scan down the list and mentally filter out the spamcop replies - with mistakes and unsures he wouldn't need to click the mouse for many of them, but the fact that they're there makes life harder. I don't think Manuel's request actually counts as whitelisting at all, and I think it's quite reasonable. What he wants (Manuel, correct me if I'm wrong) is to filter out certain senders from the training list. All messages from spamcop would be automatically set to Discard and omitted from the training list. His email client's whitelisting rules would ensure that they ended up in the right place. Any messages that claimed to be from spamcop but weren't would be problem - they would get through the filters, and they would be untrainable, but as I understand it Manuel doesn't have a problem with that (as the FAQ points out, the SpamBayes developers see much more forged senders than ordinary users do). When you look at it like this, I think it's quite a reasonable feature request. I'd appreciate this feature myself (although not enough to spend the time to implement it, I'm afraid). I get a lot of bounce messages from the victims of spammers who are using my address as a forged From address. I wouldn't be comfortable training on them, because they are pretty much indistinguishable from real bounce messages - I have to check myself that the bounced address isn't one that I've sent mail to. I could use this feature to declutter my training lists. > OK, my fault, i think i overrated the abilities of the developers. ...but Tony is dead right - this sort of thing doesn't help. -- Richie Hindle richie at entrian.com From tameyer at ihug.co.nz Sun Oct 16 23:30:51 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Mon, 17 Oct 2005 10:30:51 +1300 Subject: [Spambayes] Whitelisting for spam reports In-Reply-To: <37k4l1lpn64k6otfni0rps09f9f5thdf5v@4ax.com> References: <42393C9DA7930245AB540667607F4F500524310E@SPIKE.city> <577481328.20051015204100@web.de> <18592951.20051015212353@web.de> <71FAADCA-6C3F-492F-A110-23BFD78D8DE0@ihug.co.nz> <689327065.20051016005110@web.de> <37k4l1lpn64k6otfni0rps09f9f5thdf5v@4ax.com> Message-ID: <8B7394E7-6968-454E-A5A3-803FF94E58E1@ihug.co.nz> [Manuel] >> I prefer to always train everything to keep my filter up2date. [Richie] > I don't think Manuel's request actually counts as whitelisting at all, I agree (I said that somewhere else in the thread, I think). > and I think it's quite reasonable. What he wants (Manuel, correct > me if I'm > wrong) is to filter out certain senders from the training list. All > messages from spamcop would be automatically set to Discard and > omitted > from the training list. This is much the same as the existing ability to filter out 'bulk' mail from the training list. > When you look at it like this, I think it's quite a reasonable feature > request. I don't have time to implement this at the moment either. The thing to do, if Manuel (or anyone else interested in this) isn't able to put together a patch himself, would be to open a feature request at . Ideally, don't mention "whitelisting" (someone might mistakenly close it); call it something like "Exclusion list for training list". Someone, at some time, will probably get to it. I suppose the UI for it would just be a text box where you can enter comma separated addresses. If this gets added, is only the "From" header worth considering? Or should there be corresponding options for other headers (e.g. "To", "Subject"). =Tony.Meyer From bill.hely at helyholdings.com Mon Oct 17 10:03:08 2005 From: bill.hely at helyholdings.com (Bill Hely) Date: Mon, 17 Oct 2005 18:03:08 +1000 Subject: [Spambayes] Free SpamBayes eBook Message-ID: Hi all. I have just completed my new eBook titled "Spam Warfare: Microsoft Outlook Edition". It's a comprehensive treatment of spam, built around the SpamBayes Outlook plug-in, and written in end-user language. It's not aimed at you experts but I do need your help. Before going to market I would like to get some informed feedback, so for a few days I'm offering a free copy to any member of the SpamBayes forum willing give me that feedback. All I ask is that you write me a brief critique (ideas, suggestions, corrections) or - even better - a testimonial. The book is a 2MB password-protected PDF. Password and download directions delivered via autoresponder. It's double-opt-in (that is, requires eMail confirmation) because I want to discourage people from signing up their friends. It's you SpamBayes experts I want feedback from for now. For your free copy just send a blank eMail to: mailto:SpamBayesMember at Aweber.com?subject=Warfare-review-copy I'll never share your details with anyone for any reason, and the list will be deleted when this review process is over. Thanks for your interest and assistance. - Bill Hely - Author: "Spam Warfare: Microsoft Outlook Edition" - http://Spam-Warfare.com -- We take security very seriously. All outgoing mail is certified Virus Free. To boost YOUR security visit The Hacker's Nightmare: http://HackersNightmare.com. Checked by AVG Anti-Virus. Version: 7.0.344 / Virus Database: 267.12.2/137 - Release Date: 16/10/2005 From tweber at siemens-emis.com Tue Oct 18 01:10:28 2005 From: tweber at siemens-emis.com (Weber, Anthony A.(Tony)) Date: Mon, 17 Oct 2005 18:10:28 -0500 Subject: [Spambayes] Whitelisting for spam reports Message-ID: Tony, The "whitelist"/"blacklist" capability is very weak in most of the Spam packages I have used. I, and I suspect many others out there, have accumulated quite a lengthy list of addresses that fall into one of the two lists. It would be VERY nice if a text file could be imported into the application to add "whitelist"/"blacklist" entries. There should also be a capability to backup and reload these if possible. Just my $.25. -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of spambayes-request at python.org Sent: Monday, October 17, 2005 5:00 AM To: spambayes at python.org Subject: SpamBayes Digest, Vol 86, Issue 23 Send SpamBayes mailing list submissions to spambayes at python.org To subscribe or unsubscribe via the World Wide Web, visit http://mail.python.org/mailman/listinfo/spambayes or, via email, send a message with subject or body 'help' to spambayes-request at python.org You can reach the person managing the list at spambayes-owner at python.org When replying, please edit your Subject line so it is more specific than "Re: Contents of SpamBayes digest..." Today's Topics: 1. Re: Whitelisting for spam reports (Richie Hindle) 2. Re: Whitelisting for spam reports (Tony Meyer) 3. Free SpamBayes eBook (Bill Hely) ---------------------------------------------------------------------- Message: 1 Date: Sun, 16 Oct 2005 14:20:04 +0100 From: Richie Hindle Subject: Re: [Spambayes] Whitelisting for spam reports To: spambayes at python.org Message-ID: <37k4l1lpn64k6otfni0rps09f9f5thdf5v at 4ax.com> Content-Type: text/plain; charset=us-ascii [Manuel] > I prefer to always train everything to keep my filter up2date. [Tony] > Research has shown, in every case, that this will give you inferior > results to training on errors & unsures only. Whether you train on everything, or only on mistakes and unsures, doesn't make a lot of difference to Manuel's argument. Either way, he needs to scan down the list and mentally filter out the spamcop replies - with mistakes and unsures he wouldn't need to click the mouse for many of them, but the fact that they're there makes life harder. I don't think Manuel's request actually counts as whitelisting at all, and I think it's quite reasonable. What he wants (Manuel, correct me if I'm wrong) is to filter out certain senders from the training list. All messages from spamcop would be automatically set to Discard and omitted from the training list. His email client's whitelisting rules would ensure that they ended up in the right place. Any messages that claimed to be from spamcop but weren't would be problem - they would get through the filters, and they would be untrainable, but as I understand it Manuel doesn't have a problem with that (as the FAQ points out, the SpamBayes developers see much more forged senders than ordinary users do). When you look at it like this, I think it's quite a reasonable feature request. I'd appreciate this feature myself (although not enough to spend the time to implement it, I'm afraid). I get a lot of bounce messages from the victims of spammers who are using my address as a forged From address. I wouldn't be comfortable training on them, because they are pretty much indistinguishable from real bounce messages - I have to check myself that the bounced address isn't one that I've sent mail to. I could use this feature to declutter my training lists. > OK, my fault, i think i overrated the abilities of the developers. ...but Tony is dead right - this sort of thing doesn't help. -- Richie Hindle richie at entrian.com ------------------------------ Message: 2 Date: Mon, 17 Oct 2005 10:30:51 +1300 From: Tony Meyer Subject: Re: [Spambayes] Whitelisting for spam reports To: Richie Hindle Cc: spambayes at python.org Message-ID: <8B7394E7-6968-454E-A5A3-803FF94E58E1 at ihug.co.nz> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed [Manuel] >> I prefer to always train everything to keep my filter up2date. [Richie] > I don't think Manuel's request actually counts as whitelisting at all, I agree (I said that somewhere else in the thread, I think). > and I think it's quite reasonable. What he wants (Manuel, correct > me if I'm > wrong) is to filter out certain senders from the training list. All > messages from spamcop would be automatically set to Discard and > omitted > from the training list. This is much the same as the existing ability to filter out 'bulk' mail from the training list. > When you look at it like this, I think it's quite a reasonable feature > request. I don't have time to implement this at the moment either. The thing to do, if Manuel (or anyone else interested in this) isn't able to put together a patch himself, would be to open a feature request at . Ideally, don't mention "whitelisting" (someone might mistakenly close it); call it something like "Exclusion list for training list". Someone, at some time, will probably get to it. I suppose the UI for it would just be a text box where you can enter comma separated addresses. If this gets added, is only the "From" header worth considering? Or should there be corresponding options for other headers (e.g. "To", "Subject"). =Tony.Meyer ------------------------------ Message: 3 Date: Mon, 17 Oct 2005 18:03:08 +1000 From: "Bill Hely" Subject: [Spambayes] Free SpamBayes eBook To: Message-ID: Hi all. I have just completed my new eBook titled "Spam Warfare: Microsoft Outlook Edition". It's a comprehensive treatment of spam, built around the SpamBayes Outlook plug-in, and written in end-user language. It's not aimed at you experts but I do need your help. Before going to market I would like to get some informed feedback, so for a few days I'm offering a free copy to any member of the SpamBayes forum willing give me that feedback. All I ask is that you write me a brief critique (ideas, suggestions, corrections) or - even better - a testimonial. The book is a 2MB password-protected PDF. Password and download directions delivered via autoresponder. It's double-opt-in (that is, requires eMail confirmation) because I want to discourage people from signing up their friends. It's you SpamBayes experts I want feedback from for now. For your free copy just send a blank eMail to: mailto:SpamBayesMember at Aweber.com?subject=Warfare-review-copy I'll never share your details with anyone for any reason, and the list will be deleted when this review process is over. Thanks for your interest and assistance. - Bill Hely - Author: "Spam Warfare: Microsoft Outlook Edition" - http://Spam-Warfare.com -- We take security very seriously. All outgoing mail is certified Virus Free. To boost YOUR security visit The Hacker's Nightmare: http://HackersNightmare.com. Checked by AVG Anti-Virus. Version: 7.0.344 / Virus Database: 267.12.2/137 - Release Date: 16/10/2005 ------------------------------ _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html End of SpamBayes Digest, Vol 86, Issue 23 ***************************************** From tweber at siemens-emis.com Tue Oct 18 01:16:07 2005 From: tweber at siemens-emis.com (Weber, Anthony A.(Tony)) Date: Mon, 17 Oct 2005 18:16:07 -0500 Subject: [Spambayes] Whitelisting for spam reports Message-ID: P.S. I have tried intercepting these messages using Outlook rules and have been repeatedly frustrated with the small number of rules that Outlook lets you use. It does not work. -----Original Message----- From: Weber, Anthony A.(Tony) Sent: Monday, October 17, 2005 6:10 PM To: 'spambayes at python.org' Subject: Re: [Spambayes] Whitelisting for spam reports Tony, The "whitelist"/"blacklist" capability is very weak in most of the Spam packages I have used. I, and I suspect many others out there, have accumulated quite a lengthy list of addresses that fall into one of the two lists. It would be VERY nice if a text file could be imported into the application to add "whitelist"/"blacklist" entries. There should also be a capability to backup and reload these if possible. Just my $.25. -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of spambayes-request at python.org Sent: Monday, October 17, 2005 5:00 AM To: spambayes at python.org Subject: SpamBayes Digest, Vol 86, Issue 23 Send SpamBayes mailing list submissions to spambayes at python.org To subscribe or unsubscribe via the World Wide Web, visit http://mail.python.org/mailman/listinfo/spambayes or, via email, send a message with subject or body 'help' to spambayes-request at python.org You can reach the person managing the list at spambayes-owner at python.org When replying, please edit your Subject line so it is more specific than "Re: Contents of SpamBayes digest..." Today's Topics: 1. Re: Whitelisting for spam reports (Richie Hindle) 2. Re: Whitelisting for spam reports (Tony Meyer) 3. Free SpamBayes eBook (Bill Hely) ---------------------------------------------------------------------- Message: 1 Date: Sun, 16 Oct 2005 14:20:04 +0100 From: Richie Hindle Subject: Re: [Spambayes] Whitelisting for spam reports To: spambayes at python.org Message-ID: <37k4l1lpn64k6otfni0rps09f9f5thdf5v at 4ax.com> Content-Type: text/plain; charset=us-ascii [Manuel] > I prefer to always train everything to keep my filter up2date. [Tony] > Research has shown, in every case, that this will give you inferior > results to training on errors & unsures only. Whether you train on everything, or only on mistakes and unsures, doesn't make a lot of difference to Manuel's argument. Either way, he needs to scan down the list and mentally filter out the spamcop replies - with mistakes and unsures he wouldn't need to click the mouse for many of them, but the fact that they're there makes life harder. I don't think Manuel's request actually counts as whitelisting at all, and I think it's quite reasonable. What he wants (Manuel, correct me if I'm wrong) is to filter out certain senders from the training list. All messages from spamcop would be automatically set to Discard and omitted from the training list. His email client's whitelisting rules would ensure that they ended up in the right place. Any messages that claimed to be from spamcop but weren't would be problem - they would get through the filters, and they would be untrainable, but as I understand it Manuel doesn't have a problem with that (as the FAQ points out, the SpamBayes developers see much more forged senders than ordinary users do). When you look at it like this, I think it's quite a reasonable feature request. I'd appreciate this feature myself (although not enough to spend the time to implement it, I'm afraid). I get a lot of bounce messages from the victims of spammers who are using my address as a forged From address. I wouldn't be comfortable training on them, because they are pretty much indistinguishable from real bounce messages - I have to check myself that the bounced address isn't one that I've sent mail to. I could use this feature to declutter my training lists. > OK, my fault, i think i overrated the abilities of the developers. ...but Tony is dead right - this sort of thing doesn't help. -- Richie Hindle richie at entrian.com ------------------------------ Message: 2 Date: Mon, 17 Oct 2005 10:30:51 +1300 From: Tony Meyer Subject: Re: [Spambayes] Whitelisting for spam reports To: Richie Hindle Cc: spambayes at python.org Message-ID: <8B7394E7-6968-454E-A5A3-803FF94E58E1 at ihug.co.nz> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed [Manuel] >> I prefer to always train everything to keep my filter up2date. [Richie] > I don't think Manuel's request actually counts as whitelisting at all, I agree (I said that somewhere else in the thread, I think). > and I think it's quite reasonable. What he wants (Manuel, correct me > if I'm > wrong) is to filter out certain senders from the training list. All > messages from spamcop would be automatically set to Discard and > omitted from the training list. This is much the same as the existing ability to filter out 'bulk' mail from the training list. > When you look at it like this, I think it's quite a reasonable feature > request. I don't have time to implement this at the moment either. The thing to do, if Manuel (or anyone else interested in this) isn't able to put together a patch himself, would be to open a feature request at . Ideally, don't mention "whitelisting" (someone might mistakenly close it); call it something like "Exclusion list for training list". Someone, at some time, will probably get to it. I suppose the UI for it would just be a text box where you can enter comma separated addresses. If this gets added, is only the "From" header worth considering? Or should there be corresponding options for other headers (e.g. "To", "Subject"). =Tony.Meyer ------------------------------ Message: 3 Date: Mon, 17 Oct 2005 18:03:08 +1000 From: "Bill Hely" Subject: [Spambayes] Free SpamBayes eBook To: Message-ID: Hi all. I have just completed my new eBook titled "Spam Warfare: Microsoft Outlook Edition". It's a comprehensive treatment of spam, built around the SpamBayes Outlook plug-in, and written in end-user language. It's not aimed at you experts but I do need your help. Before going to market I would like to get some informed feedback, so for a few days I'm offering a free copy to any member of the SpamBayes forum willing give me that feedback. All I ask is that you write me a brief critique (ideas, suggestions, corrections) or - even better - a testimonial. The book is a 2MB password-protected PDF. Password and download directions delivered via autoresponder. It's double-opt-in (that is, requires eMail confirmation) because I want to discourage people from signing up their friends. It's you SpamBayes experts I want feedback from for now. For your free copy just send a blank eMail to: mailto:SpamBayesMember at Aweber.com?subject=Warfare-review-copy I'll never share your details with anyone for any reason, and the list will be deleted when this review process is over. Thanks for your interest and assistance. - Bill Hely - Author: "Spam Warfare: Microsoft Outlook Edition" - http://Spam-Warfare.com -- We take security very seriously. All outgoing mail is certified Virus Free. To boost YOUR security visit The Hacker's Nightmare: http://HackersNightmare.com. Checked by AVG Anti-Virus. Version: 7.0.344 / Virus Database: 267.12.2/137 - Release Date: 16/10/2005 ------------------------------ _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html End of SpamBayes Digest, Vol 86, Issue 23 ***************************************** From mary.weekes at gmail.com Tue Oct 18 15:56:12 2005 From: mary.weekes at gmail.com (Mary Weekes) Date: Tue, 18 Oct 2005 08:56:12 -0500 Subject: [Spambayes] problem Message-ID: <001501c5d3eb$b77c0220$6500a8c0@MARYLAPTOP> Windows XP tray icon disappears and my mail won't download at all -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051018/3e32a1fd/attachment.html -------------- next part -------------- A non-text attachment was scrubbed... Name: Mary Aleixo Weekes.vcf Type: text/x-vcard Size: 134 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051018/3e32a1fd/MaryAleixoWeekes.vcf From glogan at bstonetech.com Tue Oct 18 18:47:01 2005 From: glogan at bstonetech.com (Gina Logan) Date: Tue, 18 Oct 2005 09:47:01 -0700 Subject: [Spambayes] error Message-ID: Hi, We are running Windows XP Pro Binary version 1.0.4 (March 2005) I read the troubleshooting guide Has anyone received this message before? My user remembers deleting the Junk Suspects folder but when we re-create it we still get this message. Another thing that is weird is that in the SpamBayes Manager the 'Enable SpamBayes' checkbox is greyed out. This isn't the case when I try to reproduce on my machine. Thanks for any help on this matter. Gina Logan _____ ------------------------------------------------------------------------ ------------ David E. Mysona Blackstone Technology Group 150 California Street, 9th Floor San Francisco, CA 94111 Office: 415.837.1400 Mobile: 415.350.8436 www.bstonetech.com "Helping to shape today's innovative companies into tomorrow's industry leaders" -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051018/e5b47166/attachment.htm -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/jpeg Size: 176820 bytes Desc: image001.jpg Url : http://mail.python.org/pipermail/spambayes/attachments/20051018/e5b47166/attachment-0001.jpe From nancyhines at sbcglobal.net Tue Oct 18 22:39:57 2005 From: nancyhines at sbcglobal.net (nancyhines) Date: Tue, 18 Oct 2005 13:39:57 -0700 Subject: [Spambayes] lost my (outlook Spambayes instruction Message-ID: When deleting some contents of SpamBayes., I also deleted the whole file.... If I create a "Spam e-mails" file on the left side of Outlook window, then how do I connect it to Outlook so Outlook will populate the 'spam' file and not my inbox with juck mail?? And I can read and check the spam folder separately from my inbox.??? What is the path to do this? -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051018/a95b38ca/attachment.html From mac_sutton at iprimus.com.au Wed Oct 19 03:02:58 2005 From: mac_sutton at iprimus.com.au (Mac Sutton) Date: Wed, 19 Oct 2005 11:02:58 +1000 Subject: [Spambayes] Phishing Message-ID: <000001c5d448$d939e0f0$dbb032d2@mac> Hi I have use spambayes for a long time works great will you be adding phishing in a future version. Thanks for your time and help. -- No virus found in this outgoing message. Checked by AVG Anti-Virus. Version: 7.0.344 / Virus Database: 267.12.4/142 - Release Date: 18/10/2005 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051019/d97ce52f/attachment.htm From internat-dac-ne-adm at aviation-civile.gouv.fr Wed Oct 19 09:03:24 2005 From: internat-dac-ne-adm at aviation-civile.gouv.fr (internat-dac-ne-adm@aviation-civile.gouv.fr) Date: Wed, 19 Oct 2005 09:03:24 +0200 Subject: [Spambayes] Virus Alert Message-ID: <20051019070324.56B509B69A@relais1.dac-ne.aviation-civile.gouv.fr> ATTENTION le fichier : Part-2.zip que vous avez envoye a contenait un virus. From jsp at PKC.com Wed Oct 19 14:04:56 2005 From: jsp at PKC.com (Jesse Pelton) Date: Wed, 19 Oct 2005 08:04:56 -0400 Subject: [Spambayes] lost my (outlook Spambayes instruction Message-ID: <16E2027582CDB74180896CDB4B8CC1F901D0447B@PKCVT01.pkc.com> It sounds like this FAQ might help: http://spambayes.sourceforge.net/faq.html#help-i-deleted-the-unsure-spam -folder . ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of nancyhines Sent: Tuesday, October 18, 2005 4:40 PM To: spambayes at python.org Subject: [Spambayes] lost my (outlook Spambayes instruction When deleting some contents of SpamBayes., I also deleted the whole file.... If I create a "Spam e-mails" file on the left side of Outlook window, then how do I connect it to Outlook so Outlook will populate the 'spam' file and not my inbox with juck mail?? And I can read and check the spam folder separately from my inbox.??? What is the path to do this? -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051019/fb8929d0/attachment.htm From bill.hely at helyholdings.com Thu Oct 20 03:52:15 2005 From: bill.hely at helyholdings.com (Bill Hely) Date: Thu, 20 Oct 2005 11:52:15 +1000 Subject: [Spambayes] Free SpamBayes eBook In-Reply-To: Message-ID: Hi all. Ill be shutting down the autoresponder offer on the weekend, so if you use the SpamBayes Outlook Plug-in and would like a free preview copy of my book, don't delay. Here are the details again in case you missed my original offer... > Hi all. > > I have just completed my new eBook titled "Spam Warfare: > Microsoft Outlook Edition". It's a comprehensive treatment of > spam, built around the SpamBayes Outlook plug-in, and written in > end-user language. It's not aimed at you experts but I do need > your help. > > Before going to market I would like to get some informed > feedback, so for a few days I'm offering a free copy to any > member of the SpamBayes forum willing give me that feedback. > > All I ask is that you write me a brief critique (ideas, > suggestions, corrections) or - even better - a testimonial. > > The book is a 2MB password-protected PDF. Password and download > directions delivered via autoresponder. It's double-opt-in (that > is, requires eMail confirmation) because I want to discourage > people from signing up their friends. It's you SpamBayes experts > I want feedback from for now. > > For your free copy just send a blank eMail to: > mailto:SpamBayesMember at Aweber.com?subject=Warfare-review-copy > > I'll never share your details with anyone for any reason, and the > list will be deleted when this review process is over. > > Thanks for your interest and assistance. > - Bill Hely > - Author: "Spam Warfare: Microsoft Outlook Edition" -- We take security very seriously. All outgoing mail is certified Virus Free. To boost YOUR security visit The Hacker's Nightmare: http://HackersNightmare.com. Checked by AVG Anti-Virus. Version: 7.0.344 / Virus Database: 267.12.4/143 - Release Date: 19/10/2005 From lbolognini at gmail.com Thu Oct 20 03:57:15 2005 From: lbolognini at gmail.com (Lorenzo Bolognini) Date: Thu, 20 Oct 2005 02:57:15 +0100 Subject: [Spambayes] Using SpamBayes to filter something else than emails Message-ID: Hi all, say you have a high-traffic classifies website and want the computer to work for you approving ads that would be required to be approven by hand. These ads would be inserted by a user from a web form and, as such, wouldn't have an email format. How good would spambayes be at filtering this kind of content knowing that it won't be feeded with email headers and the like? Also could anybody compare Spambayes with Reverend by the fine folks at divmod.org (http://www.divmod.org/projects/reverend) which seems very easy to use? Thanks, Lorenzo From HerbM at learnquick.com Thu Oct 20 04:20:03 2005 From: HerbM at learnquick.com (Herb Martin) Date: Wed, 19 Oct 2005 21:20:03 -0500 Subject: [Spambayes] Using SpamBayes to filter something else than emails In-Reply-To: Message-ID: > say you have a high-traffic classifies website and want the > computer to work for you approving ads that would be required > to be approven by hand. These ads would be inserted by a user > from a web form and, as such, wouldn't have an email format. > How good would spambayes be at filtering this kind of content > knowing that it won't be feeded with email headers and the like? > > Also could anybody compare Spambayes with Reverend by the > fine folks at divmod.org > (http://www.divmod.org/projects/reverend) which seems very > easy to use? Might work, but you likely will have better luck and more control (e.g., command line version) with DSpam or CRM114. CRM114 is not just a spam filter but rather a language for writing filters and classifiers that includes a spam filter as an example (the primary example.) -- Herb Martin > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Lorenzo Bolognini > Sent: Wednesday, October 19, 2005 8:57 PM > To: spambayes at python.org > Subject: [Spambayes] Using SpamBayes to filter something else > than emails > > Hi all, > > say you have a high-traffic classifies website and want the > computer to work for you approving ads that would be required > to be approven by hand. These ads would be inserted by a user > from a web form and, as such, wouldn't have an email format. > How good would spambayes be at filtering this kind of content > knowing that it won't be feeded with email headers and the like? > > Also could anybody compare Spambayes with Reverend by the > fine folks at divmod.org > (http://www.divmod.org/projects/reverend) which seems very > easy to use? > > Thanks, > Lorenzo > > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html > From shannong at alaska.net Thu Oct 20 11:22:23 2005 From: shannong at alaska.net (Shannon Gackstetter) Date: Thu, 20 Oct 2005 01:22:23 -0800 Subject: [Spambayes] my spam folder disappeared from my folder list?! Message-ID: Hello, Why would my spam folder suddenly disappear from my folder list? Where might those spam messages be going? I'd sure appreciate any suggestions (I'm a novice...). Thanks in advance. Shannon From tameyer at ihug.co.nz Thu Oct 20 11:05:10 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Thu, 20 Oct 2005 22:05:10 +1300 Subject: [Spambayes] my spam folder disappeared from my folder list?! In-Reply-To: References: Message-ID: > Why would my spam folder suddenly disappear from my folder list? Please see FAQ 3.13: =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From HerbM at learnquick.com Thu Oct 20 17:48:40 2005 From: HerbM at learnquick.com (Herb Martin) Date: Thu, 20 Oct 2005 10:48:40 -0500 Subject: [Spambayes] Using SpamBayes to filter something else than emails In-Reply-To: Message-ID: > On 10/20/05, Herb Martin wrote: > > > CRM114 is not just a spam filter but rather a language for writing > > filters and classifiers that includes a spam filter as an > example (the > > primary example.) > > CRM114 looks like something I wanna look into... for the > moment there's nothing that can beat Reverend's ease of use: Not to criticize the "Reverend" (after Reverend Bayes) as it looks promising, especially if you are already working in Python. Please do note that CRM114 has built-in classifiers for Bayesian and Markovian models, including OSBF. It is also designed to allow addition of new classifier algorythms, and already has a 'Hyperspatial' classifier as an example of such additions. -- Herb Martin > -----Original Message----- > From: Lorenzo Bolognini [mailto:lbolognini at gmail.com] > Sent: Wednesday, October 19, 2005 10:00 PM > To: Herb Martin > Subject: Re: [Spambayes] Using SpamBayes to filter something > else than emails > > On 10/20/05, Herb Martin wrote: > > > CRM114 is not just a spam filter but rather a language for writing > > filters and classifiers that includes a spam filter as an > example (the > > primary example.) > > CRM114 looks like something I wanna look into... for the > moment there's nothing that can beat Reverend's ease of use: > > C:\>python > Python 2.4.2 (#67, Sep 28 2005, 12:41:11) [MSC v.1310 32 bit > (Intel)] on win32 Type "help", "copyright", "credits" or > "license" for more information. > >>> from reverend.thomas import Bayes > >>> guesser = Bayes() > >>> guesser.train("car", "car engine carburator mph tyre") > >>> guesser.train("spam", "viagra pills sex pharmacy") > >>> guesser.guess("Car for sale, tyres and engine in very good > >>> conditions") > [('car', 0.99990000000000001)] > >>> guesser.guess("Buy some pills of viagra from our online pharmacy") > [('spam', 0.99990000000000001)] > >>> guesser.save() #this is to save the training we made, it > uses pickle > >>> > > Thanks, > Lorenzo > From kevin at mkjeffers.com Thu Oct 20 19:45:46 2005 From: kevin at mkjeffers.com (Kevin Jeffers) Date: Thu, 20 Oct 2005 13:45:46 -0400 Subject: [Spambayes] spambytes Message-ID: A really stupid question but...I had used spambytes on my old laptop and now wish to install it on my new one. But I cant find the download. Can you direct me please? Kevin Jeffers -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051020/15766852/attachment.html From bill at acme42.com Fri Oct 21 03:31:26 2005 From: bill at acme42.com (Bill Cain) Date: Thu, 20 Oct 2005 20:31:26 -0500 Subject: [Spambayes] Spambayes filters, but every click on a spambayes toolbar buttons cause outlook to crash and restart Message-ID: <278FB28CEE44444C9DCBED32DB2006F6103E07@acmelabs.acmelabs.local> Everytime I click a spambayes button, outlook dies. No logfile is created. I've deleted the default.ini and reconfigured spambayes, no luck. Windows XP Professional SP2 Outlook 2003, exchange SBS2003 Deleted the spambayes toolbar in toosl/customize/toolbars/spambayes, restarted outlook - outlook still crashes Deleted outcmd.dat, outlook still crashes Removed and reinstalled spambayes, outlook still crashes Spambayes has been running for several years just fine, I think SP2 was the start of the problem. Bill -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051020/770d71d3/attachment.html From tameyer at ihug.co.nz Fri Oct 21 06:51:56 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Fri, 21 Oct 2005 17:51:56 +1300 Subject: [Spambayes] spambytes In-Reply-To: References: Message-ID: <14889407-B3CF-41B1-8520-D604637A6BDF@ihug.co.nz> > I cant find the download. Can you direct me please? =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Fri Oct 21 06:57:13 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Fri, 21 Oct 2005 17:57:13 +1300 Subject: [Spambayes] problem In-Reply-To: <001501c5d3eb$b77c0220$6500a8c0@MARYLAPTOP> References: <001501c5d3eb$b77c0220$6500a8c0@MARYLAPTOP> Message-ID: <114D73E7-404F-4818-9C1C-F4F28168C9CE@ihug.co.nz> > Windows XP > tray icon disappears and my mail won't download at all Please send us a copy of the most recent log file, which will have information explaining why this is happening. The troubleshooting guide (accessible via the Start menu or via ) explains where to find the log files. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From elimelecheli at 012.net.il Fri Oct 21 10:37:10 2005 From: elimelecheli at 012.net.il (Elimelech Eliaou) Date: Fri, 21 Oct 2005 10:37:10 +0200 Subject: [Spambayes] Your recent mail to remove@audible.com Message-ID: <000501c5d61a$a0fbd6c0$0200000a@elimelec6oq2o0> please remove me from here -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051021/7bf19ad7/attachment.html From tameyer at ihug.co.nz Fri Oct 21 06:57:13 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Fri, 21 Oct 2005 17:57:13 +1300 Subject: [Spambayes] problem In-Reply-To: <001501c5d3eb$b77c0220$6500a8c0@MARYLAPTOP> References: <001501c5d3eb$b77c0220$6500a8c0@MARYLAPTOP> Message-ID: <114D73E7-404F-4818-9C1C-F4F28168C9CE@ihug.co.nz> > Windows XP > tray icon disappears and my mail won't download at all Please send us a copy of the most recent log file, which will have information explaining why this is happening. The troubleshooting guide (accessible via the Start menu or via ) explains where to find the log files. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From Baxter1948 at aol.com Sun Oct 23 05:40:06 2005 From: Baxter1948 at aol.com (Baxter1948@aol.com) Date: Sat, 22 Oct 2005 23:40:06 EDT Subject: [Spambayes] Re: Error(s) with MS Outlook 2002/xp on Windows XP Message-ID: <1e4.46c6944e.308c6016@aol.com> Hello: It seems that I am experiencing this same problem within Outlook 2002. Every time I attempt to enter a new calendar entry the program crashes with an error relating to MSO.dll. What exactly do you mean when you say 'his profile in Windows XP was hammered"? Can you provide me with the details which you used to rid yourself of this error? Any help will be appreciated. Thank you. Baxter W. Leisure, Jr. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051022/a3d89b9c/attachment.htm From FreeMJ at HotPop.com Sun Oct 23 21:06:27 2005 From: FreeMJ at HotPop.com (FreeMJ@HotPop.com) Date: Sun, 23 Oct 2005 12:06:27 -0700 Subject: [Spambayes] Inspecting images (was: SpamBayes to HandleEmbedded Images) In-Reply-To: Message-ID: <20051023190617.A165A1A009C@smtp-1.hotpop.com> Something really needs to be done about this embedded image Spam. Honestly, SpamBayes appears to be ineffective against all these images, and this kind of e-mail represents almost 80% of what I'm receiving now. The flood of embedded-image based e-mail has skyrocketed. Most of my image ads: - Drug ads - Weight Loss/Energy crap - Home Refinancing - Stock tips - Watch replicas I'm sure OCR isn't the only way, but the words are there in plain view. It seems like the obvious way to resolve this. It's SO frustrating, because it's basically the exact same four or five images, just slightly modified each time. But they include all the words that would clobber this stuff if it was text based. SpamBayes has been such a great program for me and my colleges, family and friends. I can only hope that the project sees fit to resolve this soon. FMJ -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Tony Meyer Sent: Tuesday, October 04, 2005 10:24 PM To: Vincent Zweije Cc: spambayes at python.org Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to HandleEmbedded Images) >> Other than a miraculous OCR feature showing up in SpamBayes soon, I'm >> out of ideas for a simple way of managing this type of mail on my >> home PC. > > Hmm... if anyone is going to work on this, do it the Bayesian way. > Don't try to recognise text, just recognize patterns in the image. > Just like spambayes doesn't understand language, just recognizes words > (and a little of their context). FWIW, I suspect that this may be quite effective. Techniques like this are used in image processing already - for example, the Viola- Jones method of detecting patterns (e.g. faces) in an image uses a cascade of haar-like classifiers: essentially, a whole lot of tiny little classifiers that look at tiny parts of the image (which are all automatically generated via training, not specified as rules). If only there was more time in the day ... :) =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From tameyer at ihug.co.nz Mon Oct 24 06:42:57 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Mon, 24 Oct 2005 17:42:57 +1300 Subject: [Spambayes] Inspecting images (was: SpamBayes to HandleEmbedded Images) In-Reply-To: <20051023190617.A165A1A009C@smtp-1.hotpop.com> References: <20051023190617.A165A1A009C@smtp-1.hotpop.com> Message-ID: <04C54E08-C941-4FBB-B173-6294DFD42E55@ihug.co.nz> > Something really needs to be done about this embedded image Spam. > Honestly, > SpamBayes appears to be ineffective against all these images, Can you post an example of a message that is incorrectly classified, *with the spambayes clues* for the message? The Outlook plug-in provides this via the "Show Clues for this Message" item in the SpamBayes menu. [...] > I'm sure OCR isn't the only way, but the words are there in plain > view. It > seems like the obvious way to resolve this. Obvious isn't always best. One of the tenets here is "stupid beats smart" - I think doing some sort of OCR on images would fall into the "smart" category, and generating simple tokens from the images would fall into the "stupid" category and be more successful. Just my opinion, of course, but that's what I'd test if I had time (perhaps over the (southern hemisphere) summer...or maybe I can convince one of my employers that this would be worth doing in paid time). > SpamBayes has been such a great program for me and my colleges, > family and > friends. I can only hope that the project sees fit to resolve this > soon. It's not really a case of "seeing fit" - the issue is that the developers are very short on time at the moment (contributions have always been, and always will be, welcome) and, in addition, this is a complex problem. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Mon Oct 24 13:07:51 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Tue, 25 Oct 2005 00:07:51 +1300 Subject: [Spambayes] [spambayes-dev] Help In-Reply-To: <000001c5d6f5$51e01a20$6501a8c0@canonsworld> References: <000001c5d6f5$51e01a20$6501a8c0@canonsworld> Message-ID: <55E70FE3-8C9F-4C95-9394-257D93F9F328@ihug.co.nz> [Please note that spambayes-dev is for discussion about the development of spambayes. Requests for help should be directed to spambayes at python.org] > My spam bayes just stopped working! > > I tried re loading it, re installing it, re downloading it, but I > am still unable to wake it up! Check to see if Outlook has disabled the plug-in: Help->About Microsoft Outlook->Disabled Items. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Mon Oct 24 13:11:57 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Tue, 25 Oct 2005 00:11:57 +1300 Subject: [Spambayes] error In-Reply-To: References: Message-ID: <4A538949-A693-43DC-9B5B-7A35D45DC692@ihug.co.nz> > Has anyone received this message before? My user remembers > deleting the Junk Suspects folder but when we re-create it we still > get this message. SpamBayes remembers which folder it is via the Outlook ID for the folder, not the name, so simply creating a folder with the same name won't work (on the other hand, renaming the - working - folder won't break anything). Have you gone to the "Filtering" tab and selected the new "Junk Suspects" folder? If you have done that, try doing running the "Inbox Repair Tool" over any open .pst files, and see if that helps. > Another thing that is weird is that in the SpamBayes Manager the > 'Enable SpamBayes' checkbox is greyed out. This is because there isn't a valid 'unsure' folder selected. Once there is, the box will be enabled. