From Syoung26 at aol.com Sun Jul 1 04:23:46 2007 From: Syoung26 at aol.com (Syoung26 at aol.com) Date: Sat, 30 Jun 2007 22:23:46 EDT Subject: [Spambayes] Support #431041 Message-ID: I purchased two games from gamehouse. Mah Jong Medley License Name; Sandra Young License Code: HMMRV-VJBXF-MNSFN ALSO Caribbean Mah Jong License Name Sandra Young License Code: PLKSC-JSQRM-MNSFN The money has already been taken out of my bank. Please replace it or see that these games get loadeded. I have done every thin your support page said to do and I still get a Not a Valid Win32 Application error message. I also have tried to log on with my e-mail and password and it wont let me. e-mail _Syoung26 at aol_ (mailto:Syoung26 at aol) . com Password TINKER 12 OR tinker 12 Thank You Sandra Young ************************************** See what's free at http://www.aol.com. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070630/8289d223/attachment.htm From thruska at cubiclesoft.com Sun Jul 1 07:17:58 2007 From: thruska at cubiclesoft.com (Thomas Hruska) Date: Sun, 01 Jul 2007 01:17:58 -0400 Subject: [Spambayes] Spambayes classification failed! In-Reply-To: <18054.27172.70950.462352@montanaro.dyndns.org> References: <164918.16455.qm@web82101.mail.mud.yahoo.com> <4686618A.9080100@cubiclesoft.com> <18054.27172.70950.462352@montanaro.dyndns.org> Message-ID: <46873906.3090201@cubiclesoft.com> skip at pobox.com wrote: > Thomas> Today I received an e-mail in my Thunderbird inbox that has a > Thomas> 'X-Spambayes-Classification: spam'. I have a rule set up to > Thomas> automatically and permanently delete e-mails with spam > Thomas> classifications. Somehow the e-mail got by the filter. > > Thomas> Filter rule: "For incoming messages that: Match all of the > Thomas> following. > Thomas> 'X-Spambayes-Classification' is 'spam'. Perform these actions: > Thomas> Delete Message." > > Thomas> Any developers interested? > > I'm not sure what problem you're describing. Is it that SpamBayes > incorrectly classified a message or that somehow it added a spam > classification header to the message which your T-Bird filter didn't pick > up? > > I'm unsure why you're not just saving spam to a separate folder for later > review. Aren't you worried that the occasional ham will be classified as > spam and deleted? > > Skip Not really sure. Spambayes correctly classified the message as spam. It could be that Thunderbird didn't pick it up OR it could be Spambayes messed up the headers OR some combination. Of 50,000+ messages since I started using Spambayes, 0 have been false positives - I get a number of 'unsure's every day, but most of those are spam (I'll get the occasional spam in my ham). I review the ham/spam/unsure via the web interface. -- Thomas Hruska CubicleSoft President Ph: 517-803-4197 *NEW* VerifyMyPC 2.5 Change tracking and management tool. Reduce tech. support times from 2 hours to 5 minutes. http://www.CubicleSoft.com/VerifyMyPC/ From carmitafarina at sbcglobal.net Sun Jul 1 08:13:31 2007 From: carmitafarina at sbcglobal.net (carmita farina) Date: Sat, 30 Jun 2007 23:13:31 -0700 (PDT) Subject: [Spambayes] Re: Mail Delivery (failure travel@customercare.expedia.com) Message-ID: <740078.81069.qm@web80707.mail.mud.yahoo.com> My name is Carmita Farina. My itinerary # is 120245936352. I would like to change cfarina at joliet86.org to carmitafarina at sbcglobal.net because the first email address is blocked from outside mail. My user name is: cfarina5 and I am having trouble signing in to check my account for my transportation vouchers. Please send a response for a new password to my home email address: carmitafarina at sbcglobal.net. Carmita Farina -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070630/c0bf0c68/attachment.html From skip at pobox.com Sun Jul 1 13:54:40 2007 From: skip at pobox.com (skip at pobox.com) Date: Sun, 1 Jul 2007 06:54:40 -0500 Subject: [Spambayes] Support #431041 In-Reply-To: References: Message-ID: <18055.38400.476801.69921@montanaro.dyndns.org> Sandra> I purchased two games from gamehouse. Sandra> Mah Jong Medley Sandra> License Name; Sandra Young Sandra> License Code: HMMRV-VJBXF-MNSFN Sandra> ALSO Sandra> Caribbean Mah Jong Sandra> License Name Sandra Young Sandra> License Code: PLKSC-JSQRM-MNSFN Sandra> The money has already been taken out of my bank. Please replace Sandra> it or see that these games get loadeded. Sandra> I have done every thin your support page said to do and I still Sandra> get a Not a Valid Win32 Application error message. Sandra> I also have tried to log on with my e-mail and password and it Sandra> wont let me. Sandra> e-mail _Syoung26 at aol_ (mailto:Syoung26 at aol) . com Sandra> Password TINKER 12 OR Sandra> tinker 12 Sandra, Your mail went to the SpamBayes mailing list. We have nothing to do with gamehouse or its products. -- Skip Montanaro - skip at pobox.com - http://www.webfast.com/~skip/ From skip at pobox.com Sun Jul 1 13:57:50 2007 From: skip at pobox.com (skip at pobox.com) Date: Sun, 1 Jul 2007 06:57:50 -0500 Subject: [Spambayes] Spambayes classification failed! In-Reply-To: <46873906.3090201@cubiclesoft.com> References: <164918.16455.qm@web82101.mail.mud.yahoo.com> <4686618A.9080100@cubiclesoft.com> <18054.27172.70950.462352@montanaro.dyndns.org> <46873906.3090201@cubiclesoft.com> Message-ID: <18055.38590.673849.787096@montanaro.dyndns.org> Thomas> Not really sure. Spambayes correctly classified the message as Thomas> spam. It could be that Thunderbird didn't pick it up OR it Thomas> could be Spambayes messed up the headers OR some combination. It's unlikely that SpamBayes hosed the header, but feel free to send a copy of all the headers to me (skip at pobox.com) and I'll take a look. It's more likely that Thunderbird's filter missed somehow (didn't run, didn't see all the headers for some reason, etc). If that's the case, you're better off filing a bug report with the Thunderbird folks. Skip From thatguy at kevinyank.com Mon Jul 2 04:49:31 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Mon, 02 Jul 2007 12:49:31 +1000 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X Message-ID: <468867BB.4090701@kevinyank.com> Hi all, I?m using the latest SpamBayes package for Mac OS X from http://entrian.com/sbwiki/MacOSXPackage. Although SpamBayes runs perfectly for several days following installation, I find that after about a week of use (and training) the SpamBayes pop3proxy begins to crash silently while I am in the process of downloading email. The problem appears to worsen progressively until I am unable to download more than a dozen emails in one session without pop3proxy crashing. The first time this happened, I bit the bullet, blew away my SpamBayes training data, and started from scratch. This alleviated the problem in the short term, but as my training database grew, the crashes returned and I am now back in a situation of having to restart pop3proxy after every 10-15 messages I download. Any tips for diagnosing/correcting this issue? -- Kevin Yank From amedee at amedee.be Mon Jul 2 09:56:51 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Mon, 2 Jul 2007 09:56:51 +0200 (CEST) Subject: [Spambayes] Support #431041 In-Reply-To: <18055.38400.476801.69921@montanaro.dyndns.org> References: <18055.38400.476801.69921@montanaro.dyndns.org> Message-ID: <15061.193.121.250.194.1183363011.squirrel@amedee.be> On Sun, July 1, 2007 13:54, skip at pobox.com wrote: > Sandra, > > Your mail went to the SpamBayes mailing list. We have nothing to do with > gamehouse or its products. Skip, YHBS This is yet another kind of spam/email harvesting tactic. You want to be the good guy, reply that they have the wrong address, and that way you give your address to the spammers. I have already trained SpamBayes for this new kind of spam. The only reason I saw your reply, is perhaps because "Skip" is a token with a high ham score. ;-) -- Amedee From skip at pobox.com Mon Jul 2 13:48:57 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 2 Jul 2007 06:48:57 -0500 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <468867BB.4090701@kevinyank.com> References: <468867BB.4090701@kevinyank.com> Message-ID: <18056.58921.46700.785206@montanaro.dyndns.org> Kevin> I?m using the latest SpamBayes package for Mac OS X from Kevin> http://entrian.com/sbwiki/MacOSXPackage. Kevin> Although SpamBayes runs perfectly for several days following Kevin> installation, I find that after about a week of use (and Kevin> training) the SpamBayes pop3proxy begins to crash silently while Kevin> I am in the process of downloading email. ... Kevin> Any tips for diagnosing/correcting this issue? I have a few questions. First, what kind of database are you using with SpamBayes (setting of persistent_use_database config parameter)? Second, are you accessing the database from multiple applications simultaneously? Third, can you run sb_server.py under control of a debugger and let me know where it's executing when it crashes? If you need help with that last request, contact me offline. Skip From skip at pobox.com Mon Jul 2 13:51:44 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 2 Jul 2007 06:51:44 -0500 Subject: [Spambayes] Support #431041 In-Reply-To: <15061.193.121.250.194.1183363011.squirrel@amedee.be> References: <18055.38400.476801.69921@montanaro.dyndns.org> <15061.193.121.250.194.1183363011.squirrel@amedee.be> Message-ID: <18056.59088.144751.264807@montanaro.dyndns.org> >> Your mail went to the SpamBayes mailing list. We have nothing to do >> with gamehouse or its products. Amedee> YHBS "You have been snookered"? Amedee> This is yet another kind of spam/email harvesting tactic. Thanks. I've seen a couple of those recently and was beginning to wonder about them. Amedee> ... reply that they have the wrong address, and that way you Amedee> give your address to the spammers. I suspect in my case they already had it. ;-) Skip From andreww at datanet.ab.ca Mon Jul 2 14:14:59 2007 From: andreww at datanet.ab.ca (Andrew Warkentin) Date: Mon, 02 Jul 2007 06:14:59 -0600 Subject: [Spambayes] Support #431041 In-Reply-To: References: <18055.38400.476801.69921@montanaro.dyndns.org> <15061.193.121.250.194.1183363011.squirrel@amedee.be> Message-ID: <4688EC43.90105@datanet.ab.ca> skip at pobox.com wrote: > >> Your mail went to the SpamBayes mailing list. We have nothing to do > >> with gamehouse or its products. > > Amedee> YHBS > >"You have been snookered"? > > Amedee> This is yet another kind of spam/email harvesting tactic. > >Thanks. I've seen a couple of those recently and was beginning to wonder >about them. > > Amedee> ... reply that they have the wrong address, and that way you > Amedee> give your address to the spammers. > >I suspect in my case they already had it. ;-) > > > I replied to that stupid spammer as well. I kind of thought that it might be a spammer, but I wasn't sure. I guess I should train those messages as spam. From thatguy at kevinyank.com Mon Jul 2 15:30:25 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Mon, 02 Jul 2007 23:30:25 +1000 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <18056.58921.46700.785206@montanaro.dyndns.org> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> Message-ID: <4688FDF1.6090200@kevinyank.com> Hi Skip, skip at pobox.com wrote: > Kevin> I?m using the latest SpamBayes package for Mac OS X from > Kevin> http://entrian.com/sbwiki/MacOSXPackage. > > Kevin> Although SpamBayes runs perfectly for several days following > Kevin> installation, I find that after about a week of use (and > Kevin> training) the SpamBayes pop3proxy begins to crash silently while > Kevin> I am in the process of downloading email. > ... > Kevin> Any tips for diagnosing/correcting this issue? > > I have a few questions. First, what kind of database are you using with > SpamBayes (setting of persistent_use_database config parameter)? dbm > Second, are you accessing the database from multiple applications simultaneously? > Almost certainly not. The only application that is accessing it is Thunderbird. > Third, can you run sb_server.py under control of a debugger and let me know > where it's executing when it crashes? If you need help with that last > request, contact me offline. > I?ll see what I can manage. I don?t have much experience with Python, but I should be able to figure it out. Is there a log file someplace that might help? I can?t seem to find one. -- Kevin Yank From thruska at cubiclesoft.com Mon Jul 2 16:57:15 2007 From: thruska at cubiclesoft.com (Thomas Hruska) Date: Mon, 02 Jul 2007 10:57:15 -0400 Subject: [Spambayes] Support #431041 In-Reply-To: <4688EC43.90105@datanet.ab.ca> References: <18055.38400.476801.69921@montanaro.dyndns.org> <15061.193.121.250.194.1183363011.squirrel@amedee.be> <4688EC43.90105@datanet.ab.ca> Message-ID: <4689124B.5060704@cubiclesoft.com> Andrew Warkentin wrote: > skip at pobox.com wrote: > >> >> Your mail went to the SpamBayes mailing list. We have nothing to do >> >> with gamehouse or its products. >> >> Amedee> YHBS >> >> "You have been snookered"? >> >> Amedee> This is yet another kind of spam/email harvesting tactic. >> >> Thanks. I've seen a couple of those recently and was beginning to wonder >> about them. >> >> Amedee> ... reply that they have the wrong address, and that way you >> Amedee> give your address to the spammers. >> >> I suspect in my case they already had it. ;-) >> >> >> > I replied to that stupid spammer as well. I kind of thought that it > might be a spammer, but I wasn't sure. I guess I should train those > messages as spam. Hmm...I've been wondering something. If you train messages as ham and then later decide that they are spam (or vice versa), does Spambayes get really confused when you flag newer messages or does it slowly shift to unsure and then eventually ham? People's habits _DO_ change over time, for which, I suppose, is a pretty good reason to wipe the database every so often and start over. It took me two months to get Spambayes to block most incoming spam on 15 different e-mail accounts (about 10 are mail merged into two mailboxes), so I'd hate having to start over. -- Thomas Hruska CubicleSoft President Ph: 517-803-4197 *NEW* VerifyMyPC 2.5 Change tracking and management tool. Reduce tech. support times from 2 hours to 5 minutes. http://www.CubicleSoft.com/VerifyMyPC/ From skip at pobox.com Mon Jul 2 17:35:57 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 2 Jul 2007 10:35:57 -0500 Subject: [Spambayes] Support #431041 In-Reply-To: <4689124B.5060704@cubiclesoft.com> References: <18055.38400.476801.69921@montanaro.dyndns.org> <15061.193.121.250.194.1183363011.squirrel@amedee.be> <4688EC43.90105@datanet.ab.ca> <4689124B.5060704@cubiclesoft.com> Message-ID: <18057.7005.711454.109942@montanaro.dyndns.org> Thomas> Hmm...I've been wondering something. If you train messages as Thomas> ham and then later decide that they are spam (or vice versa), Thomas> does Spambayes get really confused when you flag newer messages Thomas> or does it slowly shift to unsure and then eventually ham? Thomas> People's habits _DO_ change over time, for which, I suppose, is Thomas> a pretty good reason to wipe the database every so often and Thomas> start over. If you incorrectly classify a message you will need a few trained the other way to offset that. I found it's better to find and delete the offending message. How you do that depends on the particular SpamBayes application you're using. In some cases you may not have the original messages and be forced to simply start from scratch. My training databases are stored in two Unix mbox format files so I just visit them in my favorite mail reader or text editor and delete them. Skip From dhabbershaw at earthlink.net Mon Jul 2 19:05:06 2007 From: dhabbershaw at earthlink.net (David Habbershaw) Date: Mon, 2 Jul 2007 13:05:06 -0400 Subject: [Spambayes] V1.0.4 & Outlook Express Message-ID: I am trying to set up SpamBayes sb_server on my wife's laptop running XP Home SP2 & Outlook Express 6. When I double click on the envelope in a message in the Possible Junk folder it does not display the review page but opens the message. David E. Habbershaw IntelliPark, LLC (610) 630-6978 - Office (610) 945-4452 - Cell dhabbershaw at intellipark.com From ElaineS at ekreg.com Mon Jul 2 19:28:20 2007 From: ElaineS at ekreg.com (Elaine Stephens) Date: Mon, 2 Jul 2007 10:28:20 -0700 Subject: [Spambayes] Please remove this link Message-ID: <3DA97200676CD54399364BC90BC2E3427B143D@EKSERVER.ekreg.local> Hi, My name is Elaine and I am the marketing coordinator for a small company. One of our employees sent a tech question and it needs to be deleted completely. It has some information on there that he should have not placed. This is very important. Please help me with this. Thank you Elaine Elaine Stephens | Marketing Coordinator ek Real Estate Group E-mail: elaines at ekreg.com Direct: 206.404.9823 Fax: 206.441.5695 Office: 206.374.9400 100 Fourth Avenue North Suite 155 Seattle, WA 98109 ekreg.com -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070702/adce1deb/attachment.html From jsp at PKC.com Mon Jul 2 19:48:45 2007 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 2 Jul 2007 13:48:45 -0400 Subject: [Spambayes] Please remove this link In-Reply-To: <3DA97200676CD54399364BC90BC2E3427B143D@EKSERVER.ekreg.local> References: <3DA97200676CD54399364BC90BC2E3427B143D@EKSERVER.ekreg.local> Message-ID: <16E2027582CDB74180896CDB4B8CC1F905AA82FE@PKCVT01.pkc.com> Unfortunately, this cannot be done. The issue comes up periodically, so you can see earlier discussions in the SpamBayes archive, including the following: http://mail.python.org/pipermail/spambayes/2005-December/018444.html http://mail.python.org/pipermail/spambayes/2006-January/018697.html (and responses in that thread) ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Elaine Stephens Sent: Monday, July 02, 2007 1:28 PM To: spambayes at python.org Subject: [Spambayes] Please remove this link Importance: High Hi, My name is Elaine and I am the marketing coordinator for a small company. One of our employees sent a tech question and it needs to be deleted completely. It has some information on there that he should have not placed. This is very important. Please help me with this. Thank you Elaine Elaine Stephens | Marketing Coordinator ek Real Estate Group E-mail: elaines at ekreg.com Direct: 206.404.9823 Fax: 206.441.5695 Office: 206.374.9400 100 Fourth Avenue North Suite 155 Seattle, WA 98109 ekreg.com -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070702/21c81cb2/attachment.htm From thatguy at kevinyank.com Tue Jul 3 01:28:49 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Tue, 03 Jul 2007 09:28:49 +1000 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <4688FDF1.6090200@kevinyank.com> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4688FDF1.6090200@kevinyank.com> Message-ID: <46898A31.10700@kevinyank.com> Kevin Yank wrote: > Hi Skip, > > skip at pobox.com wrote: >> Kevin> I?m using the latest SpamBayes package for Mac OS X from >> Kevin> http://entrian.com/sbwiki/MacOSXPackage. >> >> Kevin> Although SpamBayes runs perfectly for several days following >> Kevin> installation, I find that after about a week of use (and >> Kevin> training) the SpamBayes pop3proxy begins to crash silently >> while >> Kevin> I am in the process of downloading email. ... >> Kevin> Any tips for diagnosing/correcting this issue? >> Third, can you run sb_server.py under control of a debugger and let >> me know >> where it's executing when it crashes? If you need help with that last >> request, contact me offline. > > I?ll see what I can manage. I don?t have much experience with Python, > but I should be able to figure it out. Thanks for sending me your gdb setup, Skip. Unfortunately, I don?t have gdb on my system. Rather than chasing that, I opted to take a stab at debugging with pdb. Unfortunately, the Python version distributed with Mac OS X (2.3.5) doesn?t support ?python -m pdb script.py? command line syntax, so I upgraded my Python installation to 2.5.1. Now when I launch SpamBayes, I get this: Starting SpamBayes Server Traceback (most recent call last): File "/Library/SpamBayes/sb_server.py", line 104, in import spambayes.message File "/Library/SpamBayes/spambayes/message.py", line 78 from __future__ import generators SyntaxError: from __future__ imports must occur at the beginning of the file ?is SpamBayes not compatible with recent versions of Python? -- Kevin Yank From skip at pobox.com Tue Jul 3 04:46:17 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 2 Jul 2007 21:46:17 -0500 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <46898A31.10700@kevinyank.com> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4688FDF1.6090200@kevinyank.com> <46898A31.10700@kevinyank.com> Message-ID: <18057.47225.180766.532227@montanaro.dyndns.org> Kevin> Now when I launch SpamBayes, I get this: Kevin> Starting SpamBayes Server Kevin> Traceback (most recent call last): Kevin> File "/Library/SpamBayes/sb_server.py", line 104, in Kevin> import spambayes.message Kevin> File "/Library/SpamBayes/spambayes/message.py", line 78 Kevin> from __future__ import generators Kevin> SyntaxError: from __future__ imports must occur at the beginning of the file Kevin> Is SpamBayes not compatible with recent versions of Python? You're probably using 1.0.4. I don't think the Mac installer has been updated quite awhile. Just edit /Library/SpamBayes/spambayes/message.py and move the from __future__ statement up above the __author__ = statement. As I recall there are a couple other places where the from __future__ statement doesn't occur as the first statement of the file. You might also try downloading 1.1a4 from www.spambayes.org. Installing it is a simple python setup.py install --prefix=$HOME/local after which sb_server.py will be installed in ~/local/bin. Skip From thatguy at kevinyank.com Tue Jul 3 06:00:14 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Tue, 03 Jul 2007 14:00:14 +1000 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <18057.47225.180766.532227@montanaro.dyndns.org> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4688FDF1.6090200@kevinyank.com> <46898A31.10700@kevinyank.com> <18057.47225.180766.532227@montanaro.dyndns.org> Message-ID: <4689C9CE.4020002@kevinyank.com> Yes, I am indeed using 1.0.4. If this is no longer the recommended version, the SpamBayes web site should be updated. I?ve edited the necessary files, and am now running 1.0.4 under Python 2.5.1. Will report back with a debugger postmortem, or with news that this has fixed my crashes. -Kev. skip at pobox.com wrote: > Kevin> Now when I launch SpamBayes, I get this: > > Kevin> Starting SpamBayes Server > Kevin> Traceback (most recent call last): > Kevin> File "/Library/SpamBayes/sb_server.py", line 104, in > Kevin> import spambayes.message > Kevin> File "/Library/SpamBayes/spambayes/message.py", line 78 > Kevin> from __future__ import generators > Kevin> SyntaxError: from __future__ imports must occur at the beginning of the file > > Kevin> Is SpamBayes not compatible with recent versions of Python? > > You're probably using 1.0.4. I don't think the Mac installer has been > updated quite awhile. Just edit /Library/SpamBayes/spambayes/message.py and > move the from __future__ statement up above the __author__ = statement. > As I recall there are a couple other places where the from __future__ > statement doesn't occur as the first statement of the file. > > You might also try downloading 1.1a4 from www.spambayes.org. Installing it > is a simple > > python setup.py install --prefix=$HOME/local > > after which sb_server.py will be installed in ~/local/bin. > > Skip > > From thatguy at kevinyank.com Tue Jul 3 07:17:26 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Tue, 03 Jul 2007 15:17:26 +1000 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <18056.58921.46700.785206@montanaro.dyndns.org> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> Message-ID: <4689DBE6.6040501@kevinyank.com> skip at pobox.com wrote: > Third, can you run sb_server.py under control of a debugger and let me know > where it's executing when it crashes? Hmm ? not looking good: > /Library/SpamBayes/sb_server.py(42)() -> """ (Pdb) cont SpamBayes POP3 Proxy Version 1.0.4 (March 2005) and engine SpamBayes Engine Version 0.3 (January 2004). Loading database... Listener on port 110 is proxying mail.sitepoint.com:110 User interface url is http://localhost:8880/ Segmentation fault As before, the segfault occurred while downloading email. I restarted SpamBayes following the crash, and the same message downloaded without an issue. Any suggestions at this stage? -Kev. From skip at pobox.com Tue Jul 3 13:28:25 2007 From: skip at pobox.com (skip at pobox.com) Date: Tue, 3 Jul 2007 06:28:25 -0500 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <4689C9CE.4020002@kevinyank.com> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4688FDF1.6090200@kevinyank.com> <46898A31.10700@kevinyank.com> <18057.47225.180766.532227@montanaro.dyndns.org> <4689C9CE.4020002@kevinyank.com> Message-ID: <18058.13017.192963.928783@montanaro.dyndns.org> Kevin> Yes, I am indeed using 1.0.4. If this is no longer the Kevin> recommended version, the SpamBayes web site should be updated. 