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From sales at coloradotelephone.com Mon Oct 24 15:26:41 2005 From: sales at coloradotelephone.com (Colorado Telephone Exchange) Date: Mon, 24 Oct 2005 07:26:41 -0600 Subject: [Spambayes] Stock Traders Daily OTC Alert: FDEI (OTC:BB) Message-ID: <435CE111.1070003@coloradotelephone.com> quit faxing me From info at klmc.ca Mon Oct 24 15:17:32 2005 From: info at klmc.ca (Information) Date: Mon, 24 Oct 2005 09:17:32 -0400 Subject: [Spambayes] Auto Response from Kelso Lake Medical Centre Message-ID: <1130159851.10128@mail.clineosystems.com> Your request for information from Kelso Lake Medical Centre has been received. We will respond to your request via e-mail as soon as possible. Thank You. From BLScott at dow.com Mon Oct 24 17:52:40 2005 From: BLScott at dow.com (Scott, Beth (BL)) Date: Mon, 24 Oct 2005 11:52:40 -0400 Subject: [Spambayes] Junk Suspect Folders Message-ID: Hi accidentally deleted this folder...how do I get it back? Thanks, Beth ____________________________________________ Beth Scott The Dow Chemical Company Base Plastics 2040 Dow Center Midland, MI 48674 USA Phone: (989) 636-9347 Fax: (989) 638-0692 E-mail: blscott at dow.com From gstavely at guruconsult.com Mon Oct 24 22:11:50 2005 From: gstavely at guruconsult.com (Grant Stavely) Date: Mon, 24 Oct 2005 16:11:50 -0400 Subject: [Spambayes] Outlook Junk folder disappears using plugin mode Message-ID: <2802E982-9FE5-4E2D-B376-207671B68CD8@guruconsult.com> Spambayes has been running very smoothly for us on computers running XP and Outlook 2002. One of the machines will work fine for the first 30 minutes or so but at some point the "Junk" folder which we've assigned in spambayes disappears and the next attempt to sort mail in the inbox using the "delete as spam" toolbar icon gives errors alerting that spambayes needs to be reconfigured as it lacks a Junk folder. It is possible to reconfigure spambayes and use it for another half hour or so at which point the alert will repeat itself. I searched in the archives and couldn't find mention of any similar issues. I tried a scanpst against the personal folders file, then tried completely removing the spambayes configuration completely (ini and db files) and reinstalling using a new outlook profile and the same issues return. Is it possible to overzealously click the "Delete As Spam" button on the Junk folder making this user error? Could spambayes or outlook be eating it's own junk folder somehow? The error log is pasted below: ERROR: 'There appears to be a problem with the SpamBayes configuration \r\n\r\nPlease select the SpamBayes manager, and run the\r \nConfiguration Wizard to reconfigure the filter.' Traceback (most recent call last): File "addin.pyc", line 1178, in OnFolderSwitch File "msgstore.pyc", line 351, in GetFolder NotFoundException: NotFoundException: Exception 0x-7ffbfef6 (MAPI_E_OBJECT_DELETED): OLE error 0x8004010a ERROR: 'There appears to be a problem with the SpamBayes configuration \r\n\r\nPlease select the SpamBayes manager, and run the\r \nConfiguration Wizard to reconfigure the filter.' Traceback (most recent call last): File "addin.pyc", line 1178, in OnFolderSwitch File "msgstore.pyc", line 351, in GetFolder NotFoundException: NotFoundException: Exception 0x-7ffbfef6 (MAPI_E_OBJECT_DELETED): OLE error 0x8004010a Traceback (most recent call last): File "addin.pyc", line 1178, in OnFolderSwitch File "msgstore.pyc", line 351, in GetFolder NotFoundException: NotFoundException: Exception 0x-7ffbfef6 (MAPI_E_OBJECT_DELETED): OLE error 0x8004010a ERROR: Unable to open the folder to Move the message - this message was not moved __ Grant Stavely From FreeMJ at HotPop.com Tue Oct 25 04:18:23 2005 From: FreeMJ at HotPop.com (FreeMJ@HotPop.com) Date: Mon, 24 Oct 2005 19:18:23 -0700 Subject: [Spambayes] Inspecting images (was: SpamBayes to HandleEmbeddedImages) In-Reply-To: <04C54E08-C941-4FBB-B173-6294DFD42E55@ihug.co.nz> Message-ID: <20051025021825.079251A01B3@smtp-1.hotpop.com> Hi Tony, The problem is, they keep changing the meaningless text at the bottom of the e-mail all the time, to confuse the Spam filter. They're picking Hammy words. And, as you can see, it's a highly effective technique. In other words, NONE of the "Tokens" should actually be "Significant", it's the image that needs to be scored in this case. Here's the spambayes clues for one of the e-mails: Combined Score: 3% (0.0330173) Internal ham score (*H*): 0.999976 Internal spam score (*S*): 0.0660102 # ham trained on: 14237 # spam trained on: 20138 150 Significant Tokens token spamprob #ham #spam 'sender:no real name:2**0' 0.0277535 2187 88 'dismissed' 0.0374933 314 17 'raising' 0.0417704 313 19 'lives' 0.0580962 1012 88 'ill' 0.0613924 1084 100 'said' 0.0677803 6498 668 'two' 0.08226 5200 659 'put' 0.0828439 2632 336 'were' 0.0845653 6094 796 'recalled' 0.0862187 92 12 'town' 0.0883783 600 82 'being' 0.0894639 4312 599 'letter' 0.093344 1595 232 'unless' 0.0960663 687 103 'stephan' 0.0968154 15 2 'face' 0.0986506 1397 216 'who' 0.0991493 8031 1250 'knows' 0.102049 574 92 'anyone' 0.104976 1828 303 'them' 0.106325 4690 789 'think' 0.107446 3584 610 'keep' 0.109385 2517 437 'him' 0.111552 2631 467 'suspicions' 0.113796 40 7 'went' 0.11401 1331 242 'sound' 0.116592 596 111 'care' 0.117491 1244 234 'going' 0.119623 3503 673 'sort' 0.119677 511 98 'his' 0.119861 5717 1101 'remained' 0.11998 271 52 'heavily' 0.123551 232 46 'last' 0.126157 5241 1070 'subject:: ' 0.134951 9110 2010 'voice' 0.135891 644 143 'walk' 0.140296 339 78 'everyone' 0.140502 1225 283 'whatever' 0.141645 618 144 'overdosed' 0.142155 48 11 'mother' 0.144908 510 122 'way' 0.146154 3458 837 'was' 0.146612 8939 2172 'would' 0.146893 7679 1870 'but' 0.14865 8435 2083 'past' 0.155513 1932 503 'duty' 0.15756 326 86 'been' 0.158577 6937 1849 'away' 0.159247 1632 437 'soon' 0.16154 1021 278 'header:In-Reply-To:1' 0.162139 1791 490 'made' 0.163602 3467 959 'true' 0.164161 566 157 'too' 0.164462 2199 612 'then' 0.167186 3519 999 'road' 0.169212 459 132 'covington' 0.170591 18 5 'firmly' 0.171729 69 20 'received' 0.172468 1646 485 'yes' 0.17276 275 81 'other' 0.174723 6686 2002 'offered' 0.177462 702 214 'saw' 0.178119 738 226 'might' 0.184601 2399 768 'hotel' 0.185114 203 65 'thought' 0.186457 1287 417 'her' 0.187192 2831 922 'indeed' 0.18721 191 62 'lie' 0.188538 165 54 'filled' 0.188682 329 108 'assorted' 0.198662 32 11 'intent' 0.199592 596 210 'manner' 0.200765 192 68 'second' 0.203991 1311 475 'let' 0.207891 1835 681 'much' 0.210328 3345 1260 'back' 0.211425 3207 1216 'place' 0.214507 1704 658 'out' 0.216398 6503 2540 'little' 0.218176 2273 897 'within' 0.218497 1940 767 'occupied' 0.218989 56 22 'never' 0.222876 2224 902 'take' 0.223351 4101 1668 'subject:-' 0.223886 2564 1046 'find' 0.224822 2482 1018 'play' 0.230279 518 219 'skip:n 10' 0.233772 2561 1105 'eyes' 0.234231 294 127 'that' 0.245614 11155 5137 'thoughts' 0.250399 193 91 'observed' 0.252899 109 52 'not' 0.253605 9451 4542 'have' 0.260054 10350 5145 'myself' 0.268888 281 146 'with' 0.272839 10712 5685 'skip:r 10' 0.274264 4752 2540 'look' 0.276317 1963 1060 'can' 0.286752 7254 4125 'guided' 0.29442 24 14 'all' 0.300499 8283 5033 'resign' 0.304561 39 24 'contracts' 0.313223 163 105 'subject:Alert' 0.322897 61 41 'upon' 0.326586 853 585 'skip:i 10' 0.332672 4717 3326 'for' 0.339583 12494 9087 'topics' 0.371008 114 95 'the' 0.371613 13338 11157 'above' 0.380529 678 589 'header:Return-Path:1' 0.635635 6219 15346 'consults' 0.695316 3 10 'comparative' 0.728703 17 65 'earnest' 0.747547 24 101 'friendship' 0.796906 6 34 'blush' 0.797234 13 73 'skip:7 70' 0.805302 5 30 'expedition' 0.825248 9 61 'from:addr:g.wcvbss' 0.844828 0 1 'from:addr:netnitco.net' 0.844828 0 1 'from:name:raymond goins' 0.844828 0 1 'lensalizarin' 0.844828 0 1 "m'scorset" 0.844828 0 1 'message-id:@icsp.net' 0.844828 0 1 'ownthat' 0.844828 0 1 'prominents' 0.844828 0 1 'roadsthat' 0.844828 0 1 'sender:addr:athenet.net' 0.844828 0 1 'sender:addr:h.nnq' 0.844828 0 1 'subject:< ' 0.844828 0 1 'subject:Stiles' 0.844828 0 1 'totrue' 0.844828 0 1 'virus:src="cid:' 0.888282 111 1250 'congenial' 0.905802 5 70 'taters' 0.907976 1 16 'skip:7 90' 0.908163 0 2 'header:Received:2' 0.914966 886 13487 'diem' 0.92631 3 56 'subject:CBXC' 0.949438 0 4 'rotund' 0.952904 1 33 'blushingly' 0.958716 0 5 'refolding' 0.969799 0 7 'egress' 0.970088 1 53 'to:name:freemj' 0.988432 0 19 'septennial' 0.990405 0 23 'veal' 0.993066 0 32 'youll' 0.993469 0 34 'subject:Stock' 0.99571 0 52 'casteth' 0.995868 0 54 'cutlet' 0.996894 0 72 'to:addr:hotpop.com' 0.997792 23 14803 Message Stream Return-Path: Received: from 38.113.3.52 (unknown [200.107.173.172]) by mx1.hotpop.com (Postfix) with SMTP id 5B8A0E8304; Sun, 23 Oct 2005 23:49:29 +0000 (UTC) Received: from spellbound.gape.jeffersonian.gauguin.es ([200.107.173.172] helo=scatterbrain.mail.elknet.net) by smtp9.bt.com with esmtp id 0X162p-8865LL-80; Mon, 24 Oct 2005 01:48:41 +0100 Message-Id: <8927397790.37444460700 at icsp.net> Sender: H.nnq at athenet.net Date: Sun, 23 Oct 2005 20:42:41 -0400 In-Reply-To: Your message of "Sun, 23 Oct 2005 20:46:41 -0400." <98802417987115.YV37184 at joel.renaissance.arden.net> From: "Raymond Goins" To: "Freemj" Subject: Fwd: Stock - Alert-CBXC< Neil Stiles MIME-Version: 1.0 Content-Type: multipart/related; boundary="--ZZR8PVzcRDTpf2Pu68MQiz" X-HotPOP-Delivered-To: freemj at hotpop.com negligiblestymie breakwatergrist m'scorset We went to the triumph comparative at egress diem then a mouldy sort of establishment have my place so I blushingly offered to resign it The septennial who made as much of my going away as if I were going to China received me as an was dismissed and other topics occupied us he remained so seldom raising his eyes unless to true Rosanne was suspicions arose within me that it was an ill assorted friendship that he never thought of being observed by anyone but was so intent upon her and upon his ownthat I received soon recalled me to myself and put me in the road back to the hotel I was so filled with the play and with the past for it was in a manner Everyone who knows you consults with you and is guided by you Stephan but on second thoughts I shall keep him to take care of me and refolding the letter it would be insupportable to me to think of I am in earnest at last so youll soon have to arrange our contracts and to bind us firmly to them been overdosed with taters I commanded him in my deepest voice to order a veal cutlet and potatoes Yes I am on an expedition of duty My mother lives a little way out of town and the roadsthat I received soon recalled me to myself and put me in the road back to the hotel for I saw a faint blush in her face you would have let me find it out for myself that would not lie too heavily upon her purse and to do my duty in it whatever it might be and the prominents walk and the congenial sound of the rotund casteth hovering above them all 7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg7MikURq reWfg7M6dwtJ4t1Fxn as he can look at me out of his two eyes Is he indeed said Mr Covington lensalizarin impregnatecost

negligiblestymie breakwatergrist m'scorset


We went to the triumph comparative at egress diem then a mouldy sort of establishment
have my place so I blushingly offered to resign it The septennial who made as much of my going away as if I were going to China received me as an
was dismissed and other topics occupied us he remained so seldom raising his eyes unless to
true Rosanne was suspicions arose within me that it was an ill assorted friendship
that he never thought of being observed by anyone but was so intent upon her and upon his ownthat I received soon recalled me to myself and put me in the road back to the hotel
I was so filled with the play and with the past for it was in a manner
Everyone who knows you consults with you and is guided by you Stephan
but on second thoughts I shall keep him to take care of me
and refolding the letter it would be insupportable to me to think of
I am in earnest at last so youll soon have to arrange our contracts and to bind us firmly to them
been overdosed with taters I commanded him in my deepest voice to order a veal cutlet and potatoes
Yes I am on an expedition of duty My mother lives a little way out of town and the roadsthat I received soon recalled me to myself and put me in the road back to the hotel
for I saw a faint blush in her face you would have let me find it out for myself that would not lie too heavily upon her purse and to do my duty in it whatever it might be
and the prominents walk and the congenial sound of the rotund casteth hovering above them all
7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg7MikURq reWfg7M6dwtJ4t1Fxn
as he can look at me out of his two eyes Is he indeed said Mr Covington
All Message Tokens 187 unique tokens 'above' 'all' 'and' 'anyone' 'arose' 'arrange' 'assorted' 'away' 'back' 'been' 'being' 'bind' 'blush' 'blushingly' 'but' 'can' 'care' 'casteth' 'cc:none' 'china' 'commanded' 'comparative' 'congenial' 'consults' 'content-type:text/plain' 'contracts' 'covington' 'cutlet' 'deepest' 'diem' 'dismissed' 'duty' 'earnest' 'egress' 'everyone' 'expedition' 'eyes' 'face' 'faint' 'filled' 'find' 'firmly' 'for' 'friendship' 'from:addr:g.wcvbss' 'from:addr:netnitco.net' 'from:name:raymond goins' 'going' 'guided' 'have' 'header:Date:1' 'header:From:1' 'header:In-Reply-To:1' 'header:MIME-Version:1' 'header:Message-Id:1' 'header:Received:2' 'header:Return-Path:1' 'header:Subject:1' 'header:To:1' 'heavily' 'her' 'him' 'his' 'hotel' 'hovering' 'ill' 'indeed' 'intent' 'keep' 'knows' 'last' 'lensalizarin' 'let' 'letter' 'lie' 'little' 'lives' 'look' "m'scorset" 'made' 'manner' 'message-id:@icsp.net' 'might' 'mother' 'mouldy' 'much' 'myself' 'never' 'not' 'observed' 'occupied' 'offered' 'order' 'other' 'our' 'out' 'overdosed' 'ownthat' 'past' 'place' 'play' 'potatoes' 'prominents' 'purse' 'put' 'raising' 'recalled' 'received' 'refolding' 'remained' 'reply-to:none' 'resign' 'road' 'roadsthat' 'rosanne' 'rotund' 'said' 'saw' 'second' 'seldom' 'sender:addr:athenet.net' 'sender:addr:h.nnq' 'sender:no real name:2**0' 'septennial' 'shall' 'skip:7 70' 'skip:7 90' 'skip:b 10' 'skip:e 10' 'skip:i 10' 'skip:n 10' 'skip:r 10' 'soon' 'sort' 'sound' 'stephan' 'subject: ' 'subject: - ' 'subject:-' 'subject:: ' 'subject:< ' 'subject:Alert' 'subject:CBXC' 'subject:Fwd' 'subject:Neil' 'subject:Stiles' 'subject:Stock' 'suspicions' 'take' 'taters' 'that' 'the' 'them' 'then' 'think' 'thought' 'thoughts' 'to:2**0' 'to:addr:freemj' 'to:addr:hotpop.com' 'to:name:freemj' 'too' 'topics' 'totrue' 'town' 'triumph' 'true' 'two' 'unless' 'upon' 'veal' 'virus:src="cid:' 'voice' 'walk' 'was' 'way' 'went' 'were' 'whatever' 'who' 'with' 'within' 'would' 'x-mailer:none' 'yes' 'you' 'youll' -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Tony Meyer Sent: Sunday, October 23, 2005 9:43 PM To: Cc: spambayes at python.org Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to HandleEmbeddedImages) > Something really needs to be done about this embedded image Spam. > Honestly, > SpamBayes appears to be ineffective against all these images, Can you post an example of a message that is incorrectly classified, *with the spambayes clues* for the message? The Outlook plug-in provides this via the "Show Clues for this Message" item in the SpamBayes menu. [...] > I'm sure OCR isn't the only way, but the words are there in plain > view. It > seems like the obvious way to resolve this. Obvious isn't always best. One of the tenets here is "stupid beats smart" - I think doing some sort of OCR on images would fall into the "smart" category, and generating simple tokens from the images would fall into the "stupid" category and be more successful. Just my opinion, of course, but that's what I'd test if I had time (perhaps over the (southern hemisphere) summer...or maybe I can convince one of my employers that this would be worth doing in paid time). > SpamBayes has been such a great program for me and my colleges, > family and > friends. I can only hope that the project sees fit to resolve this > soon. It's not really a case of "seeing fit" - the issue is that the developers are very short on time at the moment (contributions have always been, and always will be, welcome) and, in addition, this is a complex problem. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From sobellewin at aol.com Tue Oct 25 16:19:25 2005 From: sobellewin at aol.com (Suzanne Sobel) Date: Tue, 25 Oct 2005 10:19:25 -0400 Subject: [Spambayes] I don't have "recover from spam" as a button in my menu bar Message-ID: <002701c5d96f$1ec8f1d0$6501a8c0@inspiron2650> Hi, I have the "delete as spam" button in my menu bar, but not "recover from spam". What should I do? Thanks!! Suzanne ~~~~~~~~~~~~~~~~~~~~~~~~~ Suzanne G. Sobel, Ph.D. (H) 203 497 9603 (C) 203 668 4920 suzanne.sobel at aya.yale.edu ~~~~~~~~~~~~~~~~~~~~~~~~~ -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051025/1d5c9301/attachment.html From gerstenberger at imst.de Wed Oct 26 11:15:58 2005 From: gerstenberger at imst.de (Florian Gerstenberger) Date: Wed, 26 Oct 2005 11:15:58 +0200 Subject: [Spambayes] HowTo disable the "Save and Shutdown" Button in the Webinterface on linux ? Message-ID: <435F494E.7040409@imst.de> Hi List, I would like to disable the "Save and Shutdown" Button in the Webinterface (sb_server.py) running on linux. I found something like that in the Changelog, but I think this is only relevant running as a Service on Windows ..... I am using the second init.d script found on spambayes.org to start the sb_server.py. I found the file "ui.html" in the source directory which seems to be the template of the page but I am not really familar to Python and my changes in this file took no effect. I would also like to have the feature to show only the headers of the classified mails to anybody who uses the webinterface ..... Please help me, thanks ;-) Florian Gerstenberger From bernie at amc-hln.com Wed Oct 26 16:43:38 2005 From: bernie at amc-hln.com (Bernie Adams) Date: Wed, 26 Oct 2005 08:43:38 -0600 Subject: [Spambayes] SpamBayes 1.0.4 install Message-ID: <000c01c5da3b$a7376c00$ac1ea8c0@BADAMSAMC> First, this has been a great program for filtering SPAM messages. As the product 'learns' it seems to get better in picking up real SPAM. I have to applaud your install program for the latest version of SpamBayes. It actually looked through my entire Start/Programs area and found that I had moved my original SpamBayes install from the base programs area for the Start button to a 'Utilities' folder to keep the first programs menu from the Start button to a manageable size. This is the first program I have seen that actually looks for a previous install in all areas of the Start menu. Bernie Bernard L Adams (Bernie) Systems Integration Specialist Automation & Management Consulting 2804 Billings Ave. Helena, MT 59601 Office: 1-406-442-6665 Cell: 1-406-431-9514 Fax: 1-406-443-1182 http://www.amc-hln.com Systems Integration . Custom Software . Web Development This communication is intended for the use of the recipient to which it is addressed, and may contain confidential, personal and or privileged information. Please contact us immediately if you are not the intended recipient of this communication, and do not copy, distribute, or take action relying on it. Any communication received in error, or subsequent reply, should be deleted or destroyed. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051026/409ff332/attachment.htm -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/bmp Size: 7606 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051026/409ff332/attachment.bin From coffent at bigfoot.com Wed Oct 26 19:12:14 2005 From: coffent at bigfoot.com (C Stephan) Date: Wed, 26 Oct 2005 13:12:14 -0400 Subject: [Spambayes] SpamBayes hides message content Message-ID: <6.2.3.4.0.20051026125848.0247e630@pop3.highstream.net> An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051026/b8322adc/attachment.htm From richie at entrian.com Wed Oct 26 19:19:30 2005 From: richie at entrian.com (Richie Hindle) Date: Wed, 26 Oct 2005 18:19:30 +0100 Subject: [Spambayes] SpamBayes hides message content In-Reply-To: <6.2.3.4.0.20051026125848.0247e630@pop3.highstream.net> References: <6.2.3.4.0.20051026125848.0247e630@pop3.highstream.net> Message-ID: Hi Craig, > When I look at the detailed header information on a message that does > not come through correctly, I find the following: > > X-Spambayes-Exception: Traceback (most recent call last): > [...] > DBRunRecoveryError: (-30978, 'DB_RUNRECOVERY: Fatal error, > run database recovery -- PANIC: Invalid argument') Please see FAQ 5.2: http://spambayes.sourceforge.net/faq.html#i-get-a-dbrunrecoveryerror-message Sadly the only solution is to delete your training database and train again from scratch. -- Richie Hindle richie at entrian.com From bjwertman at gmail.com Wed Oct 26 20:02:36 2005 From: bjwertman at gmail.com (Beverly Wertman) Date: Wed, 26 Oct 2005 11:02:36 -0700 Subject: [Spambayes] Undo Delete as Spam Sender Message-ID: <24ed5ff30510261102q379ec562tcf3dfefdb262c03a@mail.gmail.com> I'm not sure what version I have, I couldn't find it under the About section. I downloaded it in Jun 2005, if that helps I need to undo selecting a sender into "delete as spam" I had them selected and hit the wrong button. Thank YOU -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051026/fa413128/attachment.html From ksg at telusplanet.net Wed Oct 26 17:26:02 2005 From: ksg at telusplanet.net (Ken Gordon) Date: Wed, 26 Oct 2005 09:26:02 -0600 Subject: [Spambayes] Inspecting images (was: SpamBayes to HandleEmbeddedImages) In-Reply-To: <20051025143726.CB6921A008F@smtp-1.hotpop.com> References: <20051025143726.CB6921A008F@smtp-1.hotpop.com> Message-ID: There's a lot more to spambayes than just evaluating content. Here's the SB Evidence header from a recent spam. But for 'charset', very little of this has to do with the content, yet it was correctly classified as spam. > X-Spambayes-Evidence: '*H*': 0.00; '*S*': 1.00; 'received:192.168.1': > 0.10; 'subject:skip:B 10': 0.16; 'received:192.168': 0.20; > 'received:192': 0.21; 'url:www': 0.23; 'content-type:image/jpeg': > 0.34; 'to:addr:none': 0.38; 'header:Return-Path:1': 0.38; > 'header:MIME-Version:1': 0.61; 'url:': 0.64; 'x-mailer:none': 0.71; > 'to:no real name:2**0': 0.72; 'from:name:\x1b$b5z at nf`1{\x1b(b': 0.84; > 'message-id:@imx100522.ath.cx': 0.84; 'received:imx100522.ath.cx': > 0.84; 'url:fetish': 0.84; 'received:192.168.1.11': 0.91; > 'received:kick': 0.91; 'content-type:multipart/related': 0.92; > 'received:210.153': 0.93; 'received:ath.cx': 0.93; 'url:cc': 0.93; > 'virus:src="cid:': 0.95; 'content-type/type:multipart/alternative': > 0.96; 'received:cx': 0.97; 'email addr:yahoo.co.jp': 0.99; 'skip:\x1b > 80': 0.99; 'from:addr:yahoo.co.jp': 1.00; 'from:charset:iso-2022-jp': > 1.00; 'skip:\x1b 60': 1.00; 'skip:\x1b 30': 1.00; 'skip:\x1b 20': > 1.00; 'skip:\x1b 50': 1.00; 'subject:$': 1.00; 'received:210': 1.00; > 'charset:iso-2022-jp': 1.00; 'subject:\x1b$': 1.00; > 'subjectcharset:iso-2022-jp': 1.00 On 2005 Oct 25, at 8:37, wrote: > How? Technically speaking, what could your SpamBayes installation be > doing > differently? These are ALL ham words, so how is it that your e-mail > could > be classifying all of this as Spam? If it is, I suspect you're losing > a lot > of legitimate e-mail with it. > > FMJ > > -----Original Message----- > From: Ken Gordon [mailto:ksg at telusplanet.net] > Sent: Monday, October 24, 2005 8:58 PM > To: FreeMJ at HotPop.com > Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to > HandleEmbeddedImages) > > My installation of SpamBayes catches nearly all of these. I don't see > one a > month outside of the Spam folder. > > --- > Ken Gordon > (780) 628-2758 > http://www.wolfe-gordon.ca > On 2005 Oct 24, at 20:18, wrote: > >> Hi Tony, >> The problem is, they keep changing the meaningless text at the bottom >> of the e-mail all the time, to confuse the Spam filter. They're >> picking Hammy words. And, as you can see, it's a highly effective >> technique. In other words, NONE of the "Tokens" should actually be >> "Significant", it's the image that needs to be scored in this case. >> Here's the spambayes clues for one of the e-mails: >> >> Combined Score: 3% (0.0330173) >> Internal ham score (*H*): 0.999976 >> Internal spam score (*S*): 0.0660102 >> >> # ham trained on: 14237 >> # spam trained on: 20138 >> >> 150 Significant Tokens >> token spamprob #ham #spam >> 'sender:no real name:2**0' 0.0277535 2187 88 >> 'dismissed' 0.0374933 314 17 >> 'raising' 0.0417704 313 19 >> 'lives' 0.0580962 1012 88 >> 'ill' 0.0613924 1084 100 >> 'said' 0.0677803 6498 668 >> 'two' 0.08226 5200 659 >> 'put' 0.0828439 2632 336 >> 'were' 0.0845653 6094 796 >> 'recalled' 0.0862187 92 12 >> 'town' 0.0883783 600 82 >> 'being' 0.0894639 4312 599 >> 'letter' 0.093344 1595 232 >> 'unless' 0.0960663 687 103 >> 'stephan' 0.0968154 15 2 >> 'face' 0.0986506 1397 216 >> 'who' 0.0991493 8031 1250 >> 'knows' 0.102049 574 92 >> 'anyone' 0.104976 1828 303 >> 'them' 0.106325 4690 789 >> 'think' 0.107446 3584 610 >> 'keep' 0.109385 2517 437 >> 'him' 0.111552 2631 467 >> 'suspicions' 0.113796 40 7 >> 'went' 0.11401 1331 242 >> 'sound' 0.116592 596 111 >> 'care' 0.117491 1244 234 >> 'going' 0.119623 3503 673 >> 'sort' 0.119677 511 98 >> 'his' 0.119861 5717 1101 >> 'remained' 0.11998 271 52 >> 'heavily' 0.123551 232 46 >> 'last' 0.126157 5241 1070 >> 'subject:: ' 0.134951 9110 2010 >> 'voice' 0.135891 644 143 >> 'walk' 0.140296 339 78 >> 'everyone' 0.140502 1225 283 >> 'whatever' 0.141645 618 144 >> 'overdosed' 0.142155 48 11 >> 'mother' 0.144908 510 122 >> 'way' 0.146154 3458 837 >> 'was' 0.146612 8939 2172 >> 'would' 0.146893 7679 1870 >> 'but' 0.14865 8435 2083 >> 'past' 0.155513 1932 503 >> 'duty' 0.15756 326 86 >> 'been' 0.158577 6937 1849 >> 'away' 0.159247 1632 437 >> 'soon' 0.16154 1021 278 >> 'header:In-Reply-To:1' 0.162139 1791 490 >> 'made' 0.163602 3467 959 >> 'true' 0.164161 566 157 >> 'too' 0.164462 2199 612 >> 'then' 0.167186 3519 999 >> 'road' 0.169212 459 132 >> 'covington' 0.170591 18 5 >> 'firmly' 0.171729 69 20 >> 'received' 0.172468 1646 485 >> 'yes' 0.17276 275 81 >> 'other' 0.174723 6686 2002 >> 'offered' 0.177462 702 214 >> 'saw' 0.178119 738 226 >> 'might' 0.184601 2399 768 >> 'hotel' 0.185114 203 65 >> 'thought' 0.186457 1287 417 >> 'her' 0.187192 2831 922 >> 'indeed' 0.18721 191 62 >> 'lie' 0.188538 165 54 >> 'filled' 0.188682 329 108 >> 'assorted' 0.198662 32 11 >> 'intent' 0.199592 596 210 >> 'manner' 0.200765 192 68 >> 'second' 0.203991 1311 475 >> 'let' 0.207891 1835 681 >> 'much' 0.210328 3345 1260 >> 'back' 0.211425 3207 1216 >> 'place' 0.214507 1704 658 >> 'out' 0.216398 6503 2540 >> 'little' 0.218176 2273 897 >> 'within' 0.218497 1940 767 >> 'occupied' 0.218989 56 22 >> 'never' 0.222876 2224 902 >> 'take' 0.223351 4101 1668 >> 'subject:-' 0.223886 2564 1046 >> 'find' 0.224822 2482 1018 >> 'play' 0.230279 518 219 >> 'skip:n 10' 0.233772 2561 1105 >> 'eyes' 0.234231 294 127 >> 'that' 0.245614 11155 5137 >> 'thoughts' 0.250399 193 91 >> 'observed' 0.252899 109 52 >> 'not' 0.253605 9451 4542 >> 'have' 0.260054 10350 5145 >> 'myself' 0.268888 281 146 >> 'with' 0.272839 10712 5685 >> 'skip:r 10' 0.274264 4752 2540 >> 'look' 0.276317 1963 1060 >> 'can' 0.286752 7254 4125 >> 'guided' 0.29442 24 14 >> 'all' 0.300499 8283 5033 >> 'resign' 0.304561 39 24 >> 'contracts' 0.313223 163 105 >> 'subject:Alert' 0.322897 61 41 >> 'upon' 0.326586 853 585 >> 'skip:i 10' 0.332672 4717 3326 >> 'for' 0.339583 12494 9087 >> 'topics' 0.371008 114 95 >> 'the' 0.371613 13338 11157 >> 'above' 0.380529 678 589 >> 'header:Return-Path:1' 0.635635 6219 15346 >> 'consults' 0.695316 3 10 >> 'comparative' 0.728703 17 65 >> 'earnest' 0.747547 24 101 >> 'friendship' 0.796906 6 34 >> 'blush' 0.797234 13 73 >> 'skip:7 70' 0.805302 5 30 >> 'expedition' 0.825248 9 61 >> 'from:addr:g.wcvbss' 0.844828 0 1 >> 'from:addr:netnitco.net' 0.844828 0 1 >> 'from:name:raymond goins' 0.844828 0 1 >> 'lensalizarin' 0.844828 0 1 >> "m'scorset" 0.844828 0 1 >> 'message-id:@icsp.net' 0.844828 0 1 >> 'ownthat' 0.844828 0 1 >> 'prominents' 0.844828 0 1 >> 'roadsthat' 0.844828 0 1 >> 'sender:addr:athenet.net' 0.844828 0 1 >> 'sender:addr:h.nnq' 0.844828 0 1 >> 'subject:< ' 0.844828 0 1 >> 'subject:Stiles' 0.844828 0 1 >> 'totrue' 0.844828 0 1 >> 'virus:src="cid:' 0.888282 111 1250 >> 'congenial' 0.905802 5 70 >> 'taters' 0.907976 1 16 >> 'skip:7 90' 0.908163 0 2 >> 'header:Received:2' 0.914966 886 13487 >> 'diem' 0.92631 3 56 >> 'subject:CBXC' 0.949438 0 4 >> 'rotund' 0.952904 1 33 >> 'blushingly' 0.958716 0 5 >> 'refolding' 0.969799 0 7 >> 'egress' 0.970088 1 53 >> 'to:name:freemj' 0.988432 0 19 >> 'septennial' 0.990405 0 23 >> 'veal' 0.993066 0 32 >> 'youll' 0.993469 0 34 >> 'subject:Stock' 0.99571 0 52 >> 'casteth' 0.995868 0 54 >> 'cutlet' 0.996894 0 72 >> 'to:addr:hotpop.com' 0.997792 23 14803 >> >> Message Stream >> Return-Path: >> Received: from 38.113.3.52 (unknown [200.107.173.172]) >> by mx1.hotpop.com (Postfix) with SMTP >> id 5B8A0E8304; Sun, 23 Oct 2005 23:49:29 +0000 (UTC) >> Received: from spellbound.gape.jeffersonian.gauguin.es >> ([200.107.173.172] >> helo=scatterbrain.mail.elknet.net) by smtp9.bt.com with esmtp >> id 0X162p-8865LL-80; Mon, 24 Oct 2005 01:48:41 +0100 >> Message-Id: <8927397790.37444460700 at icsp.net> >> Sender: H.nnq at athenet.net >> Date: Sun, 23 Oct 2005 20:42:41 -0400 >> In-Reply-To: Your message of "Sun, 23 Oct 2005 20:46:41 -0400." >> <98802417987115.YV37184 at joel.renaissance.arden.net> >> From: "Raymond Goins" >> To: "Freemj" >> Subject: Fwd: Stock - Alert-CBXC< Neil Stiles >> MIME-Version: 1.0 >> Content-Type: multipart/related; >> boundary="--ZZR8PVzcRDTpf2Pu68MQiz" >> X-HotPOP-Delivered-To: freemj at hotpop.com >> >> >> negligiblestymie breakwatergrist m'scorset >> >> >> >> We went to the triumph comparative at egress diem then a mouldy sort >> of >> establishment >> have my place so I blushingly offered to resign it The septennial who >> made as much of my going away as if I were going to China received me >> as >> an >> was dismissed and other topics occupied us he remained so seldom >> raising >> his eyes unless to >> true Rosanne was suspicions arose within me that it was an ill >> assorted >> friendship >> that he never thought of being observed by anyone but was so intent >> upon >> her and upon his ownthat I received soon recalled me to myself and put >> me in the road back to the hotel >> I was so filled with the play and with the past for it was in a manner >> Everyone who knows you consults with you and is guided by you Stephan >> but on second thoughts I shall keep him to take care of me >> and refolding the letter it would be insupportable to me to think of >> I am in earnest at last so youll soon have to arrange our contracts >> and >> to bind us firmly to them >> been overdosed with taters I commanded him in my deepest voice to >> order >> a veal cutlet and potatoes >> Yes I am on an expedition of duty My mother lives a little way out of >> town and the roadsthat I received soon recalled me to myself and put >> me >> in the road back to the hotel >> for I saw a faint blush in her face you would have let me find it out >> for myself that would not lie too heavily upon her purse and to do my >> duty in it whatever it might be >> and the prominents walk and the congenial sound of the rotund casteth >> hovering above them all >> 7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg7MikU >> R >> q >> reWfg7M6dwtJ4t1Fxn >> as he can look at me out of his two eyes Is he indeed said Mr >> Covington >> >> >> >> lensalizarin impregnatecost >> >> >> >>
>>
> SRC="cid:lTN1QnT11CtJIk8H6J5X7INGgMff2pS at prairieweb.com" border="0" >> ALT="negligiblestymie breakwatergrist m'scorset"> >>
> size=1>
> size=1>

We went to the triumph >> comparative at egress diem then a mouldy sort of >> establishment
have my >> place so I blushingly offered to resign it >> The septennial who made as much of >> my >> going away as if I were going to China received me as an
was >> dismissed >> and other topics occupied us he remained so seldom raising his eyes >> unless >> to
true Rosanne was suspicions >> arose >> within me that it was an ill assorted friendship
that he never >> thought >> of being observed by anyone but was so intent upon her and upon his >> ownthat I received soon recalled me >> to >> myself and put me in the road back to the hotel
I was so filled >> with the >> play and with the past for it was in a manner
Everyone who >> knows you >> consults with you and is guided by you Stephan
but on second >> thoughts I shall keep him to take care of me >>
and refolding the letter it >> would be >> insupportable to me to think of
I am in earnest at last so >> youll soon >> have to arrange our contracts and to bind us firmly to >> them
been overdosed with taters I commanded him in >> my >> deepest voice to order a veal cutlet and potatoes
Yes I am on an >> expedition of duty My mother lives a little way out of town and the >> roadsthat I received soon recalled >> me to >> myself and put me in the road back to the hotel
for I saw a faint >> blush >> in her face you would have let me find it out for myself >> that >> would not lie too heavily upon her purse and to do my duty in it >> whatever >> it might be
and the prominents walk and the congenial sound of >> the >> rotund casteth hovering above them all >>
7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg7 >> M >> ikURq >> reWfg7M6dwtJ4t1Fxn
as he can look at me out of his two eyes Is he >> indeed >> said Mr Covington
>> >> >> >> All Message Tokens >> 187 unique tokens >> >> 'above' >> 'all' >> 'and' >> 'anyone' >> 'arose' >> 'arrange' >> 'assorted' >> 'away' >> 'back' >> 'been' >> 'being' >> 'bind' >> 'blush' >> 'blushingly' >> 'but' >> 'can' >> 'care' >> 'casteth' >> 'cc:none' >> 'china' >> 'commanded' >> 'comparative' >> 'congenial' >> 'consults' >> 'content-type:text/plain' >> 'contracts' >> 'covington' >> 'cutlet' >> 'deepest' >> 'diem' >> 'dismissed' >> 'duty' >> 'earnest' >> 'egress' >> 'everyone' >> 'expedition' >> 'eyes' >> 'face' >> 'faint' >> 'filled' >> 'find' >> 'firmly' >> 'for' >> 'friendship' >> 'from:addr:g.wcvbss' >> 'from:addr:netnitco.net' >> 'from:name:raymond goins' >> 'going' >> 'guided' >> 'have' >> 'header:Date:1' >> 'header:From:1' >> 'header:In-Reply-To:1' >> 'header:MIME-Version:1' >> 'header:Message-Id:1' >> 'header:Received:2' >> 'header:Return-Path:1' >> 'header:Subject:1' >> 'header:To:1' >> 'heavily' >> 'her' >> 'him' >> 'his' >> 'hotel' >> 'hovering' >> 'ill' >> 'indeed' >> 'intent' >> 'keep' >> 'knows' >> 'last' >> 'lensalizarin' >> 'let' >> 'letter' >> 'lie' >> 'little' >> 'lives' >> 'look' >> "m'scorset" >> 'made' >> 'manner' >> 'message-id:@icsp.net' >> 'might' >> 'mother' >> 'mouldy' >> 'much' >> 'myself' >> 'never' >> 'not' >> 'observed' >> 'occupied' >> 'offered' >> 'order' >> 'other' >> 'our' >> 'out' >> 'overdosed' >> 'ownthat' >> 'past' >> 'place' >> 'play' >> 'potatoes' >> 'prominents' >> 'purse' >> 'put' >> 'raising' >> 'recalled' >> 'received' >> 'refolding' >> 'remained' >> 'reply-to:none' >> 'resign' >> 'road' >> 'roadsthat' >> 'rosanne' >> 'rotund' >> 'said' >> 'saw' >> 'second' >> 'seldom' >> 'sender:addr:athenet.net' >> 'sender:addr:h.nnq' >> 'sender:no real name:2**0' >> 'septennial' >> 'shall' >> 'skip:7 70' >> 'skip:7 90' >> 'skip:b 10' >> 'skip:e 10' >> 'skip:i 10' >> 'skip:n 10' >> 'skip:r 10' >> 'soon' >> 'sort' >> 'sound' >> 'stephan' >> 'subject: ' >> 'subject: - ' >> 'subject:-' >> 'subject:: ' >> 'subject:< ' >> 'subject:Alert' >> 'subject:CBXC' >> 'subject:Fwd' >> 'subject:Neil' >> 'subject:Stiles' >> 'subject:Stock' >> 'suspicions' >> 'take' >> 'taters' >> 'that' >> 'the' >> 'them' >> 'then' >> 'think' >> 'thought' >> 'thoughts' >> 'to:2**0' >> 'to:addr:freemj' >> 'to:addr:hotpop.com' >> 'to:name:freemj' >> 'too' >> 'topics' >> 'totrue' >> 'town' >> 'triumph' >> 'true' >> 'two' >> 'unless' >> 'upon' >> 'veal' >> 'virus:src="cid:' >> 'voice' >> 'walk' >> 'was' >> 'way' >> 'went' >> 'were' >> 'whatever' >> 'who' >> 'with' >> 'within' >> 'would' >> 'x-mailer:none' >> 'yes' >> 'you' >> 'youll' >> >> -----Original Message----- >> From: spambayes-bounces at python.org >> [mailto:spambayes-bounces at python.org] On >> Behalf Of Tony Meyer >> Sent: Sunday, October 23, 2005 9:43 PM >> To: >> Cc: spambayes at python.org >> Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to >> HandleEmbeddedImages) >> >>> Something really needs to be done about this embedded image Spam. >>> Honestly, >>> SpamBayes appears to be ineffective against all these images, >> >> Can you post an example of a message that is incorrectly classified, >> *with >> the spambayes clues* for the message? The Outlook plug-in provides >> this via >> the "Show Clues for this Message" item in the SpamBayes menu. >> >> [...] >>> I'm sure OCR isn't the only way, but the words are there in plain >>> view. It >>> seems like the obvious way to resolve this. >> >> Obvious isn't always best. One of the tenets here is "stupid beats >> smart" - I think doing some sort of OCR on images would fall into the >> "smart" category, and generating simple tokens from the images would >> fall into the "stupid" category and be more successful. Just my >> opinion, of course, but that's what I'd test if I had time (perhaps >> over the (southern hemisphere) summer...or maybe I can convince one >> of my employers that this would be worth doing in paid time). >> >>> SpamBayes has been such a great program for me and my colleges, >>> family and >>> friends. I can only hope that the project sees fit to resolve this >>> soon. >> >> It's not really a case of "seeing fit" - the issue is that the >> developers are very short on time at the moment (contributions have >> always been, and always will be, welcome) and, in addition, this is a >> complex problem. >> >> =Tony.Meyer >> >> -- >> Please always include the list (spambayes at python.org) in your >> replies >> (reply-all), and please don't send me personal mail about SpamBayes. >> http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. >> >> >> _______________________________________________ >> SpamBayes at python.org >> http://mail.python.org/mailman/listinfo/spambayes >> Check the FAQ before asking: http://spambayes.sf.net/faq.html >> >> >> _______________________________________________ >> SpamBayes at python.org >> http://mail.python.org/mailman/listinfo/spambayes >> Check the FAQ before asking: http://spambayes.sf.net/faq.html >> > > From FreeMJ at HotPop.com Thu Oct 27 05:55:00 2005 From: FreeMJ at HotPop.com (FreeMJ@HotPop.com) Date: Wed, 26 Oct 2005 20:55:00 -0700 Subject: [Spambayes] Inspecting images (was: SpamBayes toHandleEmbeddedImages) In-Reply-To: Message-ID: <20051027035446.46AD01A03E1@smtp-1.hotpop.com> Ken, Please post the entire Spambayes Clues listing, so I can see what Spambayes is doing with all the erroneous ham text that's included at the bottom of your e-mail message example. Thanks, FMJ -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Ken Gordon Sent: Wednesday, October 26, 2005 8:26 AM To: spambayes at python.org; Subject: Re: [Spambayes] Inspecting images (was: SpamBayes toHandleEmbeddedImages) There's a lot more to spambayes than just evaluating content. Here's the SB Evidence header from a recent spam. But for 'charset', very little of this has to do with the content, yet it was correctly classified as spam. > X-Spambayes-Evidence: '*H*': 0.00; '*S*': 1.00; 'received:192.168.1': > 0.10; 'subject:skip:B 10': 0.16; 'received:192.168': 0.20; > 'received:192': 0.21; 'url:www': 0.23; 'content-type:image/jpeg': > 0.34; 'to:addr:none': 0.38; 'header:Return-Path:1': 0.38; > 'header:MIME-Version:1': 0.61; 'url:': 0.64; 'x-mailer:none': 0.71; > 'to:no real name:2**0': 0.72; 'from:name:\x1b$b5z at nf`1{\x1b(b': 0.84; > 'message-id:@imx100522.ath.cx': 0.84; 'received:imx100522.ath.cx': > 0.84; 'url:fetish': 0.84; 'received:192.168.1.11': 0.91; > 'received:kick': 0.91; 'content-type:multipart/related': 0.92; > 'received:210.153': 0.93; 'received:ath.cx': 0.93; 'url:cc': 0.93; > 'virus:src="cid:': 0.95; 'content-type/type:multipart/alternative': > 0.96; 'received:cx': 0.97; 'email addr:yahoo.co.jp': 0.99; 'skip:\x1b > 80': 0.99; 'from:addr:yahoo.co.jp': 1.00; 'from:charset:iso-2022-jp': > 1.00; 'skip:\x1b 60': 1.00; 'skip:\x1b 30': 1.00; 'skip:\x1b 20': > 1.00; 'skip:\x1b 50': 1.00; 'subject:$': 1.00; 'received:210': 1.00; > 'charset:iso-2022-jp': 1.00; 'subject:\x1b$': 1.00; > 'subjectcharset:iso-2022-jp': 1.00 On 2005 Oct 25, at 8:37, wrote: > How? Technically speaking, what could your SpamBayes installation be > doing differently? These are ALL ham words, so how is it that your > e-mail could be classifying all of this as Spam? If it is, I suspect > you're losing a lot of legitimate e-mail with it. > > FMJ > > -----Original Message----- > From: Ken Gordon [mailto:ksg at telusplanet.net] > Sent: Monday, October 24, 2005 8:58 PM > To: FreeMJ at HotPop.com > Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to > HandleEmbeddedImages) > > My installation of SpamBayes catches nearly all of these. I don't see > one a month outside of the Spam folder. > > --- > Ken Gordon > (780) 628-2758 > http://www.wolfe-gordon.ca > On 2005 Oct 24, at 20:18, wrote: > >> Hi Tony, >> The problem is, they keep changing the meaningless text at the bottom >> of the e-mail all the time, to confuse the Spam filter. They're >> picking Hammy words. And, as you can see, it's a highly effective >> technique. In other words, NONE of the "Tokens" should actually be >> "Significant", it's the image that needs to be scored in this case. >> Here's the spambayes clues for one of the e-mails: >> >> Combined Score: 3% (0.0330173) >> Internal ham score (*H*): 0.999976 >> Internal spam score (*S*): 0.0660102 >> >> # ham trained on: 14237 >> # spam trained on: 20138 >> >> 150 Significant Tokens >> token spamprob #ham #spam >> 'sender:no real name:2**0' 0.0277535 2187 88 >> 'dismissed' 0.0374933 314 17 >> 'raising' 0.0417704 313 19 >> 'lives' 0.0580962 1012 88 >> 'ill' 0.0613924 1084 100 >> 'said' 0.0677803 6498 668 >> 'two' 0.08226 5200 659 >> 'put' 0.0828439 2632 336 >> 'were' 0.0845653 6094 796 >> 'recalled' 0.0862187 92 12 >> 'town' 0.0883783 600 82 >> 'being' 0.0894639 4312 599 >> 'letter' 0.093344 1595 232 >> 'unless' 0.0960663 687 103 >> 'stephan' 0.0968154 15 2 >> 'face' 0.0986506 1397 216 >> 'who' 0.0991493 8031 1250 >> 'knows' 0.102049 574 92 >> 'anyone' 0.104976 1828 303 >> 'them' 0.106325 4690 789 >> 'think' 0.107446 3584 610 >> 'keep' 0.109385 2517 437 >> 'him' 0.111552 2631 467 >> 'suspicions' 0.113796 40 7 >> 'went' 0.11401 1331 242 >> 'sound' 0.116592 596 111 >> 'care' 0.117491 1244 234 >> 'going' 0.119623 3503 673 >> 'sort' 0.119677 511 98 >> 'his' 0.119861 5717 1101 >> 'remained' 0.11998 271 52 >> 'heavily' 0.123551 232 46 >> 'last' 0.126157 5241 1070 >> 'subject:: ' 0.134951 9110 2010 >> 'voice' 0.135891 644 143 >> 'walk' 0.140296 339 78 >> 'everyone' 0.140502 1225 283 >> 'whatever' 0.141645 618 144 >> 'overdosed' 0.142155 48 11 >> 'mother' 0.144908 510 122 >> 'way' 0.146154 3458 837 >> 'was' 0.146612 8939 2172 >> 'would' 0.146893 7679 1870 >> 'but' 0.14865 8435 2083 >> 'past' 0.155513 1932 503 >> 'duty' 0.15756 326 86 >> 'been' 0.158577 6937 1849 >> 'away' 0.159247 1632 437 >> 'soon' 0.16154 1021 278 >> 'header:In-Reply-To:1' 0.162139 1791 490 >> 'made' 0.163602 3467 959 >> 'true' 0.164161 566 157 >> 'too' 0.164462 2199 612 >> 'then' 0.167186 3519 999 >> 'road' 0.169212 459 132 >> 'covington' 0.170591 18 5 >> 'firmly' 0.171729 69 20 >> 'received' 0.172468 1646 485 >> 'yes' 0.17276 275 81 >> 'other' 0.174723 6686 2002 >> 'offered' 0.177462 702 214 >> 'saw' 0.178119 738 226 >> 'might' 0.184601 2399 768 >> 'hotel' 0.185114 203 65 >> 'thought' 0.186457 1287 417 >> 'her' 0.187192 2831 922 >> 'indeed' 0.18721 191 62 >> 'lie' 0.188538 165 54 >> 'filled' 0.188682 329 108 >> 'assorted' 0.198662 32 11 >> 'intent' 0.199592 596 210 >> 'manner' 0.200765 192 68 >> 'second' 0.203991 1311 475 >> 'let' 0.207891 1835 681 >> 'much' 0.210328 3345 1260 >> 'back' 0.211425 3207 1216 >> 'place' 0.214507 1704 658 >> 'out' 0.216398 6503 2540 >> 'little' 0.218176 2273 897 >> 'within' 0.218497 1940 767 >> 'occupied' 0.218989 56 22 >> 'never' 0.222876 2224 902 >> 'take' 0.223351 4101 1668 >> 'subject:-' 0.223886 2564 1046 >> 'find' 0.224822 2482 1018 >> 'play' 0.230279 518 219 >> 'skip:n 10' 0.233772 2561 1105 >> 'eyes' 0.234231 294 127 >> 'that' 0.245614 11155 5137 >> 'thoughts' 0.250399 193 91 >> 'observed' 0.252899 109 52 >> 'not' 0.253605 9451 4542 >> 'have' 0.260054 10350 5145 >> 'myself' 0.268888 281 146 >> 'with' 0.272839 10712 5685 >> 'skip:r 10' 0.274264 4752 2540 >> 'look' 0.276317 1963 1060 >> 'can' 0.286752 7254 4125 >> 'guided' 0.29442 24 14 >> 'all' 0.300499 8283 5033 >> 'resign' 0.304561 39 24 >> 'contracts' 0.313223 163 105 >> 'subject:Alert' 0.322897 61 41 >> 'upon' 0.326586 853 585 >> 'skip:i 10' 0.332672 4717 3326 >> 'for' 0.339583 12494 9087 >> 'topics' 0.371008 114 95 >> 'the' 0.371613 13338 11157 >> 'above' 0.380529 678 589 >> 'header:Return-Path:1' 0.635635 6219 15346 >> 'consults' 0.695316 3 10 >> 'comparative' 0.728703 17 65 >> 'earnest' 0.747547 24 101 >> 'friendship' 0.796906 6 34 >> 'blush' 0.797234 13 73 >> 'skip:7 70' 0.805302 5 30 >> 'expedition' 0.825248 9 61 >> 'from:addr:g.wcvbss' 0.844828 0 1 >> 'from:addr:netnitco.net' 0.844828 0 1 >> 'from:name:raymond goins' 0.844828 0 1 >> 'lensalizarin' 0.844828 0 1 >> "m'scorset" 0.844828 0 1 >> 'message-id:@icsp.net' 0.844828 0 1 >> 'ownthat' 0.844828 0 1 >> 'prominents' 0.844828 0 1 >> 'roadsthat' 0.844828 0 1 >> 'sender:addr:athenet.net' 0.844828 0 1 >> 'sender:addr:h.nnq' 0.844828 0 1 >> 'subject:< ' 0.844828 0 1 >> 'subject:Stiles' 0.844828 0 1 >> 'totrue' 0.844828 0 1 >> 'virus:src="cid:' 0.888282 111 1250 >> 'congenial' 0.905802 5 70 >> 'taters' 0.907976 1 16 >> 'skip:7 90' 0.908163 0 2 >> 'header:Received:2' 0.914966 886 13487 >> 'diem' 0.92631 3 56 >> 'subject:CBXC' 0.949438 0 4 >> 'rotund' 0.952904 1 33 >> 'blushingly' 0.958716 0 5 >> 'refolding' 0.969799 0 7 >> 'egress' 0.970088 1 53 >> 'to:name:freemj' 0.988432 0 19 >> 'septennial' 0.990405 0 23 >> 'veal' 0.993066 0 32 >> 'youll' 0.993469 0 34 >> 'subject:Stock' 0.99571 0 52 >> 'casteth' 0.995868 0 54 >> 'cutlet' 0.996894 0 72 >> 'to:addr:hotpop.com' 0.997792 23 14803 >> >> Message Stream >> Return-Path: >> Received: from 38.113.3.52 (unknown [200.107.173.172]) >> by mx1.hotpop.com (Postfix) with SMTP >> id 5B8A0E8304; Sun, 23 Oct 2005 23:49:29 +0000 (UTC) >> Received: from spellbound.gape.jeffersonian.gauguin.es >> ([200.107.173.172] >> helo=scatterbrain.mail.elknet.net) by smtp9.bt.com with esmtp >> id 0X162p-8865LL-80; Mon, 24 Oct 2005 01:48:41 +0100 >> Message-Id: <8927397790.37444460700 at icsp.net> >> Sender: H.nnq at athenet.net >> Date: Sun, 23 Oct 2005 20:42:41 -0400 >> In-Reply-To: Your message of "Sun, 23 Oct 2005 20:46:41 -0400." >> <98802417987115.YV37184 at joel.renaissance.arden.net> >> From: "Raymond Goins" >> To: "Freemj" >> Subject: Fwd: Stock - Alert-CBXC< Neil Stiles >> MIME-Version: 1.0 >> Content-Type: multipart/related; >> boundary="--ZZR8PVzcRDTpf2Pu68MQiz" >> X-HotPOP-Delivered-To: freemj at hotpop.com >> >> >> negligiblestymie breakwatergrist m'scorset >> >> >> >> We went to the triumph comparative at egress diem then a mouldy sort >> of establishment have my place so I blushingly offered to resign it >> The septennial who made as much of my going away as if I were going >> to China received me as an was dismissed and other topics occupied us >> he remained so seldom raising >> his eyes unless to >> true Rosanne was suspicions arose within me that it was an ill >> assorted friendship that he never thought of being observed by anyone >> but was so intent upon her and upon his ownthat I received soon >> recalled me to myself and put me in the road back to the hotel I was >> so filled with the play and with the past for it was in a manner >> Everyone who knows you consults with you and is guided by you Stephan >> but on second thoughts I shall keep him to take care of me >> and refolding the letter it would be insupportable to me to think of >> I am in earnest at last so youll soon have to arrange our contracts >> and to bind us firmly to them been overdosed with taters I commanded >> him in my deepest voice to order a veal cutlet and potatoes Yes I am >> on an expedition of duty My mother lives a little way out of town and >> the roadsthat I received soon recalled me to myself and put me in the >> road back to the hotel for I saw a faint blush in her face you would >> have let me find it out for myself that would not lie too heavily >> upon her purse and to do my duty in it whatever it might be and the >> prominents walk and the congenial sound of the rotund casteth >> hovering above them all >> 7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg7Mik >> U >> R >> q >> reWfg7M6dwtJ4t1Fxn >> as he can look at me out of his two eyes Is he indeed said Mr >> Covington >> >> >> lensalizarin impregnatecost >> >>
>>
> SRC="cid:lTN1QnT11CtJIk8H6J5X7INGgMff2pS at prairieweb.com" border="0" >> ALT="negligiblestymie breakwatergrist m'scorset"> >>
> size=1>
> size=1>

We went to the triumph >> comparative at egress diem then a mouldy sort of >> establishment
have my place so I blushingly offered to resign it >> The septennial who made as much of >> my going away as if I were going to China received me as an
was >> dismissed and other topics occupied us he remained so seldom raising >> his eyes unless to
true Rosanne >> was suspicions arose within me that it was an ill assorted >> friendship
that he never thought of being observed by anyone but >> was so intent upon her and upon his own> SIZE=2>that I received soon recalled me to >> myself and put me in the road back to the hotel
I was so filled >> with the >> play and with the past for it was in a manner
Everyone who >> knows you >> consults with you and is guided by you Stephan
but on second >> thoughts I shall keep him to take care of me >>
and refolding the letter it >> would be >> insupportable to me to think of
I am in earnest at last so >> youll soon >> have to arrange our contracts and to bind us firmly to >> them
been overdosed with taters I commanded him in >> my deepest voice to order a veal cutlet and potatoes
Yes I am on >> an expedition of duty My mother lives a little way out of town and >> the roadsthat I received soon >> recalled me to myself and put me in the road back to the >> hotel
for I saw a faint blush in her face you would have let me >> find it out for myself that would not lie too heavily >> upon her purse and to do my duty in it whatever it might be
and >> the prominents walk and the congenial sound of the rotund casteth >> hovering above them all >>
7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg >> 7 >> M >> ikURq >> reWfg7M6dwtJ4t1Fxn
as he can look at me out of his two eyes Is he >> indeed said Mr Covington
>> >> All Message Tokens >> 187 unique tokens >> >> 'above' >> 'all' >> 'and' >> 'anyone' >> 'arose' >> 'arrange' >> 'assorted' >> 'away' >> 'back' >> 'been' >> 'being' >> 'bind' >> 'blush' >> 'blushingly' >> 'but' >> 'can' >> 'care' >> 'casteth' >> 'cc:none' >> 'china' >> 'commanded' >> 'comparative' >> 'congenial' >> 'consults' >> 'content-type:text/plain' >> 'contracts' >> 'covington' >> 'cutlet' >> 'deepest' >> 'diem' >> 'dismissed' >> 'duty' >> 'earnest' >> 'egress' >> 'everyone' >> 'expedition' >> 'eyes' >> 'face' >> 'faint' >> 'filled' >> 'find' >> 'firmly' >> 'for' >> 'friendship' >> 'from:addr:g.wcvbss' >> 'from:addr:netnitco.net' >> 'from:name:raymond goins' >> 'going' >> 'guided' >> 'have' >> 'header:Date:1' >> 'header:From:1' >> 'header:In-Reply-To:1' >> 'header:MIME-Version:1' >> 'header:Message-Id:1' >> 'header:Received:2' >> 'header:Return-Path:1' >> 'header:Subject:1' >> 'header:To:1' >> 'heavily' >> 'her' >> 'him' >> 'his' >> 'hotel' >> 'hovering' >> 'ill' >> 'indeed' >> 'intent' >> 'keep' >> 'knows' >> 'last' >> 'lensalizarin' >> 'let' >> 'letter' >> 'lie' >> 'little' >> 'lives' >> 'look' >> "m'scorset" >> 'made' >> 'manner' >> 'message-id:@icsp.net' >> 'might' >> 'mother' >> 'mouldy' >> 'much' >> 'myself' >> 'never' >> 'not' >> 'observed' >> 'occupied' >> 'offered' >> 'order' >> 'other' >> 'our' >> 'out' >> 'overdosed' >> 'ownthat' >> 'past' >> 'place' >> 'play' >> 'potatoes' >> 'prominents' >> 'purse' >> 'put' >> 'raising' >> 'recalled' >> 'received' >> 'refolding' >> 'remained' >> 'reply-to:none' >> 'resign' >> 'road' >> 'roadsthat' >> 'rosanne' >> 'rotund' >> 'said' >> 'saw' >> 'second' >> 'seldom' >> 'sender:addr:athenet.net' >> 'sender:addr:h.nnq' >> 'sender:no real name:2**0' >> 'septennial' >> 'shall' >> 'skip:7 70' >> 'skip:7 90' >> 'skip:b 10' >> 'skip:e 10' >> 'skip:i 10' >> 'skip:n 10' >> 'skip:r 10' >> 'soon' >> 'sort' >> 'sound' >> 'stephan' >> 'subject: ' >> 'subject: - ' >> 'subject:-' >> 'subject:: ' >> 'subject:< ' >> 'subject:Alert' >> 'subject:CBXC' >> 'subject:Fwd' >> 'subject:Neil' >> 'subject:Stiles' >> 'subject:Stock' >> 'suspicions' >> 'take' >> 'taters' >> 'that' >> 'the' >> 'them' >> 'then' >> 'think' >> 'thought' >> 'thoughts' >> 'to:2**0' >> 'to:addr:freemj' >> 'to:addr:hotpop.com' >> 'to:name:freemj' >> 'too' >> 'topics' >> 'totrue' >> 'town' >> 'triumph' >> 'true' >> 'two' >> 'unless' >> 'upon' >> 'veal' >> 'virus:src="cid:' >> 'voice' >> 'walk' >> 'was' >> 'way' >> 'went' >> 'were' >> 'whatever' >> 'who' >> 'with' >> 'within' >> 'would' >> 'x-mailer:none' >> 'yes' >> 'you' >> 'youll' >> >> -----Original Message----- >> From: spambayes-bounces at python.org >> [mailto:spambayes-bounces at python.org] On Behalf Of Tony Meyer >> Sent: Sunday, October 23, 2005 9:43 PM >> To: >> Cc: spambayes at python.org >> Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to >> HandleEmbeddedImages) >> >>> Something really needs to be done about this embedded image Spam. >>> Honestly, >>> SpamBayes appears to be ineffective against all these images, >> >> Can you post an example of a message that is incorrectly classified, >> *with the spambayes clues* for the message? The Outlook plug-in >> provides this via the "Show Clues for this Message" item in the >> SpamBayes menu. >> >> [...] >>> I'm sure OCR isn't the only way, but the words are there in plain >>> view. It seems like the obvious way to resolve this. >> >> Obvious isn't always best. One of the tenets here is "stupid beats >> smart" - I think doing some sort of OCR on images would fall into the >> "smart" category, and generating simple tokens from the images would >> fall into the "stupid" category and be more successful. Just my >> opinion, of course, but that's what I'd test if I had time (perhaps >> over the (southern hemisphere) summer...or maybe I can convince one >> of my employers that this would be worth doing in paid time). >> >>> SpamBayes has been such a great program for me and my colleges, >>> family and friends. I can only hope that the project sees fit to >>> resolve this soon. >> >> It's not really a case of "seeing fit" - the issue is that the >> developers are very short on time at the moment (contributions have >> always been, and always will be, welcome) and, in addition, this is a >> complex problem. >> >> =Tony.Meyer >> >> -- >> Please always include the list (spambayes at python.org) in your >> replies (reply-all), and please don't send me personal mail about >> SpamBayes. >> http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. >> >> >> _______________________________________________ >> SpamBayes at python.org >> http://mail.python.org/mailman/listinfo/spambayes >> Check the FAQ before asking: http://spambayes.sf.net/faq.html >> >> >> _______________________________________________ >> SpamBayes at python.org >> http://mail.python.org/mailman/listinfo/spambayes >> Check the FAQ before asking: http://spambayes.sf.net/faq.html >> > > _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From andis59 at gmail.com Thu Oct 27 10:40:13 2005 From: andis59 at gmail.com (Anders Eriksson) Date: Thu, 27 Oct 2005 10:40:13 +0200 Subject: [Spambayes] Best in Test Message-ID: <1alhe85x3lopl.dlg@morateknikutveckling.se> Hello! In the latest issue of "Datormagazin" a Swedish Computer Magazine there is a test of Anti-Spam software and SpamBayes is named "Best in Test" The test contained about 15 different programs most Commercial. Nice working all on the Developing Team! // Anders -- English isn't my first, or second, language. So anything rude or strange are due to the translation From ksg at telusplanet.net Thu Oct 27 16:11:58 2005 From: ksg at telusplanet.net (Ken Gordon) Date: Thu, 27 Oct 2005 08:11:58 -0600 Subject: [Spambayes] Inspecting images (was: SpamBayes toHandleEmbeddedImages) In-Reply-To: <20051027035446.46AD01A03E1@smtp-1.hotpop.com> References: <20051027035446.46AD01A03E1@smtp-1.hotpop.com> Message-ID: <4c66d630fac1d32ad79dd72dbbc1064e@telusplanet.net> I was wrong - misled by my own failure to run a controlled experiment. These things run so well and smoothly that one tends to forget about them - they merge with the background. But I run SpamBayes in combination with the Mail.app spam filter under OS X. So as a control, I turned the Mail.app filter off for a while. The results of the experiment are that SB catches some; Mail.app catches others; I see very few. Except for those that are trapped by the sort of things that are pointed to in the SB header that I posted, the mainly-image spams are being caught by Mail.app, not by SpamBayes. I won't presume to comment on whether there is anything in Mail.app that could inform how SB deals with images. Now I will return to my blissful spam-free existence by turning the Mail.app filter on again. Ahhhhh ... that's better. --- Ken Gordon On 2005 Oct 26, at 21:55, wrote: > Ken, > Please post the entire Spambayes Clues listing, so I can see what > Spambayes > is doing with all the erroneous ham text that's included at the bottom > of > your e-mail message example. > > Thanks, > FMJ > > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On > Behalf Of Ken Gordon > Sent: Wednesday, October 26, 2005 8:26 AM > To: spambayes at python.org; > Subject: Re: [Spambayes] Inspecting images (was: SpamBayes > toHandleEmbeddedImages) > > There's a lot more to spambayes than just evaluating content. Here's > the SB > Evidence header from a recent spam. But for 'charset', very little of > this > has to do with the content, yet it was correctly classified as spam. > >> X-Spambayes-Evidence: '*H*': 0.00; '*S*': 1.00; > 'received:192.168.1': >> 0.10; 'subject:skip:B 10': 0.16; 'received:192.168': 0.20; >> 'received:192': 0.21; 'url:www': 0.23; 'content-type:image/jpeg': >> 0.34; 'to:addr:none': 0.38; 'header:Return-Path:1': 0.38; >> 'header:MIME-Version:1': 0.61; 'url:': 0.64; 'x-mailer:none': 0.71; >> 'to:no real name:2**0': 0.72; 'from:name:\x1b$b5z at nf`1{\x1b(b': 0.84; >> 'message-id:@imx100522.ath.cx': 0.84; 'received:imx100522.ath.cx': >> 0.84; 'url:fetish': 0.84; 'received:192.168.1.11': 0.91; >> 'received:kick': 0.91; 'content-type:multipart/related': 0.92; >> 'received:210.153': 0.93; 'received:ath.cx': 0.93; 'url:cc': 0.93; >> 'virus:src="cid:': 0.95; 'content-type/type:multipart/alternative': >> 0.96; 'received:cx': 0.97; 'email addr:yahoo.co.jp': 0.99; 'skip:\x1b >> 80': 0.99; 'from:addr:yahoo.co.jp': 1.00; 'from:charset:iso-2022-jp': >> 1.00; 'skip:\x1b 60': 1.00; 'skip:\x1b 30': 1.00; 'skip:\x1b 20': >> 1.00; 'skip:\x1b 50': 1.00; 'subject:$': 1.00; 'received:210': 1.00; >> 'charset:iso-2022-jp': 1.00; 'subject:\x1b$': 1.00; >> 'subjectcharset:iso-2022-jp': 1.00 > > > > On 2005 Oct 25, at 8:37, wrote: > >> How? Technically speaking, what could your SpamBayes installation be >> doing differently? These are ALL ham words, so how is it that your >> e-mail could be classifying all of this as Spam? If it is, I suspect >> you're losing a lot of legitimate e-mail with it. >> >> FMJ >> >> -----Original Message----- >> From: Ken Gordon [mailto:ksg at telusplanet.net] >> Sent: Monday, October 24, 2005 8:58 PM >> To: FreeMJ at HotPop.com >> Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to >> HandleEmbeddedImages) >> >> My installation of SpamBayes catches nearly all of these. I don't see >> one a month outside of the Spam folder. >> >> --- >> Ken Gordon >> (780) 628-2758 >> http://www.wolfe-gordon.ca >> On 2005 Oct 24, at 20:18, wrote: >> >>> Hi Tony, >>> The problem is, they keep changing the meaningless text at the bottom >>> of the e-mail all the time, to confuse the Spam filter. They're >>> picking Hammy words. And, as you can see, it's a highly effective >>> technique. In other words, NONE of the "Tokens" should actually be >>> "Significant", it's the image that needs to be scored in this case. >>> Here's the spambayes clues for one of the e-mails: >>> >>> Combined Score: 3% (0.0330173) >>> Internal ham score (*H*): 0.999976 >>> Internal spam score (*S*): 0.0660102 >>> >>> # ham trained on: 14237 >>> # spam trained on: 20138 >>> >>> 150 Significant Tokens >>> token spamprob #ham #spam >>> 'sender:no real name:2**0' 0.0277535 2187 88 >>> 'dismissed' 0.0374933 314 17 >>> 'raising' 0.0417704 313 19 >>> 'lives' 0.0580962 1012 88 >>> 'ill' 0.0613924 1084 100 >>> 'said' 0.0677803 6498 668 >>> 'two' 0.08226 5200 659 >>> 'put' 0.0828439 2632 336 >>> 'were' 0.0845653 6094 796 >>> 'recalled' 0.0862187 92 12 >>> 'town' 0.0883783 600 82 >>> 'being' 0.0894639 4312 599 >>> 'letter' 0.093344 1595 232 >>> 'unless' 0.0960663 687 103 >>> 'stephan' 0.0968154 15 2 >>> 'face' 0.0986506 1397 216 >>> 'who' 0.0991493 8031 1250 >>> 'knows' 0.102049 574 92 >>> 'anyone' 0.104976 1828 303 >>> 'them' 0.106325 4690 789 >>> 'think' 0.107446 3584 610 >>> 'keep' 0.109385 2517 437 >>> 'him' 0.111552 2631 467 >>> 'suspicions' 0.113796 40 7 >>> 'went' 0.11401 1331 242 >>> 'sound' 0.116592 596 111 >>> 'care' 0.117491 1244 234 >>> 'going' 0.119623 3503 673 >>> 'sort' 0.119677 511 98 >>> 'his' 0.119861 5717 1101 >>> 'remained' 0.11998 271 52 >>> 'heavily' 0.123551 232 46 >>> 'last' 0.126157 5241 1070 >>> 'subject:: ' 0.134951 9110 2010 >>> 'voice' 0.135891 644 143 >>> 'walk' 0.140296 339 78 >>> 'everyone' 0.140502 1225 283 >>> 'whatever' 0.141645 618 144 >>> 'overdosed' 0.142155 48 11 >>> 'mother' 0.144908 510 122 >>> 'way' 0.146154 3458 837 >>> 'was' 0.146612 8939 2172 >>> 'would' 0.146893 7679 1870 >>> 'but' 0.14865 8435 2083 >>> 'past' 0.155513 1932 503 >>> 'duty' 0.15756 326 86 >>> 'been' 0.158577 6937 1849 >>> 'away' 0.159247 1632 437 >>> 'soon' 0.16154 1021 278 >>> 'header:In-Reply-To:1' 0.162139 1791 490 >>> 'made' 0.163602 3467 959 >>> 'true' 0.164161 566 157 >>> 'too' 0.164462 2199 612 >>> 'then' 0.167186 3519 999 >>> 'road' 0.169212 459 132 >>> 'covington' 0.170591 18 5 >>> 'firmly' 0.171729 69 20 >>> 'received' 0.172468 1646 485 >>> 'yes' 0.17276 275 81 >>> 'other' 0.174723 6686 2002 >>> 'offered' 0.177462 702 214 >>> 'saw' 0.178119 738 226 >>> 'might' 0.184601 2399 768 >>> 'hotel' 0.185114 203 65 >>> 'thought' 0.186457 1287 417 >>> 'her' 0.187192 2831 922 >>> 'indeed' 0.18721 191 62 >>> 'lie' 0.188538 165 54 >>> 'filled' 0.188682 329 108 >>> 'assorted' 0.198662 32 11 >>> 'intent' 0.199592 596 210 >>> 'manner' 0.200765 192 68 >>> 'second' 0.203991 1311 475 >>> 'let' 0.207891 1835 681 >>> 'much' 0.210328 3345 1260 >>> 'back' 0.211425 3207 1216 >>> 'place' 0.214507 1704 658 >>> 'out' 0.216398 6503 2540 >>> 'little' 0.218176 2273 897 >>> 'within' 0.218497 1940 767 >>> 'occupied' 0.218989 56 22 >>> 'never' 0.222876 2224 902 >>> 'take' 0.223351 4101 1668 >>> 'subject:-' 0.223886 2564 1046 >>> 'find' 0.224822 2482 1018 >>> 'play' 0.230279 518 219 >>> 'skip:n 10' 0.233772 2561 1105 >>> 'eyes' 0.234231 294 127 >>> 'that' 0.245614 11155 5137 >>> 'thoughts' 0.250399 193 91 >>> 'observed' 0.252899 109 52 >>> 'not' 0.253605 9451 4542 >>> 'have' 0.260054 10350 5145 >>> 'myself' 0.268888 281 146 >>> 'with' 0.272839 10712 5685 >>> 'skip:r 10' 0.274264 4752 2540 >>> 'look' 0.276317 1963 1060 >>> 'can' 0.286752 7254 4125 >>> 'guided' 0.29442 24 14 >>> 'all' 0.300499 8283 5033 >>> 'resign' 0.304561 39 24 >>> 'contracts' 