1.0.4 is indeed the latest "stable" release, but it is getting quite long-in-the-tooth. Many people use the 1.1aN series even though they are only "alpha" releases. Skip From skip at pobox.com Tue Jul 3 13:30:52 2007 From: skip at pobox.com (skip at pobox.com) Date: Tue, 3 Jul 2007 06:30:52 -0500 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <4689DBE6.6040501@kevinyank.com> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4689DBE6.6040501@kevinyank.com> Message-ID: <18058.13164.673792.102700@montanaro.dyndns.org> Kevin> Segmentation fault Kevin> As before, the segfault occurred while downloading email. I Kevin> restarted SpamBayes following the crash, and the same message Kevin> downloaded without an issue. Kevin> Any suggestions at this stage? If you're getting segfaults in the Python interpreter pdb won't help. I suspect gdb is part of the Xcode install (you should have it on your Tiger install DVD or you can get it from Apple). If that doesn't appeal to you, it's likely that gdb is also available via Fink or DarwinPorts. Skip From thatguy at kevinyank.com Tue Jul 3 14:19:01 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Tue, 03 Jul 2007 22:19:01 +1000 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <18058.13164.673792.102700@montanaro.dyndns.org> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4689DBE6.6040501@kevinyank.com> <18058.13164.673792.102700@montanaro.dyndns.org> Message-ID: <468A3EB5.50209@kevinyank.com> Okay, at this point, how do you think my time is best spent? - Migrate to 1.1a (can I migrate my training database, or must I start over?) - Debug with gdb in the hopes of finding the problem with 1.0.4. -Kev. skip at pobox.com wrote: > Kevin> Segmentation fault > > Kevin> As before, the segfault occurred while downloading email. I > Kevin> restarted SpamBayes following the crash, and the same message > Kevin> downloaded without an issue. > > Kevin> Any suggestions at this stage? > > If you're getting segfaults in the Python interpreter pdb won't help. I > suspect gdb is part of the Xcode install (you should have it on your Tiger > install DVD or you can get it from Apple). If that doesn't appeal to you, > it's likely that gdb is also available via Fink or DarwinPorts. > > Skip > > From skip at pobox.com Tue Jul 3 15:21:31 2007 From: skip at pobox.com (skip at pobox.com) Date: Tue, 3 Jul 2007 08:21:31 -0500 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <468A3EB5.50209@kevinyank.com> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4689DBE6.6040501@kevinyank.com> <18058.13164.673792.102700@montanaro.dyndns.org> <468A3EB5.50209@kevinyank.com> Message-ID: <18058.19803.63769.900213@montanaro.dyndns.org> Kevin> Okay, at this point, how do you think my time is best spent? Kevin> - Migrate to 1.1a (can I migrate my training database, or must I Kevin> start over?) Kevin> - Debug with gdb in the hopes of finding the problem with 1.0.4. I would update to 1.1a4, but I'm one of the SB developers, so that's a pretty trivial for me. (The gdb option is also pretty trivial for me.) I don't know what your experience is in these matters. If you choose to upgrade you should be able to continue to use your existing database, just make sure your SB config file (~/.spambayesrc is one of the defaults it will look for) contains persistent_use_database:dbm in the [Storage] section and that the persistent_storage_file option references your existing dbm file. For example, I use hammie.db in my home directory: persistent_storage_file:~/hammie.db Note that I'm assuming you are just using the defaults provided by Sam Thorne's Mac installer package. I believe at the time that dbm format was what he used by default. You should be able to riffle through the config information in the web interface to double-check this stuff. Trying out 1.1a4 would have the added benefit of performing a little extra testing for the developers so we can move toward a beta release, then eventually to an actual honest-to-God 1.1final release. Knowing that there is at least one person interested in a Mac installer will motivate me to investigate creating one for 1.1. I sent mail to Sam Thorne yesterday about what he used to create the one you're using but haven't heard back from him yet. Skip From skip at pobox.com Tue Jul 3 16:23:51 2007 From: skip at pobox.com (skip at pobox.com) Date: Tue, 3 Jul 2007 09:23:51 -0500 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <18058.19803.63769.900213@montanaro.dyndns.org> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4689DBE6.6040501@kevinyank.com> <18058.13164.673792.102700@montanaro.dyndns.org> <468A3EB5.50209@kevinyank.com> <18058.19803.63769.900213@montanaro.dyndns.org> Message-ID: <18058.23543.358151.282405@montanaro.dyndns.org> skip> If you choose to upgrade you should be able to continue to use skip> your existing database, just make sure your SB config file skip> (~/.spambayesrc is one of the defaults it will look for) contains skip> persistent_use_database:dbm ***bzzzt*** Hold on a minute. I never applied Sam Thorne's dbm patch, so this won't work with 1.1a4. I just applied it in CVS. I'll try to do a 1.1a5 release later today or tomorrow. In the meantime perhaps installing gdb would be the better approach. (A quick look suggests it's not part of DarwinPorts, btw. Dunno about Fink. It's clearly in the Xcode distribution.) Skip From bordencl at pctcnet.net Tue Jul 3 18:57:32 2007 From: bordencl at pctcnet.net (Sue Borden) Date: Tue, 3 Jul 2007 11:57:32 -0500 Subject: [Spambayes] problem Message-ID: <000601c7bd93$423d3c20$0301a8c0@D7L2K521> I am not receiving ANY e-mails. I suspect that Spambayes is sending them somewhere or blocking them but I cannot figure out where. Sue Borden W 1095 Cty Hwy W Winter, WI 54896 2928 North Shore Dr. Delevan, WI 53115 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070703/edb0cf99/attachment.htm -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/jpeg Size: 3781 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20070703/edb0cf99/attachment.jpe -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/gif Size: 15492 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20070703/edb0cf99/attachment.gif From thatguy at kevinyank.com Wed Jul 4 02:19:23 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Wed, 04 Jul 2007 10:19:23 +1000 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <18058.13164.673792.102700@montanaro.dyndns.org> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4689DBE6.6040501@kevinyank.com> <18058.13164.673792.102700@montanaro.dyndns.org> Message-ID: <468AE78B.2050507@kevinyank.com> skip at pobox.com wrote: > If you're getting segfaults in the Python interpreter pdb won't help. Hi Skip, Here?s what gdb is telling me. It still isn?t much, and in particular pystack isn?t telling me anything at all. I?d be happy to hear what you suggest at this point. SpamBayes POP3 Proxy Version 1.0.4 (March 2005) and engine SpamBayes Engine Version 0.3 (January 2004). Loading database... Listener on port 110 is proxying mail.sitepoint.com:110 User interface url is http://localhost:8880/ Program received signal EXC_BAD_ACCESS, Could not access memory. Reason: KERN_INVALID_ADDRESS at address: 0x02008000 0x90100d1f in hash4 () (gdb) pystack (gdb) -Kev. From skip at pobox.com Wed Jul 4 02:37:34 2007 From: skip at pobox.com (skip at pobox.com) Date: Tue, 3 Jul 2007 19:37:34 -0500 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <468AE78B.2050507@kevinyank.com> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4689DBE6.6040501@kevinyank.com> <18058.13164.673792.102700@montanaro.dyndns.org> <468AE78B.2050507@kevinyank.com> Message-ID: <18058.60366.745216.3838@montanaro.dyndns.org> Kevin> Program received signal EXC_BAD_ACCESS, Could not access memory. Kevin> Reason: KERN_INVALID_ADDRESS at address: 0x02008000 Kevin> 0x90100d1f in hash4 () Kevin> (gdb) pystack Kevin> (gdb) What does a basic gdb "bt" command tell you? Skip From dandh at bridson.org Tue Jul 3 22:17:45 2007 From: dandh at bridson.org (David and Heather Bridson) Date: Tue, 3 Jul 2007 21:17:45 +0100 Subject: [Spambayes] (no subject) Message-ID: <000201c7bdaf$38dbe4d0$0101a8c0@BRIDSON> Dear Spambayes I am using Windows XP Pro SP-2 My version of SpamBayes is: SpamBayes 1.0.4 The key error seems to be: Hope you can untangle this. Bye for now David Bridson Owls Barn Staithe Farm Langley Street Loddon Norfolk NR14 6AD Phone 01508 522 106 Mobile 07824 548 310 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070703/dc498057/attachment.html -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/jpeg Size: 170949 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20070703/dc498057/attachment-0002.jpe -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/jpeg Size: 6623 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20070703/dc498057/attachment-0003.jpe From amedee at amedee.be Wed Jul 4 15:25:31 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Wed, 4 Jul 2007 15:25:31 +0200 (CEST) Subject: [Spambayes] Support #431041 In-Reply-To: <18056.59088.144751.264807@montanaro.dyndns.org> References: <18055.38400.476801.69921@montanaro.dyndns.org> <15061.193.121.250.194.1183363011.squirrel@amedee.be> <18056.59088.144751.264807@montanaro.dyndns.org> Message-ID: <9723.193.121.250.194.1183555531.squirrel@amedee.be> On Mon, July 2, 2007 13:51, skip at pobox.com wrote: > > >> Your mail went to the SpamBayes mailing list. We have nothing to > do > >> with gamehouse or its products. > > Amedee> YHBS > > "You have been snookered"? "spammed". -- Amedee From amedee at amedee.be Wed Jul 4 15:30:40 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Wed, 4 Jul 2007 15:30:40 +0200 (CEST) Subject: [Spambayes] Please remove this link In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F905AA82FE@PKCVT01.pkc.com> References: <3DA97200676CD54399364BC90BC2E3427B143D@EKSERVER.ekreg.local> <16E2027582CDB74180896CDB4B8CC1F905AA82FE@PKCVT01.pkc.com> Message-ID: <14612.193.121.250.194.1183555840.squirrel@amedee.be> Jesse, Couldn't this be yet another kind of spammer? See my mail to Skip about the "support question". I mean, real estates... some of those real estate agents are just as bad as ph4rm4cy sellers. In case I'm wrong, my excuses to the R.E. company. Amedee. On Mon, July 2, 2007 19:48, Jesse Pelton wrote: > Unfortunately, this cannot be done. The issue comes up periodically, so > you can see earlier discussions in the SpamBayes archive, including the > following: > > http://mail.python.org/pipermail/spambayes/2005-December/018444.html > http://mail.python.org/pipermail/spambayes/2006-January/018697.html (and > responses in that thread) > > ________________________________ > > From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] > On Behalf Of Elaine Stephens > Sent: Monday, July 02, 2007 1:28 PM > To: spambayes at python.org > Subject: [Spambayes] Please remove this link > Importance: High > > > > Hi, > > > > My name is Elaine and I am the marketing coordinator for a small > company. One of our employees sent a tech question and it needs to be > deleted completely. It has some information on there that he should have > not placed. This is very important. Please help me with this. > > > Thank you > > > Elaine > > > > Elaine Stephens | Marketing Coordinator > > ek Real Estate Group > > E-mail: elaines at ekreg.com > > Direct: 206.404.9823 > > Fax: 206.441.5695 > > Office: 206.374.9400 > > 100 Fourth Avenue North > > Suite 155 > > Seattle, WA 98109 > > ekreg.com > > > > _______________________________________________ > 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 Wed Jul 4 15:32:44 2007 From: skip at pobox.com (skip at pobox.com) Date: Wed, 4 Jul 2007 08:32:44 -0500 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <468B1EAB.8020503@kevinyank.com> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4689DBE6.6040501@kevinyank.com> <18058.13164.673792.102700@montanaro.dyndns.org> <468AE78B.2050507@kevinyank.com> <18058.60366.745216.3838@montanaro.dyndns.org> <468AFDD0.7010900@kevinyank.com> <18059.6939.997399.77367@montanaro.dyndns.org> <468B1EAB.8020503@kevinyank.com> Message-ID: <18059.41340.878538.421959@montanaro.dyndns.org> (CC'ing spambayes at python.org to make sure the conversion procedure outlined below is saved for posterity. I'll add it to the SpamBayes wiki as well.) Kevin> Wouldn't a corrupt database produce consistent results Kevin> (i.e. always crash on a particular message)? The behavior I'm Kevin> seeing is that the crash tends to occur about 7 messages (and Kevin> steadily decreasing) into an email download session. Following Kevin> the crash, if I restart SpamBayes and begin downloading messages Kevin> again, the first message (the one the previous session crashed Kevin> on) is downloaded without an issue. Okay, a little more investigation. When Sam Thorne built the installer you used he added a new storage format type, "dbm" (that's the patch referred to on the wiki). I suspect he added that because at the time SpamBayes didn't have a db185hash database type name. I'm not sure why he didn't simply use the pickle format. On Macs, importing the "dbm" package doesn't actually use the old Unix dbm file format. It used the not as old, but just as bereft of merit, Berkeley DB 1.85 file format. This file format is known to have serious errors in its design. It's likely that you've encountered one of those errors. Here's a note I wrote to the SpamBayes list back in 2002: http://mail.python.org/pipermail/spambayes/2002-December/002394.html I reverted the change I made yesterday which added a "dbm" file type to SpamBayes. It's simply not needed and would only lead to more grief such as you've encountered. Now the fun begins... The simplest way to solve your problem is to switch to the pickle file format for your database storage. Everything happens in a Terminal window, so fire up your Mac's Terminal app. You will have to sudo to root because the permissions on the files and directories seem incorrect (at least to me). So, execute sudo bash at the shell prompt and enter your password when prompted. (I assume for this exercise that your user account is an administrative account.) Stop the POP3 proxy: /Library/StartupItems/SpamBayes stop Change directory to the SpamBayes installation: cd /Library/SpamBayes Edit your bayescustomize.ini file (vi, ex, Emacs, the TextEdit app, whatever your favorite editor is - just make sure to save it as plain text if you use an editor which likes "rich" formats). Change the persistent_use_database option to pickle and set the persistent_storage_file option to hammie.pck. If you don't have a bayescustomize.ini file for some reason or it's missing either of these options, just make sure you edit or create it so that it contains these lines: [Storage] persistent_use_database: pickle persistent_storage_file: hammie.pck In that same directory you should have two files, _pop3proxyham.mbox and _pop3proxyspam.mbox. We need to train on them to create the hammie.pck file. Alas, it appears the POP3 proxy created those files incorrectly, adding a spurious From_ line before every message. Execute these two commands to clean up that mess: sed -e '/^From pop3proxy at spambayes.org/d' < _pop3proxyham.mbox > _pop3proxyham.mbox.new sed -e '/^From pop3proxy at spambayes.org/d' < _pop3proxyspam.mbox > _pop3proxyspam.mbox.new Now execute /usr/bin/python sb_mboxtrain.py -p hammie.pck -g _pop3proxyham.mbox.new -s _pop3proxyspam.mbox.new -f to generate hammie.pck. Remove the output files from the sed commands: rm _pop3proxy*.mbox.new Restart the POP3 proxy with this command: /Library/StartupItems/SpamBayes start Hopefully that will get you going again. Let me know if it doesn't. Now to uninstall this package from my Mac... Skip From thatguy at kevinyank.com Wed Jul 4 16:24:00 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Thu, 05 Jul 2007 00:24:00 +1000 Subject: [Spambayes] SpamBayes crashes silently on Mac OS X In-Reply-To: <18059.41340.878538.421959@montanaro.dyndns.org> References: <468867BB.4090701@kevinyank.com> <18056.58921.46700.785206@montanaro.dyndns.org> <4689DBE6.6040501@kevinyank.com> <18058.13164.673792.102700@montanaro.dyndns.org> <468AE78B.2050507@kevinyank.com> <18058.60366.745216.3838@montanaro.dyndns.org> <468AFDD0.7010900@kevinyank.com> <18059.6939.997399.77367@montanaro.dyndns.org> <468B1EAB.8020503@kevinyank.com> <18059.41340.878538.421959@montanaro.dyndns.org> Message-ID: <468BAD80.3040603@kevinyank.com> I followed your procedure (thanks for it, by the way!). Unfortunately, I ran into a couple of snags: My bayescustomize.ini file didn?t contain the persistent_storage_filename and persistent_use_database options, and adding them as you suggested didn?t seem to make a difference?the server still choked at startup trying to open a pickle file. In the end, I reversed the changes and fired SpamBayes back up. I then used the SpamBayes web config UI to change the Storage file name, the Message information file name, and (on the Advanced screen) the database format. After making these changes in that order, the Web UI threw up an ugly error message. The best I can gather is that after changing the file names, SpamBayes created a dbm format file with the new hammie.pck filename. Then when I changed the database format, it choked on that same file. Shutting down the server, deleting the hammie.pck file, and restarting the server got things working in the end. This is the bayescustomize.ini file generated by this process: [pop3proxy] listen_ports:110 remote_servers:mail.sitepoint.com [Storage] messageinfo_storage_file:spambayes.messageinfo.pck persistent_storage_file:hammie.pck persistent_use_database:pickle My best guess as to the cause of the startup crashes when I edited the file manually was you didn?t mention setting messageinfo_storage_file. With that issue sorted, the next problem I had was that there was no _pop3proxyham.mbox file in my data directory, and the _pop3proxyspam.mbox file apparently only had two messages inside it. Looks like I?ll be retraining from scratch? Anyway, I?m now running on the pickle database format. Hopefully this marks the end of my SpamBayes crashes! :-) Thanks again, -- Kevin Yank From PAULHCOHEN at comcast.net Wed Jul 4 23:16:44 2007 From: PAULHCOHEN at comcast.net (PAULHCOHEN at comcast.net) Date: Wed, 04 Jul 2007 21:16:44 +0000 Subject: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? Message-ID: <070420072116.9179.468C0E3C0002D7C6000023DB2213484373B2BAB8B1BCB8B4AABEAF@comcast.net> Have switched from corrupted Outlook to Thunderbird - is your great spam filter product available for that program? Thank you, Paul Cohen -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070704/5499b0ef/attachment.html From skip at pobox.com Thu Jul 5 03:26:23 2007 From: skip at pobox.com (skip at pobox.com) Date: Wed, 4 Jul 2007 20:26:23 -0500 Subject: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? In-Reply-To: <070420072116.9179.468C0E3C0002D7C6000023DB2213484373B2BAB8B1BCB8B4AABEAF@comcast.net> References: <070420072116.9179.468C0E3C0002D7C6000023DB2213484373B2BAB8B1BCB8B4AABEAF@comcast.net> Message-ID: <18060.18623.577651.731301@montanaro.dyndns.org> Paul> Have switched from corrupted Outlook to Thunderbird - is your Paul> great spam filter product available for that program? Yes, but not with the tight integration of the Outlook plugin. There are separate servers to handle both POP3 and IMAP. You manage their settings via a web interface on your local machine. Training spam and ham is done through review web pages. It works fine. Same classifier, different management interface. Skip From thatguy at kevinyank.com Thu Jul 5 03:47:59 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Thu, 05 Jul 2007 11:47:59 +1000 Subject: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? In-Reply-To: <18060.18623.577651.731301@montanaro.dyndns.org> References: <070420072116.9179.468C0E3C0002D7C6000023DB2213484373B2BAB8B1BCB8B4AABEAF@comcast.net> <18060.18623.577651.731301@montanaro.dyndns.org> Message-ID: <468C4DCF.3040403@kevinyank.com> ThunderBayes is an add-on for Thunderbird that provides very nice integration between Thunderbird and SpamBayes. SpamBayes status for each message can be shown in a message list column, and messages may be trained as spam/ham with a convenient toolbar button. Get it here: http://www.openpolitics.com/pieces/ -Kev. skip at pobox.com wrote: > Paul> Have switched from corrupted Outlook to Thunderbird - is your > Paul> great spam filter product available for that program? > > Yes, but not with the tight integration of the Outlook plugin. There are > separate servers to handle both POP3 and IMAP. You manage their settings > via a web interface on your local machine. Training spam and ham is done > through review web pages. > > It works fine. Same classifier, different management interface. > > Skip > > _______________________________________________ > 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 Thu Jul 5 04:02:11 2007 From: skip at pobox.com (skip at pobox.com) Date: Wed, 4 Jul 2007 21:02:11 -0500 Subject: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? In-Reply-To: <468C4DCF.3040403@kevinyank.com> References: <070420072116.9179.468C0E3C0002D7C6000023DB2213484373B2BAB8B1BCB8B4AABEAF@comcast.net> <18060.18623.577651.731301@montanaro.dyndns.org> <468C4DCF.3040403@kevinyank.com> Message-ID: <18060.20771.761031.415059@montanaro.dyndns.org> Kevin> ThunderBayes is an add-on for Thunderbird that provides very nice Kevin> integration between Thunderbird and SpamBayes. SpamBayes status Kevin> for each message can be shown in a message list column, and Kevin> messages may be trained as spam/ham with a convenient toolbar Kevin> button. How does it integrate? It looks like the only download is an xpi file. Isn't that a little extension for Thunderbird? Does it include SpamBayes? Skip From thatguy at kevinyank.com Thu Jul 5 04:15:31 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Thu, 05 Jul 2007 12:15:31 +1000 Subject: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? In-Reply-To: <18060.20771.761031.415059@montanaro.dyndns.org> References: <070420072116.9179.468C0E3C0002D7C6000023DB2213484373B2BAB8B1BCB8B4AABEAF@comcast.net> <18060.18623.577651.731301@montanaro.dyndns.org> <468C4DCF.3040403@kevinyank.com> <18060.20771.761031.415059@montanaro.dyndns.org> Message-ID: <468C5443.9070902@kevinyank.com> The current version of ThunderBayes requires that you install SpamBayes separately. You then configure the ThunderBayes add-on to point at the web interface for your SpamBayes installation. -Kev. skip at pobox.com wrote: > Kevin> ThunderBayes is an add-on for Thunderbird that provides very nice > Kevin> integration between Thunderbird and SpamBayes. SpamBayes status > Kevin> for each message can be shown in a message list column, and > Kevin> messages may be trained as spam/ham with a convenient toolbar > Kevin> button. > > How does it integrate? It looks like the only download is an xpi file. > Isn't that a little extension for Thunderbird? Does it include SpamBayes? > > Skip > > From mhammond at skippinet.com.au Thu Jul 5 06:25:40 2007 From: mhammond at skippinet.com.au (Mark Hammond) Date: Thu, 5 Jul 2007 14:25:40 +1000 Subject: [Spambayes] (no subject) In-Reply-To: <000201c7bdaf$38dbe4d0$0101a8c0@BRIDSON> Message-ID: <053101c7bebc$8c3a0450$0200a8c0@enfoldsystems.local> It appears that a particular mail is malformed, and SpamBayes isn't robust enough. Looking inside the traceback, the code arond like 1371 of tokenize.py is: try: subjcharsetlist = email.Header.decode_header(x) except (binascii.Error, email.Errors.HeaderParseError): subjcharsetlist = [(x, 'invalid')] It looks like that except clause should be changed to include ValueError at least - eg: except (binascii.Error, email.Errors.HeaderParseError, ValueError): Could you please try that change and see if it goes away? I've also CCd spambayes-dev in the hope that someone there will offer some opinion if this is indeed a fix that should be checked in... Cheers, Mark -----Original Message----- From: spambayes-bounces+mhammond=keypoint.com.au at python.org [mailto:spambayes-bounces+mhammond=keypoint.com.au at python.org]On Behalf Of David and Heather Bridson Sent: Wednesday, 4 July 2007 6:18 AM To: spambayes at python.org Subject: [Spambayes] (no subject) Dear Spambayes I am using Windows XP Pro SP-2 My version of SpamBayes is: SpamBayes 1.0.4 The key error seems to be: Hope you can untangle this. Bye for now David Bridson Owls Barn Staithe Farm Langley Street Loddon Norfolk NR14 6AD Phone 01508 522 106 Mobile 07824 548 310 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070705/05361ef0/attachment.htm -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/jpeg Size: 170949 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20070705/05361ef0/attachment-0002.jpe -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/jpeg Size: 6623 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20070705/05361ef0/attachment-0003.jpe From jsp at PKC.com Thu Jul 5 13:58:36 2007 From: jsp at PKC.com (Jesse Pelton) Date: Thu, 5 Jul 2007 07:58:36 -0400 Subject: [Spambayes] Please remove this link In-Reply-To: <14612.193.121.250.194.1183555840.squirrel@amedee.be> References: <3DA97200676CD54399364BC90BC2E3427B143D@EKSERVER.ekreg.local> <16E2027582CDB74180896CDB4B8CC1F905AA82FE@PKCVT01.pkc.com> <14612.193.121.250.194.1183555840.squirrel@amedee.be> Message-ID: <16E2027582CDB74180896CDB4B8CC1F905AA860A@PKCVT01.pkc.com> That's a reasonable suspicion. It must be reasonable because I suspected the same thing. ;-) So I did a simple search and turned up what I suspect was the original message. It looked like a legitimate cause for concern, so I won't detail the search for posterity, but it really wasn't hard to find. I sent a more detailed message directly to Elaine suggesting that her company learn more about the security limitations of e-mail and implement measures (such as encryption) to protect sensitive information transmitted through the wilds of the public internet. -----Original Message----- From: Amedee Van Gasse [mailto:amedee at amedee.be] Sent: Wednesday, July 04, 2007 9:31 AM To: Jesse Pelton Cc: spambayes at python.org Subject: Re: [Spambayes] Please remove this link Jesse, Couldn't this be yet another kind of spammer? See my mail to Skip about the "support question". I mean, real estates... some of those real estate agents are just as bad as ph4rm4cy sellers. In case I'm wrong, my excuses to the R.E. company. Amedee. On Mon, July 2, 2007 19:48, Jesse Pelton wrote: > Unfortunately, this cannot be done. The issue comes up periodically, so > you can see earlier discussions in the SpamBayes archive, including the > following: > > http://mail.python.org/pipermail/spambayes/2005-December/018444.html > http://mail.python.org/pipermail/spambayes/2006-January/018697.html (and > responses in that thread) > > ________________________________ > > From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] > On Behalf Of Elaine Stephens > Sent: Monday, July 02, 2007 1:28 PM > To: spambayes at python.org > Subject: [Spambayes] Please remove this link > Importance: High > > > > Hi, > > > > My name is Elaine and I am the marketing coordinator for a small > company. One of our employees sent a tech question and it needs to be > deleted completely. It has some information on there that he should have > not placed. This is very important. Please help me with this. > > > Thank you > > > Elaine > > > > Elaine Stephens | Marketing Coordinator > > ek Real Estate Group > > E-mail: elaines at ekreg.com > > Direct: 206.404.9823 > > Fax: 206.441.5695 > > Office: 206.374.9400 > > 100 Fourth Avenue North > > Suite 155 > > Seattle, WA 98109 > > ekreg.com > > > > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html -- From Administrator at bag.python.org Thu Jul 5 17:21:23 2007 From: Administrator at bag.python.org (Administrator at bag.python.org) Date: Thu, 5 Jul 2007 11:21:23 -0400 Subject: [Spambayes] [MailServer Notification]To Sender file blocking settings matched and action taken. Message-ID: <002801c7bf18$25a6b0b0$020110ac@rentex.com> ScanMail for Microsoft Exchange has blocked an attachment. Sender = spambayes at python.org Recipient(s) = Info Subject = Mail Delivery (failure info at rentex.com) Scanning time = 7/5/2007 11:21:23 AM Action on file blocking: The attachment message.scr matches the file blocking settings. ScanMail has Deleted it. Warning to Sender: Action taken by attachment blocking. From becky at showsteers.com Thu Jul 5 18:42:01 2007 From: becky at showsteers.com (Becky Thompson) Date: Thu, 5 Jul 2007 11:42:01 -0500 Subject: [Spambayes] Tool Bar Buttons Message-ID: I can not get my spambayes buttons on the tool bar to respond when I click on them. It has worked for 2 years and now they are not. I have updated spambayes and resorted my computer and still no response. I can't recover or delete from the suspect folder. Becky Thompson Showsteers.com 333 LeNeta Dr. Whitesboro, TX 76273 903-564-5186 From PCPete at audiography.com.au Fri Jul 6 04:25:02 2007 From: PCPete at audiography.com.au (Peter Naus) Date: Fri, 6 Jul 2007 12:25:02 +1000 Subject: [Spambayes] Simple problem with Spambayes on Outlook 2003, XP64 Message-ID: <59F56263E5014BC8B220A271C037C8F7@odysseus> G'day, I've been running Spambayes 1.0.4 for a couple of months now, with Outlook 2003, on a Windows XP 64 system. It has worked pretty well, and certainly there were no problems that I couldn't solve with the help of the troubleshooting docs! However, that was a trial version of XP64, so I've just done a clean install of the full XP64 (i.e. licenced!). Unfortunately, I cut the timing too fine, and I didn't finish backing up my user data before the system had to be rebooted, so I'm starting SB from scratch. Now I'm in the situation where I can't get SB to run at all without killing outlook immediately. Outlook 2003 is installed fine, and the first time the Spambayes addin ran, it asked me to select the good and bad folders, which I did, and it started sorting. About 6 minutes in, Outlook checked for POP mail and of course SB's database got corrupted and Outlook crashed immediately. When I restarted, Outlook starts to run and asks me to disable the SB addin, if I don't Outlook crashes immediately. I uninstalled SB and reinstalled it, but the problem remains. If I manually enable (tick the little box) in the COM Addin list in Outlook, it's disabled (unticked) as soon as I close that dialog. If I manually remove that entry, and add the dll manually and enable it, the instant I enable it, Outlook crashes with the same error. The SB log files consist of either: Registered: SpamBayes.OutlookAddin Registration complete. Or : Unregistered: SpamBayes.OutlookAddin I can't seem to find any logfiles for Outlook. I will try a complete uninstall and reinstall of Outlook AND SB, and see if I can fix it that way, but I did want you to be aware of this behaviour. As this is a business machine, I need to be careful about what I have cluttering it up, but I'd be more than happy to download and install the Python tool and then to build and try out the 1.1a SB alpha release , but I don't have the resources right now to figure out which Python build and which scripts and what libs and PILs I need, so if there's a clear spot on the SB Wiki, having all that info together in one place would be really useful to me (and maybe to others?) Thanks and regards, PC Pete Peter Naus Manager Audiography From fturtle at gmail.com Fri Jul 6 07:34:40 2007 From: fturtle at gmail.com (Fast Turtle) Date: Thu, 5 Jul 2007 22:34:40 -0700 Subject: [Spambayes] Simple problem with Spambayes on Outlook 2003, XP64 References: <59F56263E5014BC8B220A271C037C8F7@odysseus> Message-ID: <001101c7bf8f$5a8f0760$0501a8c0@hydra> Sounds like a corrupted plug-in file. Only solution is locate where the plug-in is and delete it. Then simply reinstall spambayes to add the plug-in once again. ----- Original Message ----- From: "Peter Naus" To: Sent: Thursday, July 05, 2007 7:25 PM Subject: [Spambayes] Simple problem with Spambayes on Outlook 2003, XP64 > G'day, > > I've been running Spambayes 1.0.4 for a couple of months now, with Outlook > 2003, on a Windows XP 64 system. > > It has worked pretty well, and certainly there were no problems that I > couldn't solve with the help of the troubleshooting docs! > > However, that was a trial version of XP64, so I've just done a clean > install > of the full XP64 (i.e. licenced!). Unfortunately, I cut the timing too > fine, > and I didn't finish backing up my user data before the system had to be > rebooted, so I'm starting SB from scratch. > > Now I'm in the situation where I can't get SB to run at all without > killing > outlook immediately. > > Outlook 2003 is installed fine, and the first time the Spambayes addin > ran, > it asked me to select the good and bad folders, which I did, and it > started > sorting. About 6 minutes in, Outlook checked for POP mail and of course > SB's > database got corrupted and Outlook crashed immediately. > > When I restarted, Outlook starts to run and asks me to disable the SB > addin, > if I don't Outlook crashes immediately. > > I uninstalled SB and reinstalled it, but the problem remains. > > If I manually enable (tick the little box) in the COM Addin list in > Outlook, > it's disabled (unticked) as soon as I close that dialog. If I manually > remove that entry, and add the dll manually and enable it, the instant I > enable it, Outlook crashes with the same error. > > The SB log files consist of either: > > Registered: SpamBayes.OutlookAddin > Registration complete. > > Or : > > Unregistered: SpamBayes.OutlookAddin > > I can't seem to find any logfiles for Outlook. > > I will try a complete uninstall and reinstall of Outlook AND SB, and see > if > I can fix it that way, but I did want you to be aware of this behaviour. > > As this is a business machine, I need to be careful about what I have > cluttering it up, but I'd be more than happy to download and install the > Python tool and then to build and try out the 1.1a SB alpha release , but > I > don't have the resources right now to figure out which Python build and > which scripts and what libs and PILs I need, so if there's a clear spot on > the SB Wiki, having all that info together in one place would be really > useful to me (and maybe to others?) > > Thanks and regards, > > PC Pete > > Peter Naus > Manager > Audiography > > > > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html From thatguy at kevinyank.com Fri Jul 6 12:13:03 2007 From: thatguy at kevinyank.com (Kevin Yank) Date: Fri, 06 Jul 2007 20:13:03 +1000 Subject: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? In-Reply-To: References: <070420072116.9179.468C0E3C0002D7C6000023DB2213484373B2BAB8B1BCB8B4AABEAF@comcast.net><18060.18623.577651.731301@montanaro.dyndns.org> <468C4DCF.3040403@kevinyank.com> Message-ID: <468E15AF.60704@kevinyank.com> It doesn?t conflict per se, but having both of them switched on is redundant. Personally, I?ve found SpamBayes to be much more reliable, so I?ve disabled the built-in spam filtering, removed the relevant buttons from all my Thunderbird toolbars, and removed the built-in junk status column from the message list. In theory, however, if you wanted to leave both spam filtering systems enabled, you could. -Kev. Katz, Amir wrote: > Does it conflict with the built-in Bayesian filter that TB already has? > > -- Amir > > > >> -----Original Message----- >> From: spambayes-bounces at python.org >> [mailto:spambayes-bounces at python.org] On Behalf Of Kevin Yank >> Sent: Thursday, July 05, 2007 04:48 >> To: PAULHCOHEN at comcast.net >> Cc: spambayes at python.org >> Subject: Re: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? >> >> ThunderBayes is an add-on for Thunderbird that provides very nice >> integration between Thunderbird and SpamBayes. SpamBayes status for >> each message can be shown in a message list column, and >> messages may be >> trained as spam/ham with a convenient toolbar button. >> >> Get it here: http://www.openpolitics.com/pieces/ >> >> -Kev. >> >> skip at pobox.com wrote: >> >>> Paul> Have switched from corrupted Outlook to >>> >> Thunderbird - is your >> >>> Paul> great spam filter product available for that program? >>> >>> Yes, but not with the tight integration of the Outlook >>> >> plugin. There are >> >>> separate servers to handle both POP3 and IMAP. You manage >>> >> their settings >> >>> via a web interface on your local machine. Training spam >>> >> and ham is done >> >>> through review web pages. >>> >>> It works fine. Same classifier, different management interface. >>> >>> Skip >>> >>> _______________________________________________ >>> 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 Amir_Katz at bmc.com Fri Jul 6 11:55:15 2007 From: Amir_Katz at bmc.com (Katz, Amir) Date: Fri, 6 Jul 2007 12:55:15 +0300 Subject: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? In-Reply-To: <468C4DCF.3040403@kevinyank.com> References: <070420072116.9179.468C0E3C0002D7C6000023DB2213484373B2BAB8B1BCB8B4AABEAF@comcast.net><18060.18623.577651.731301@montanaro.dyndns.org> <468C4DCF.3040403@kevinyank.com> Message-ID: Does it conflict with the built-in Bayesian filter that TB already has? -- Amir > -----Original Message----- > From: spambayes-bounces at python.org > [mailto:spambayes-bounces at python.org] On Behalf Of Kevin Yank > Sent: Thursday, July 05, 2007 04:48 > To: PAULHCOHEN at comcast.net > Cc: spambayes at python.org > Subject: Re: [Spambayes] AVAILABILITY FOR MOZILLA THUNDERBIRD?? > > ThunderBayes is an add-on for Thunderbird that provides very nice > integration between Thunderbird and SpamBayes. SpamBayes status for > each message can be shown in a message list column, and > messages may be > trained as spam/ham with a convenient toolbar button. > > Get it here: http://www.openpolitics.com/pieces/ > > -Kev. > > skip at pobox.com wrote: > > Paul> Have switched from corrupted Outlook to > Thunderbird - is your > > Paul> great spam filter product available for that program? > > > > Yes, but not with the tight integration of the Outlook > plugin. There are > > separate servers to handle both POP3 and IMAP. You manage > their settings > > via a web interface on your local machine. Training spam > and ham is done > > through review web pages. > > > > It works fine. Same classifier, different management interface. > > > > Skip > > > > _______________________________________________ > > 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 PCPete at audiography.com.au Sat Jul 7 03:29:52 2007 From: PCPete at audiography.com.au (Peter Naus) Date: Sat, 7 Jul 2007 11:29:52 +1000 Subject: [Spambayes] Simple problem with Spambayes on Outlook 2003, XP64 In-Reply-To: <001101c7bf8f$5a8f0760$0501a8c0@hydra> References: <59F56263E5014BC8B220A271C037C8F7@odysseus> <001101c7bf8f$5a8f0760$0501a8c0@hydra> Message-ID: <6E63F74924F94C058CE7A3D131A56527@odysseus> That's what I thought when I restarted after the initial crash; but removing SB (and removing all references in the Outlook COM "manager" and rebuilding the toolbar) hasn't fixed the problem when SB is reinstalled. So there must be a reference or link maintained outside of the com manager list and the toolbar file that's not properly removed or cleaned up when SB is uninstalled. Most likely, Outlook is protecting it's references and not allowing a "clean" uninstall after an addin has gone ballistic and Outlook has 'disabled' it... Manually deleting the COM list entry does appear to delete the reference, but after rebooting and reinstalling SB, Outlook immediately crashes, so it's not a part of the SB install kit that appears to be corrupted - unless SB stores data somewhere else (registry?) and doesn't remove it when it is uninstalled after a problem occurs? That seems unlikely, instead I'd be inclined to suspect Outlook, but I'm a SB newbie. Reinstalling Outlook would almost certainly fix the problem, but that's not really fixing anything, it's fixing the symptom. From the number of enquiries and comments around, this issue with Outlook being unable to work with the SB addin after a failure like this is a fairly typical problem, and so far the only answer has been to remove Office and reinstall it. Reinstalling windows would also fix the problem, guaranteed, but I'm unlikely to do that either - there must be something that someone on this list has seen that could help to identify where the "leftover" code reference is and help to clean it up. I'm looking, and if I find out where the problem is, I'll let everyone know, but it's been a few years since I was the Outlook support manager, and I've gotten very rusty. And fat. I can't slip between lines of code like I used to... If anyone has any ideas where to start looking, I'd be most grateful. -----Original Message----- From: Fast Turtle [mailto:fturtle at gmail.com] Sent: Friday, 6 July 2007 3:35 PM To: Peter Naus; Spambayes Subject: Re: [Spambayes] Simple problem with Spambayes on Outlook 2003, XP64 Sounds like a corrupted plug-in file. Only solution is locate where the plug-in is and delete it. Then simply reinstall spambayes to add the plug-in once again. From mhammond at skippinet.com.au Sat Jul 7 08:32:20 2007 From: mhammond at skippinet.com.au (Mark Hammond) Date: Sat, 7 Jul 2007 16:32:20 +1000 Subject: [Spambayes] Pre-release 1.1a4 windows binary available for testing Message-ID: <023201c7c060$92a07090$090a0a0a@enfoldsystems.local> Hi all, I've made a pre-release of SpamBayes 1.1a4 available for Windows users. Note that this is pre-release, so it is expected to have issues (and the point of this release is to find them!) Do NOT use this package unless you are willing to find it does not work, and that you need to revert to the previous version you have been using. There is even the (remote) possibility that you will lose your training data - this is NOT recommended for general use. An official binary will be made available soon, so unless you like tinkering with your PC, I suggest you wait for an official release. The primary new feature in this release is 'image cracking' for the Outlook addin - ie, the ability to use OCR to peek inside images embedded in emails. It is enabled by default. While I'm sure this sounds like an attractive feature to try, please keep the previous paragraph in mind - its not yet suitable for general release; be patient, it will be soon. Also note that we have *not* made any changes specific to Outlook 2007 or Vista, but we wecome all reports about how things work there. Vista users should almost certainly use "Run as Administrator" when executing the installer - our installer probably isn't smart enough to force that yet. The release can be found at http://starship.python.net/crew/mhammond/spambayes-1.1a4-070629.exe and I'd welcome all feedback - even just telling me it seems to work well. Please do *not* mail me with general questions about the OCR support, or about any other new or old features - please mail spambayes-dev at python.org with such questions etc. Any questions not specifically related to the new version should continue to be posted on this mailing list. Cheers, Mark From dave at boost-consulting.com Sat Jul 7 15:34:00 2007 From: dave at boost-consulting.com (David Abrahams) Date: Sat, 07 Jul 2007 09:34:00 -0400 Subject: [Spambayes] Pre-release 1.1a4 windows binary available for testing References: <023201c7c060$92a07090$090a0a0a@enfoldsystems.local> Message-ID: <87r6nkuylz.fsf@grogan.peloton> on Sat Jul 07 2007, "Mark Hammond" wrote: > Hi all, > I've made a pre-release of SpamBayes 1.1a4 available for Windows users. Hi Mark, what are the CVS tags identifying 1.1a4 and 1.1a3? I can't find them. Thanks, -- Dave Abrahams Boost Consulting http://www.boost-consulting.com The Astoria Seminar ==> http://www.astoriaseminar.com From info at certified-penis-enlargement.com Sun Jul 8 18:22:14 2007 From: info at certified-penis-enlargement.com (Steve Jones) Date: Mon, 09 Jul 2007 02:22:14 +1000 Subject: [Spambayes] Reciprocal Link Trade Request Message-ID: <5vrfma$1kj9nf@smtp06.syd.iprimus.net.au> Hello there, Just sending this email out in hope for a reciprocal link exchange with your site. This will help to increase the rankings of both of our sites in the search engines as I'm sure you already know. I'll put your link on my site at www.certified-penis-enlargement.com in return for a link from your site. I hope to hear back from you soon regarding this exchange! Thanks for your time, Steve Jones From PCPete at audiography.com.au Mon Jul 9 00:08:18 2007 From: PCPete at audiography.com.au (Peter Naus) Date: Mon, 9 Jul 2007 08:08:18 +1000 Subject: [Spambayes] Reciprocal Link Trade Request In-Reply-To: <5vrfma$1kj9nf@smtp06.syd.iprimus.net.au> References: <5vrfma$1kj9nf@smtp06.syd.iprimus.net.au> Message-ID: <324E0F182F394518AFB458FACF1C586D@odysseus> Well, I'm only going to do a link exchange if I get a free sample... Lobster knows, I need all the length I can get. I spend too much time in front of a monitor to chase girls. (Plus there's the whole "I'm married" thing). But even She Who Must Be Obeyed would enjoy the benefits of such a simple link arrangement in exchange for certified 'percy' enlargement. FWIW, I've noticed a similar sudden surge in spam contacts through the Gentoo Familiar mailing list, which I unsubscribed from a few months ago. Seems that someone's been harvesting, since I've received a number "resubscribe" email sent to my old email address in the past 3 days. I suspect other members of this and similar lists may see the same thing. You can tell it's the school holidays here. I wish there was a Bayesian response to this kind of harvesting... -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Steve Jones Sent: Monday, 9 July 2007 2:22 AM To: mail.python.org Administrator Subject: [Spambayes] Reciprocal Link Trade Request Hello there, Just sending this email out in hope for a reciprocal link exchange with your site. This will help to increase the rankings of both of our sites in the search engines as I'm sure you already know. I'll put your link on my site at www.certified-penis-enlargement.com in return for a link from your site. I hope to hear back from you soon regarding this exchange! Thanks for your time, Steve Jones _______________________________________________ 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 Mon Jul 9 15:11:11 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 9 Jul 2007 08:11:11 -0500 Subject: [Spambayes] Pre-release 1.1a4 windows binary available for testing In-Reply-To: <87r6nkuylz.fsf@grogan.peloton> References: <023201c7c060$92a07090$090a0a0a@enfoldsystems.local> <87r6nkuylz.fsf@grogan.peloton> Message-ID: <18066.13295.447518.197493@montanaro.dyndns.org> Dave> what are the CVS tags identifying 1.1a4 and 1.1a3? I can't find Dave> them. That's because the bozo (that would be me) failed to create them when I created those releases. My apologies. I will try to remember that next time. Skip From mhammond at skippinet.com.au Tue Jul 10 03:14:20 2007 From: mhammond at skippinet.com.au (Mark Hammond) Date: Tue, 10 Jul 2007 11:14:20 +1000 Subject: [Spambayes] Pre-release 1.1a4 windows binary available fortesting In-Reply-To: <18066.13295.447518.197493@montanaro.dyndns.org> Message-ID: <042201c7c28f$a55ce930$090a0a0a@enfoldsystems.local> > Dave> what are the CVS tags identifying 1.1a4 and 1.1a3? > I can't find > Dave> them. > > That's because the bozo (that would be me) failed to create > them when I > created those releases. My apologies. I will try to > remember that next > time. There is also the issue that a bozo downunder had a number of changes he checked in *after* skip's initial email, and yet more changes that weren't even identified until I tried to put my package together... so in this case at least, the lack of a tag is a good thing, otherwise we'd be forced to brand my binary 'a5' or similar. The way things stand at the moment, we can pick some date in the future, nominate that as the *real* a4, make a tag and binaries, and forget about it for another few months (that is assmuming we can consider Skip's build 'release 1.1a4 beta 1" or something painfully convoluted...) Sadly, I fear my email about the binary scared too many people off - I'm yet to receive a single confirmation that the binary package works for someone. Oh well - I suggest that we just wait a few more days, then re-package a4 and release it anyway (and make a tag at that point). In private email I've been told that a number of the links in our docs and on the web site are broken, which I'll try and address, or if that fails, forward details here... Cheers, Mark From gbrandenburg1 at comcast.net Tue Jul 10 12:27:10 2007 From: gbrandenburg1 at comcast.net (Gil Brandenburg) Date: Tue, 10 Jul 2007 06:27:10 -0400 Subject: [Spambayes] Pre-release 1.1a4 windows binary available Message-ID: <000001c7c2dc$e3339270$0300a8c0@amd2000> >Sadly, I fear my email about the binary scared too many people off - I'm yet to receive a single confirmation that the binary package works for someone. >Oh well - I suggest that we just wait a few more days, then re-package a4 and release it anyway (and make a tag at that point). In private email I've been told that a number of the links in our docs and on the web site are broken, which I'll try and address, or if that fails, forward details here... >Cheers, >Mark Hi Mark, The binary package installed without a hitch on my XP/sp2, Outlook 2003 setup! Thanks, Gil -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070710/817b0ec9/attachment.html From rarendt at 2300executive.com Wed Jul 11 21:04:57 2007 From: rarendt at 2300executive.com (Ron Arendt) Date: Wed, 11 Jul 2007 12:04:57 -0700 Subject: [Spambayes] (no subject) Message-ID: <000601c7c3ee$61bb5c10$030a0a0a@RON> Hi, I have installed the Spambayes but when I open up my Outlook Express there is not Spambayes showing. Can you please help me. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070711/a62decb7/attachment.html From skip at pobox.com Wed Jul 11 22:30:52 2007 From: skip at pobox.com (skip at pobox.com) Date: Wed, 11 Jul 2007 15:30:52 -0500 Subject: [Spambayes] (no subject) In-Reply-To: <000601c7c3ee$61bb5c10$030a0a0a@RON> References: <000601c7c3ee$61bb5c10$030a0a0a@RON> Message-ID: <18069.15868.692146.501484@montanaro.dyndns.org> Ron> Hi, I have installed the Spambayes but when I open up my Outlook Ron> Express there is not Spambayes showing. Can you please help me. Ron, First, make sure you're not trying to use the Outlook Plugin: http://spambayes.sourceforge.net/faq.html#does-spambayes-work-with-outlook-express If that doesn't help, drop the list another message with some details about what you've tried. Skip From geraldine at can.rogers.com Thu Jul 12 15:30:02 2007 From: geraldine at can.rogers.com (Geraldine Jansz) Date: Thu, 12 Jul 2007 09:30:02 -0400 Subject: [Spambayes] Spambayes does not show me messages anymore Message-ID: <002401c7c488$c1ca5e90$234b6395@yourkybtg65gxe> Hello, I have used spambayes successfully for some time now. Unfortunately, more spam has started to creep back into my email. I have followed the help instructions to try to train spambayes on the new emails, but now, as I right-click on the tray icon and choose review messages, I get no messages to review. How do I make my incoming emails appear in the review messages window so that I can train more messages? I am running Outlook Express and Windows XP, Service Pack 2 Thank you for your help, Geraldine de Saram-Jansz -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070712/37283fde/attachment.htm From pollyn at appliedglobal.com Thu Jul 12 20:19:55 2007 From: pollyn at appliedglobal.com (Polly Neal) Date: Thu, 12 Jul 2007 14:19:55 -0400 Subject: [Spambayes] Problem with training Message-ID: <00a201c7c4b1$3f777f80$b21017ac@appliedglobal.com> Each time I try to train, I get the same report - It always says(no matter how many junk mails I move to the folder) that it has completed training with 4 spam and 0 good messages. I can't believe this is working properly. Can you assist me? Thank you, Polly Neal Polly Neal Applied Global Technologies 200 Chastain Center Blvd., Suite 235 Kennesaw, GA 30144 Phone: 678-594-4402 Cell: 678-642-7911 Fax: 770-427-6688 View a Demo of AGT'S Video Presenter! http://www.appliedglobal.com/content/VPLaunch/ViewPresentation.htm -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070712/4e3cad42/attachment.html From lists at stringsutils.com Fri Jul 13 00:17:09 2007 From: lists at stringsutils.com (Francisco Reyes) Date: Thu, 12 Jul 2007 18:17:09 -0400 Subject: [Spambayes] Multiuser support? Message-ID: I recently found spambayes and looking through archives and the documentation I have been unable to find any recent information if spambayes is multiuser or if there are any plans to make it multiuser. Anyone can shed any light on this? From skip at pobox.com Fri Jul 13 01:02:00 2007 From: skip at pobox.com (skip at pobox.com) Date: Thu, 12 Jul 2007 18:02:00 -0500 Subject: [Spambayes] Multiuser support? In-Reply-To: References: Message-ID: <18070.45800.641884.487639@montanaro.dyndns.org> Francisco> I recently found spambayes and looking through archives and Francisco> the documentation I have been unable to find any recent Francisco> information if spambayes is multiuser or if there are any Francisco> plans to make it multiuser. This FAQ should shed a little light on the problem: http://spambayes.sourceforge.net/faq.html#are-there-plans-to-develop-a-server-side-spambayes-solution Skip From skip at pobox.com Fri Jul 13 01:02:00 2007 From: skip at pobox.com (skip at pobox.com) Date: Thu, 12 Jul 2007 18:02:00 -0500 Subject: [Spambayes] Multiuser support? In-Reply-To: References: Message-ID: <18070.45800.641884.487639@montanaro.dyndns.org> Francisco> I recently found spambayes and looking through archives and Francisco> the documentation I have been unable to find any recent Francisco> information if spambayes is multiuser or if there are any Francisco> plans to make it multiuser. This FAQ should shed a little light on the problem: http://spambayes.sourceforge.net/faq.html#are-there-plans-to-develop-a-server-side-spambayes-solution Skip From dcs at dewitts.biz Fri Jul 13 07:09:50 2007 From: dcs at dewitts.biz (Dewitts Media) Date: Thu, 12 Jul 2007 22:09:50 -0700 (PDT) Subject: [Spambayes] donations Message-ID: <116057.26063.qm@web901.biz.mail.mud.yahoo.com> Hey I am a big fan of open source donations, the reason being is because I wouldn't have my company today if it wasn't for the open source community that has helped me out so much, but I was interested in making a donation to you, but will my company url be showed that I made a donation? I'm also raising a project for all open source communities, and I'm going to donate to numerous places with the money that I raise, cause I just feel like this can be in return for the wonderful community that has helped me with so much! DeWitt's Media "Internet Marketing and Designs that Effectively Build your Brand" Serving Clients World Wide 765-274-6877 Rank Higher in The Search Engines Buy Contextual Links Now! Get Paid To Blog, $10 Dollars Per Post SEO Services, Article Submissions, and Custom Programming. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070712/4b5c33fb/attachment.html From dale at BriannasSaladDressing.com Fri Jul 13 15:31:17 2007 From: dale at BriannasSaladDressing.com (Dale Schroeder) Date: Fri, 13 Jul 2007 08:31:17 -0500 Subject: [Spambayes] ham, Multiuser support? In-Reply-To: References: Message-ID: <46977EA5.7060005@BriannasSaladDressing.com> Francisco, I am using Spambayes on an ~20 workstation network. Apparently we all have the same idea as to what is spam because it is working wonderfully. I am using sb_server.py configured through the web interface. You can allow/control whatever connections you desire on the advanced configuration page. I have allowed all users on the local network to have filtering and the ability to train if they wish. For the Thunderbird users, training is quite easy with the ThunderBayes extension - click on a button that gives the choice of ham/spam. Outlook Express users have to use the smtp proxy of Spambayes to train, which unfortunately chokes on outgoing messages greater than ~1MB. The Outlook plugin would not be used in this setup, so it would be configured similarly to OE. If you don't trust your other users to train properly, you can limit access to the UI and smtp proxy to certain workstations. My current project is building a linux router/firewall that redirects all pop3 requests to Spambayes - no reconfiguration required in the mail client. That's especially useful to simplify the configuration for antivirus programs that scan mail through a proxy. I've been training this router for a while, and when I make the switch, users should not even notice. Dale Francisco Reyes wrote: > I recently found spambayes and looking through archives and the > documentation I have been unable to find any recent information if spambayes > is multiuser or if there are any plans to make it multiuser. > > Anyone can shed any light on this? > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html > > > From will.doak at gmail.com Fri Jul 13 17:26:20 2007 From: will.doak at gmail.com (Will Doak) Date: Fri, 13 Jul 2007 11:26:20 -0400 Subject: [Spambayes] Outlook has a problem with SpamBayes after last Office update Message-ID: <15392b420707130826r1b5d3eedwcae18f36937654a0@mail.gmail.com> Outlook froze and reported a "major problem with SpamBayes," if I recall the error message correctly, and offered to disable it. I agreed, and now I'm getting a lot more spam in my inbox. Anyone else had this problem? Fix? BTW, my IT people tell me they already block 70% of the email we get at work, 15 million messages this year. Thanks, Will -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070713/eccfa9c7/attachment.html From scoopjeff at bigfoot.com Fri Jul 13 22:44:11 2007 From: scoopjeff at bigfoot.com (scoopjeff) Date: Fri, 13 Jul 2007 13:44:11 -0700 (PDT) Subject: [Spambayes] Pre-release 1.1a4 windows binary available In-Reply-To: <000001c7c2dc$e3339270$0300a8c0@amd2000> References: <000001c7c2dc$e3339270$0300a8c0@amd2000> Message-ID: <11587160.post@talk.nabble.com> Yes its working here too, Windows Vista ultimate and office 2003 although it still states that its 1.1a3 april 2007 (Is this the tag issue or have I an older installed version??? Regards Scoop Gil Brandenburg-3 wrote: > >>Sadly, I fear my email about the binary scared too many people off - I'm > yet to receive a single confirmation that the binary package works for > someone. > >>Oh well - I suggest that we just wait a few more days, then re-package a4 > and release it anyway (and make a tag at that point). In private email > I've > been told that a number of the links in our docs and on the web site are > broken, which I'll try and address, or if that fails, forward details > here... > >>Cheers, > >>Mark > > Hi Mark, > > The binary package installed without a hitch on my XP/sp2, Outlook 2003 > setup! > > Thanks, > Gil > > > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html > -- View this message in context: http://www.nabble.com/Re%3A-Pre-release-1.1a4-windows-binary-available-tf4055011.html#a11587160 Sent from the Spambayes - General mailing list archive at Nabble.com. From skip at pobox.com Fri Jul 13 23:30:42 2007 From: skip at pobox.com (skip at pobox.com) Date: Fri, 13 Jul 2007 16:30:42 -0500 Subject: [Spambayes] Pre-release 1.1a4 windows binary available In-Reply-To: <11587160.post@talk.nabble.com> References: <000001c7c2dc$e3339270$0300a8c0@amd2000> <11587160.post@talk.nabble.com> Message-ID: <18071.61186.446358.43775@montanaro.dyndns.org> Scoop> Yes its working here too, Windows Vista ultimate and office 2003 Scoop> although it still states that its 1.1a3 april 2007 (Is this the Scoop> tag issue or have I an older installed version??? Probably a flub on my part when generating the release. I have a patch to add for an unrelated issue. I'll try to do a 1.1a5 release over the weekend and have Mark do a corresponding Windows installer based on that. Skip From beer at freakmail.de Fri Jul 13 23:13:11 2007 From: beer at freakmail.de (vbargsten) Date: Fri, 13 Jul 2007 23:13:11 +0200 Subject: [Spambayes] Problem with training In-Reply-To: <00a201c7c4b1$3f777f80$b21017ac@appliedglobal.com> References: <00a201c7c4b1$3f777f80$b21017ac@appliedglobal.com> Message-ID: <4697EAE7.3070903@freakmail.de> hi, You should explain your problem more precisely, e.g. what commands you run on which setup/version/operating system etc. mfg vb Polly Neal schrieb: > > Each time I try to train, I get the same report - It always says(no > matter how many junk mails I move to the folder) that it has completed > training with 4 spam and 0 good messages. I can't believe this is > working properly. > > Can you assist me? > > Thank you, > > Polly Neal > > > > /Polly Neal/ > /Applied Global Technologies/ > /200 Chastain Center Blvd., Suite 235/ > /Kennesaw, GA 30144/ > /Phone: 678-594-4402/ > /Cell: 678-642-7911/ > /Fax: 770-427-6688/ > > View a Demo of AGT'S Video Presenter! > /http://www.appliedglobal.com/content/VPLaunch/ViewPresentation.htm/ > > > > ------------------------------------------------------------------------ > > _______________________________________________ > SpamBayes at python.org > http://mail.python.org/mailman/listinfo/spambayes > Check the FAQ before asking: http://spambayes.sf.net/faq.html -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070713/7e9aa4c9/attachment.htm From papaDoc at videotron.ca Mon Jul 16 15:13:17 2007 From: papaDoc at videotron.ca (Remi) Date: Mon, 16 Jul 2007 09:13:17 -0400 Subject: [Spambayes] [spambayes-dev] CVS to Subversion - complete I think In-Reply-To: <18075.27983.75044.354024@montanaro.dyndns.org> References: <18074.16594.941758.730872@montanaro.dyndns.org> <08d301c7c770$7272f6f0$090a0a0a@enfoldsystems.local> <87lkdgeeki.fsf@grogan.peloton> <18075.27983.75044.354024@montanaro.dyndns.org> Message-ID: <469B6EED.4000303@videotron.ca> Hi Skip, > Dave> Because you're not connecting using ssh; you're using https. > > Any idea how I can get this to work without having to give my SF password on > every commit? You can use ssh-agent for a new shell and then ssh-add. N.B. You will have to add a key This should be done once: ssh-keygen -t dsa -C "USERNAME at shell.sf.net" This is done at the beginning of the day ssh-agent D:/Devtools/mks/mksnt/sh.exe or what ever shell you use. ssh-add t:/.ssh/id_dsa Remi From skip at pobox.com Mon Jul 16 16:01:46 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 16 Jul 2007 09:01:46 -0500 Subject: [Spambayes] [spambayes-dev] CVS to Subversion - complete I think In-Reply-To: <469B6EED.4000303@videotron.ca> References: <18074.16594.941758.730872@montanaro.dyndns.org> <08d301c7c770$7272f6f0$090a0a0a@enfoldsystems.local> <87lkdgeeki.fsf@grogan.peloton> <18075.27983.75044.354024@montanaro.dyndns.org> <469B6EED.4000303@videotron.ca> Message-ID: <18075.31306.989404.439687@montanaro.dyndns.org> Dave> Because you're not connecting using ssh; you're using https. >> Any idea how I can get this to work without having to give my SF >> password on every commit? Remi> You can use ssh-agent for a new shell Remi> and then ssh-add. Remi> N.B. You will have to add a key Remi> This should be done once: Remi> ssh-keygen -t dsa -C "USERNAME at shell.sf.net" Remi> This is done at the beginning of the day Remi> ssh-agent D:/Devtools/mks/mksnt/sh.exe or what ever shell you use. Remi> ssh-add t:/.ssh/id_dsa I don't think that will help. SF already has my pubkey. I can ssh into shell.sourceforge.net without giving my password. I tried using an svn+ssh://montanaro at ... url to checkout the SB repository (how I checkout the Python repository, but that URL form appears not to be supported by SourceForge. Skip From michael.stella at unisys.com Mon Jul 16 16:39:50 2007 From: michael.stella at unisys.com (Stella, Michael J.) Date: Mon, 16 Jul 2007 09:39:50 -0500 Subject: [Spambayes] Junk emails not going to configured directorys Message-ID: <7ECBFE60CB7F02478CDDDE40C985813A051531B5@USEA-EXCH4.na.uis.unisys.com> Problem - I configured SpamBayes Manger to send junk email and suspected junk email to directories under my "Personal Folders" but SpamBayes instead is sending junk email to the default "Junk E-mail" directory under Mail Box. It looks like the changes I the Filtering changes are not in affect. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070716/54c82eda/attachment.html From jsp at PKC.com Mon Jul 16 20:36:53 2007 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 16 Jul 2007 14:36:53 -0400 Subject: [Spambayes] Junk emails not going to configured directorys In-Reply-To: <7ECBFE60CB7F02478CDDDE40C985813A051531B5@USEA-EXCH4.na.uis.unisys.com> References: <7ECBFE60CB7F02478CDDDE40C985813A051531B5@USEA-EXCH4.na.uis.unisys.com> Message-ID: <16E2027582CDB74180896CDB4B8CC1F905B49B79@PKCVT01.pkc.com> Are you certain that SpamBayes is putting them there? You appear to be using Outlook and Exchange, in which case Exchange (or maybe Outlook; I can never remember) may be putting the files there. If you haven't instructed SpamBayes to filter the Outlook's junk and junk candidates folders, any messages that Exchange puts there will remain there until you do something with them. If you need further assistance, please include: * the version of Windows you are using, * the version of SpamBayes, * any log files. ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Stella, Michael J. Sent: Monday, July 16, 2007 10:40 AM To: spambayes at python.org Subject: [Spambayes] Junk emails not going to configured directorys Problem - I configured SpamBayes Manger to send junk email and suspected junk email to directories under my "Personal Folders" but SpamBayes instead is sending junk email to the default "Junk E-mail" directory under Mail Box. It looks like the changes I the Filtering changes are not in affect. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070716/ed908ec5/attachment.html From jsp at PKC.com Mon Jul 16 20:40:00 2007 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 16 Jul 2007 14:40:00 -0400 Subject: [Spambayes] FW: Junk emails not going to configured directorys Message-ID: <16E2027582CDB74180896CDB4B8CC1F905B49B7D@PKCVT01.pkc.com> For posterity. ________________________________ From: Stella, Michael J. [mailto:michael.stella at unisys.com] Sent: Monday, July 16, 2007 2:38 PM To: Jesse Pelton Subject: RE: [Spambayes] Junk emails not going to configured directorys It is working now, I ran the training , thank you ________________________________ From: Jesse Pelton [mailto:jsp at PKC.com] Sent: Monday, July 16, 2007 1:37 PM To: Stella, Michael J.; spambayes at python.org Subject: RE: [Spambayes] Junk emails not going to configured directorys Are you certain that SpamBayes is putting them there? You appear to be using Outlook and Exchange, in which case Exchange (or maybe Outlook; I can never remember) may be putting the files there. If you haven't instructed SpamBayes to filter the Outlook's junk and junk candidates folders, any messages that Exchange puts there will remain there until you do something with them. If you need further assistance, please include: * the version of Windows you are using, * the version of SpamBayes, * any log files. ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Stella, Michael J. Sent: Monday, July 16, 2007 10:40 AM To: spambayes at python.org Subject: [Spambayes] Junk emails not going to configured directorys Problem - I configured SpamBayes Manger to send junk email and suspected junk email to directories under my "Personal Folders" but SpamBayes instead is sending junk email to the default "Junk E-mail" directory under Mail Box. It looks like the changes I the Filtering changes are not in affect. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070716/8eb84d84/attachment.htm From jcover at reprographicsone.com Tue Jul 17 22:00:33 2007 From: jcover at reprographicsone.com (Jean Cover) Date: Tue, 17 Jul 2007 16:00:33 -0400 Subject: [Spambayes] OUTLOOK 2007 Message-ID: <5DFB8DA1DEC8E74FB5A76B47C8877A8D17064E@repro-srv1.Reprographics.local> I love your product and use it at work every day. When will you have a version available for Outlook 2007 under Windows Vista Ultimate so I can get it going at home? If you get a minute, please let me know. Best regards, Jean Cover Office Manager Reprographics One, Inc. 36060 Industrial Road Livonia, MI 48150 (734) 542-8800 - PHONE (800) 968-7788 - TOLL-FREE (734) 542-8480 - FAX E-mail: jcover at reprographicsone.com Web: http://www.reprographicsone.com -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070717/537f10fd/attachment.htm From skip at pobox.com Wed Jul 18 01:58:03 2007 From: skip at pobox.com (skip at pobox.com) Date: Tue, 17 Jul 2007 18:58:03 -0500 Subject: [Spambayes] OUTLOOK 2007 In-Reply-To: <5DFB8DA1DEC8E74FB5A76B47C8877A8D17064E@repro-srv1.Reprographics.local> References: <5DFB8DA1DEC8E74FB5A76B47C8877A8D17064E@repro-srv1.Reprographics.local> Message-ID: <18077.22411.572610.739173@montanaro.dyndns.org> Jean> I love your product and use it at work every day. When will you Jean> have a version available for Outlook 2007 under Windows Vista Jean> Ultimate so I can get it going at home? As far as I know it should work, but read this before installing: http://spambayes.sourceforge.net/faq.html#does-spambayes-work-on-windows-vista Skip From J.Bowler at computer-pros.com Fri Jul 20 18:07:48 2007 From: J.Bowler at computer-pros.com (Jesse Bowler) Date: Fri, 20 Jul 2007 09:07:48 -0700 Subject: [Spambayes] Office 2007 Compatibility Message-ID: Hello, I am Jesse Bowler and I was trying to install spambayes on my new computer. I have always used it on my other machines in the past. I have upgraded my office version from office 2003 Professional, to the newest version of Office 2007. But every time I went to install spambayes, it would crash Microsoft Outlook 2007. Is there any known compatibility issues with this new version of Outlook or was there something that I was not doing correctly with the install. Any information you can give me would be completely and greatly appreciated. Thank you, Jesse Bowler -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070720/41477bf4/attachment.html From cheshirecastle at verizon.net Sat Jul 21 05:31:12 2007 From: cheshirecastle at verizon.net (Karl Bruck) Date: Fri, 20 Jul 2007 20:31:12 -0700 Subject: [Spambayes] New hardrive Message-ID: <000801c7cb47$96d55b70$0401a8c0@karljmqjm95lrz> Have a new hardrive and now I can't get Spambays to load. It starts but wont complete and the download bar scale stops just shy of completion. What do I do to download Spambays?? Karl Bruck -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070720/1cdb16db/attachment.html From coffent at bigfoot.com Sat Jul 21 17:46:42 2007 From: coffent at bigfoot.com (C Stephan) Date: Sat, 21 Jul 2007 11:46:42 -0400 Subject: [Spambayes] How best to train SpamBayes? Message-ID: <20070721154650.61F0F1E4008@bag.python.org> I understand SpamBayes works best when trained on roughly equal numbers of ham & spam messages. After initial training, I've been training it only on messages it got wrong or was unsure about. Should I also be including some (or all) correctly-labeled ham & spam in the training? Thanks. From boffsatoz at bigpond.com Sun Jul 22 02:04:02 2007 From: boffsatoz at bigpond.com (Brenda Boff) Date: Sun, 22 Jul 2007 10:04:02 +1000 Subject: [Spambayes] retrieve mail Message-ID: My spam is filtering and putting the mail into the Training section how do I recover my mail and why is it sending it somewhere else? I have nil messages in my inbox but apparently loads of mail in my Training box. Regards Brenda Boff boffsatoz at bigpond.com From PCPete at audiography.com.au Sun Jul 22 03:03:49 2007 From: PCPete at audiography.com.au (Peter Naus) Date: Sun, 22 Jul 2007 11:03:49 +1000 Subject: [Spambayes] retrieve mail In-Reply-To: References: Message-ID: <7552E25F8D914B0F94AA78B5AC90E6AA@odysseus> G'day Brenda, It sounds like Spambayes didn't get quite enough material to identify spam and ham when you first installed it. So by putting material into the Training folder, Spambayes is asking you to go through that folder and help it identify what's spam and what's ham. It could also be that the "suspect" mail handling is a bit aggressive, and the details on how to change that is below. If you open the folder in Outlook and select a message, you can then use the buttons in the Spambayes toolbar to set each message to either "Spam" (frowning face) or "Not Spam" (smiley face). It sounds like you'll have to do this for quite a while, as it isn't able to categorise any of the email at this point - that's why it's so important to train the program when it's first installed. But even if it does get enough training material, it still may not have enough information to categorise each message at this time. So each time you tell it what's good and what's bad, it will filter more of your email more correctly, and more good mail will end up in your Inbox and less in the Training Folder. It's also possible to change the Spambayes behaviour towards "unknown" mail, if it's too aggressive towards good mail (or not aggressive enough). Open the Spambayes manager, go to the "Filtering" tab, and look at the "Suspect" section - you can tell Spambayes where to put suspect mail, how suspect it has to be before it's considered as "suspect", and you can even turn off this behaviour if you don't want the hassle of a second folder to check for spam. Please also remember to check your "Junk Email" folder for misidentified mail. As time goes by, Spambayes will misidentify less and less often, but it's utterly impossible for any program, no matter how sophisticated, to get 100% accuracy on bad and good email, and you'll always need to check your junk mail folder before deleting it. I hope this helps, and (even more) it's correct, and I'm not standing on anyone's toes... Cheers, PC Pete -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Brenda Boff Sent: Sunday, 22 July 2007 10:04 AM To: spambayes at python.org Subject: [Spambayes] retrieve mail My spam is filtering and putting the mail into the Training section how do I recover my mail and why is it sending it somewhere else? I have nil messages in my inbox but apparently loads of mail in my Training box. Regards Brenda Boff boffsatoz at bigpond.com _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From stapleton at mps.ohio-state.edu Sun Jul 22 14:41:30 2007 From: stapleton at mps.ohio-state.edu (S James S Stapleton) Date: Sun, 22 Jul 2007 08:41:30 -0400 Subject: [Spambayes] A couple questions regarding spambayes and it's features Message-ID: <200707220841.30752.stapleton@mps.ohio-state.edu> Background; I've been using Spambayes for a while, it starts out good, quickly is trained to great, but at some critical point drops to crud. At the great state, I get no false positives, and the false negatives/uncertains are low. But spammers change their tactics and I have too keep training to keep SB in the great state, until at one point it gets overtrained and *everything* pretty much goes into spam and I just get the few (1-5%) false negatives, and some mailing list stuff, in my box. (1) Is there any way to whitelist email addresses? The only address I get spam from regularly is when they spoof mine. (2) Can values be modified and locked? For example, I'm part of several mailing lists which tag their emails, [PyQt], [PHP], [PHP-WIN], [SDL], etc. I would like to be able to mark those tags, and some common keywords things like that as 'minimal spam probability]. Add to that some keywords I know I'll never see in a legitimate email, I wouldn't mind fast-fowarding them to the 'this is a spam word' state. Please CC me any responses, as I am not on the list. Thank you, -Jim Stapleton From rfxnoreply at asp-4.reflexion.net Mon Jul 23 05:33:51 2007 From: rfxnoreply at asp-4.reflexion.net (Reflexion) Date: Mon, 23 Jul 2007 05:33:51 +0200 (CEST) Subject: [Spambayes] RFX ALERT: Virus-infected message asp-4.reflexion.net Message-ID: <20070723033351.95CD91E4007@bag.python.org> Hi. This is the Reflexion Total Control server at asp-4.reflexion.net. A message sent to mary at lee-merchandising.com.au was found to contain a virus (or phishing exploit), and will not be delivered. From: spambayes at python.org To: mary at lee-merchandising.com.au IP: 58.160.121.239 Subject: Re: Mail Server Virus name: Worm.SomeFool.P Reflexion Total Control: Managed Email Threat Protection -- http://www.reflexion.net -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070723/d45ce9f3/attachment.htm -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/gif Size: 4385 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20070723/d45ce9f3/attachment.gif From amedee at amedee.be Mon Jul 23 09:11:26 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Mon, 23 Jul 2007 09:11:26 +0200 (CEST) Subject: [Spambayes] How best to train SpamBayes? In-Reply-To: <20070721154650.61F0F1E4008@bag.python.org> References: <20070721154650.61F0F1E4008@bag.python.org> Message-ID: <58089.193.121.250.194.1185174686.squirrel@amedee.be> On Sat, July 21, 2007 17:46, C Stephan wrote: > I understand SpamBayes works best when trained on roughly equal > numbers of ham & spam messages. After initial training, I've been > training it only on messages it got wrong or was unsure > about. Should I also be including some (or all) correctly-labeled > ham & spam in the training? Thanks. You train the same way as most people do. (I think) You don't have to train correctly-labeled ham & spam. Except perhaps when your traing db has a very unequal number of ham vs spam. And even then... -- Amedee From amedee at amedee.be Mon Jul 23 09:32:22 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Mon, 