0.313223 163 105 >>> 'subject:Alert' 0.322897 61 41 >>> 'upon' 0.326586 853 585 >>> 'skip:i 10' 0.332672 4717 3326 >>> 'for' 0.339583 12494 9087 >>> 'topics' 0.371008 114 95 >>> 'the' 0.371613 13338 11157 >>> 'above' 0.380529 678 589 >>> 'header:Return-Path:1' 0.635635 6219 15346 >>> 'consults' 0.695316 3 10 >>> 'comparative' 0.728703 17 65 >>> 'earnest' 0.747547 24 101 >>> 'friendship' 0.796906 6 34 >>> 'blush' 0.797234 13 73 >>> 'skip:7 70' 0.805302 5 30 >>> 'expedition' 0.825248 9 61 >>> 'from:addr:g.wcvbss' 0.844828 0 1 >>> 'from:addr:netnitco.net' 0.844828 0 1 >>> 'from:name:raymond goins' 0.844828 0 1 >>> 'lensalizarin' 0.844828 0 1 >>> "m'scorset" 0.844828 0 1 >>> 'message-id:@icsp.net' 0.844828 0 1 >>> 'ownthat' 0.844828 0 1 >>> 'prominents' 0.844828 0 1 >>> 'roadsthat' 0.844828 0 1 >>> 'sender:addr:athenet.net' 0.844828 0 1 >>> 'sender:addr:h.nnq' 0.844828 0 1 >>> 'subject:< ' 0.844828 0 1 >>> 'subject:Stiles' 0.844828 0 1 >>> 'totrue' 0.844828 0 1 >>> 'virus:src="cid:' 0.888282 111 1250 >>> 'congenial' 0.905802 5 70 >>> 'taters' 0.907976 1 16 >>> 'skip:7 90' 0.908163 0 2 >>> 'header:Received:2' 0.914966 886 13487 >>> 'diem' 0.92631 3 56 >>> 'subject:CBXC' 0.949438 0 4 >>> 'rotund' 0.952904 1 33 >>> 'blushingly' 0.958716 0 5 >>> 'refolding' 0.969799 0 7 >>> 'egress' 0.970088 1 53 >>> 'to:name:freemj' 0.988432 0 19 >>> 'septennial' 0.990405 0 23 >>> 'veal' 0.993066 0 32 >>> 'youll' 0.993469 0 34 >>> 'subject:Stock' 0.99571 0 52 >>> 'casteth' 0.995868 0 54 >>> 'cutlet' 0.996894 0 72 >>> 'to:addr:hotpop.com' 0.997792 23 14803 >>> >>> Message Stream >>> Return-Path: >>> Received: from 38.113.3.52 (unknown [200.107.173.172]) >>> by mx1.hotpop.com (Postfix) with SMTP >>> id 5B8A0E8304; Sun, 23 Oct 2005 23:49:29 +0000 (UTC) >>> Received: from spellbound.gape.jeffersonian.gauguin.es >>> ([200.107.173.172] >>> helo=scatterbrain.mail.elknet.net) by smtp9.bt.com with esmtp >>> id 0X162p-8865LL-80; Mon, 24 Oct 2005 01:48:41 +0100 >>> Message-Id: <8927397790.37444460700 at icsp.net> >>> Sender: H.nnq at athenet.net >>> Date: Sun, 23 Oct 2005 20:42:41 -0400 >>> In-Reply-To: Your message of "Sun, 23 Oct 2005 20:46:41 -0400." >>> <98802417987115.YV37184 at joel.renaissance.arden.net> >>> From: "Raymond Goins" >>> To: "Freemj" >>> Subject: Fwd: Stock - Alert-CBXC< Neil Stiles >>> MIME-Version: 1.0 >>> Content-Type: multipart/related; >>> boundary="--ZZR8PVzcRDTpf2Pu68MQiz" >>> X-HotPOP-Delivered-To: freemj at hotpop.com >>> >>> >>> negligiblestymie breakwatergrist m'scorset >>> >>> >>> >>> We went to the triumph comparative at egress diem then a mouldy sort >>> of establishment have my place so I blushingly offered to resign it >>> The septennial who made as much of my going away as if I were going >>> to China received me as an was dismissed and other topics occupied us >>> he remained so seldom raising >>> his eyes unless to >>> true Rosanne was suspicions arose within me that it was an ill >>> assorted friendship that he never thought of being observed by anyone >>> but was so intent upon her and upon his ownthat I received soon >>> recalled me to myself and put me in the road back to the hotel I was >>> so filled with the play and with the past for it was in a manner >>> Everyone who knows you consults with you and is guided by you Stephan >>> but on second thoughts I shall keep him to take care of me >>> and refolding the letter it would be insupportable to me to think of >>> I am in earnest at last so youll soon have to arrange our contracts >>> and to bind us firmly to them been overdosed with taters I commanded >>> him in my deepest voice to order a veal cutlet and potatoes Yes I am >>> on an expedition of duty My mother lives a little way out of town and >>> the roadsthat I received soon recalled me to myself and put me in the >>> road back to the hotel for I saw a faint blush in her face you would >>> have let me find it out for myself that would not lie too heavily >>> upon her purse and to do my duty in it whatever it might be and the >>> prominents walk and the congenial sound of the rotund casteth >>> hovering above them all >>> 7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg7Mik >>> U >>> R >>> q >>> reWfg7M6dwtJ4t1Fxn >>> as he can look at me out of his two eyes Is he indeed said Mr >>> Covington >>> >>> >>> lensalizarin impregnatecost >>> >>>
>>>
>> SRC="cid:lTN1QnT11CtJIk8H6J5X7INGgMff2pS at prairieweb.com" border="0" >>> ALT="negligiblestymie breakwatergrist m'scorset"> >>>
>> size=1>
>> size=1>

We went to the triumph >>> comparative at egress diem then a mouldy sort of >>> establishment
have my place so I blushingly offered to resign it >>> The septennial who made as much of >>> my going away as if I were going to China received me as an
was >>> dismissed and other topics occupied us he remained so seldom raising >>> his eyes unless to
true Rosanne >>> was suspicions arose within me that it was an ill assorted >>> friendship
that he never thought of being observed by anyone but >>> was so intent upon her and upon his own>> SIZE=2>that I received soon recalled me to >>> myself and put me in the road back to the hotel
I was so filled >>> with the >>> play and with the past for it was in a manner
Everyone who >>> knows you >>> consults with you and is guided by you Stephan
but on second >>> thoughts I shall keep him to take care of me >>>
and refolding the letter it >>> would be >>> insupportable to me to think of
I am in earnest at last so >>> youll soon >>> have to arrange our contracts and to bind us firmly to >>> them
been overdosed with taters I commanded him in >>> my deepest voice to order a veal cutlet and potatoes
Yes I am on >>> an expedition of duty My mother lives a little way out of town and >>> the roadsthat I received soon >>> recalled me to myself and put me in the road back to the >>> hotel
for I saw a faint blush in her face you would have let me >>> find it out for myself that would not lie too heavily >>> upon her purse and to do my duty in it whatever it might be
and >>> the prominents walk and the congenial sound of the rotund casteth >>> hovering above them all >>>
7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg >>> 7 >>> M >>> ikURq >>> reWfg7M6dwtJ4t1Fxn
as he can look at me out of his two eyes Is he >>> indeed said Mr Covington
>>> >>> All Message Tokens >>> 187 unique tokens >>> >>> 'above' >>> 'all' >>> 'and' >>> 'anyone' >>> 'arose' >>> 'arrange' >>> 'assorted' >>> 'away' >>> 'back' >>> 'been' >>> 'being' >>> 'bind' >>> 'blush' >>> 'blushingly' >>> 'but' >>> 'can' >>> 'care' >>> 'casteth' >>> 'cc:none' >>> 'china' >>> 'commanded' >>> 'comparative' >>> 'congenial' >>> 'consults' >>> 'content-type:text/plain' >>> 'contracts' >>> 'covington' >>> 'cutlet' >>> 'deepest' >>> 'diem' >>> 'dismissed' >>> 'duty' >>> 'earnest' >>> 'egress' >>> 'everyone' >>> 'expedition' >>> 'eyes' >>> 'face' >>> 'faint' >>> 'filled' >>> 'find' >>> 'firmly' >>> 'for' >>> 'friendship' >>> 'from:addr:g.wcvbss' >>> 'from:addr:netnitco.net' >>> 'from:name:raymond goins' >>> 'going' >>> 'guided' >>> 'have' >>> 'header:Date:1' >>> 'header:From:1' >>> 'header:In-Reply-To:1' >>> 'header:MIME-Version:1' >>> 'header:Message-Id:1' >>> 'header:Received:2' >>> 'header:Return-Path:1' >>> 'header:Subject:1' >>> 'header:To:1' >>> 'heavily' >>> 'her' >>> 'him' >>> 'his' >>> 'hotel' >>> 'hovering' >>> 'ill' >>> 'indeed' >>> 'intent' >>> 'keep' >>> 'knows' >>> 'last' >>> 'lensalizarin' >>> 'let' >>> 'letter' >>> 'lie' >>> 'little' >>> 'lives' >>> 'look' >>> "m'scorset" >>> 'made' >>> 'manner' >>> 'message-id:@icsp.net' >>> 'might' >>> 'mother' >>> 'mouldy' >>> 'much' >>> 'myself' >>> 'never' >>> 'not' >>> 'observed' >>> 'occupied' >>> 'offered' >>> 'order' >>> 'other' >>> 'our' >>> 'out' >>> 'overdosed' >>> 'ownthat' >>> 'past' >>> 'place' >>> 'play' >>> 'potatoes' >>> 'prominents' >>> 'purse' >>> 'put' >>> 'raising' >>> 'recalled' >>> 'received' >>> 'refolding' >>> 'remained' >>> 'reply-to:none' >>> 'resign' >>> 'road' >>> 'roadsthat' >>> 'rosanne' >>> 'rotund' >>> 'said' >>> 'saw' >>> 'second' >>> 'seldom' >>> 'sender:addr:athenet.net' >>> 'sender:addr:h.nnq' >>> 'sender:no real name:2**0' >>> 'septennial' >>> 'shall' >>> 'skip:7 70' >>> 'skip:7 90' >>> 'skip:b 10' >>> 'skip:e 10' >>> 'skip:i 10' >>> 'skip:n 10' >>> 'skip:r 10' >>> 'soon' >>> 'sort' >>> 'sound' >>> 'stephan' >>> 'subject: ' >>> 'subject: - ' >>> 'subject:-' >>> 'subject:: ' >>> 'subject:< ' >>> 'subject:Alert' >>> 'subject:CBXC' >>> 'subject:Fwd' >>> 'subject:Neil' >>> 'subject:Stiles' >>> 'subject:Stock' >>> 'suspicions' >>> 'take' >>> 'taters' >>> 'that' >>> 'the' >>> 'them' >>> 'then' >>> 'think' >>> 'thought' >>> 'thoughts' >>> 'to:2**0' >>> 'to:addr:freemj' >>> 'to:addr:hotpop.com' >>> 'to:name:freemj' >>> 'too' >>> 'topics' >>> 'totrue' >>> 'town' >>> 'triumph' >>> 'true' >>> 'two' >>> 'unless' >>> 'upon' >>> 'veal' >>> 'virus:src="cid:' >>> 'voice' >>> 'walk' >>> 'was' >>> 'way' >>> 'went' >>> 'were' >>> 'whatever' >>> 'who' >>> 'with' >>> 'within' >>> 'would' >>> 'x-mailer:none' >>> 'yes' >>> 'you' >>> 'youll' >>> >>> -----Original Message----- >>> From: spambayes-bounces at python.org >>> [mailto:spambayes-bounces at python.org] On Behalf Of Tony Meyer >>> Sent: Sunday, October 23, 2005 9:43 PM >>> To: >>> Cc: spambayes at python.org >>> Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to >>> HandleEmbeddedImages) >>> >>>> Something really needs to be done about this embedded image Spam. >>>> Honestly, >>>> SpamBayes appears to be ineffective against all these images, >>> >>> Can you post an example of a message that is incorrectly classified, >>> *with the spambayes clues* for the message? The Outlook plug-in >>> provides this via the "Show Clues for this Message" item in the >>> SpamBayes menu. >>> >>> [...] >>>> I'm sure OCR isn't the only way, but the words are there in plain >>>> view. It seems like the obvious way to resolve this. >>> >>> Obvious isn't always best. One of the tenets here is "stupid beats >>> smart" - I think doing some sort of OCR on images would fall into the >>> "smart" category, and generating simple tokens from the images would >>> fall into the "stupid" category and be more successful. Just my >>> opinion, of course, but that's what I'd test if I had time (perhaps >>> over the (southern hemisphere) summer...or maybe I can convince one >>> of my employers that this would be worth doing in paid time). >>> >>>> SpamBayes has been such a great program for me and my colleges, >>>> family and friends. I can only hope that the project sees fit to >>>> resolve this soon. >>> >>> It's not really a case of "seeing fit" - the issue is that the >>> developers are very short on time at the moment (contributions have >>> always been, and always will be, welcome) and, in addition, this is a >>> complex problem. >>> >>> =Tony.Meyer >>> >>> -- >>> Please always include the list (spambayes at python.org) in your >>> replies (reply-all), and please don't send me personal mail about >>> SpamBayes. >>> http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains >>> this. >>> >>> >>> _______________________________________________ >>> SpamBayes at python.org >>> http://mail.python.org/mailman/listinfo/spambayes >>> Check the FAQ before asking: http://spambayes.sf.net/faq.html >>> >>> >>> _______________________________________________ >>> SpamBayes at python.org >>> http://mail.python.org/mailman/listinfo/spambayes >>> Check the FAQ before asking: http://spambayes.sf.net/faq.html >>> >> >> > > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html > > From richie at entrian.com Thu Oct 27 18:03:56 2005 From: richie at entrian.com (Richie Hindle) Date: Thu, 27 Oct 2005 17:03:56 +0100 Subject: [Spambayes] HowTo disable the "Save and Shutdown" Button in the Webinterface on linux ? In-Reply-To: <435F494E.7040409@imst.de> References: <435F494E.7040409@imst.de> Message-ID: Hi Florian, > I found the file "ui.html" in the source directory which seems to be the > template of the page but I am not really familar to Python and my > changes in this file took no effect. I assume you're running from source. You need to install resourcepackage from http://resourcepackage.sourceforge.net/ in order for your changes to anything in the "resource" directory to take effect. Download ResourcePackage-1.0.0.tar.gz, unpack it into a temporary area, cd to that area, and run "python setup.py install". You can then delete the unpacked files. > I would also like to have the feature to show only the headers of the > classified mails to anybody who uses the webinterface ..... In ProxyUI.py there's a class called ProxyUserInterface with a member function called onView() - it's that function that shows the emails: if message is not None: self.write("
%s
" % cgi.escape(message.as_string())) You need to change that to just show the headers... I don't know off the top of my head whether the "email" package has a way to do that, but this hack should work: if message is not None: whole_message = message.as_string() split_message = re.split(r'\r*\n\r*\n', whole_message, 1) self.write("
%s
" % cgi.escape(split_message[0])) -- Richie Hindle richie at entrian.com From Debra.Tatu at unisys.com Fri Oct 28 02:00:35 2005 From: Debra.Tatu at unisys.com (Tatu, Debra) Date: Thu, 27 Oct 2005 19:00:35 -0500 Subject: [Spambayes] Help... Message-ID: <089B0D75973E1241B941D0A9854F23FC025CF515@USEA-EXCH2.na.uis.unisys.com> I have read through the Troubleshooting Guide and the Bug List but cannot find help. I have uninstalled and reinstalled SpamBayes several times. When I first Open Outlook, SpamBayes appears to work properly. But later, I'll notice that it's not filtering. I'll mark the item for deletion and it won't move to the Junk Folder. When I go to the Suspect folder and mark and item for deletion, it won't move to the Junk Folder either. Something appears to be stopping the filtering. Attached is the log. If you can provide any assistance, I would be grateful. Debra Six Sigma Lean Green Belt Image Exchange Services Net 299-4544 Imagine it. Done. THIS COMMUNICATION MAY CONTAIN CONFIDENTIAL AND/OR OTHERWISE PROPRIETARY MATERIAL and is thus for use only by the intended recipient. If you received this in error, please contact the sender and delete the e-mail and its attachments from all computers. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051027/cb86e9fc/attachment.htm -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/gif Size: 51076 bytes Desc: 8_1_231.gif Url : http://mail.python.org/pipermail/spambayes/attachments/20051027/cb86e9fc/attachment-0002.gif -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/gif Size: 568 bytes Desc: Unisys.gif Url : http://mail.python.org/pipermail/spambayes/attachments/20051027/cb86e9fc/attachment-0003.gif -------------- next part -------------- A non-text attachment was scrubbed... Name: spambayes1.log Type: application/octet-stream Size: 39399 bytes Desc: spambayes1.log Url : http://mail.python.org/pipermail/spambayes/attachments/20051027/cb86e9fc/spambayes1-0001.obj From ksg at telusplanet.net Fri Oct 28 03:14:52 2005 From: ksg at telusplanet.net (Ken Gordon) Date: Thu, 27 Oct 2005 19:14:52 -0600 Subject: [Spambayes] Inspecting images (was: SpamBayes toHandleEmbeddedImages) In-Reply-To: <4c66d630fac1d32ad79dd72dbbc1064e@telusplanet.net> References: <20051027035446.46AD01A03E1@smtp-1.hotpop.com> <4c66d630fac1d32ad79dd72dbbc1064e@telusplanet.net> Message-ID: Now I'm not so sure. Here's a message - including the SB headings - that was almost entirely images (trackable, but I don't download images by default), just a bit of white text (I'm sending the source). SB caught it before it got to my Mail spam filter. > Return-Path: <22-6103047-telusplanet.net?ksg at stderr.coolhealer.com> > Received: from bal.coolhealer.com ([65.223.9.164]) > by priv-edtnes09.telusplanet.net > (InterMail vM.6.01.04.04 201-2131-118-104-20050224) with SMTP id > <20051027235225.EKWU17196.priv- > edtnes09.telusplanet.net at bal.coolhealer.com> > for ; Thu, 27 Oct 2005 17:52:25 -0600 > MIME-Version: 1.0 > X-Accept-Language: en > X-Priority: Normal > From: BotoxAlert > To: ksg at telusplanet.net > Subject: Spa Weekend for two > Date: Thu, 27 Oct 2005 14:27:07 PST > Message-ID: > Content-Type: text/html; charset="ISO-8859-1" > Content-Transfer-Encoding: 7bit > X-Spambayes-Classification: spam > X-Spambayes-Spam-Probability: 0.95 > X-Spambayes-Level: ********* > X-Spambayes-Evidence: '*H*': 0.07; '*S*': 0.96; 'url:images': 0.14; > 'url:email': 0.20; 'to:addr:ksg': 0.22; 'url:gif': 0.23; > 'to:addr:telusplanet.net': 0.24; 'url:3': 0.27; 'url:2': 0.31; > 'url:0': 0.32; 'url:unsub': 0.33; 'url:e': 0.36; 'url:1': 0.38; > 'header:Return-Path:1': 0.38; 'header:MIME-Version:1': 0.61; > 'header:Message-ID:1': 0.61; 'received:65': 0.65; > 'header:Received:1': 0.69; 'x-mailer:none': 0.71; > 'to:no real name:2**0': 0.72; 'url:php': 0.73; 'url:track': 0.81; > 'received:65.223': 0.91; 'received:65.223.9': 0.91; > 'url:6yb5nrgfbbuffzgrpzgr': 0.98; 'url:7jieivl3wib3hhlvohlv': 0.98; > 'url:clickopen': 0.99; 'url:msgid': 0.99 > X-Spambayes-MailId: 1130458223 > > > > >
> href="http://coolhealer.com/track? > e=7JiEIVL3wiB3HhLVohLV&m=6103047&l=0"> > src="http://coolhealer.com/track?e=6Yb5NrGFBbuFfzGrPzGr&m=6103047&l=1" > border=0>
> href="http://coolhealer.com:8080/track?m=6103047&l=2"> > src="http://coolhealer.com:8080/track?m=6103047&l=3" > border=0>


> > > > >

size='1'><22;36S3nsTX5SgXBITsYITs;6103047> > src="http://coolhealer.com/clickopen? > msgid=6103047&email=6Yb5NrGFBbuFfzGrPzGr" width="1" > height="1"> > --- Ken Gordon On 2005 Oct 27, at 8:11, Ken Gordon wrote: > I was wrong - misled by my own failure to run a controlled experiment. > > These things run so well and smoothly that one tends to forget about > them - they merge with the background. But I run SpamBayes in > combination with the Mail.app spam filter under OS X. So as a control, > I turned the Mail.app filter off for a while. The results of the > experiment are that SB catches some; Mail.app catches others; I see > very few. Except for those that are trapped by the sort of things that > are pointed to in the SB header that I posted, the mainly-image spams > are being caught by Mail.app, not by SpamBayes. I won't presume to > comment on whether there is anything in Mail.app that could inform how > SB deals with images. > > Now I will return to my blissful spam-free existence by turning the > Mail.app filter on again. > > Ahhhhh ... that's better. > > --- > Ken Gordon > > On 2005 Oct 26, at 21:55, wrote: > >> Ken, >> Please post the entire Spambayes Clues listing, so I can see what >> Spambayes >> is doing with all the erroneous ham text that's included at the bottom >> of >> your e-mail message example. >> >> Thanks, >> FMJ >> >> -----Original Message----- >> From: spambayes-bounces at python.org >> [mailto:spambayes-bounces at python.org] On >> Behalf Of Ken Gordon >> Sent: Wednesday, October 26, 2005 8:26 AM >> To: spambayes at python.org; >> Subject: Re: [Spambayes] Inspecting images (was: SpamBayes >> toHandleEmbeddedImages) >> >> There's a lot more to spambayes than just evaluating content. Here's >> the SB >> Evidence header from a recent spam. But for 'charset', very little of >> this >> has to do with the content, yet it was correctly classified as spam. >> >>> X-Spambayes-Evidence: '*H*': 0.00; '*S*': 1.00; >> 'received:192.168.1': >>> 0.10; 'subject:skip:B 10': 0.16; 'received:192.168': 0.20; >>> 'received:192': 0.21; 'url:www': 0.23; 'content-type:image/jpeg': >>> 0.34; 'to:addr:none': 0.38; 'header:Return-Path:1': 0.38; >>> 'header:MIME-Version:1': 0.61; 'url:': 0.64; 'x-mailer:none': 0.71; >>> 'to:no real name:2**0': 0.72; 'from:name:\x1b$b5z at nf`1{\x1b(b': 0.84; >>> 'message-id:@imx100522.ath.cx': 0.84; 'received:imx100522.ath.cx': >>> 0.84; 'url:fetish': 0.84; 'received:192.168.1.11': 0.91; >>> 'received:kick': 0.91; 'content-type:multipart/related': 0.92; >>> 'received:210.153': 0.93; 'received:ath.cx': 0.93; 'url:cc': 0.93; >>> 'virus:src="cid:': 0.95; 'content-type/type:multipart/alternative': >>> 0.96; 'received:cx': 0.97; 'email addr:yahoo.co.jp': 0.99; 'skip:\x1b >>> 80': 0.99; 'from:addr:yahoo.co.jp': 1.00; 'from:charset:iso-2022-jp': >>> 1.00; 'skip:\x1b 60': 1.00; 'skip:\x1b 30': 1.00; 'skip:\x1b 20': >>> 1.00; 'skip:\x1b 50': 1.00; 'subject:$': 1.00; 'received:210': 1.00; >>> 'charset:iso-2022-jp': 1.00; 'subject:\x1b$': 1.00; >>> 'subjectcharset:iso-2022-jp': 1.00 >> >> >> >> On 2005 Oct 25, at 8:37, wrote: >> >>> How? Technically speaking, what could your SpamBayes installation be >>> doing differently? These are ALL ham words, so how is it that your >>> e-mail could be classifying all of this as Spam? If it is, I suspect >>> you're losing a lot of legitimate e-mail with it. >>> >>> FMJ >>> >>> -----Original Message----- >>> From: Ken Gordon [mailto:ksg at telusplanet.net] >>> Sent: Monday, October 24, 2005 8:58 PM >>> To: FreeMJ at HotPop.com >>> Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to >>> HandleEmbeddedImages) >>> >>> My installation of SpamBayes catches nearly all of these. I don't see >>> one a month outside of the Spam folder. >>> >>> --- >>> Ken Gordon >>> (780) 628-2758 >>> http://www.wolfe-gordon.ca >>> On 2005 Oct 24, at 