23 Jul 2007 09:32:22 +0200 (CEST) Subject: [Spambayes] A couple questions regarding spambayes and it's features In-Reply-To: <200707220841.30752.stapleton@mps.ohio-state.edu> References: <200707220841.30752.stapleton@mps.ohio-state.edu> Message-ID: <14616.193.121.250.194.1185175942.squirrel@amedee.be> On Sun, July 22, 2007 14:41, S James S Stapleton wrote: > Background; I've been using Spambayes for a while, it starts out good, > quickly > is trained to great, but at some critical point drops to crud. > > At the great state, I get no false positives, and the false > negatives/uncertains are low. But spammers change their tactics and I have > too keep training to keep SB in the great state, until at one point it > gets > overtrained and *everything* pretty much goes into spam and I just get the > few (1-5%) false negatives, and some mailing list stuff, in my box. > > (1) Is there any way to whitelist email addresses? The only address I get > spam > from regularly is when they spoof mine. > > (2) Can values be modified and locked? For example, I'm part of several > mailing lists which tag their emails, [PyQt], [PHP], [PHP-WIN], [SDL], > etc. I > would like to be able to mark those tags, and some common keywords things > like that as 'minimal spam probability]. Add to that some keywords I know > I'll never see in a legitimate email, I wouldn't mind fast-fowarding them > to > the 'this is a spam word' state. > > Please CC me any responses, as I am not on the list. I learned from your mail headers that you use Kmail so there is a 99% possibility you're on Linux. Is that correct? How do you have SpamBayes set up? I use it as a procmail filter, like this: (I don't have access to my .procmailrc ATM, perhaps later) * First, a few rules that move mailing list traffic & mail from friends to certain folders. This is a sort of procmail whitelist. These kinds of mail don't get spamfiltered, however I have used them for initial training. --> This already answers your two questions. * A rule that scores mail with SB * Everything with spamscore 100% gets the /dev/null treatment * Remaining spam is moved to my spam suspect folder. (to move manually to the training folder later) * Unsures are _copied_ to my unsures folder * Ham is moved to my inbox or processed by other procmail rules. The exact syntax of this .procmailrc file is left as an exercise to the reader. :) -- Amedee From stapleton at mps.ohio-state.edu Mon Jul 23 13:17:48 2007 From: stapleton at mps.ohio-state.edu (S James S Stapleton) Date: Mon, 23 Jul 2007 07:17:48 -0400 Subject: [Spambayes] A couple questions regarding spambayes and it's features In-Reply-To: <14616.193.121.250.194.1185175942.squirrel@amedee.be> References: <200707220841.30752.stapleton@mps.ohio-state.edu> <14616.193.121.250.194.1185175942.squirrel@amedee.be> Message-ID: <200707230717.48949.stapleton@mps.ohio-state.edu> > I learned from your mail headers that you use Kmail so there is a 99% > possibility you're on Linux. Is that correct? > How do you have SpamBayes set up? > > I use it as a procmail filter, like this: > (I don't have access to my .procmailrc ATM, perhaps later) > > * First, a few rules that move mailing list traffic & mail from friends to > certain folders. This is a sort of procmail whitelist. These kinds of mail > don't get spamfiltered, however I have used them for initial training. --> > This already answers your two questions. > * A rule that scores mail with SB > * Everything with spamscore 100% gets the /dev/null treatment > * Remaining spam is moved to my spam suspect folder. (to move manually to > the training folder later) > * Unsures are _copied_ to my unsures folder > * Ham is moved to my inbox or processed by other procmail rules. > > The exact syntax of this .procmailrc file is left as an exercise to the > reader. :) FreeBSD actually. Close enough for most userland things I guess. I have the daemon running, and have my email client pointed to localhost for receiving. I do my training and such through the web interface (I started using Spambayes in Windows, and have grown used to that interface, as it is fairly simple). The database is stored in /var/db/sb/ The subject line and the recipient metadata are not marked. Kmail has a filter to - Move mail classified as spam to 'junk' - Move mail classified as unsure to 'unsure' - It does not mark any mail as read. The POP server is on a Windows machine. It is MailEnable I believe (I didn't set it up, and until I get my own connection, I'm stuck with it). From Pwathens at aol.com Mon Jul 23 18:27:28 2007 From: Pwathens at aol.com (Pwathens at aol.com) Date: Mon, 23 Jul 2007 12:27:28 EDT Subject: [Spambayes] Delete as Spam / Recovery from Spam button does not work Message-ID: I try to move what is not spam into my regular e-mail box and it is no t transfered. Can I retrieve it? What's the problem? This has only become a problem in the last couple of months. Peggy Wallace ************************************** Get a sneak peek of the all-new AOL at http://discover.aol.com/memed/aolcom30tour -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070723/f05710c3/attachment.htm From dave at boost-consulting.com Mon Jul 23 19:48:59 2007 From: dave at boost-consulting.com (David Abrahams) Date: Mon, 23 Jul 2007 13:48:59 -0400 Subject: [Spambayes] some SpamBayes errors from my procmail log Message-ID: <878x971050.fsf@grogan.peloton> I'm not sure what this one means: procmail: Executing "sb_filter.py" Traceback (most recent call last): File "/usr/local/bin/sb_filter.py", line 83, in ? from spambayes import hammie, Options, mboxutils, storage File "/usr/local/lib/python2.4/site-packages/spambayes/hammie.py", line 7, in ? from spambayes.tokenizer import tokenize File "/usr/local/lib/python2.4/site-packages/spambayes/tokenizer.py", line 44, in ? cache = dnscache.cache(cachefile=options["Tokenizer", "lookup_ip_cache"]) File "/usr/local/lib/python2.4/site-packages/spambayes/dnscache.py", line 98, in __init__ self.caches = pickle.load(open(self.cachefile, "rb")) EOFError Also troubling is: Persisting /home/dave/spambayes/hammie.fs state in database Exception bsddb._db.DBAccessError: (13, 'Permission denied -- put: attempt to modify a read-only tree') in > ignored which happens for every message. I have r/w access to all the relevant files. Can anyone help explain these? Thanks, -- Dave Abrahams Boost Consulting http://www.boost-consulting.com The Astoria Seminar ==> http://www.astoriaseminar.com From dalmolin at e-cology.ca Tue Jul 24 03:54:22 2007 From: dalmolin at e-cology.ca (Joseph Dal Molin) Date: Mon, 23 Jul 2007 21:54:22 -0400 Subject: [Spambayes] Spambayes does not start automatically anymore - Kubuntu Feisty Message-ID: <46A55BCE.3030208@e-cology.ca> Hi folks, Have been a delighted user of Spambayes for over 5 years now....thank you to the developers for such a great tool....it is terrific!! I am writing because I need some help getting sb_server.py to start automatically. I installed Spambayes using Adept as I had for the previous version of Kubuntu....and for some reason it is not starting automatically anymore. Is there perhaps a problem in the Spambayes install script and Kubuntu Feisty??? Thanks for your help Joseph From skip at pobox.com Tue Jul 24 04:20:53 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 23 Jul 2007 21:20:53 -0500 Subject: [Spambayes] Spambayes does not start automatically anymore - Kubuntu Feisty In-Reply-To: <46A55BCE.3030208@e-cology.ca> References: <46A55BCE.3030208@e-cology.ca> Message-ID: <18085.25093.744595.579337@montanaro.dyndns.org> Joseph> I installed Spambayes using Adept as I had for the previous Joseph> version of Kubuntu....and for some reason it is not starting Joseph> automatically anymore. Is there perhaps a problem in the Joseph> Spambayes install script and Kubuntu Feisty??? I don't speak Kubuntu Feisty, Kubuntu, or even just plain Ubuntu, so I can't guess what it's doing (or not doing, as the case may be). Can you rummage around in your system logs to see if there is an attempt to start SpamBayes? Does Adept have some documentation which will help you troubleshoot the problem? The dmesg(1) command might come in handy as might the contents of the /var/log directory. -- Skip Montanaro - skip at pobox.com - http://www.webfast.com/~skip/ From skip at pobox.com Tue Jul 24 04:22:29 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 23 Jul 2007 21:22:29 -0500 Subject: [Spambayes] some SpamBayes errors from my procmail log In-Reply-To: <878x971050.fsf@grogan.peloton> References: <878x971050.fsf@grogan.peloton> Message-ID: <18085.25189.816247.969243@montanaro.dyndns.org> Dave> I'm not sure what this one means: Dave> procmail: Executing "sb_filter.py" ... Dave> EOFError Looks like a corrupt pickle file. Dave> Also troubling is: Dave> Persisting /home/dave/spambayes/hammie.fs state in database Dave> Exception bsddb._db.DBAccessError: (13, 'Permission denied -- put: attempt to modify a read-only tree') in > ignored That one I have no clue about. Skip From dalmolin at e-cology.ca Tue Jul 24 07:24:28 2007 From: dalmolin at e-cology.ca (Joseph Dal Molin) Date: Tue, 24 Jul 2007 01:24:28 -0400 Subject: [Spambayes] Spambayes does not start automatically anymore - Kubuntu Feisty In-Reply-To: <18085.25093.744595.579337@montanaro.dyndns.org> References: <46A55BCE.3030208@e-cology.ca> <18085.25093.744595.579337@montanaro.dyndns.org> Message-ID: <46A58D0C.1050507@e-cology.ca> Nothing showed up in the logs.... should there be a script in /etc/init.d/ ? skip at pobox.com wrote: > Joseph> I installed Spambayes using Adept as I had for the previous > Joseph> version of Kubuntu....and for some reason it is not starting > Joseph> automatically anymore. Is there perhaps a problem in the > Joseph> Spambayes install script and Kubuntu Feisty??? > > I don't speak Kubuntu Feisty, Kubuntu, or even just plain Ubuntu, so I can't > guess what it's doing (or not doing, as the case may be). Can you rummage > around in your system logs to see if there is an attempt to start SpamBayes? > Does Adept have some documentation which will help you troubleshoot the > problem? The dmesg(1) command might come in handy as might the contents of > the /var/log directory. > From skip at pobox.com Tue Jul 24 12:55:25 2007 From: skip at pobox.com (skip at pobox.com) Date: Tue, 24 Jul 2007 05:55:25 -0500 Subject: [Spambayes] Spambayes does not start automatically anymore - Kubuntu Feisty In-Reply-To: <46A58D0C.1050507@e-cology.ca> References: <46A55BCE.3030208@e-cology.ca> <18085.25093.744595.579337@montanaro.dyndns.org> <46A58D0C.1050507@e-cology.ca> Message-ID: <18085.55965.889037.536729@montanaro.dyndns.org> Joseph> Nothing showed up in the logs.... should there be a script in Joseph> /etc/init.d/ ? Normally, I would say "yes" though I have no idea how Adept works its magic. Is it just a simple front-end tool that builds the necessary symlinks in /etc/rc?.d for you? Are there any? Skip From skip at pobox.com Tue Jul 24 13:00:01 2007 From: skip at pobox.com (skip at pobox.com) Date: Tue, 24 Jul 2007 06:00:01 -0500 Subject: [Spambayes] Spambayes does not start automatically anymore - Kubuntu Feisty In-Reply-To: <46A58D0C.1050507@e-cology.ca> References: <46A55BCE.3030208@e-cology.ca> <18085.25093.744595.579337@montanaro.dyndns.org> <46A58D0C.1050507@e-cology.ca> Message-ID: <18085.56241.834055.397742@montanaro.dyndns.org> Joseph> Nothing showed up in the logs.... should there be a script in Joseph> /etc/init.d/ ? Skip> Normally, I would say "yes" though I have no idea how Adept works Skip> its magic. Is it just a simple front-end tool that builds the Skip> necessary symlinks in /etc/rc?.d for you? Are there any? Ah, it's the Ubuntu package manager. A little googling shows that the SpamBayes package doesn't include any /etc/init.d start files: http://packages.ubuntu.com/cgi-bin/search_contents.pl?searchmode=filelist&word=spambayes&version=feisty&arch=all If you want sb_server.py to start when the machine is booted, why not just add an @reboot line to your crontab? Skip From dalmolin at e-cology.ca Tue Jul 24 15:22:35 2007 From: dalmolin at e-cology.ca (Joseph Dal Molin) Date: Tue, 24 Jul 2007 09:22:35 -0400 Subject: [Spambayes] Spambayes does not start automatically anymore - Kubuntu Feisty In-Reply-To: <18085.56241.834055.397742@montanaro.dyndns.org> References: <46A55BCE.3030208@e-cology.ca> <18085.25093.744595.579337@montanaro.dyndns.org> <46A58D0C.1050507@e-cology.ca> <18085.56241.834055.397742@montanaro.dyndns.org> Message-ID: <46A5FD1B.30109@e-cology.ca> Thanks Skip that will work... I also found the following script on the Spambayes site which sounds very good as it is tied to starting and stopping my mail client... will let the list know if it works: "This script launches SpamBayes then Thunderbird. Once Thunderbird quits, SpamBayes is shut down." #!/bin/bash # SpamBayes database and configuration files are stored at $SB_HOME SB_HOME=~/spambayes [ ! -d $SB_HOME ] && mkdir $SB_HOME cd $SB_HOME # Launch the proxy in background sb_server.py & # Launch the email client mozilla-thunderbird # Shutdown the server (taken from sb_server.py) python - <<-EOS from urllib import urlopen, urlencode urlopen('http://localhost:8880/save', urlencode({'how': 'Save & shutdown'})).read() EOS skip at pobox.com wrote: > Joseph> Nothing showed up in the logs.... should there be a script in > Joseph> /etc/init.d/ ? > > Skip> Normally, I would say "yes" though I have no idea how Adept works > Skip> its magic. Is it just a simple front-end tool that builds the > Skip> necessary symlinks in /etc/rc?.d for you? Are there any? > > Ah, it's the Ubuntu package manager. A little googling shows that the > SpamBayes package doesn't include any /etc/init.d start files: > > http://packages.ubuntu.com/cgi-bin/search_contents.pl?searchmode=filelist&word=spambayes&version=feisty&arch=all > > If you want sb_server.py to start when the machine is booted, why not just > add an @reboot line to your crontab? > > Skip > . > From amedee at amedee.be Tue Jul 24 16:56:19 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Tue, 24 Jul 2007 16:56:19 +0200 (CEST) Subject: [Spambayes] Spambayes does not start automatically anymore - Kubuntu Feisty In-Reply-To: <18085.55965.889037.536729@montanaro.dyndns.org> References: <46A55BCE.3030208@e-cology.ca> <18085.25093.744595.579337@montanaro.dyndns.org> <46A58D0C.1050507@e-cology.ca> <18085.55965.889037.536729@montanaro.dyndns.org> Message-ID: <15433.193.121.250.194.1185288979.squirrel@amedee.be> On Tue, July 24, 2007 12:55, skip at pobox.com wrote: > > Joseph> Nothing showed up in the logs.... should there be a script in > Joseph> /etc/init.d/ ? > > Normally, I would say "yes" though I have no idea how Adept works its > magic. > Is it just a simple front-end tool that builds the necessary symlinks in > /etc/rc?.d for you? Are there any? Adept is a (K)ubuntu frontend for apt-get, which is the default package installer for Debian based distros. Sort of like rpm for Fedora and Mandriva. -- Amedee From amedee at amedee.be Tue Jul 24 16:57:58 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Tue, 24 Jul 2007 16:57:58 +0200 (CEST) Subject: [Spambayes] Spambayes does not start automatically anymore - Kubuntu Feisty In-Reply-To: <18085.56241.834055.397742@montanaro.dyndns.org> References: <46A55BCE.3030208@e-cology.ca> <18085.25093.744595.579337@montanaro.dyndns.org> <46A58D0C.1050507@e-cology.ca> <18085.56241.834055.397742@montanaro.dyndns.org> Message-ID: <16707.193.121.250.194.1185289078.squirrel@amedee.be> On Tue, July 24, 2007 13:00, skip at pobox.com wrote: > > Joseph> Nothing showed up in the logs.... should there be a script in > Joseph> /etc/init.d/ ? > > Skip> Normally, I would say "yes" though I have no idea how Adept > works > Skip> its magic. Is it just a simple front-end tool that builds the > Skip> necessary symlinks in /etc/rc?.d for you? Are there any? > > Ah, it's the Ubuntu package manager. A little googling shows that the > SpamBayes package doesn't include any /etc/init.d start files: > > http://packages.ubuntu.com/cgi-bin/search_contents.pl?searchmode=filelist&word=spambayes&version=feisty&arch=all > > If you want sb_server.py to start when the machine is booted, why not just > add an @reboot line to your crontab? Or why not write your own init.d script based on a template whose name I've forgotten, and make a symlink to the right runlevel(s)? -- Amedee From suporte at rotamil.com Tue Jul 24 23:37:37 2007 From: suporte at rotamil.com (suporte rotamil) Date: Tue, 24 Jul 2007 21:37:37 GMT Subject: [Spambayes] PNID Message-ID: <20070724215012.8CDBE1E4007@bag.python.org> An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070724/f7aa9fe7/attachment.htm From Tmark86 at ameritech.net Wed Jul 25 17:34:43 2007 From: Tmark86 at ameritech.net (Thomas Mark) Date: Wed, 25 Jul 2007 10:34:43 -0500 Subject: [Spambayes] Sensitive E-mail between My company and You showing up online!!! Message-ID: <001b01c7ced1$5379dad0$fa6d9070$@net> Dear Spambayes, Recently I sent copies of e-mails to you because we were having trouble with our configuration and certain spam still getting through. I thought that these e-mails were between your company and ours but through google searches I have found the exact copies of the e-mails that I sent you. These e-mails contain sensitive company information and I would like it if you could please remove them immediately and confirm to me that they were removed. Below are the links to the specific e-mails. http://mail.python.org/pipermail/spambayes/2007-January/020380.html http://mail.python.org/pipermail/spambayes/2007-January/020383.html http://mail.python.org/pipermail/spambayes/2007-January/020366.html http://mail.python.org/pipermail/spambayes/2007-January/020367.html I would greatly appreciate it if each one of these messages could be removed ASAP. Thank you very much and I would like a confirmation if possible when this has been accomplished. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070725/cc7d3407/attachment.html From tmark at insightbb.com Wed Jul 25 17:51:40 2007 From: tmark at insightbb.com (Thomas Mark) Date: Wed, 25 Jul 2007 10:51:40 -0500 Subject: [Spambayes] Breach of Privacy Message-ID: <001701c7ced3$b122aed0$13680c70$@com> Dear Spambayes, I sent an e-mail earlier about some e-mails from my company to your company regarding tech support. These e-mails found on google.com contained confidential information and had disclaimers as such in the e-mails. I have since found several of these e-mails easily searchable on google.com and free for the world to see. This puts my company at financial jeopardy as we are held liable for content that was supposed to be kept in private and via your servers with the rest of the world. We consider this an egregious breach of security and privacy between my company and Spambayes. I would appreciate a full scan of your database for any and all reference to IMERGE Consulting and have it cleared from public record. This breach could cause serious trouble for my company and we are placing utmost concern with this issue. An Immediate response would be very appreciated. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070725/bf432440/attachment.htm From skip at pobox.com Wed Jul 25 19:17:56 2007 From: skip at pobox.com (skip at pobox.com) Date: Wed, 25 Jul 2007 12:17:56 -0500 Subject: [Spambayes] Breach of Privacy In-Reply-To: <001701c7ced3$b122aed0$13680c70$@com> References: <001701c7ced3$b122aed0$13680c70$@com> Message-ID: <18087.34244.26335.23448@montanaro.dyndns.org> Thomas> I sent an e-mail earlier about some e-mails from my company to Thomas> your company regarding tech support. These e-mails found on Thomas> google.com contained confidential information and had Thomas> disclaimers as such in the e-mails. I have since found several Thomas> of these e-mails easily searchable on google.com and free for Thomas> the world to see. This puts my company at financial jeopardy as Thomas> we are held liable for content that was supposed to be kept in Thomas> private and via your servers with the rest of the world. Thomas, I'm not sure where you got the idea that posting messages to a public mailing list about an open source tool such as SpamBayes constituted private communication with the tech support group of another company. I presume you subscribed to the list or at least visited the subscription page. Right there is a link to the mailing list archives. Anyone can read them. The fact that you found your messages via Google is not surprising and demonstrates how the system is supposed to work. If Google found them then Yahoo!, MSN and other search engines almost certainly found them as well. In addition, email mirroring services will have them: Gmane, Google Groups, etc. Finally, I suspect you can find your messages via Alexa's Wayback Machine. The responsibility for using the technology appropriately rests with you. The horse left the barn months ago. Now you want someone else to close the door. That's not going to help. -- Skip Montanaro - skip at pobox.com - http://www.webfast.com/~skip/ From tmark at insightbb.com Wed Jul 25 19:21:32 2007 From: tmark at insightbb.com (Thomas Mark) Date: Wed, 25 Jul 2007 12:21:32 -0500 Subject: [Spambayes] Breach of Privacy In-Reply-To: <18087.34244.26335.23448@montanaro.dyndns.org> References: <001701c7ced3$b122aed0$13680c70$@com> <18087.34244.26335.23448@montanaro.dyndns.org> Message-ID: <002001c7cee0$3f1dc420$bd594c60$@com> I have talked with our IT department here and they now recognize and confess to the fact that they have let slip certain confidential documents without consent. I was under the notion and I apologize that they had not done this. I know that it is too late to take it back but I was wondering if there would be any way to remove these messages from the public server. -----Original Message----- From: skip at pobox.com [mailto:skip at pobox.com] Sent: Wednesday, July 25, 2007 12:18 PM To: Thomas Mark Cc: spambayes at python.org Subject: Re: [Spambayes] Breach of Privacy Thomas> I sent an e-mail earlier about some e-mails from my company to Thomas> your company regarding tech support. These e-mails found on Thomas> google.com contained confidential information and had Thomas> disclaimers as such in the e-mails. I have since found several Thomas> of these e-mails easily searchable on google.com and free for Thomas> the world to see. This puts my company at financial jeopardy as Thomas> we are held liable for content that was supposed to be kept in Thomas> private and via your servers with the rest of the world. Thomas, I'm not sure where you got the idea that posting messages to a public mailing list about an open source tool such as SpamBayes constituted private communication with the tech support group of another company. I presume you subscribed to the list or at least visited the subscription page. Right there is a link to the mailing list archives. Anyone can read them. The fact that you found your messages via Google is not surprising and demonstrates how the system is supposed to work. If Google found them then Yahoo!, MSN and other search engines almost certainly found them as well. In addition, email mirroring services will have them: Gmane, Google Groups, etc. Finally, I suspect you can find your messages via Alexa's Wayback Machine. The responsibility for using the technology appropriately rests with you. The horse left the barn months ago. Now you want someone else to close the door. That's not going to help. -- Skip Montanaro - skip at pobox.com - http://www.webfast.com/~skip/ From jsp at PKC.com Wed Jul 25 19:25:43 2007 From: jsp at PKC.com (Jesse Pelton) Date: Wed, 25 Jul 2007 13:25:43 -0400 Subject: [Spambayes] Breach of Privacy In-Reply-To: <001701c7ced3$b122aed0$13680c70$@com> References: <001701c7ced3$b122aed0$13680c70$@com> Message-ID: <16E2027582CDB74180896CDB4B8CC1F905BD8E8A@PKCVT01.pkc.com> Please see http://mail.python.org/mailman/listinfo/spambayes , the sign-up page for the SpamBayes discussion list. Among other things, it says the following: "Please note that this is a public mailing list: all messages sent to this list are visible to the public, and are publicly archived." Some archives are beyond the control of the people who run the list. (For instance, a quick search turned up copies on readlist dot com.) Posting anything to a public list is conceptually equivalent to broadcasting it on a radio frequency that anyone can choose to tune in to - forever after. You might also want to read a recent message thread on the same topic: http://mail.python.org/pipermail/spambayes/2007-July/020952.html . (Maybe it's time for someone to write up a FAQ entry about this; it seems to be coming up with increasing frequency.) In other words, a) you put this information out there, despite the warning that it would be public, and no disclaimer can change that, and b) it probably is not possible to retract it. Furthermore, your previous message compounded your error by adding links to the offending messages. Also note that sending sensitive information in an unencrypted e-mail message is an invitation for interested snoopers to tune in while the message is routed from its source to its destination. You appear to be using Outlook; I'd strongly encourage you and any technical staff you have to search for "encrypt messages" in the Outlook help system, read the results carefully, and act on what you learn. While Outlook's help system refers you to providers of digital IDs (aka certificates) that charge a fee, there are other services that provide certificates free of charge. I use Thawte (www.thawte.com ) myself. ________________________________ From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Thomas Mark Sent: Wednesday, July 25, 2007 11:52 AM To: spambayes at python.org Subject: [Spambayes] Breach of Privacy Dear Spambayes, I sent an e-mail earlier about some e-mails from my company to your company regarding tech support. These e-mails found on google.com contained confidential information and had disclaimers as such in the e-mails. I have since found several of these e-mails easily searchable on google.com and free for the world to see. This puts my company at financial jeopardy as we are held liable for content that was supposed to be kept in private and via your servers with the rest of the world. We consider this an egregious breach of security and privacy between my company and Spambayes. I would appreciate a full scan of your database for any and all reference to IMERGE Consulting and have it cleared from public record. This breach could cause serious trouble for my company and we are placing utmost concern with this issue. An Immediate response would be very appreciated. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070725/9841eb25/attachment.html From skip at pobox.com Wed Jul 25 19:39:18 2007 From: skip at pobox.com (skip at pobox.com) Date: Wed, 25 Jul 2007 12:39:18 -0500 Subject: [Spambayes] Breach of Privacy In-Reply-To: <002001c7cee0$3f1dc420$bd594c60$@com> References: <001701c7ced3$b122aed0$13680c70$@com> <18087.34244.26335.23448@montanaro.dyndns.org> <002001c7cee0$3f1dc420$bd594c60$@com> Message-ID: <18087.35526.923436.153314@montanaro.dyndns.org> Thomas> I have talked with our IT department here and they now recognize Thomas> and confess to the fact that they have let slip certain Thomas> confidential documents without consent. I was under the notion Thomas> and I apologize that they had not done this. I know that it is Thomas> too late to take it back but I was wondering if there would be Thomas> any way to remove these messages from the public server. I passed along your first note (with the URLs) to the python.org postmaster. We'll see what they can do. Skip From Rich at RBarger.com Wed Jul 25 19:26:39 2007 From: Rich at RBarger.com (Richard B Barger ABC APR) Date: Wed, 25 Jul 2007 12:26:39 -0500 Subject: [Spambayes] Breach of Privacy References: <001701c7ced3$b122aed0$13680c70$@com> Message-ID: <46A787CF.3459A3E6@RBarger.com> An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070725/ff55d009/attachment.htm From dave at boost-consulting.com Wed Jul 25 21:13:25 2007 From: dave at boost-consulting.com (David Abrahams) Date: Wed, 25 Jul 2007 15:13:25 -0400 Subject: [Spambayes] Permission error trying to persist hamie.fs state (was: some SpamBayes errors from my procmail log) References: <878x971050.fsf@grogan.peloton> Message-ID: <87tzrsuwiy.fsf@grogan.peloton> An embedded and charset-unspecified text was scrubbed... Name: .spambayesrc Url: http://mail.python.org/pipermail/spambayes/attachments/20070725/fba6d199/attachment.asc From Ernst.Schmid at swisslife.ch Thu Jul 26 07:58:03 2007 From: Ernst.Schmid at swisslife.ch (Ernst.Schmid at swisslife.ch) Date: Thu, 26 Jul 2007 07:58:03 +0200 Subject: [Spambayes] Compiling sb_filter on Win32 Message-ID: Hi Manoj, you request for help is about a half year back. I had the same problem. I just added the missing Python *.pyc in the prog.zip Library. All files included in the directory /email I had to copy the email directory directly under c:. After adding all missing files my program worked just fine. Maybe you fixed your Problem to and you have a different solution for this problem I would be glad to know it best regards Ernst Schmid -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070726/d848a63c/attachment.html From amedee at amedee.be Thu Jul 26 08:56:00 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Thu, 26 Jul 2007 08:56:00 +0200 (CEST) Subject: [Spambayes] Sensitive E-mail between My company and You showing up online!!! In-Reply-To: <001b01c7ced1$5379dad0$fa6d9070$@net> References: <001b01c7ced1$5379dad0$fa6d9070$@net> Message-ID: <38183.193.121.250.194.1185432960.squirrel@amedee.be> On Wed, July 25, 2007 17:34, Thomas Mark wrote: > Dear Spambayes, > > Recently I sent copies of e-mails to you because we were having trouble > with > our configuration and certain spam still getting through. I thought that > these e-mails were between your company SpamBayes is not a company but an Open Source project by some volonteers. Open means open development, but also open support channels. > and ours but through google > searches > I have found the exact copies of the e-mails that I sent you. These > e-mails > contain sensitive company information and I would like it if you could > please remove them immediately and confirm to me that they were removed. I don't understand. The mailing list info clearly states: This mailing list discusses a Python implementation of a Bayesian classifier, with anti-spam aspirations. It is the discussion list adjunct to the SpamBayes project on SourceForge. Please note that this is a public mailing list: all messages sent to this list are visible to the public, and are publicly archived. To see the collection of prior postings to the list, visit the SpamBayes Archives. http://mail.python.org/mailman/listinfo/spambayes You should have read that. It's like an instruction manual. You do read instruction manuals, don't you? > I would greatly appreciate it if each one of these messages could be > removed > ASAP. > > > > Thank you > very much and I would like a confirmation if possible when this has been > accomplished. Mission: impossible. To the SpamBayes devs: could you add this as a FAQ? -- Amedee Yet Another Happy SpamBayes User (YAHSU) From amedee at amedee.be Thu Jul 26 08:58:12 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Thu, 26 Jul 2007 08:58:12 +0200 (CEST) Subject: [Spambayes] Breach of Privacy In-Reply-To: <001701c7ced3$b122aed0$13680c70$@com> References: <001701c7ced3$b122aed0$13680c70$@com> Message-ID: <39976.193.121.250.194.1185433092.squirrel@amedee.be> On Wed, July 25, 2007 17:51, Thomas Mark wrote: > Dear Spambayes, > > I sent an e-mail earlier about some e-mails from my company to your > company > regarding tech support. These e-mails found on google.com contained > confidential information and had disclaimers as such in the e-mails. I > have > since found several of these e-mails easily searchable on google.com and > free for the world to see. This puts my company at financial jeopardy as > we > are held liable for content that was supposed to be kept in private and > via > your servers with the rest of the world. We consider this an egregious > breach of security and privacy between my company and Spambayes. I would > appreciate a full scan of your database for any and all reference to > IMERGE > Consulting and have it cleared from public record. This breach could cause > serious trouble for my company and we are placing utmost concern with this > issue. An Immediate response would be very appreciated. LOL!!! This is getting funnier. -- Amedee (YAHSU) From chungshan.machworks.ltd at hotmail.com Thu Jul 26 11:45:44 2007 From: chungshan.machworks.ltd at hotmail.com (CHUNG SHAN MACH.WORKS) Date: Thu, 26 Jul 2007 11:45:44 +0200 (CEST) Subject: [Spambayes] Be Our Agent Message-ID: <20070726094544.5A86F1E97AE@mail.awebs.at> CHUNG SHAN MACHINERY WORKS No.49-16, CHI TZU TOU, KUAN SHIN VILLAGE, SHUI SHANG HSIANG, CHIA YI HSIEN 608, TAIWAN R.O.C. Email: chungshan.machworks.ltd at hotmail.com Website: www.chung-shan.com.tw/eng/index.htm Tel :886-5-236-2685, Fax:886-2-6602-1090 Dear Sir/Ma, Since the beginning of our company's establishment, Chung Shan Machinery Works Co., Ltd. has been an industry leader with its wide range of superior quality form-fill-Seal Packaging Machinery. We have put forward a variety of innovative ideas for the advancement of the food industry and have striven to bring our ideas to come true. We have reached big sales volume of Packaging Machinery products in the United Kingdom and European market and now trying to penetrate the more into the UK/USA and Canada. Quiet soon we shall open representative offices or authorized sales centers in the United State of America/Canada and therefore we are currently looking for people who will assist us in establishing a new distribution network here and there. The fact is that despite that United State of America/Canada market is new for us we already have regular clients also speaks for itself. WHAT YOU NEED TO DO FOR US: The international money transfer tax for legal entities (companies) in Taiwan is 25%, whereas for the individual it is only 7%.There is no sense for us to work this way, while tax for international money transfer made by a private individual is 7%. That's why we need you! We need an agent to receive payment for our Packaging Machinery products inform of bank wire transfers and to resend the money to us via our bank account in Taiwan while the tax shall be 7% instead of 25% which will absolutely favour our company. JOB DESCRIPTION 1. Receive payment from Clients either by check or wire transfer 2. Cash Payments at your Bank 3. Deduct 10% which will be your commission on each payment processed. 4. Forward balance after deduction of 10% commission to offices which shall be provided by us as soon as the fund becomes available. HOW MUCH WILL YOU EARN: 10% from each operation! For instance: you receive $5000 via checks or wire transfer on our behalf. You will cash the money and keep $500 (10% from $5000) for yourself! At the beginning your commission will equal 10%, though later it will increase up to 12%! ADVANTAGES: You do not have to go out as you will work as an independent contractor right from your home office. Your job is absolutely legal. You can earn up to $3000-$4000 monthly depending on time will spend on this job. You do not need any capital to start. You can do the Work easily without leaving or affecting your present Job. Employee who make more efforts and work hard has strong possibility of becoming manager. Anyway our employee never leave us due to our excellent working condition. MAIN REQUIREMENTS: 18 years or older legally capable responsible ready to work 3-4 hours per week.with PC knowledge e-mail and internet experience (minimal). And please be mindful that everything is absolutely legal. Kindly contact us on the above address and you can also view our website to enable you know more about our company. Best Regards, KUAN SHANG(MR) From j.benlin.lee at gmail.com Fri Jul 27 00:55:30 2007 From: j.benlin.lee at gmail.com (John Lee) Date: Thu, 26 Jul 2007 18:55:30 -0400 Subject: [Spambayes] sb_filter.py startup time Message-ID: <1c24ea390707261555o2d692eaboca6211ec38700f84@mail.gmail.com> Hello, I'm having some trouble with sb_filter.py startup performance that I'm hoping someone may be able to help with. Invocation of sb_filter.py takes several seconds and spikes CPU usage. It seems that importing the Spambayes libraries takes a lot of time: $ time python -c "from spambayes import hammie, Options, mboxutils, storage" real 0m16.708s user 0m0.456s sys 0m9.005s Importing other packages doesn't seem to produce this problem. For example: $ time python -c "from os import *" real 0m2.760s user 0m0.030s sys 0m1.531s I'm not a python programmer, so I can only speculate that this is not normal behavior. Can anyone shed some light on this? 16 second startup times are inconvenient when fetching a lot of mail. I've had this problem with both Spambayes 1.0.4 as well as 1.1a4. I'm running Python 2.5.1, compiled from source, on MacOS X 10.4.10. I'm currently using the ZODB persistent store but have seen this problem with pickles and DBM stores as well. The database is currently at 3MB. Thanks for your help. Cheers, John From skip at pobox.com Fri Jul 27 03:16:57 2007 From: skip at pobox.com (skip at pobox.com) Date: Thu, 26 Jul 2007 20:16:57 -0500 Subject: [Spambayes] sb_filter.py startup time In-Reply-To: <1c24ea390707261555o2d692eaboca6211ec38700f84@mail.gmail.com> References: <1c24ea390707261555o2d692eaboca6211ec38700f84@mail.gmail.com> Message-ID: <18089.18313.681034.515250@montanaro.dyndns.org> John> I'm having some trouble with sb_filter.py startup performance that John> I'm hoping someone may be able to help with. Invocation of John> sb_filter.py takes several seconds and spikes CPU usage. Try switching to sb_bnfilter.py. On first invocation it spins of a server in the background. Successive invocations chat with that server. The server quietly exits after several seconds without an incoming connection. Skip From skip at pobox.com Fri Jul 27 12:34:20 2007 From: skip at pobox.com (skip at pobox.com) Date: Fri, 27 Jul 2007 05:34:20 -0500 Subject: [Spambayes] Breach of Privacy In-Reply-To: <001701c7ced3$b122aed0$13680c70$@com> References: <001701c7ced3$b122aed0$13680c70$@com> Message-ID: <18089.51756.731594.355813@montanaro.dyndns.org> Thomas, The Python postmaster manually deleted your emails from the raw and HTML versions of the mailing list archives. As I and others have noted however, the information they contained is still out there in a number of different forms for anyone interested enough to look. -- Skip Montanaro - skip at pobox.com - http://www.webfast.com/~skip/ From newsgroups at Lastwebpage.de Fri Jul 20 19:04:24 2007 From: newsgroups at Lastwebpage.de (Peter Flindt) Date: Fri, 20 Jul 2007 19:04:24 +0200 Subject: [Spambayes] Office 2007 Compatibility References: Message-ID: Jesse Bowler wrote at 20.07.2007 : > Hello, I am Jesse Bowler and I was trying to install spambayes on my new > computer. I have always used it on my other machines in the past. I have > upgraded my office version from office 2003 Professional, to the newest > version of Office 2007. But every time I went to install spambayes, it > would crash Microsoft Outlook 2007. The official release version 1.0.4. works here without any problems, if you use Vista read the posting "Outlook 2007" below. Only the beta versions from SpamBayes make some troubles here. Peter From amedee at amedee.be Fri Jul 27 12:49:42 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Fri, 27 Jul 2007 12:49:42 +0200 (CEST) Subject: [Spambayes] Breach of Privacy In-Reply-To: <18089.51756.731594.355813@montanaro.dyndns.org> References: <001701c7ced3$b122aed0$13680c70$@com> <18089.51756.731594.355813@montanaro.dyndns.org> Message-ID: <6854.193.121.250.194.1185533382.squirrel@amedee.be> On Fri, July 27, 2007 12:34, skip at pobox.com wrote: > Thomas, > > The Python postmaster manually deleted your emails from the raw and HTML > versions of the mailing list archives. As I and others have noted > however, > the information they contained is still out there in a number of different > forms for anyone interested enough to look. I still have his emails somewhere in my mailbox, and I'm not going to delete them! -- Amedee Van Gasse Disclaimer: By sending an email to ANY of my addresses you are agreeing that: 1. I am by definition, "the intended recipient" 2. All information in the email is mine to do with as I see fit and make such financial profit, political mileage, or good joke as it lends itself to. In particular, I may quote it on usenet. 3. I may take the contents as representing the views of your company. 4. This overrides any disclaimer or statement of confidentiality that may be included on your message. http://www.goldmark.org/jeff/stupid-disclaimers/ From Tmark86 at ameritech.net Fri Jul 27 19:01:07 2007 From: Tmark86 at ameritech.net (Thomas Mark) Date: Fri, 27 Jul 2007 12:01:07 -0500 Subject: [Spambayes] Thank you! In-Reply-To: <18089.51756.731594.355813@montanaro.dyndns.org> References: <001701c7ced3$b122aed0$13680c70$@com> <18089.51756.731594.355813@montanaro.dyndns.org> Message-ID: <000001c7d06f$bd43e880$37cbb980$@net> Skip, I would just like to thank you and everyone at Spambayes. Although the problem was my own, I appreciate your understanding and helpfulness in solving the problem. As a token of my appreciation my company will be making a nice donation to the Python Software Foundation. I thank you and everyone again. -----Original Message----- From: skip at pobox.com [mailto:skip at pobox.com] Sent: Friday, July 27, 2007 5:34 AM To: Thomas Mark Cc: spambayes at python.org Subject: Re: [Spambayes] Breach of Privacy Thomas, The Python postmaster manually deleted your emails from the raw and HTML versions of the mailing list archives. As I and others have noted however, the information they contained is still out there in a number of different forms for anyone interested enough to look. -- Skip Montanaro - skip at pobox.com - http://www.webfast.com/~skip/ From bunkie at stevensleinweber.com Fri Jul 27 22:52:37 2007 From: bunkie at stevensleinweber.com (Bunkie McBride) Date: Fri, 27 Jul 2007 13:52:37 -0700 Subject: [Spambayes] Windows Reported an Error --- Message-ID: <20070727205252.A998D39446@StevensLeinweber.stevensleinweber.com> About a week ago, upon closing, Windows (XP Professional) reported that an add-in program had caused a serious error in Outlook and wanted to know if I wanted to disable this feature. I confirmed it be disabled but the next time I closed windows I rec'd the same message again. I again confirmed to disable. SpamBayes is currently not functioning. Please advise what I should do. Thanks, Bunkie -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070727/beebbb77/attachment.htm From spambayes at whateley.com Sat Jul 28 00:50:04 2007 From: spambayes at whateley.com (Brendon Whateley) Date: Fri, 27 Jul 2007 15:50:04 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? Message-ID: <46AA769C.3030009@whateley.com> Hi all, I've just started using spambayes again after a while away from it. Now, 3 days in, I notice that I've trained on far more spam than ham. (Total emails trained: Spam: *432* Ham: *64) I seem to remember that this was previously my experience in the past. My question is; has anybody really tested the assertion that leads to the message: "**Warning: you have much more spam than ham - SpamBayes works best with approximately even numbers of ham and spam."?* * For the record, my statistics so far are: *SpamBayes has processed 5411 messages - 1279 (24%) good, 3189 (59%) spam and 943 (17%) unsure. Thanks, Brendon. From StandnOnPromises at aol.com Sat Jul 28 05:35:27 2007 From: StandnOnPromises at aol.com (StandnOnPromises at aol.com) Date: Fri, 27 Jul 2007 23:35:27 EDT Subject: [Spambayes] Error-Guard Support Request Message-ID: I PURCHASED ERRORGUARD LAST YEAR AND I STILL HAVE MY ACTIVATION CODE BUT I CANNOT FIND OUT HOW TO GET BACK TO THE SITE TO PUT IT BACK IN I HAD TO WIPE OUT AND DO RESTORE DISC ON MU COMPUTER SO NOW I NEED TO BE ABLE TO PUT MY ERRORGUARD BACK ON AND EVERYTIME I TYPE IN ERRORGUARD.COM, ERROR PAGE NOT FOUND? NEED TO GET BACK TO THE ACTIVATION PAGE THANK YOU MELVADEAN NELSON ************************************** Get a sneak peek of the all-new AOL at http://discover.aol.com/memed/aolcom30tour -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070727/3738d76b/attachment.html From skip at pobox.com Sat Jul 28 06:12:14 2007 From: skip at pobox.com (skip at pobox.com) Date: Fri, 27 Jul 2007 23:12:14 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <46AA769C.3030009@whateley.com> References: <46AA769C.3030009@whateley.com> Message-ID: <18090.49694.414574.721564@montanaro.dyndns.org> Brendon> I've just started using spambayes again after a while away from Brendon> it. Now, 3 days in, I notice that I've trained on far more Brendon> spam than ham. (Total emails trained: Spam: *432* Ham: *64) I Brendon> seem to remember that this was previously my experience in the Brendon> past. Are you training on every message you receive or just the mistakes? Most people generally only train on the mistakes and unsures. Your ratio is about 7:1. That's a bit high. I'm maintaining about a 1:1 ratio, currently have about 120 each of ham and spam dating back to March (4+ months). (I cheat though. My email comes through Gmail these days, so I get the benefits - and shortcomings - of their system.) Brendon> My question is; has anybody really tested the assertion that Brendon> leads to the message: "**Warning: you have much more spam than Brendon> ham - SpamBayes works best with approximately even numbers of Brendon> ham and spam."?* Yes, I believe it was tested pretty thoroughly back in the day. Skip From spambayes at whateley.com Sat Jul 28 06:57:30 2007 From: spambayes at whateley.com (Brendon Whateley) Date: Fri, 27 Jul 2007 21:57:30 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <18090.49694.414574.721564@montanaro.dyndns.org> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> Message-ID: <46AACCBA.6070004@whateley.com> skip at pobox.com wrote: > Brendon> I've just started using spambayes again after a while away from > Brendon> it. Now, 3 days in, I notice that I've trained on far more > Brendon> spam than ham. (Total emails trained: Spam: *432* Ham: *64) I > Brendon> seem to remember that this was previously my experience in the > Brendon> past. > > Are you training on every message you receive or just the mistakes? Most > I just train on errors and some unsure. At the moment, I'm getting almost no ham in unsure. > people generally only train on the mistakes and unsures. Your ratio is > about 7:1. That's a bit high. I'm maintaining about a 1:1 ratio, currently > That is high relative to the conventional wisdom, but I'm questioning the correctness of that wisdom. > have about 120 each of ham and spam dating back to March (4+ months). (I > Perhaps I receive much more spam than you do! :) > Yes, I believe it was tested pretty thoroughly back in the day. > I couldn't find any reference to such testing and don't remember any from back when Tony and I were writing Spambayes the paper for CEAS. If anybody knows of some research, I'd love to see it. Perhaps its time to re-evaluate that statement? Brendon. From mhammond at skippinet.com.au Sat Jul 28 08:31:11 2007 From: mhammond at skippinet.com.au (Mark Hammond) Date: Sat, 28 Jul 2007 16:31:11 +1000 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <46AACCBA.6070004@whateley.com> Message-ID: <11a601c7d0e0$e435a0c0$090a0a0a@enfoldsystems.local> > That is high relative to the conventional wisdom, but I'm questioning > the correctness of that wisdom. Check out this thread, which should give you a reasonable idea: http://mail.python.org/pipermail/spambayes-dev/2003-November/001578.html > Perhaps its time to re-evaluate that statement? Google also shows anecdotal reports of poor results after an imbalance as low as 2:1, so I don't think it would be responsible to re-evaluate that statement until clear evidence was presented to the contrary. Cheers, Mark From mike at ingenious.co.nz Sat Jul 28 23:23:01 2007 From: mike at ingenious.co.nz (Mike Morrin) Date: Sat, 28 Jul 2007 22:23:01 +0100 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <11a601c7d0e0$e435a0c0$090a0a0a@enfoldsystems.local> References: <11a601c7d0e0$e435a0c0$090a0a0a@enfoldsystems.local> Message-ID: <46ABB3B5.2090100@ingenious.co.nz> An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070728/91ff3d17/attachment.htm From spambayes at whateley.com Sun Jul 29 00:08:06 2007 From: spambayes at whateley.com (Brendon Whateley) Date: Sat, 28 Jul 2007 15:08:06 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <11a601c7d0e0$e435a0c0$090a0a0a@enfoldsystems.local> References: <11a601c7d0e0$e435a0c0$090a0a0a@enfoldsystems.local> Message-ID: <46ABBE46.7070008@whateley.com> Mark Hammond wrote: >> That is high relative to the conventional wisdom, but I'm questioning >> the correctness of that wisdom. >> > > Check out this thread, which should give you a reasonable idea: > > http://mail.python.org/pipermail/spambayes-dev/2003-November/001578.html > That thread was interesting, but still runs under the assumption that balanced training is the ideal. > >> Perhaps its time to re-evaluate that statement? >> > > Google also shows anecdotal reports of poor results after an imbalance as > low as 2:1, so I don't think it would be responsible to re-evaluate that > "responsible"? I'm not sure what you mean. > statement until clear evidence was presented to the contrary. > I assumed that running a test to evaluate the effects of imbalance would be the way to generate or refute such evidence? When I get back from Hawaii, I think I'll dust off the old test corpus and try some tests. If anybody else has some test results, I'd be very interested in seeing them. My current thought is that getting a (very) large mount of spam with very few clues results in each email results in the imbalance. I've just checked some of todays spam and some had as few as 31 clues. With so few clues, it is relatively easy for a spam message to end up with an unsure or even ham classification while the most ham is being correctly classified. The alternative to an imbalanced training set is to find an easy way to train on extra ham, but only the ham that still has some classification value to add. Brendon. From amedee at amedee.be Sun Jul 29 00:34:42 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Sun, 29 Jul 2007 00:34:42 +0200 (CEST) Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <46ABB3B5.2090100@ingenious.co.nz> References: <11a601c7d0e0$e435a0c0$090a0a0a@enfoldsystems.local> <46ABB3B5.2090100@ingenious.co.nz> Message-ID: <3004.213.118.146.15.1185662082.squirrel@amedee.be> On Sat, July 28, 2007 23:23, Mike Morrin wrote: > > > > > > > > Mark Hammond wrote: >
cite="mid:11a601c7d0e0$e435a0c0$090a0a0a at enfoldsystems.local" > type="cite"> >
> 
That is high relative to the conventional wisdom, but I'm
> questioning
> the correctness of that wisdom.
>
>
> 

> Check out this thread, which should give you a reasonable idea:
>
>  href="http://mail.python.org/pipermail/spambayes-dev/2003-November/001578.html">http://mail.python.org/pipermail/spambayes-dev/2003-November/001578.html
>
>
>
> 
Perhaps its time to re-evaluate that statement?