20:18, wrote: >>> >>>> Hi Tony, >>>> The problem is, they keep changing the meaningless text at the >>>> bottom >>>> of the e-mail all the time, to confuse the Spam filter. They're >>>> picking Hammy words. And, as you can see, it's a highly effective >>>> technique. In other words, NONE of the "Tokens" should actually be >>>> "Significant", it's the image that needs to be scored in this case. >>>> Here's the spambayes clues for one of the e-mails: >>>> >>>> Combined Score: 3% (0.0330173) >>>> Internal ham score (*H*): 0.999976 >>>> Internal spam score (*S*): 0.0660102 >>>> >>>> # ham trained on: 14237 >>>> # spam trained on: 20138 >>>> >>>> 150 Significant Tokens >>>> token spamprob #ham #spam >>>> 'sender:no real name:2**0' 0.0277535 2187 88 >>>> 'dismissed' 0.0374933 314 17 >>>> 'raising' 0.0417704 313 19 >>>> 'lives' 0.0580962 1012 88 >>>> 'ill' 0.0613924 1084 100 >>>> 'said' 0.0677803 6498 668 >>>> 'two' 0.08226 5200 659 >>>> 'put' 0.0828439 2632 336 >>>> 'were' 0.0845653 6094 796 >>>> 'recalled' 0.0862187 92 12 >>>> 'town' 0.0883783 600 82 >>>> 'being' 0.0894639 4312 599 >>>> 'letter' 0.093344 1595 232 >>>> 'unless' 0.0960663 687 103 >>>> 'stephan' 0.0968154 15 2 >>>> 'face' 0.0986506 1397 216 >>>> 'who' 0.0991493 8031 1250 >>>> 'knows' 0.102049 574 92 >>>> 'anyone' 0.104976 1828 303 >>>> 'them' 0.106325 4690 789 >>>> 'think' 0.107446 3584 610 >>>> 'keep' 0.109385 2517 437 >>>> 'him' 0.111552 2631 467 >>>> 'suspicions' 0.113796 40 7 >>>> 'went' 0.11401 1331 242 >>>> 'sound' 0.116592 596 111 >>>> 'care' 0.117491 1244 234 >>>> 'going' 0.119623 3503 673 >>>> 'sort' 0.119677 511 98 >>>> 'his' 0.119861 5717 1101 >>>> 'remained' 0.11998 271 52 >>>> 'heavily' 0.123551 232 46 >>>> 'last' 0.126157 5241 1070 >>>> 'subject:: ' 0.134951 9110 2010 >>>> 'voice' 0.135891 644 143 >>>> 'walk' 0.140296 339 78 >>>> 'everyone' 0.140502 1225 283 >>>> 'whatever' 0.141645 618 144 >>>> 'overdosed' 0.142155 48 11 >>>> 'mother' 0.144908 510 122 >>>> 'way' 0.146154 3458 837 >>>> 'was' 0.146612 8939 2172 >>>> 'would' 0.146893 7679 1870 >>>> 'but' 0.14865 8435 2083 >>>> 'past' 0.155513 1932 503 >>>> 'duty' 0.15756 326 86 >>>> 'been' 0.158577 6937 1849 >>>> 'away' 0.159247 1632 437 >>>> 'soon' 0.16154 1021 278 >>>> 'header:In-Reply-To:1' 0.162139 1791 490 >>>> 'made' 0.163602 3467 959 >>>> 'true' 0.164161 566 157 >>>> 'too' 0.164462 2199 612 >>>> 'then' 0.167186 3519 999 >>>> 'road' 0.169212 459 132 >>>> 'covington' 0.170591 18 5 >>>> 'firmly' 0.171729 69 20 >>>> 'received' 0.172468 1646 485 >>>> 'yes' 0.17276 275 81 >>>> 'other' 0.174723 6686 2002 >>>> 'offered' 0.177462 702 214 >>>> 'saw' 0.178119 738 226 >>>> 'might' 0.184601 2399 768 >>>> 'hotel' 0.185114 203 65 >>>> 'thought' 0.186457 1287 417 >>>> 'her' 0.187192 2831 922 >>>> 'indeed' 0.18721 191 62 >>>> 'lie' 0.188538 165 54 >>>> 'filled' 0.188682 329 108 >>>> 'assorted' 0.198662 32 11 >>>> 'intent' 0.199592 596 210 >>>> 'manner' 0.200765 192 68 >>>> 'second' 0.203991 1311 475 >>>> 'let' 0.207891 1835 681 >>>> 'much' 0.210328 3345 1260 >>>> 'back' 0.211425 3207 1216 >>>> 'place' 0.214507 1704 658 >>>> 'out' 0.216398 6503 2540 >>>> 'little' 0.218176 2273 897 >>>> 'within' 0.218497 1940 767 >>>> 'occupied' 0.218989 56 22 >>>> 'never' 0.222876 2224 902 >>>> 'take' 0.223351 4101 1668 >>>> 'subject:-' 0.223886 2564 1046 >>>> 'find' 0.224822 2482 1018 >>>> 'play' 0.230279 518 219 >>>> 'skip:n 10' 0.233772 2561 1105 >>>> 'eyes' 0.234231 294 127 >>>> 'that' 0.245614 11155 5137 >>>> 'thoughts' 0.250399 193 91 >>>> 'observed' 0.252899 109 52 >>>> 'not' 0.253605 9451 4542 >>>> 'have' 0.260054 10350 5145 >>>> 'myself' 0.268888 281 146 >>>> 'with' 0.272839 10712 5685 >>>> 'skip:r 10' 0.274264 4752 2540 >>>> 'look' 0.276317 1963 1060 >>>> 'can' 0.286752 7254 4125 >>>> 'guided' 0.29442 24 14 >>>> 'all' 0.300499 8283 5033 >>>> 'resign' 0.304561 39 24 >>>> 'contracts' 0.313223 163 105 >>>> 'subject:Alert' 0.322897 61 41 >>>> 'upon' 0.326586 853 585 >>>> 'skip:i 10' 0.332672 4717 3326 >>>> 'for' 0.339583 12494 9087 >>>> 'topics' 0.371008 114 95 >>>> 'the' 0.371613 13338 11157 >>>> 'above' 0.380529 678 589 >>>> 'header:Return-Path:1' 0.635635 6219 15346 >>>> 'consults' 0.695316 3 10 >>>> 'comparative' 0.728703 17 65 >>>> 'earnest' 0.747547 24 101 >>>> 'friendship' 0.796906 6 34 >>>> 'blush' 0.797234 13 73 >>>> 'skip:7 70' 0.805302 5 30 >>>> 'expedition' 0.825248 9 61 >>>> 'from:addr:g.wcvbss' 0.844828 0 1 >>>> 'from:addr:netnitco.net' 0.844828 0 1 >>>> 'from:name:raymond goins' 0.844828 0 1 >>>> 'lensalizarin' 0.844828 0 1 >>>> "m'scorset" 0.844828 0 1 >>>> 'message-id:@icsp.net' 0.844828 0 1 >>>> 'ownthat' 0.844828 0 1 >>>> 'prominents' 0.844828 0 1 >>>> 'roadsthat' 0.844828 0 1 >>>> 'sender:addr:athenet.net' 0.844828 0 1 >>>> 'sender:addr:h.nnq' 0.844828 0 1 >>>> 'subject:< ' 0.844828 0 1 >>>> 'subject:Stiles' 0.844828 0 1 >>>> 'totrue' 0.844828 0 1 >>>> 'virus:src="cid:' 0.888282 111 1250 >>>> 'congenial' 0.905802 5 70 >>>> 'taters' 0.907976 1 16 >>>> 'skip:7 90' 0.908163 0 2 >>>> 'header:Received:2' 0.914966 886 13487 >>>> 'diem' 0.92631 3 56 >>>> 'subject:CBXC' 0.949438 0 4 >>>> 'rotund' 0.952904 1 33 >>>> 'blushingly' 0.958716 0 5 >>>> 'refolding' 0.969799 0 7 >>>> 'egress' 0.970088 1 53 >>>> 'to:name:freemj' 0.988432 0 19 >>>> 'septennial' 0.990405 0 23 >>>> 'veal' 0.993066 0 32 >>>> 'youll' 0.993469 0 34 >>>> 'subject:Stock' 0.99571 0 52 >>>> 'casteth' 0.995868 0 54 >>>> 'cutlet' 0.996894 0 72 >>>> 'to:addr:hotpop.com' 0.997792 23 14803 >>>> >>>> Message Stream >>>> Return-Path: >>>> Received: from 38.113.3.52 (unknown [200.107.173.172]) >>>> by mx1.hotpop.com (Postfix) with SMTP >>>> id 5B8A0E8304; Sun, 23 Oct 2005 23:49:29 +0000 (UTC) >>>> Received: from spellbound.gape.jeffersonian.gauguin.es >>>> ([200.107.173.172] >>>> helo=scatterbrain.mail.elknet.net) by smtp9.bt.com with esmtp >>>> id 0X162p-8865LL-80; Mon, 24 Oct 2005 01:48:41 +0100 >>>> Message-Id: <8927397790.37444460700 at icsp.net> >>>> Sender: H.nnq at athenet.net >>>> Date: Sun, 23 Oct 2005 20:42:41 -0400 >>>> In-Reply-To: Your message of "Sun, 23 Oct 2005 20:46:41 -0400." >>>> <98802417987115.YV37184 at joel.renaissance.arden.net> >>>> From: "Raymond Goins" >>>> To: "Freemj" >>>> Subject: Fwd: Stock - Alert-CBXC< Neil Stiles >>>> MIME-Version: 1.0 >>>> Content-Type: multipart/related; >>>> boundary="--ZZR8PVzcRDTpf2Pu68MQiz" >>>> X-HotPOP-Delivered-To: freemj at hotpop.com >>>> >>>> >>>> negligiblestymie breakwatergrist m'scorset >>>> >>>> >>>> >>>> We went to the triumph comparative at egress diem then a mouldy sort >>>> of establishment have my place so I blushingly offered to resign it >>>> The septennial who made as much of my going away as if I were going >>>> to China received me as an was dismissed and other topics occupied >>>> us >>>> he remained so seldom raising >>>> his eyes unless to >>>> true Rosanne was suspicions arose within me that it was an ill >>>> assorted friendship that he never thought of being observed by >>>> anyone >>>> but was so intent upon her and upon his ownthat I received soon >>>> recalled me to myself and put me in the road back to the hotel I was >>>> so filled with the play and with the past for it was in a manner >>>> Everyone who knows you consults with you and is guided by you >>>> Stephan >>>> but on second thoughts I shall keep him to take care of me >>>> and refolding the letter it would be insupportable to me to think of >>>> I am in earnest at last so youll soon have to arrange our contracts >>>> and to bind us firmly to them been overdosed with taters I commanded >>>> him in my deepest voice to order a veal cutlet and potatoes Yes I am >>>> on an expedition of duty My mother lives a little way out of town >>>> and >>>> the roadsthat I received soon recalled me to myself and put me in >>>> the >>>> road back to the hotel for I saw a faint blush in her face you would >>>> have let me find it out for myself that would not lie too heavily >>>> upon her purse and to do my duty in it whatever it might be and the >>>> prominents walk and the congenial sound of the rotund casteth >>>> hovering above them all >>>> 7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXeg7Mi >>>> k >>>> U >>>> R >>>> q >>>> reWfg7M6dwtJ4t1Fxn >>>> as he can look at me out of his two eyes Is he indeed said Mr >>>> Covington >>>> >>>> >>>> lensalizarin impregnatecost >>>> >>>>
>>>>
>>> SRC="cid:lTN1QnT11CtJIk8H6J5X7INGgMff2pS at prairieweb.com" border="0" >>>> ALT="negligiblestymie breakwatergrist m'scorset"> >>>>
>>> size=1>
>>> size=1>

We went to the triumph >>>> comparative at egress diem then a mouldy sort of >>>> establishment
have my place so I blushingly offered to resign it >>>> The septennial who made as much >>>> of >>>> my going away as if I were going to China received me as an
was >>>> dismissed and other topics occupied us he remained so seldom >>>> raising >>>> his eyes unless to
true Rosanne >>>> was suspicions arose within me that it was an ill assorted >>>> friendship
that he never thought of being observed by anyone >>>> but >>>> was so intent upon her and upon his own>>> SIZE=2>that I received soon recalled me to >>>> myself and put me in the road back to the hotel
I was so filled >>>> with the >>>> play and with the past for it was in a manner
Everyone who >>>> knows you >>>> consults with you and is guided by you Stephan
but on second >>>> thoughts I shall keep him to take care of me >>>>
and refolding the letter it >>>> would be >>>> insupportable to me to think of
I am in earnest at last so >>>> youll soon >>>> have to arrange our contracts and to bind us firmly to >>>> them
been overdosed with taters I commanded him in >>>> my deepest voice to order a veal cutlet and potatoes
Yes I am >>>> on >>>> an expedition of duty My mother lives a little way out of town and >>>> the roadsthat I received soon >>>> recalled me to myself and put me in the road back to the >>>> hotel
for I saw a faint blush in her face you would have let me >>>> find it out for myself that would not lie too heavily >>>> upon her purse and to do my duty in it whatever it might be
and >>>> the prominents walk and the congenial sound of the rotund casteth >>>> hovering above them all >>>>
7iVHrKDJTsgBJsJa4Nezv5RgkNpN5NYq6gowYZF0z3De6QLplaiyWM4rm4wSXsXe >>>> g >>>> 7 >>>> M >>>> ikURq >>>> reWfg7M6dwtJ4t1Fxn
as he can look at me out of his two eyes Is he >>>> indeed said Mr Covington
>>>> >>>> All Message Tokens >>>> 187 unique tokens >>>> >>>> 'above' >>>> 'all' >>>> 'and' >>>> 'anyone' >>>> 'arose' >>>> 'arrange' >>>> 'assorted' >>>> 'away' >>>> 'back' >>>> 'been' >>>> 'being' >>>> 'bind' >>>> 'blush' >>>> 'blushingly' >>>> 'but' >>>> 'can' >>>> 'care' >>>> 'casteth' >>>> 'cc:none' >>>> 'china' >>>> 'commanded' >>>> 'comparative' >>>> 'congenial' >>>> 'consults' >>>> 'content-type:text/plain' >>>> 'contracts' >>>> 'covington' >>>> 'cutlet' >>>> 'deepest' >>>> 'diem' >>>> 'dismissed' >>>> 'duty' >>>> 'earnest' >>>> 'egress' >>>> 'everyone' >>>> 'expedition' >>>> 'eyes' >>>> 'face' >>>> 'faint' >>>> 'filled' >>>> 'find' >>>> 'firmly' >>>> 'for' >>>> 'friendship' >>>> 'from:addr:g.wcvbss' >>>> 'from:addr:netnitco.net' >>>> 'from:name:raymond goins' >>>> 'going' >>>> 'guided' >>>> 'have' >>>> 'header:Date:1' >>>> 'header:From:1' >>>> 'header:In-Reply-To:1' >>>> 'header:MIME-Version:1' >>>> 'header:Message-Id:1' >>>> 'header:Received:2' >>>> 'header:Return-Path:1' >>>> 'header:Subject:1' >>>> 'header:To:1' >>>> 'heavily' >>>> 'her' >>>> 'him' >>>> 'his' >>>> 'hotel' >>>> 'hovering' >>>> 'ill' >>>> 'indeed' >>>> 'intent' >>>> 'keep' >>>> 'knows' >>>> 'last' >>>> 'lensalizarin' >>>> 'let' >>>> 'letter' >>>> 'lie' >>>> 'little' >>>> 'lives' >>>> 'look' >>>> "m'scorset" >>>> 'made' >>>> 'manner' >>>> 'message-id:@icsp.net' >>>> 'might' >>>> 'mother' >>>> 'mouldy' >>>> 'much' >>>> 'myself' >>>> 'never' >>>> 'not' >>>> 'observed' >>>> 'occupied' >>>> 'offered' >>>> 'order' >>>> 'other' >>>> 'our' >>>> 'out' >>>> 'overdosed' >>>> 'ownthat' >>>> 'past' >>>> 'place' >>>> 'play' >>>> 'potatoes' >>>> 'prominents' >>>> 'purse' >>>> 'put' >>>> 'raising' >>>> 'recalled' >>>> 'received' >>>> 'refolding' >>>> 'remained' >>>> 'reply-to:none' >>>> 'resign' >>>> 'road' >>>> 'roadsthat' >>>> 'rosanne' >>>> 'rotund' >>>> 'said' >>>> 'saw' >>>> 'second' >>>> 'seldom' >>>> 'sender:addr:athenet.net' >>>> 'sender:addr:h.nnq' >>>> 'sender:no real name:2**0' >>>> 'septennial' >>>> 'shall' >>>> 'skip:7 70' >>>> 'skip:7 90' >>>> 'skip:b 10' >>>> 'skip:e 10' >>>> 'skip:i 10' >>>> 'skip:n 10' >>>> 'skip:r 10' >>>> 'soon' >>>> 'sort' >>>> 'sound' >>>> 'stephan' >>>> 'subject: ' >>>> 'subject: - ' >>>> 'subject:-' >>>> 'subject:: ' >>>> 'subject:< ' >>>> 'subject:Alert' >>>> 'subject:CBXC' >>>> 'subject:Fwd' >>>> 'subject:Neil' >>>> 'subject:Stiles' >>>> 'subject:Stock' >>>> 'suspicions' >>>> 'take' >>>> 'taters' >>>> 'that' >>>> 'the' >>>> 'them' >>>> 'then' >>>> 'think' >>>> 'thought' >>>> 'thoughts' >>>> 'to:2**0' >>>> 'to:addr:freemj' >>>> 'to:addr:hotpop.com' >>>> 'to:name:freemj' >>>> 'too' >>>> 'topics' >>>> 'totrue' >>>> 'town' >>>> 'triumph' >>>> 'true' >>>> 'two' >>>> 'unless' >>>> 'upon' >>>> 'veal' >>>> 'virus:src="cid:' >>>> 'voice' >>>> 'walk' >>>> 'was' >>>> 'way' >>>> 'went' >>>> 'were' >>>> 'whatever' >>>> 'who' >>>> 'with' >>>> 'within' >>>> 'would' >>>> 'x-mailer:none' >>>> 'yes' >>>> 'you' >>>> 'youll' >>>> >>>> -----Original Message----- >>>> From: spambayes-bounces at python.org >>>> [mailto:spambayes-bounces at python.org] On Behalf Of Tony Meyer >>>> Sent: Sunday, October 23, 2005 9:43 PM >>>> To: >>>> Cc: spambayes at python.org >>>> Subject: Re: [Spambayes] Inspecting images (was: SpamBayes to >>>> HandleEmbeddedImages) >>>> >>>>> Something really needs to be done about this embedded image Spam. >>>>> Honestly, >>>>> SpamBayes appears to be ineffective against all these images, >>>> >>>> Can you post an example of a message that is incorrectly classified, >>>> *with the spambayes clues* for the message? The Outlook plug-in >>>> provides this via the "Show Clues for this Message" item in the >>>> SpamBayes menu. >>>> >>>> [...] >>>>> I'm sure OCR isn't the only way, but the words are there in plain >>>>> view. It seems like the obvious way to resolve this. >>>> >>>> Obvious isn't always best. One of the tenets here is "stupid beats >>>> smart" - I think doing some sort of OCR on images would fall into >>>> the >>>> "smart" category, and generating simple tokens from the images would >>>> fall into the "stupid" category and be more successful. Just my >>>> opinion, of course, but that's what I'd test if I had time (perhaps >>>> over the (southern hemisphere) summer...or maybe I can convince one >>>> of my employers that this would be worth doing in paid time). >>>> >>>>> SpamBayes has been such a great program for me and my colleges, >>>>> family and friends. I can only hope that the project sees fit to >>>>> resolve this soon. >>>> >>>> It's not really a case of "seeing fit" - the issue is that the >>>> developers are very short on time at the moment (contributions have >>>> always been, and always will be, welcome) and, in addition, this is >>>> a >>>> complex problem. >>>> >>>> =Tony.Meyer >>>> >>>> -- >>>> Please always include the list (spambayes at python.org) in your >>>> replies (reply-all), and please don't send me personal mail about >>>> SpamBayes. >>>> http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains >>>> this. >>>> >>>> >>>> _______________________________________________ >>>> SpamBayes at python.org >>>> http://mail.python.org/mailman/listinfo/spambayes >>>> Check the FAQ before asking: http://spambayes.sf.net/faq.html >>>> >>>> >>>> _______________________________________________ >>>> SpamBayes at python.org >>>> http://mail.python.org/mailman/listinfo/spambayes >>>> Check the FAQ before asking: http://spambayes.sf.net/faq.html >>>> >>> >>> >> >> _______________________________________________ >> SpamBayes at python.org >> http://mail.python.org/mailman/listinfo/spambayes >> Check the FAQ before asking: http://spambayes.sf.net/faq.html >> >> > > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html > From gerstenberger at imst.de Fri Oct 28 09:54:34 2005 From: gerstenberger at imst.de (Florian Gerstenberger) Date: Fri, 28 Oct 2005 09:54:34 +0200 Subject: [Spambayes] HowTo disable the "Save and Shutdown" Button in the Webinterface on linux ? In-Reply-To: References: <435F494E.7040409@imst.de> Message-ID: <4361D93A.9050000@imst.de> Richie Hindle wrote: >I assume you're running from source. You need to install resourcepackage >from http://resourcepackage.sourceforge.net/ in order for your changes to >anything in the "resource" directory to take effect. Download >ResourcePackage-1.0.0.tar.gz, unpack it into a temporary area, cd to that >area, and run "python setup.py install". You can then delete the unpacked >files. > > > Hi Richie, I already found that out yesterday but you're right. In my opinion this is something that should be contained in the Spambayes FAQ..... >In ProxyUI.py there's a class called ProxyUserInterface with a member >function called onView() - it's that function that shows the emails: > > if message is not None: > self.write("
%s
" % cgi.escape(message.as_string())) > >You need to change that to just show the headers... I don't know off the >top of my head whether the "email" package has a way to do that, but this >hack should work: > > if message is not None: > whole_message = message.as_string() > split_message = re.split(r'\r*\n\r*\n', whole_message, 1) > self.write("
%s
" % cgi.escape(split_message[0])) > > > This piece of Code helped me a lot. Thank you very much for your help. With best regard, Florian Gerstenberger -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051028/c7d3c12d/attachment.htm From sergio817423 at yahoo.es Fri Oct 28 19:08:31 2005 From: sergio817423 at yahoo.es (sergio) Date: Fri, 28 Oct 2005 14:08:31 -0300 Subject: [Spambayes] FREE FOR LIMITED TIME OPORTUNITY!!!! Message-ID: <4199-220051052817831150@pc> Oportunity Work ˇFREE FOR LIMITED TIME! We do NOT use a pyramidal structure or forced matrices. We do NOT have magical systems or experiments. In November we launch the renovation of ComoSerLibre, it will include the first form of telework with four systems of gains, services and tools that all worker online needs. 5,000 GRATUITOUS representations will be granted, these include a personal Web site, virtual office, packs of services and the possibility of participation in the great campaign launching. I am a member of ComoSerLibre and I am inviting you to participate in my group of distributors, if it seems interesting to you respond this mail with the subject INCLUDE ME IN THE VIP LIST, your name and your email. In the launching period you will receive by e- mail URL, password and user from your business center. Subscribe today, it is Free! Best wishes, An Active member of ComoSerLibre This mail is only for my personal contact list. If you have received it by mistake you equally can subscribe, in the other case respond this message with the word REMOVE in order to purify my subscibers list. THANKS. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051028/498a3c87/attachment.htm From dehart at charter.net Fri Oct 28 19:35:57 2005 From: dehart at charter.net (Dale Hart) Date: Fri, 28 Oct 2005 12:35:57 -0500 Subject: [Spambayes] ENABLE Message-ID: How in blue blazes do you enable spambayes, so it will work? -------------- next part -------------- A non-text attachment was scrubbed... Name: winmail.dat Type: application/ms-tnef Size: 3040 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051028/5507c69f/winmail.bin From jsp at PKC.com Fri Oct 28 19:55:44 2005 From: jsp at PKC.com (Jesse Pelton) Date: Fri, 28 Oct 2005 13:55:44 -0400 Subject: [Spambayes] ENABLE Message-ID: <16E2027582CDB74180896CDB4B8CC1F901D044B6@PKCVT01.pkc.com> In order to help, we need more information, such as the name of your e-mail client (it appears to be Outlook), operating system (presumably some flavor of Windows), what symptoms you're seeing, what (if anything) you've tried to do to fix them, and what results you got. You might want to take a look at the FAQ, too: http://spambayes.sourceforge.net/faq.html. (I don't remember seeing anything about blue blazes in there, though.) http://spambayes.sourceforge.net/faq.html#i-get-a-message-that-says-i-ne ed-to-enable-spambayes-or-the-enable-button-is-greyed-out might be relevant. > _____________________________________________ > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Dale Hart > Sent: Friday, October 28, 2005 1:36 PM > To: spambayes at python.org > Subject: [Spambayes] ENABLE > > How in blue blazes do you enable spambayes, so it will work? << File: > ATT208193.txt >> -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051028/032117e9/attachment.html From twalton at bluemarble.net Sat Oct 29 00:29:01 2005 From: twalton at bluemarble.net (Tony Walton) Date: Fri, 28 Oct 2005 17:29:01 -0500 Subject: [Spambayes] "Suspects" folder missing Message-ID: Greetings! For several weeks now when I receive some email messages, I see them appear in my inbox and then disappear. Unfortunately, some of these messages are not Spam. Today, I thought that I would do some checking and as I read the material, I realized that I don't have a "suspects" folder. I'm hopeful that the missing emails are there but I can't locate that folder. I even right clicked on the Outlook tool bar and Spambayes is checked. I unchecked and rechecked it and I still only show "Delete as Spam". There is no "suspects" button. Is that where my emails are ending up? This is making me crazy. Thanks, Tony -------------- next part -------------- A non-text attachment was scrubbed... Name: winmail.dat Type: application/ms-tnef Size: 1860 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051028/29bdd6d3/winmail.bin From tameyer at ihug.co.nz Sat Oct 29 08:41:23 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sat, 29 Oct 2005 19:41:23 +1300 Subject: [Spambayes] SpamBayes hides message content In-Reply-To: References: <6.2.3.4.0.20051026125848.0247e630@pop3.highstream.net> Message-ID: <57E1ED29-CB4A-455D-9C81-6F06C16CD5CB@ihug.co.nz> >> When I look at the detailed header information on a message that does >> not come through correctly, I find the following: > > Please see FAQ 5.2: > > http://spambayes.sourceforge.net/faq.html#i-get-a- > dbrunrecoveryerror-message > > Sadly the only solution is to delete your training database and train > again from scratch. This will fix the cause (I wonder if we ought to switch to defaulting to ZODB for 1.1a2; I've been using it for over a year without any database problems). Just as a FYI: When a problem like this occurs, what is meant to happen is that the exception header is added and the message is let through. 1.1a1 (and maybe CVS; I'm not sure if I have checked in the fix yet) has a bug, however, that means that when this occurs the message is stuffed in with the headers. If you're using sb_server, then 1.0.4 is a much better choice than 1.1a1, for this reason and others. When we finally get time to release 1.1a2, you could try that. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From logies at logies.de Sat Oct 29 16:21:51 2005 From: logies at logies.de (Michael Logies) Date: Sat, 29 Oct 2005 16:21:51 +0200 Subject: [Spambayes] Better default configuration for SpamBayes? Message-ID: <4.3.2.7.2.20051029154017.04c94008@pop.onlinehome.de> Hello, I switched from POPFile to Spambayes about 6 months ago, because I had false positives with POPFile from time to time and POPFile is lacking the "unsure"-classification. I didn`t change the default configuration when I started with SpamBayes, because I didn`t know the product. But I already was wondering about the default configuration on the "untrained messages"-page, which is "defer" for unsure messages, "ham" for presumably ham messages and "spam" for presumably spam messages. PopFile was more restrictive, it only trained on messages which were manually chosen for being trained. The problem I have with this configuration is, that overtraining and wrong classification happen too easily. I get hundreds of emails every day, and I often found myself checking only the "unsure"-messages, then pressing the "train"-button. I think, I did mistakes this way and the performance of SpamBayes didn`t become better with time. Luckily my hammie.db got corrupted recently when I was coming back from holidays, did training of messages and the computer did a scheduled reboot in the middle of the training... The hammie.db had grown to over 20 MB, and classification had become a bit slow. Now I have a different default configuration: "defer" for unsure, "discard" for ham/spam-messages. This way I avoid errors of classification. hammie.db is only 650 kB now, SpamBayes is faster and seems to be as reliable as ever. So perhaps you should change the default configuration of SpamBayes accordingly? Keep up the good work! Best Regards Michael -- http://www.logies.de/ (u. a. _die_ Mailingliste f?r die Dentalbranche) PGP-key (RSA/IDEA) kommt mit angeforderter Empfangsbest?tigung (return receipt) From john.penrose at progtechltd.com Sat Oct 29 12:17:00 2005 From: john.penrose at progtechltd.com (John D. Penrose) Date: Sat, 29 Oct 2005 06:17:00 -0400 Subject: [Spambayes] Outlook Reminders not working Message-ID: <0IP400J9N9WF2SAR@mta7.srv.hcvlny.cv.net> I just installed the Outlook plugin from the installer, binary version 1.0.4. I'm running Windows XP Pro version 2002 SP2. I'm running Outlook 2003 11.5608.5606 After I installed SpamBayes, I no longer had reminders. I clicked View, Reminders Window, and it came up empty. Before this I had reminders pending. I also created an appointment in Outlook with a reminder set to go off 10 minutes before, and it does not show up in the Reminders Window. Is there something I can do to get reminders back? (Other than that, it works great! Thanks for all your hard work!) Thanks, John -------------- next part -------------- A non-text attachment was scrubbed... Name: spambayes3.log Type: application/octet-stream Size: 59 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051029/0cd86800/spambayes3-0001.obj -------------- next part -------------- A non-text attachment was scrubbed... Name: spambayes1.log Type: application/octet-stream Size: 72133 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051029/0cd86800/spambayes1-0001.obj -------------- next part -------------- A non-text attachment was scrubbed... Name: spambayes2.log Type: application/octet-stream Size: 527 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20051029/0cd86800/spambayes2-0001.obj From richie at entrian.com Sat Oct 29 18:36:38 2005 From: richie at entrian.com (Richie Hindle) Date: Sat, 29 Oct 2005 17:36:38 +0100 Subject: [Spambayes] Better default configuration for SpamBayes? In-Reply-To: <4.3.2.7.2.20051029154017.04c94008@pop.onlinehome.de> References: <4.3.2.7.2.20051029154017.04c94008@pop.onlinehome.de> Message-ID: [Michael] > The problem I have with this configuration is, that overtraining and wrong > classification happen too easily. [...] perhaps you should change the > default configuration of SpamBayes accordingly? +1 This sounds reasonable to me, but I admit I'm not very clued up on which training techniques have proven to work the best in most cases. I seem to recall that training on exceptions was the best approach in general, in which case we should probably implement Michael's suggestion (it's a trivial edit). Any other opinions? -- Richie From richie at entrian.com Sat Oct 29 18:39:48 2005 From: richie at entrian.com (Richie Hindle) Date: Sat, 29 Oct 2005 17:39:48 +0100 Subject: [Spambayes] SpamBayes hides message content In-Reply-To: <57E1ED29-CB4A-455D-9C81-6F06C16CD5CB@ihug.co.nz> References: <6.2.3.4.0.20051026125848.0247e630@pop3.highstream.net> <57E1ED29-CB4A-455D-9C81-6F06C16CD5CB@ihug.co.nz> Message-ID: [Tony] > I wonder if we ought to switch to defaulting to ZODB for 1.1a2; > I've been using it for over a year without any database problems +1 provided there aren't multi-process issues - as I understand it, ZODB (without ZEO) isn't multi-process safe. Which means it should be fine for the POP3 proxy and (I assume?) the Outlook add-in, but maybe not for the Unix side of things? -- Richie Hindle richie at entrian.com From richie at entrian.com Sat Oct 29 18:42:09 2005 From: richie at entrian.com (Richie Hindle) Date: Sat, 29 Oct 2005 17:42:09 +0100 Subject: [Spambayes] HowTo disable the "Save and Shutdown" Button in the Webinterface on linux ? In-Reply-To: <4361D93A.9050000@imst.de> References: <435F494E.7040409@imst.de> <4361D93A.9050000@imst.de> Message-ID: [Richie] > You need to install resourcepackage [Florian] > I already found that out yesterday but you're right. In my opinion this > is something that should be contained in the Spambayes FAQ..... Maybe, although I'm not sure I'd think to look there. Might a README.txt in the resources directory be better? Florian, would that have helped you? -- Richie From gerstenberger at hardwarepreise.com Sat Oct 29 23:13:59 2005 From: gerstenberger at hardwarepreise.com (Florian Gerstenberger) Date: Sat, 29 Oct 2005 23:13:59 +0200 Subject: [Spambayes] HowTo disable the "Save and Shutdown" Button in the Webinterface on linux ? In-Reply-To: References: <435F494E.7040409@imst.de> <4361D93A.9050000@imst.de> Message-ID: <4363E617.20202@hardwarepreise.com> Hi Richie, this is what i did : - "fgrep -ri "save" * | grep shutdown" over the source directory - after that I cd'd into that directory (spambayes/resources/) and did a "ls -la" So I think it would have helped me. But I think that after that I've looked into the FAQ and found simply nothing about making changes in the webinterface or the package at all. A Readme File is a good Idea in my opinion. Florian Richie Hindle wrote: >[Richie] > > >>You need to install resourcepackage >> >> > >[Florian] > > >>I already found that out yesterday but you're right. In my opinion this >>is something that should be contained in the Spambayes FAQ..... >> >> > >Maybe, although I'm not sure I'd think to look there. Might a README.txt >in the resources directory be better? Florian, would that have helped >you? > > > -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051029/d32e3178/attachment.html From tameyer at ihug.co.nz Sun Oct 30 04:13:28 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 30 Oct 2005 16:13:28 +1300 Subject: [Spambayes] "Suspects" folder missing In-Reply-To: References: Message-ID: > For several weeks now when I receive some email messages, I see > them appear > in my inbox and then disappear. Unfortunately, some of these > messages are > not Spam. SpamBayes, by design, knows nothing other than what you teach it. Since both ham and spam change as time progresses, you'll always need to keep doing a little bit of training. > Today, I thought that I would do some checking and as I read the > material, I > realized that I don't have a "suspects" folder. I'm hopeful that the > missing emails are there but I can't locate that folder. FAQs 3.12 and 3.13 should help: > I even right > clicked on the Outlook tool bar and Spambayes is checked. I > unchecked and > rechecked it and I still only show "Delete as Spam". There is no > "suspects" > button. There is no "suspects" button. There's a folder, like any other Outlook folder, where messages that SpamBayes is unsure about will end up. On the toolbar, you should have a "SpamBayes" button, and when you are in any folder apart from the spam folder, a "Delete as Spam" button, and when you are in the unsure ("suspects") or spam folders, also a "Recover from Spam" button. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 30 04:20:44 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 30 Oct 2005 16:20:44 +1300 Subject: [Spambayes] Better default configuration for SpamBayes? In-Reply-To: References: <4.3.2.7.2.20051029154017.04c94008@pop.onlinehome.de> Message-ID: <0EA47B9B-8E2A-4AA7-9C1A-2A2BB2694896@ihug.co.nz> [Michael] >> The problem I have with this configuration is, that overtraining >> and wrong >> classification happen too easily. [...] perhaps you should change >> the >> default configuration of SpamBayes accordingly? [Richie] > +1 +1 from me, too. I've wondered about doing this in the past, but haven't got around to it (it is simple enough for users to change the default themselves, but it would be nice if they didn't have to). =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 30 04:22:33 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 30 Oct 2005 16:22:33 +1300 Subject: [Spambayes] SpamBayes 1.0.4 install In-Reply-To: <000c01c5da3b$a7376c00$ac1ea8c0@BADAMSAMC> References: <000c01c5da3b$a7376c00$ac1ea8c0@BADAMSAMC> Message-ID: <86ACCE91-E8A6-4777-96CE-6CF7C19CD301@ihug.co.nz> > I have to applaud your install program for the latest version of > SpamBayes. It actually looked through my entire Start/Programs > area and found that I had moved my original SpamBayes install from > the base programs area for the Start button to a 'Utilities' folder > to keep the first programs menu from the Start button to a > manageable size. This is the first program I have seen that > actually looks for a previous install in all areas of the Start menu. Thanks for the kind words. To give credit where it's due - the installer is built with Inno Setup, which is responsible for doing all of this. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From tameyer at ihug.co.nz Sun Oct 30 04:23:38 2005 From: tameyer at ihug.co.nz (Tony Meyer) Date: Sun, 30 Oct 2005 16:23:38 +1300 Subject: [Spambayes] Undo Delete as Spam Sender In-Reply-To: <24ed5ff30510261102q379ec562tcf3dfefdb262c03a@mail.gmail.com> References: <24ed5ff30510261102q379ec562tcf3dfefdb262c03a@mail.gmail.com> Message-ID: <1A9E3DB5-9A90-4A1C-A166-31D68336CAF8@ihug.co.nz> > I need to undo selecting a sender into "delete as spam" I had them > selected and hit the wrong button. Open up your spam (or "junk") folder, find the incorrectly trained message, select it, and then press the "Recover from Spam" button on the toolbar. SpamBayes will take care of correcting the training, and the message will be moved back to where it came from. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. From jsp at PKC.com Mon Oct 31 18:57:20 2005 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 31 Oct 2005 12:57:20 -0500 Subject: [Spambayes] FW: Help... Message-ID: <16E2027582CDB74180896CDB4B8CC1F901D044BD@PKCVT01.pkc.com> Forwarding to the list for other suggestions. It sounds like your problem is indeed not the same as mine, and I don't have any other ideas. ________________________________ From: Tatu, Debra [mailto:Debra.Tatu at unisys.com] Sent: Monday, October 31, 2005 9:33 AM To: Jesse Pelton Subject: RE: [Spambayes] Help... Hum... that doesn't seem to work either. I deleted this message as Spam, then went to my Junk folder and the message was not there. I really appreciate you taking the time to answer my email. I have no idea what's wrong here. My SpamBayes was working just fine and all of a sudden one day... it didn't. The only thing - I think - that changed on my laptop was the fact that I installed the latest version of MSN Messenger. I also noticed that my Computer Browser service start automatically (as designed) but then for some reason stops. This is causing my laptop not to shut down properly. I noticed the SpamBayes problem right around the same time. These events may not be related at all. I'm just trying to figure it out. I love using SpamBayes and I really want to get it working properly. Thanks, Debra ________________________________ From: Jesse Pelton [mailto:jsp at PKC.com] Sent: Friday, October 28, 2005 9:38 AM To: Tatu, Debra Subject: RE: [Spambayes] Help... What happens if you mark an item for deletion, then click a folder in the sidebar? You may find that the item has in fact moved, but Outlook doesn't update the display. This has been happening on my system since I installed SP2 for Windows XP, and it happens on some number of other machines as well. Nobody knows why it happens, but I'm inclined to doubt it's SpamBayes' fault, since SP2 seems to have introduced other Outlook display problems. I find that I can live with it, knowing that the messages are actually getting moved properly. Of course, you may have a different problem, maybe even one for which there's a solution. ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Tatu, Debra Sent: Thursday, October 27, 2005 8:01 PM To: spambayes at python.org Subject: [Spambayes] Help... I have read through the Troubleshooting Guide and the Bug List but cannot find help. I have uninstalled and reinstalled SpamBayes several times. When I first Open Outlook, SpamBayes appears to work properly. But later, I'll notice that it's not filtering. I'll mark the item for deletion and it won't move to the Junk Folder. When I go to the Suspect folder and mark and item for deletion, it won't move to the Junk Folder either. Something appears to be stopping the filtering. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051031/f377ac95/attachment.html From kenny.pitt at gmail.com Mon Oct 31 19:37:52 2005 From: kenny.pitt at gmail.com (Kenny Pitt) Date: Mon, 31 Oct 2005 13:37:52 -0500 Subject: [Spambayes] Better default configuration for SpamBayes? In-Reply-To: <0EA47B9B-8E2A-4AA7-9C1A-2A2BB2694896@ihug.co.nz> References: <4.3.2.7.2.20051029154017.04c94008@pop.onlinehome.de> <0EA47B9B-8E2A-4AA7-9C1A-2A2BB2694896@ihug.co.nz> Message-ID: <2a052b990510311037t1172f42boadbd0e071049503d@mail.gmail.com> On 10/29/05, Tony Meyer wrote: > [Michael] > > >> The problem I have with this configuration is, that overtraining > >> and wrong > >> classification happen too easily. [...] perhaps you should change > >> the > >> default configuration of SpamBayes accordingly? > > [Richie] > > +1 > > +1 from me, too. I've wondered about doing this in the past, but > haven't got around to it (it is simple enough for users to change the > default themselves, but it would be nice if they didn't have to). Another +1 here. For anyone whose received mail is not balanced between ham and spam, train-on-everything will quickly drive their training to an imbalanced state as well, so it should probably be discouraged for any inexperienced users (i.e. those who generally stick to defaults). -- Kenny Pitt From kenny.pitt at gmail.com Mon Oct 31 19:47:20 2005 From: kenny.pitt at gmail.com (Kenny Pitt) Date: Mon, 31 Oct 2005 13:47:20 -0500 Subject: [Spambayes] Outlook Reminders not working In-Reply-To: <0IP400J9N9WF2SAR@mta7.srv.hcvlny.cv.net> References: <0IP400J9N9WF2SAR@mta7.srv.hcvlny.cv.net> Message-ID: <2a052b990510311047t1e067917m129362be28c2a7c@mail.gmail.com> On 10/29/05, John D. Penrose wrote: > After I installed SpamBayes, I no longer had reminders. SpamBayes doesn't do anything that should affect reminders, and I've never had a problem receiving them in Outlook 2003 on my system. I don't see anything out of the ordinary in your logfiles, either. The first step is to make sure that SpamBayes is the cause. On the General tab in SpamBayes Manager, turn off the "Enable SpamBayes" checkbox and then restart Outlook. If you still have the problem, it is unlikely to be from SpamBayes. If you want to be 100% sure, uninstall SpamBayes entirely and restart Outlook again. If uninstalling SpamBayes eliminates the problem, please let us know so that we can look into it further. -- Kenny Pitt From juliopetrement at wanadoo.es Mon Oct 31 19:18:57 2005 From: juliopetrement at wanadoo.es (julio petrement) Date: Mon, 31 Oct 2005 19:18:57 +0100 Subject: [Spambayes] Error-Guard Support Request Message-ID: <000401c5de47$a3993be0$182a6750@juliopetrement> Hace unos meses paue la inscripci?n en su programa,asin?ndome la referencia LY 351G12,la cual recib? junto a las claves de instalacion, Debido a una averia he tenido que forematear el disco,perdiendp la instalacion del programa.He intentado contectarme de nuevo con Error Guard y no encuentro las pantallas con las cuales estaba familiarizado y que utilice para hacer el pago y recibir su infoirmacion como usuario. Por favor indiquenme que debo hacer para conectarme de nuevo.Gracia Dr.Petrement -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20051031/7eef6512/attachment.htm From twalton at bluemarble.net Mon Oct 31 22:46:58 2005 From: twalton at bluemarble.net (Tony Walton) Date: Mon, 31 Oct 2005 16:46:58 -0500 Subject: [Spambayes] "Suspects" folder missing In-Reply-To: Message-ID: Tony, Today, I was looking around my PC and when I went to the SpamBayes Manager and looked at where "suspects" went and did a browse, I found the suspects folder as a sub-folder under a folder I had created some time ago but there still wasn't a "recover from Spam" button. I found that button under the folder I had created some time ago for other emails. I have no idea how that happened so I renamed my fodder to "Junk Suspects", moved the emails I had saved in the original file and all seems to be working now. Tony Walton -----Original Message----- From: Tony Meyer [mailto:tameyer at ihug.co.nz] Sent: Saturday, October 29, 2005 10:13 PM To: Tony Walton Cc: spambayes at python.org Subject: Re: [Spambayes] "Suspects" folder missing > For several weeks now when I receive some email messages, I see > them appear > in my inbox and then disappear. Unfortunately, some of these > messages are > not Spam. SpamBayes, by design, knows nothing other than what you teach it. Since both ham and spam change as time progresses, you'll always need to keep doing a little bit of training. > Today, I thought that I would do some checking and as I read the > material, I > realized that I don't have a "suspects" folder. I'm hopeful that the > missing emails are there but I can't locate that folder. FAQs 3.12 and 3.13 should help: > I even right > clicked on the Outlook tool bar and Spambayes is checked. I > unchecked and > rechecked it and I still only show "Delete as Spam". There is no > "suspects" > button. There is no "suspects" button. There's a folder, like any other Outlook folder, where messages that SpamBayes is unsure about will end up. On the toolbar, you should have a "SpamBayes" button, and when you are in any folder apart from the spam folder, a "Delete as Spam" button, and when you are in the unsure ("suspects") or spam folders, also a "Recover from Spam" button. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this.