>
>
> 

> Google also shows anecdotal reports of poor results after an imbalance as
> low as 2:1, so I don't think it would be responsible to re-evaluate that
> statement until clear evidence was presented to the contrary.
>
>
> I don't get a lot of ham, and currently have 55 ham and 580 spam in my > Spambayes database.  Despite this, it seems to be working > admirably.  > It is however very sensitive to just one spam mistakenly put into the > ham base, which then completely upsets the filtering.
>
> So if the perceived wisdom is that I need to balance the ratios, what > should I do?  send myself ham? or not use spam from my unsure folder > for training? or get more friends???
Get more friends. Definitely! ;-) (and don't use html to write emails) -- Amedee From wendy at acknowledgeit.co.uk Sun Jul 29 01:39:01 2007 From: wendy at acknowledgeit.co.uk (Wendy Baird) Date: Sun, 29 Jul 2007 00:39:01 +0100 Subject: [Spambayes] Missing toolbars Outlook 2007 Message-ID: <000001c7d170$7a7e7a40$6f7b6ec0$@co.uk> The installation completed successfully but no toolbars appear. The logfile only contains one line : Unregistered: SpamBayes.OutlookAddin. SpamBayes appears in the Trust Center but is described as Inactive. Does anyone have any suggestions how I might activate it? Thanks Wendy -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070729/2f303f37/attachment.htm From mhammond at skippinet.com.au Sun Jul 29 03:26:52 2007 From: mhammond at skippinet.com.au (Mark Hammond) Date: Sun, 29 Jul 2007 11:26:52 +1000 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <46ABBE46.7070008@whateley.com> Message-ID: <003901c7d17f$8bcd2e40$1c0a0a0a@enfoldsystems.local> > Mark Hammond wrote: > >> That is high relative to the conventional wisdom, but I'm > questioning > >> the correctness of that wisdom. > >> > > > > Check out this thread, which should give you a reasonable idea: > > > > > http://mail.python.org/pipermail/spambayes-dev/2003-November/0 01578.html > That thread was interesting, but still runs under the assumption that > balanced training is the ideal. I read that thread as *demonstrating* why unbalanced training will skew your results. It makes no assumptions at all, but simply considers the facts about how spambayes works and the math behind it. The assumptions you refer to are a direct result of the facts presented there. Do you disagree with the analysis of the math in that thread? If you don't disagree, then I completely miss your point. >> Google also shows anecdotal reports of poor results after an imbalance as >> low as 2:1, so I don't think it would be responsible to re-evaluate that > "responsible"? I'm not sure what you mean. responsible: worthy of or requiring trust. In my opinion, it would be irresponsible to our users, who generally trust the spambayes developers, for us to give out information that current wisdom says to be incorrect, especially when backed up by a solid theoretical understanding of why that wisdom exists. It would be irresponsible for us to change our current wisdom based on anecdotes of a single individual, especially when opposite anecdotes can be easily found. > I assumed that running a test to evaluate the effects of imbalance would > be the way to generate or refute such evidence? One person running a test is unlikely to cut it. If you design a test, you may have luck getting others to run it against their email, in which case the results will start to get interesting as the number of people increase. > When I get back from Hawaii, I think I'll dust off the old test corpus and try > some tests. If anybody else has some test results, I'd be very interested in > seeing them. Google is your friend here - you can find many discussions about the effects of imbalances, and plenty of discussions about why a single test from a single user isn't a useful indicator of anything. Searching for anything Tim Peters has to say would be the most productive thing to do :) > My current thought is that getting a (very) large mount of spam with > very few clues results in each email results in the imbalance. I've > just checked some of todays spam and some had as few as 31 clues. With > so few clues, it is relatively easy for a spam message to end up with an > unsure or even ham classification while the most ham is being correctly > classified. The alternative to an imbalanced training set is to find an > easy way to train on extra ham, but only the ham that still has some > classification value to add. I'm glad that spambayes appears to work well for you with a significant imbalance, but I think we've already pointed out that there is solid reasoning behind our position. Cheers, Mark From tim.peters at gmail.com Sun Jul 29 05:21:18 2007 From: tim.peters at gmail.com (Tim Peters) Date: Sat, 28 Jul 2007 23:21:18 -0400 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <46AA769C.3030009@whateley.com> References: <46AA769C.3030009@whateley.com> Message-ID: <1f7befae0707282021o193e0e29i84b0c15e940b0749@mail.gmail.com> [Brendon Whateley] > I've just started using spambayes again after a while away from it. > Now, 3 days in, I notice that I've trained on far more spam than ham. > (Total emails trained: Spam: *432* Ham: *64) I seem to remember that > this was previously my experience in the past. > > My question is; has anybody really tested the assertion that leads to > the message: "**Warning: you have much more spam than ham - SpamBayes > works best with approximately even numbers of ham and spam."?* Yes, but by the time you and Tony wrote your paper, serious multi-corpus testing had long since essentially stopped. The results with large imbalances were so dramatically worse that I introduced the infamous "experimental ham spam imbalance adjustment" switch, which tried to stop "the math" from drawing absurdly confident conclusions from wildly unbalanced data (see the thread Mark pointed out). The results of that were a mixed bag, helping some people a little but hurting others more, so we dropped it. As I'm sure one of the text files in the project says, /all/ decisions "should be" reevaluated periodically. Alas, a one-corpus test is essentially useless, and it was hard even some years ago to arrange for multi-corpus tests. When the original testing was done, almost all spam was text-heavy, meaning lots of tokens were generated. The paucity of tokens generated for more recent image-based spam, and spam hiding in attachments, makes SB's basic /approach/ less useful for that kind of spam. No real idea how imbalance affects scoring spam of that kind. The only thing I've done in response to it is lower my "spam threshold", down to 70 now, with ham at 5. My unsure rate is about 6%, most of which are spam. Every now and again I add the 10 most recent ham to my ham training data, but even so I've got about a 3:1 spam:ham training ratio. I do expect my stats would improve if I added more ham (I'm one of the ones the old imbalance option helped), but I spend so little time looking at unsures it's just not worth even tiny efforts to improve it. From spambayes at whateley.com Sun Jul 29 07:55:41 2007 From: spambayes at whateley.com (Brendon Whateley) Date: Sat, 28 Jul 2007 22:55:41 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <003901c7d17f$8bcd2e40$1c0a0a0a@enfoldsystems.local> References: <003901c7d17f$8bcd2e40$1c0a0a0a@enfoldsystems.local> Message-ID: <46AC2BDD.2090109@whateley.com> Mark Hammond wrote: >> That thread was interesting, but still runs under the assumption that >> balanced training is the ideal. >> > > I read that thread as *demonstrating* why unbalanced training will skew your > results. It makes no assumptions at all, but simply considers the facts > We are suffering a semantic disagreement here. That thread explains how an imbalance influences token scores, but doesn't explain one way or another if that harms classification in the wild. Presumably at some point it will cause harm, but just when is unclear. > about how spambayes works and the math behind it. The assumptions you refer > to are a direct result of the facts presented there. > > Do you disagree with the analysis of the math in that thread? If you don't > disagree, then I completely miss your point. > > >>> Google also shows anecdotal reports of poor results after an imbalance as >>> low as 2:1, so I don't think it would be responsible to re-evaluate that >>> Anecdotal, as you also point out is not the same as proof. >> "responsible"? I'm not sure what you mean. >> > > responsible: worthy of or requiring trust. > > In my opinion, it would be irresponsible to our users, who generally trust > I was assuming that you didn't mean that, since in no way was I suggesting changing anything at all. At least not until the facts behind the statement had been reevaluated and proven to be incorrect. > the spambayes developers, for us to give out information that current wisdom > says to be incorrect, especially when backed up by a solid theoretical > understanding of why that wisdom exists. It would be irresponsible for us > to change our current wisdom based on anecdotes of a single individual, > especially when opposite anecdotes can be easily found. > I really don't know what this was in response to. I ask a question and you are replying as if I am demanding change. That has never been the spambayes way. > >> I assumed that running a test to evaluate the effects of imbalance would >> be the way to generate or refute such evidence? >> > > One person running a test is unlikely to cut it. If you design a test, you > may have luck getting others to run it against their email, in which case > the results will start to get interesting as the number of people increase. > Again, I never claimed that one person would "cut anything". However, if one person doesn't start carry the effort forward, it will never get reevaluated. If my efforts at building a test lead to a result confirming the status quo, then nothing more need be said. At least until some other wise guy comes along and challenges it :) Since the nature of Spam changes over time, the results of these challenges may also change? > >> When I get back from Hawaii, I think I'll dust off the old test corpus and >> > try > >> some tests. If anybody else has some test results, I'd be very interested >> > in > >> seeing them. >> > > Google is your friend here - you can find many discussions about the effects > of imbalances, and plenty of discussions about why a single test from a > single user isn't a useful indicator of anything. Searching for anything > Tim Peters has to say would be the most productive thing to do :) > That is a good idea, since gathering info from some of the core folks would seem to save time in developing an effective test. >> My current thought is that getting a (very) large mount of spam with >> very few clues results in each email results in the imbalance. I've >> just checked some of todays spam and some had as few as 31 clues. With >> so few clues, it is relatively easy for a spam message to end up with an >> unsure or even ham classification while the most ham is being correctly >> classified. The alternative to an imbalanced training set is to find an >> easy way to train on extra ham, but only the ham that still has some >> classification value to add. >> > > I'm glad that spambayes appears to work well for you with a significant > imbalance, but I think we've already pointed out that there is solid > reasoning behind our position. > As a long time spambayes user, promoter and sometimes contributer, I've yet to find a user for whom spambayes does not work very well! I understand the theory but would like to understand the real world implications, especially given the anecdotal evidence that imbalance doesn't always harm performance. Even Tim Peters has a 3:1 ratio :) Anyway, I'm not trying to rock the boat, start a fight or anything else. I've now got to go and pack, Brendon. From spambayes at whateley.com Sun Jul 29 08:06:54 2007 From: spambayes at whateley.com (Brendon Whateley) Date: Sat, 28 Jul 2007 23:06:54 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <1f7befae0707282021o193e0e29i84b0c15e940b0749@mail.gmail.com> References: <46AA769C.3030009@whateley.com> <1f7befae0707282021o193e0e29i84b0c15e940b0749@mail.gmail.com> Message-ID: <46AC2E7E.4050207@whateley.com> Tim Peters wrote: > [Brendon Whateley] > >> I've just started using spambayes again after a while away from it. >> Now, 3 days in, I notice that I've trained on far more spam than ham. >> (Total emails trained: Spam: *432* Ham: *64) I seem to remember that >> this was previously my experience in the past. >> >> My question is; has anybody really tested the assertion that leads to >> the message: "**Warning: you have much more spam than ham - SpamBayes >> works best with approximately even numbers of ham and spam."?* >> > > Yes, but by the time you and Tony wrote your paper, serious > multi-corpus testing had long since essentially stopped. The results > with large imbalances were so dramatically worse that I introduced the > infamous "experimental ham spam imbalance adjustment" switch, which > tried to stop "the math" from drawing absurdly confident conclusions > from wildly unbalanced data (see the thread Mark pointed out). The > results of that were a mixed bag, helping some people a little but > hurting others more, so we dropped it. > Yes I remember that. I can also guess why serious multi-corpus testing stopped... as I recall, the pain of putting them together is not for the faint of heart :) > As I'm sure one of the text files in the project says, /all/ decisions > "should be" reevaluated periodically. Alas, a one-corpus test is > essentially useless, and it was hard even some years ago to arrange > for multi-corpus tests. > In the worst case, I can satisfy my own curiosity and possibly provide some insight. I may be able to gather several different corpora for some testing. How many separate corpora would you consider a valid test? > When the original testing was done, almost all spam was text-heavy, > meaning lots of tokens were generated. The paucity of tokens > generated for more recent image-based spam, and spam hiding in > attachments, makes SB's basic /approach/ less useful for that kind of > spam. No real idea how imbalance affects scoring spam of that kind. > That is the thinking that lead to my question of the imbalance effect. Perhaps some method of generating tokens from images would restore order to our world. > The only thing I've done in response to it is lower my "spam > threshold", down to 70 now, with ham at 5. My unsure rate is about > 6%, most of which are spam. Every now and again I add the 10 most > recent ham to my ham training data, but even so I've got about a 3:1 > spam:ham training ratio. I do expect my stats would improve if I > added more ham (I'm one of the ones the old imbalance option helped), > but I spend so little time looking at unsures it's just not worth even > tiny efforts to improve it. At the very least I can test your approach vs what I've been doing which is to just let the imbalance grow until some ham gets pulled into unsure. At that point I add unsure ham and continue on. At the very least, that answer may be of some help to those who find their training leads to large imbalances. When I get back, I'll start playing with this and see if anything useful develops. Brendon. From csjrswofford at bellsouth.net Sun Jul 29 16:19:59 2007 From: csjrswofford at bellsouth.net (Carl) Date: Sun, 29 Jul 2007 09:19:59 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <46AC2BDD.2090109@whateley.com> Message-ID: <006101c7d1eb$8d230230$6101a8c0@carlsw> I begin by saying that I am neither a mathematician nor a programmer. I do have an understanding of statistical analysis. I am a relatively new user of spambayes and I am greatly please the product and the results. I have been following the discussion of training balance with great interest. I do not save or archive much ham and we receive 200-300 spam emails daily. Therefore, I did not have 1:1 mix to train spambayes on. My training ratio is 4957 ham to 18932 spam. Spambayes misses a few spams, especially as the spammers change their content and format. Spambayes has yet to incorrectly identify a ham as spam. I have adjusted my filtering settings for questionable emails to 80.0 for certain spam and 8.0 for uncertain. I am extremely pleased with spambayes and I thank all who obviously have put so much time into developing and tweaking this product. Carl Swofford -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Brendon Whateley Sent: Sunday, July 29, 2007 12:56 AM To: Mark Hammond; spambayes at python.org; skip at pobox.com Subject: Re: [Spambayes] Is Equal Ham & Spam really the best? Mark Hammond wrote: >> That thread was interesting, but still runs under the assumption that >> balanced training is the ideal. >> > > I read that thread as *demonstrating* why unbalanced training will skew your > results. It makes no assumptions at all, but simply considers the facts > We are suffering a semantic disagreement here. That thread explains how an imbalance influences token scores, but doesn't explain one way or another if that harms classification in the wild. Presumably at some point it will cause harm, but just when is unclear. > about how spambayes works and the math behind it. The assumptions you refer > to are a direct result of the facts presented there. > > Do you disagree with the analysis of the math in that thread? If you don't > disagree, then I completely miss your point. > > >>> Google also shows anecdotal reports of poor results after an imbalance as >>> low as 2:1, so I don't think it would be responsible to re-evaluate that >>> Anecdotal, as you also point out is not the same as proof. >> "responsible"? I'm not sure what you mean. >> > > responsible: worthy of or requiring trust. > > In my opinion, it would be irresponsible to our users, who generally trust > I was assuming that you didn't mean that, since in no way was I suggesting changing anything at all. At least not until the facts behind the statement had been reevaluated and proven to be incorrect. > the spambayes developers, for us to give out information that current wisdom > says to be incorrect, especially when backed up by a solid theoretical > understanding of why that wisdom exists. It would be irresponsible for us > to change our current wisdom based on anecdotes of a single individual, > especially when opposite anecdotes can be easily found. > I really don't know what this was in response to. I ask a question and you are replying as if I am demanding change. That has never been the spambayes way. > >> I assumed that running a test to evaluate the effects of imbalance would >> be the way to generate or refute such evidence? >> > > One person running a test is unlikely to cut it. If you design a test, you > may have luck getting others to run it against their email, in which case > the results will start to get interesting as the number of people increase. > Again, I never claimed that one person would "cut anything". However, if one person doesn't start carry the effort forward, it will never get reevaluated. If my efforts at building a test lead to a result confirming the status quo, then nothing more need be said. At least until some other wise guy comes along and challenges it :) Since the nature of Spam changes over time, the results of these challenges may also change? > >> When I get back from Hawaii, I think I'll dust off the old test corpus and >> > try > >> some tests. If anybody else has some test results, I'd be very interested >> > in > >> seeing them. >> > > Google is your friend here - you can find many discussions about the effects > of imbalances, and plenty of discussions about why a single test from a > single user isn't a useful indicator of anything. Searching for anything > Tim Peters has to say would be the most productive thing to do :) > That is a good idea, since gathering info from some of the core folks would seem to save time in developing an effective test. >> My current thought is that getting a (very) large mount of spam with >> very few clues results in each email results in the imbalance. I've >> just checked some of todays spam and some had as few as 31 clues. With >> so few clues, it is relatively easy for a spam message to end up with an >> unsure or even ham classification while the most ham is being correctly >> classified. The alternative to an imbalanced training set is to find an >> easy way to train on extra ham, but only the ham that still has some >> classification value to add. >> > > I'm glad that spambayes appears to work well for you with a significant > imbalance, but I think we've already pointed out that there is solid > reasoning behind our position. > As a long time spambayes user, promoter and sometimes contributer, I've yet to find a user for whom spambayes does not work very well! I understand the theory but would like to understand the real world implications, especially given the anecdotal evidence that imbalance doesn't always harm performance. Even Tim Peters has a 3:1 ratio :) Anyway, I'm not trying to rock the boat, start a fight or anything else. I've now got to go and pack, Brendon. _______________________________________________ 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 Sun Jul 29 16:18:48 2007 From: skip at pobox.com (skip at pobox.com) Date: Sun, 29 Jul 2007 09:18:48 -0500 Subject: [Spambayes] Alternative to Gmail? Message-ID: <18092.41416.21814.970818@montanaro.dyndns.org> This is more than a bit off-topic for this list, but as the folks here are interested in email and spam I thought I'd see what recommendations you have. Since leaving the Mojam/Musi-Cal space about 6-8 months ago and no longer having easy, guaranteed long-term access to a mail server I've been using Gmail. On the surface it's quite nice. I can read mail through the web wherever I happen to be, and it seemed that it was doing a pretty good job of filtering out spam, taking a load off both SpamBayes and my laptop. Over the past few days it's become increasingly obvious though that Gmail is actually doing a very bad job of spam filtering. I don't mind the few true spams that it misses, maybe 10-15 per day, most of which SpamBayes classifies correctly. I first noticed it when I noticed much of the mail I sent to lists I post to frequently were themselves being classified as spam. It seems that Gmail is mistakenly classifying several good emails each day as spam, again, maybe 10-15 messages. That means I must wade through the thousands of emails in my spam box searching among the detritus for the good messages Gmail missed. Hardly makes sense to use a spam filter if you have to pick through your spam manually. To make matters worse, they provide essentially no tools to help in that search. For instance, you can't select all the non-English (or non-Roman character set) spams to quickly get them out of the way. You can't turn a knob to make their spam filter less aggressive (or disable it altogether). The mail messages aren't marked in any way that would indicate why Gmail thought a particular message was spam. Long story short, I think I want to find an alternative email provider. Are any of the others any better? I do need POP or IMAP access. Beyond that I'm pretty flexible. Thx, Skip From dave at boost-consulting.com Sun Jul 29 20:25:46 2007 From: dave at boost-consulting.com (David Abrahams) Date: Sun, 29 Jul 2007 11:25:46 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> Message-ID: <87sl7783th.fsf@grogan.peloton> on Fri Jul 27 2007, skip-AT-pobox.com wrote: > Brendon> I've just started using spambayes again after a while away from > Brendon> it. Now, 3 days in, I notice that I've trained on far more > Brendon> spam than ham. (Total emails trained: Spam: *432* Ham: *64) I > Brendon> seem to remember that this was previously my experience in the > Brendon> past. > > Are you training on every message you receive or just the mistakes? Most > people generally only train on the mistakes and unsures. Your ratio is > about 7:1. That's a bit high. Even training only on mistakes and unsures, I have had a steadily increasing ratio for months. I almost never see a misclassified ham and only very rarely a ham about which the system is unsure. It's unsure about spam every day. -- Dave Abrahams Boost Consulting http://www.boost-consulting.com The Astoria Seminar ==> http://www.astoriaseminar.com From dave at boost-consulting.com Sun Jul 29 20:32:09 2007 From: dave at boost-consulting.com (David Abrahams) Date: Sun, 29 Jul 2007 11:32:09 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? References: <46AACCBA.6070004@whateley.com> <11a601c7d0e0$e435a0c0$090a0a0a@enfoldsystems.local> Message-ID: <87myxf83iu.fsf@grogan.peloton> on Fri Jul 27 2007, "Mark Hammond" wrote: >> That is high relative to the conventional wisdom, but I'm questioning >> the correctness of that wisdom. > > Check out this thread, which should give you a reasonable idea: > > http://mail.python.org/pipermail/spambayes-dev/2003-November/001578.html > >> Perhaps its time to re-evaluate that statement? > > Google also shows anecdotal reports of poor results after an imbalance as > low as 2:1, so I don't think it would be responsible to re-evaluate that > statement until clear evidence was presented to the contrary. Because those tests don't have all the same real-world constraints as I do, I'm still trying to figure out whether they answer my question: Is it better to withold data (some previously-misclassified spams) from the system when training in order to keep ham and spam balanced, or will I get better results if I let it see all the previously-misclassified spam despite the imbalance? In my admittedly not-rigorously-tested experience, it's generally better to let the system see more data (at least with train-to-exhaustion). -- Dave Abrahams Boost Consulting http://www.boost-consulting.com The Astoria Seminar ==> http://www.astoriaseminar.com From shawn at 12pointdesign.com Sun Jul 29 21:25:23 2007 From: shawn at 12pointdesign.com (Shawn K. Hall) Date: Sun, 29 Jul 2007 12:25:23 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <87sl7783th.fsf@grogan.peloton> References: <46AA769C.3030009@whateley.com><18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> Message-ID: <01f901c7d216$36375d60$1e00a8c0@Yoda> > Even training only on mistakes and unsures, I have had a steadily > increasing ratio for months. I almost never see a misclassified > ham and only very rarely a ham about which the system is unsure. > It's unsure about spam every day. I run several servers, and hundreds of domains, so I get quite a bit of email - even if much of it is just for archival purposes (logs mostly). I keep MOST of my ham. I no longer keep spam beyond about 2 months or so, but in that period I can easily collect some 100,000 spam that would otherwise totally dwarf the amount of ham I receive. I get at least 2k messages per day, sometimes as much as 5k. I never exactly plan to rebuild the database, but always do when I make a big mistake. While I never really had a problem with the effectiveness of SpamBayes before, a couple times I've clicked the wrong button in the 'unsure' folder when I had fifteen+ spam or ham selected, which can quite effectively destroy the database. So I purge it and retrain on my current archive of spam and a couple known good folders under the inbox that I have stored a few thousand messages. Having that archive of known good messages makes all the difference in the world. I now have a database of about 90k/80k (the db is about 330mb) and only receive about 25 unclassified messages per day on average, which consists of about 20% either gobbledygook or legit messages with no content except for their attachments or a blank subject - the other 80% are 'trainable' spam. I train on all ham and only those spam messages that look like they'll make a difference to the validity of future checks. If it's a gobbledygook spam message, I usually just delete it directly from unsure. I still use 75%/15% as the spam cutoffs. While I could probably avoid looking at subject lines for approximately 50-60% of the spam that goes to unsure by lowering the spam cutoff to 60%, it takes only a few extra seconds to look through those other subjects or senders once per day to correct their status. I'd rather not risk losing an important message from a client that is forwarding a spam message they received directly to the spam folder. Once it's in there I don't even bother looking at it but once per month when I use the library of spam I've collected to fine-tune my server-side filters. Legitimate forum and group messages can often be flagged higher than 10%, so I don't want to lower my ham threshold. If anything, it could use to go up to 20% or so. The no-subject or attachment-only ham are almost always high teens or low twenty scores, but if I adjust the ham setting I'll get a bit more of the gobbledygook to my inbox, too. Anyway... Just thought a bit more anecdotal evidence might be interesting to some. ;) Regards, Shawn K. Hall http://12PointDesign.com/ '// ======================================================== "You have to change the map, not the world." -- Marcus Kaarto From amedee at amedee.be Sun Jul 29 22:09:27 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Sun, 29 Jul 2007 22:09:27 +0200 (CEST) Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <87sl7783th.fsf@grogan.peloton> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> Message-ID: <1490.213.118.146.15.1185739767.squirrel@amedee.be> On Sun, July 29, 2007 20:25, David Abrahams wrote: > > on Fri Jul 27 2007, skip-AT-pobox.com wrote: > >> Brendon> I've just started using spambayes again after a while away >> from >> Brendon> it. Now, 3 days in, I notice that I've trained on far more >> Brendon> spam than ham. (Total emails trained: Spam: *432* Ham: >> *64) I >> Brendon> seem to remember that this was previously my experience in >> the >> Brendon> past. >> >> Are you training on every message you receive or just the mistakes? >> Most >> people generally only train on the mistakes and unsures. Your ratio is >> about 7:1. That's a bit high. > > Even training only on mistakes and unsures, I have had a steadily > increasing ratio for months. I almost never see a misclassified ham > and only very rarely a ham about which the system is unsure. It's > unsure about spam every day. I have the same experience: amedee at elbereth { ~ }$ ./spamstats Spam: 2415 Ham: 651 That's 3.7:1, and it's increasing. Nonetheless I have never seen a false positive. I only train on mistakes and unsures. Most of my email is to/from the same 50 people or so, and most of the time they write messages longer than 50 words, and almost all of them in Dutch. The very few times I saw a spam classified as ham, it had Dutch nonsense words in it. I would agree that in theory having equal amounts of ham and spam would be better, however in my particular case there are significant factors that mitigate the need of a 1:1 ratio. I'm also claiming that my particular situation cannot be used to draw general conclusions, and that Your Mileage May Vary(tm). -- Amedee From skip at pobox.com Mon Jul 30 00:54:27 2007 From: skip at pobox.com (skip at pobox.com) Date: Sun, 29 Jul 2007 17:54:27 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <87sl7783th.fsf@grogan.peloton> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> Message-ID: <18093.6819.626754.974890@montanaro.dyndns.org> Dave> Even training only on mistakes and unsures, I have had a steadily Dave> increasing ratio for months. I almost never see a misclassified Dave> ham and only very rarely a ham about which the system is unsure. Dave> It's unsure about spam every day. What are your ham and spam thresholds set to? Have you tried lowering your spam threshold a bit? Skip From skip at pobox.com Mon Jul 30 00:57:32 2007 From: skip at pobox.com (skip at pobox.com) Date: Sun, 29 Jul 2007 17:57:32 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <1490.213.118.146.15.1185739767.squirrel@amedee.be> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <1490.213.118.146.15.1185739767.squirrel@amedee.be> Message-ID: <18093.7004.379114.50403@montanaro.dyndns.org> Amedee> I have the same experience: Amedee> amedee at elbereth { ~ }$ ./spamstats Amedee> Spam: 2415 Ham: 651 Amedee> That's 3.7:1, and it's increasing. One of the reasons I can keep a nearly 1:1 ratio is that when it gets a bit out of whack I simply delete some old spam. In my experience the nature of spam changes over time while the nature of ham rarely does. I also use train-to-exhaustion which only trains in fixed ratios. Skip From dave at boost-consulting.com Mon Jul 30 03:14:32 2007 From: dave at boost-consulting.com (David Abrahams) Date: Sun, 29 Jul 2007 18:14:32 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <18093.7004.379114.50403@montanaro.dyndns.org> (skip@pobox.com's message of "Sun\, 29 Jul 2007 17\:57\:32 -0500") References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <1490.213.118.146.15.1185739767.squirrel@amedee.be> <18093.7004.379114.50403@montanaro.dyndns.org> Message-ID: <8764428zgn.fsf@grogan.peloton> A non-text attachment was scrubbed... Name: tte.patch Type: text/x-diff Size: 554 bytes Desc: not available Url : http://mail.python.org/pipermail/spambayes/attachments/20070729/b2e91c20/attachment.bin From dave at boost-consulting.com Mon Jul 30 02:59:12 2007 From: dave at boost-consulting.com (David Abrahams) Date: Sun, 29 Jul 2007 17:59:12 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <18093.6819.626754.974890@montanaro.dyndns.org> (skip@pobox.com's message of "Sun\, 29 Jul 2007 17\:54\:27 -0500") References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <18093.6819.626754.974890@montanaro.dyndns.org> Message-ID: <87abte9067.fsf@grogan.peloton> on Sun Jul 29 2007, skip-AT-pobox.com wrote: > Dave> Even training only on mistakes and unsures, I have had a steadily > Dave> increasing ratio for months. I almost never see a misclassified > Dave> ham and only very rarely a ham about which the system is unsure. > Dave> It's unsure about spam every day. > > What are your ham and spam thresholds set to? The default, whatever that is, for classification. And I've been using -o Categorization:ham_cutoff:0.02 \ -o Categorization:spam_cutoff:0.98 \ when I invoke tte.py > Have you tried lowering your spam threshold a bit? No, I haven't tried that. I suppose I run the risk of a few false positives if I go too far with that? -- Dave Abrahams Boost Consulting http://www.boost-consulting.com The Astoria Seminar ==> http://www.astoriaseminar.com From skip at pobox.com Mon Jul 30 04:01:03 2007 From: skip at pobox.com (skip at pobox.com) Date: Sun, 29 Jul 2007 21:01:03 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <87abte9067.fsf@grogan.peloton> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <18093.6819.626754.974890@montanaro.dyndns.org> <87abte9067.fsf@grogan.peloton> Message-ID: <18093.18015.114885.957106@montanaro.dyndns.org> >> Have you tried lowering your spam threshold a bit? Dave> No, I haven't tried that. I suppose I run the risk of a few false Dave> positives if I go too far with that? Take a look at the scores in the spams marked unsure and in any hams which are marked unsure. You might well be able to lower the spam threshold a fair amount without running the risk of too many (if any) false positives. I use: [Categorization] ham_cutoff:0.20 spam_cutoff:0.7 Skip From amedee at amedee.be Mon Jul 30 09:56:00 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Mon, 30 Jul 2007 09:56:00 +0200 (CEST) Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <18093.7004.379114.50403@montanaro.dyndns.org> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <1490.213.118.146.15.1185739767.squirrel@amedee.be> <18093.7004.379114.50403@montanaro.dyndns.org> Message-ID: <10678.193.121.250.194.1185782160.squirrel@amedee.be> On Mon, July 30, 2007 00:57, skip at pobox.com wrote: > > Amedee> I have the same experience: > > Amedee> amedee at elbereth { ~ }$ ./spamstats > Amedee> Spam: 2415 Ham: 651 > > Amedee> That's 3.7:1, and it's increasing. > > One of the reasons I can keep a nearly 1:1 ratio is that when it gets a > bit > out of whack I simply delete some old spam. In my experience the nature > of > spam changes over time while the nature of ham rarely does. I also use > train-to-exhaustion which only trains in fixed ratios. I don't keep any spam at all. Should I? I don't understand. >From the beginning I trained SpamBayes only on mistakes and unsures. After about a week, it performed so good that I was confident enough to /dev/null anything with a spam score of 100%. Anything with a score between 90% and 99% gets moved to my spam training folder (after vgrepping it for hammy clues) and after my training script is run by a daily cron job, the training folders are purged. The only place where I have old spam, is inside the token database. Do you mean you delete the old tokens? How do you do that? Or do you keep your old spam and retrain from scratch every ??t? -- Amedee From jsp at PKC.com Mon Jul 30 13:50:14 2007 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 30 Jul 2007 07:50:14 -0400 Subject: [Spambayes] Alternative to Gmail? In-Reply-To: <18092.41416.21814.970818@montanaro.dyndns.org> References: <18092.41416.21814.970818@montanaro.dyndns.org> Message-ID: <16E2027582CDB74180896CDB4B8CC1F905BD9349@PKCVT01.pkc.com> A friend of mine swears by usermail.com. It costs $19.95/year and includes POP3 and IMAP access in the clear or over SSL. They claim to have "fully customizable spam filtering," but not having used their services myself, I don't know whether the customization is useful. They also do virus scanning on inbound messages. -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of skip at pobox.com Sent: Sunday, July 29, 2007 10:19 AM To: spambayes at python.org Subject: [Spambayes] Alternative to Gmail? This is more than a bit off-topic for this list, but as the folks here are interested in email and spam I thought I'd see what recommendations you have. Since leaving the Mojam/Musi-Cal space about 6-8 months ago and no longer having easy, guaranteed long-term access to a mail server I've been using Gmail. On the surface it's quite nice. I can read mail through the web wherever I happen to be, and it seemed that it was doing a pretty good job of filtering out spam, taking a load off both SpamBayes and my laptop. Over the past few days it's become increasingly obvious though that Gmail is actually doing a very bad job of spam filtering. I don't mind the few true spams that it misses, maybe 10-15 per day, most of which SpamBayes classifies correctly. I first noticed it when I noticed much of the mail I sent to lists I post to frequently were themselves being classified as spam. It seems that Gmail is mistakenly classifying several good emails each day as spam, again, maybe 10-15 messages. That means I must wade through the thousands of emails in my spam box searching among the detritus for the good messages Gmail missed. Hardly makes sense to use a spam filter if you have to pick through your spam manually. To make matters worse, they provide essentially no tools to help in that search. For instance, you can't select all the non-English (or non-Roman character set) spams to quickly get them out of the way. You can't turn a knob to make their spam filter less aggressive (or disable it altogether). The mail messages aren't marked in any way that would indicate why Gmail thought a particular message was spam. Long story short, I think I want to find an alternative email provider. Are any of the others any better? I do need POP or IMAP access. Beyond that I'm pretty flexible. Thx, Skip _______________________________________________ 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 Mon Jul 30 15:06:47 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 30 Jul 2007 08:06:47 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <10678.193.121.250.194.1185782160.squirrel@amedee.be> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <1490.213.118.146.15.1185739767.squirrel@amedee.be> <18093.7004.379114.50403@montanaro.dyndns.org> <10678.193.121.250.194.1185782160.squirrel@amedee.be> Message-ID: <18093.57959.680628.844523@montanaro.dyndns.org> Amedee> I don't keep any spam at all. Should I? I don't understand. I keep small mailboxes of hams and spams for retraining. Amedee> The only place where I have old spam, is inside the token Amedee> database. Do you mean you delete the old tokens? How do you do Amedee> that? Or do you keep your old spam and retrain from scratch Amedee> every ??t? I'm almost certainly using a different SpamBayes application than you. They all use the same classifier but have different ways of managing the database of messages used as input to the token database. My guess would be that you're using the POP3 proxy or the Outlook plugin. I'm not sure what their facilities for retraining are. Skip From amedee at amedee.be Mon Jul 30 16:32:12 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Mon, 30 Jul 2007 16:32:12 +0200 (CEST) Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <18093.57959.680628.844523@montanaro.dyndns.org> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <1490.213.118.146.15.1185739767.squirrel@amedee.be> <18093.7004.379114.50403@montanaro.dyndns.org> <10678.193.121.250.194.1185782160.squirrel@amedee.be> <18093.57959.680628.844523@montanaro.dyndns.org> Message-ID: <26376.193.121.250.194.1185805932.squirrel@amedee.be> On Mon, July 30, 2007 15:06, skip at pobox.com wrote: > > Amedee> I don't keep any spam at all. Should I? I don't understand. > > I keep small mailboxes of hams and spams for retraining. OK. > I'm almost certainly using a different SpamBayes application than you. > They > all use the same classifier but have different ways of managing the > database > of messages used as input to the token database. My guess would be that > you're using the POP3 proxy or the Outlook plugin. I'm not sure what > their > facilities for retraining are. I'm using the procmail filter. -- Amedee From skip at pobox.com Mon Jul 30 16:48:21 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 30 Jul 2007 09:48:21 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <26376.193.121.250.194.1185805932.squirrel@amedee.be> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <1490.213.118.146.15.1185739767.squirrel@amedee.be> <18093.7004.379114.50403@montanaro.dyndns.org> <10678.193.121.250.194.1185782160.squirrel@amedee.be> <18093.57959.680628.844523@montanaro.dyndns.org> <26376.193.121.250.194.1185805932.squirrel@amedee.be> Message-ID: <18093.64053.172914.624738@montanaro.dyndns.org> Amedee> I'm using the procmail filter. You're using "sb_filter.py -t" (or sb_bnfilter.py)? I'd recommend that you also save the messages you train on and occasionally retrain from scratch if you discover you've made a mistake. You might also try the train-to-exhaustion script in contrib/tte.py and only use the sb_filter script to score messages. Skip From dlwiii at gmail.com Mon Jul 30 17:55:29 2007 From: dlwiii at gmail.com (Daniel Williams) Date: Mon, 30 Jul 2007 09:55:29 -0600 Subject: [Spambayes] New version, or alternative program? Message-ID: I have been using SpamBayes for a while now, and occasionally look for updates. Is there any chance of an update in the future, or is the project dead? Are there any alternatives you could recommend? I use the SpamBayes outlook plugin on Windows. It is working fine, but I just want to make sure that I have alternatives in case a new version of Outlook or Windows breaks it. Cheers, Daniel Williams From dalmolin at e-cology.ca Mon Jul 30 18:38:28 2007 From: dalmolin at e-cology.ca (Joseph Dal Molin) Date: Mon, 30 Jul 2007 12:38:28 -0400 Subject: [Spambayes] Alternative to Gmail? In-Reply-To: <16E2027582CDB74180896CDB4B8CC1F905BD9349@PKCVT01.pkc.com> References: <18092.41416.21814.970818@montanaro.dyndns.org> <16E2027582CDB74180896CDB4B8CC1F905BD9349@PKCVT01.pkc.com> Message-ID: <46AE1404.5090809@e-cology.ca> Have a look at Fastmail www.fastmail.fm..... don't know how good their filters etc. are I use them as a backup. Joseph Jesse Pelton wrote: > A friend of mine swears by usermail.com. It costs $19.95/year and > includes POP3 and IMAP access in the clear or over SSL. They claim to > have "fully customizable spam filtering," but not having used their > services myself, I don't know whether the customization is useful. They > also do virus scanning on inbound messages. > > -----Original Message----- > From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] > On Behalf Of skip at pobox.com > Sent: Sunday, July 29, 2007 10:19 AM > To: spambayes at python.org > Subject: [Spambayes] Alternative to Gmail? > > This is more than a bit off-topic for this list, but as the folks here > are > interested in email and spam I thought I'd see what recommendations you > have. > > Since leaving the Mojam/Musi-Cal space about 6-8 months ago and no > longer > having easy, guaranteed long-term access to a mail server I've been > using > Gmail. On the surface it's quite nice. I can read mail through the web > wherever I happen to be, and it seemed that it was doing a pretty good > job > of filtering out spam, taking a load off both SpamBayes and my laptop. > > Over the past few days it's become increasingly obvious though that > Gmail is > actually doing a very bad job of spam filtering. I don't mind the few > true > spams that it misses, maybe 10-15 per day, most of which SpamBayes > classifies correctly. I first noticed it when I noticed much of the > mail I > sent to lists I post to frequently were themselves being classified as > spam. > It seems that Gmail is mistakenly classifying several good emails each > day > as spam, again, maybe 10-15 messages. That means I must wade through > the > thousands of emails in my spam box searching among the detritus for the > good > messages Gmail missed. Hardly makes sense to use a spam filter if you > have > to pick through your spam manually. > > To make matters worse, they provide essentially no tools to help in that > search. For instance, you can't select all the non-English (or > non-Roman > character set) spams to quickly get them out of the way. You can't turn > a > knob to make their spam filter less aggressive (or disable it > altogether). > The mail messages aren't marked in any way that would indicate why Gmail > thought a particular message was spam. > > Long story short, I think I want to find an alternative email provider. > Are > any of the others any better? I do need POP or IMAP access. Beyond > that > I'm pretty flexible. > > Thx, > > Skip > _______________________________________________ > 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 jsp at PKC.com Mon Jul 30 19:11:54 2007 From: jsp at PKC.com (Jesse Pelton) Date: Mon, 30 Jul 2007 13:11:54 -0400 Subject: [Spambayes] New version, or alternative program? In-Reply-To: References: Message-ID: <16E2027582CDB74180896CDB4B8CC1F905C53141@PKCVT01.pkc.com> A new version has been imminent for many moons. After a year or two of quiet, there's been more activity lately, so there may in fact be a 1.1 version that attempts to extract clues from images before long. There's no schedule, but I wouldn't let that get in the way. The long period without a release is more indicative of a mature project with software that just works than of a lack of interest. For what it's worth, people have reported working installations of SpamBayes with Vista and Outlook 2007. -----Original Message----- From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On Behalf Of Daniel Williams Sent: Monday, July 30, 2007 11:55 AM To: spambayes at python.org Subject: [Spambayes] New version, or alternative program? I have been using SpamBayes for a while now, and occasionally look for updates. Is there any chance of an update in the future, or is the project dead? Are there any alternatives you could recommend? I use the SpamBayes outlook plugin on Windows. It is working fine, but I just want to make sure that I have alternatives in case a new version of Outlook or Windows breaks it. Cheers, Daniel Williams _______________________________________________ SpamBayes at python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html From dave at boost-consulting.com Mon Jul 30 19:49:16 2007 From: dave at boost-consulting.com (David Abrahams) Date: Mon, 30 Jul 2007 10:49:16 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <18093.6819.626754.974890@montanaro.dyndns.org> <87abte9067.fsf@grogan.peloton> <18093.18015.114885.957106@montanaro.dyndns.org> Message-ID: <8764416aub.fsf@grogan.peloton> on Sun Jul 29 2007, skip-AT-pobox.com wrote: > >> Have you tried lowering your spam threshold a bit? > > Dave> No, I haven't tried that. I suppose I run the risk of a few false > Dave> positives if I go too far with that? > > Take a look at the scores in the spams marked unsure and in any hams which > are marked unsure. You might well be able to lower the spam threshold a > fair amount without running the risk of too many (if any) false positives. > > I use: > > [Categorization] > ham_cutoff:0.20 > spam_cutoff:0.7 OK, I have some hams that scored as high as 0.85 Is everything between the ham_cutoff and spam_cutoff classified as unsure? Moving my spam_cutoff to 0.86 probably would make only a small dent in my results. -- Dave Abrahams Boost Consulting http://www.boost-consulting.com The Astoria Seminar ==> http://www.astoriaseminar.com From dave at boost-consulting.com Mon Jul 30 19:50:20 2007 From: dave at boost-consulting.com (David Abrahams) Date: Mon, 30 Jul 2007 10:50:20 -0700 Subject: [Spambayes] New version, or alternative program? References: <16E2027582CDB74180896CDB4B8CC1F905C53141@PKCVT01.pkc.com> Message-ID: <87zm1d4w83.fsf@grogan.peloton> on Mon Jul 30 2007, "Jesse Pelton" wrote: > A new version has been imminent for many moons. After a year or two of > quiet, there's been more activity lately, so there may in fact be a 1.1 > version that attempts to extract clues from images before long. There's > no schedule, but I wouldn't let that get in the way. The long period > without a release is more indicative of a mature project with software > that just works than of a lack of interest. I've been using the development version, with the image clue extraction, for a while now. It works well. -- Dave Abrahams Boost Consulting http://www.boost-consulting.com The Astoria Seminar ==> http://www.astoriaseminar.com From DHASKINS1 at PARTNERS.ORG Mon Jul 30 20:44:25 2007 From: DHASKINS1 at PARTNERS.ORG (Haskins, Doryce) Date: Mon, 30 Jul 2007 14:44:25 -0400 Subject: [Spambayes] Re: Mail Delivery (failure travel@customercare.expedia.com) Message-ID: I doryce Haskins need to correct my e-mail address as well as reset my password. and my phone #is 617-732-6421 Doryce Haskins BIMA dhaskins1 at partners.org The information transmitted in this electronic communication is intended only for the person or entity to whom it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of or taking of any action in reliance upon this information by persons or entities other than the intended recipient is prohibited. If you received this information in error, please contact the Compliance HelpLine at 800-856-1983 and properly dispose of this information. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.python.org/pipermail/spambayes/attachments/20070730/cae01a3e/attachment.html -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/gif Size: 5999 bytes Desc: Currency.gif Url : http://mail.python.org/pipermail/spambayes/attachments/20070730/cae01a3e/attachment.gif From skip at pobox.com Mon Jul 30 22:03:37 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 30 Jul 2007 15:03:37 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <8764416aub.fsf@grogan.peloton> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <18093.6819.626754.974890@montanaro.dyndns.org> <87abte9067.fsf@grogan.peloton> <18093.18015.114885.957106@montanaro.dyndns.org> <8764416aub.fsf@grogan.peloton> Message-ID: <18094.17433.601230.156362@montanaro.dyndns.org> Dave> OK, I have some hams that scored as high as 0.85 I will assert without any further evidence that you have one or more classification mistakes in your database. Can you post the evidence header from that message? Dave> Is everything between the ham_cutoff and spam_cutoff classified as Dave> unsure? Moving my spam_cutoff to 0.86 probably would make only a Dave> small dent in my results. If everything is properly trained SpamBayes should produce a distribution of scores with a bimodal distribution, hams near 0.0 and spams near 1.0. A ham scoring above 0.5 tells me that you have classified a number of hams as spam. Skip From amedee at amedee.be Mon Jul 30 23:23:34 2007 From: amedee at amedee.be (Amedee Van Gasse) Date: Mon, 30 Jul 2007 23:23:34 +0200 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <18093.64053.172914.624738@montanaro.dyndns.org> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <1490.213.118.146.15.1185739767.squirrel@amedee.be> <18093.7004.379114.50403@montanaro.dyndns.org> <10678.193.121.250.194.1185782160.squirrel@amedee.be> <18093.57959.680628.844523@montanaro.dyndns.org> <26376.193.121.250.194.1185805932.squirrel@amedee.be> <18093.64053.172914.624738@montanaro.dyndns.org> Message-ID: <1185830614.10319.14.camel@saruman> Op maandag 30-07-2007 om 09:48 uur [tijdzone -0500], schreef skip at pobox.com: > Amedee> I'm using the procmail filter. > > You're using "sb_filter.py -t" (or sb_bnfilter.py)? I'm using sb_filter.py to score messages. For training, I use sb_mboxtrain.py -n -r -d $HOME/.hammiedb -g $HOME/Maildir/.ztrain.confirmed-ham -s $HOME/Maildir/.ztrain.confirmed-spam > I'd recommend that you also save the messages you train on OK. > and occasionally retrain from scratch if you discover you've made a > mistake. So far I have not yet made a mistake, because when I move mail to a traing folder, it only gets trained on the next daily cron run. That means I have enough time to move misclassified mail. > You might also try the train-to-exhaustion script in contrib/tte.py OK. How does that work? With sb_mboxtrain.py I just "drag & forget". Can I do the same with contrib/tte.py? Can I use it as a drop-in replacement and let a cron job run on it every night? > and only use the sb_filter script to score messages. OK, I'm already doing that. -- Amedee Van Gasse -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: Dit berichtdeel is digitaal ondertekend Url : http://mail.python.org/pipermail/spambayes/attachments/20070730/c0d7ba82/attachment-0001.pgp From dave at boost-consulting.com Tue Jul 31 01:56:18 2007 From: dave at boost-consulting.com (David Abrahams) Date: Mon, 30 Jul 2007 16:56:18 -0700 Subject: [Spambayes] Is Equal Ham & Spam really the best? References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <18093.6819.626754.974890@montanaro.dyndns.org> <87abte9067.fsf@grogan.peloton> <18093.18015.114885.957106@montanaro.dyndns.org> <8764416aub.fsf@grogan.peloton> <18094.17433.601230.156362@montanaro.dyndns.org> Message-ID: <87d4y94fa5.fsf@grogan.peloton> An embedded and charset-unspecified text was scrubbed... Name: cheese.txt Url: http://mail.python.org/pipermail/spambayes/attachments/20070730/13bd90bb/attachment.txt From skip at pobox.com Tue Jul 31 04:32:09 2007 From: skip at pobox.com (skip at pobox.com) Date: Mon, 30 Jul 2007 21:32:09 -0500 Subject: [Spambayes] Is Equal Ham & Spam really the best? In-Reply-To: <87d4y94fa5.fsf@grogan.peloton> References: <46AA769C.3030009@whateley.com> <18090.49694.414574.721564@montanaro.dyndns.org> <87sl7783th.fsf@grogan.peloton> <18093.6819.626754.974890@montanaro.dyndns.org> <87abte9067.fsf@grogan.peloton> <18093.18015.114885.957106@montanaro.dyndns.org> <8764416aub.fsf@grogan.peloton> <18094.17433.601230.156362@montanaro.dyndns.org> <87d4y94fa5.fsf@grogan.peloton> Message-ID: <18094.40745.843582.198200@montanaro.dyndns.org> Dave, Can you try adding this to your bayescustomize.ini file: [Headers] include_evidence:True then run your brother-in-law's message through sb_filter.py? That will tell us which tokens are causing that message's score to be so spammy. (You will need to take his message out of your training database first, retrain, then run sb_filter.py.). Maybe it's that he's a Hotmail user. Skip