From matthew at veradox.com Wed Oct 4 06:05:09 2006 From: matthew at veradox.com (Matthew Wilson) Date: Wed, 04 Oct 2006 14:05:09 +0100 Subject: [Kc] meeting Tuesday Oct 10 2006 Message-ID: Unless someone else comes up with another topic, I would like to discuss (preferably exclusively) the Netflix Prize. 3 of the 4 code snippets posted so far on the forums are in perl. The other is in ruby. -Matthew -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.pm.org/pipermail/kc/attachments/20061004/125f68ea/attachment.html From ggoebel at goebel.ws Wed Oct 4 15:36:35 2006 From: ggoebel at goebel.ws (Garrett Goebel) Date: Wed, 4 Oct 2006 17:36:35 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: References: Message-ID: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> Sounds good. Synchronicity. I just finished reading the rules about 10 minutes before you posted this. On Oct 4, 2006, at 8:05 AM, Matthew Wilson wrote: > Unless someone else comes up with another topic, I would like to > discuss (preferably exclusively) the Netflix Prize. 3 of the 4 > code snippets posted so far on the forums are in perl. The other > is in ruby. > > -Matthew > _______________________________________________ > kc mailing list > kc at pm.org > http://mail.pm.org/mailman/listinfo/kc From djgoku at gmail.com Wed Oct 4 20:34:08 2006 From: djgoku at gmail.com (djgoku) Date: Wed, 4 Oct 2006 22:34:08 -0500 Subject: [Kc] OT: Mac Users Message-ID: <99dd19c90610042034t61234ab8sc3082787cd838553@mail.gmail.com> I just got a base (1.66Ghz Dual-Core 512MB) Mac Mini yesterday and I know it probably needs more RAM, but I was wondering what RAM usages other new MacBook and Mac Mini Intel users are seeing. What concerns me is the Inactive memory and Free, I would of thought those mean the same? Only problem I had was when trying to install OO.org I couldn't find X11User.pkg on the install CDs that came with the Mini. They had X11SDK.pkg and after search with Spotlight I found X11User.pkg. http://tektronic.org/images/Activity_Monitor.png From ironicface at earthlink.net Thu Oct 5 05:06:20 2006 From: ironicface at earthlink.net (Teal) Date: Thu, 05 Oct 2006 07:06:20 -0500 Subject: [Kc] Find Jobs - Sr. LAMP developer Jobs in Kansas City, MO Message-ID: <4524F53C.7090207@earthlink.net> Nice pay, anyhow. Teal -- Five minutes of Silence, Meditate. Breathe. Be Alive. From davidnicol at gmail.com Thu Oct 5 12:10:59 2006 From: davidnicol at gmail.com (David Nicol) Date: Thu, 5 Oct 2006 14:10:59 -0500 Subject: [Kc] netflix prize Message-ID: <934f64a20610051210s155bcb71m4154a681d3324ddf@mail.gmail.com> anyone feel like forming a team to try for the netflix prize? http://netflixprize.com/ -- The Country Of The Blind, by H.G. Wells http://cronos.advenge.com/pc/Wells/p528.html From davidnicol at gmail.com Thu Oct 5 12:13:23 2006 From: davidnicol at gmail.com (David Nicol) Date: Thu, 5 Oct 2006 14:13:23 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> Message-ID: <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> ha ha -- me too -- I can't get there until ten pm though -- anyone for a meeting-after-the-meeting, perhaps at Chubby's? > On Oct 4, 2006, at 8:05 AM, Matthew Wilson wrote: > > > Unless someone else comes up with another topic, I would like to > > discuss (preferably exclusively) the Netflix Prize. From matthew at veradox.com Thu Oct 5 06:19:30 2006 From: matthew at veradox.com (Matthew Wilson) Date: Thu, 05 Oct 2006 14:19:30 +0100 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> Message-ID: Perhaps... I've got a testing/development framework up and going, and a pile of relevant academic PDFs on collaborative filtering and recommender systems. I've created a team already (no submissions yet), but the rules state that users can be members of more than one team. How about "KC Perl Mongers" for our team name .... btw, the system is flawed in that once you create a password for the team, you should not change it unless you don't want anyone else to be able to join the team, even if they have the new password. (says the forums) -----Original Message----- From: "David Nicol" To: "Garrett Goebel" Cc: "Matthew Wilson" , kc at pm.org Date: Thu, 5 Oct 2006 14:13:23 -0500 Subject: Re: [Kc] meeting Tuesday Oct 10 2006 ha ha -- me too -- I can't get there until ten pm though -- anyone for a meeting-after-the-meeting, perhaps at Chubby's? > On Oct 4, 2006, at 8:05 AM, Matthew Wilson wrote: > > > Unless someone else comes up with another topic, I would like to > > discuss (preferably exclusively) the Netflix Prize. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.pm.org/pipermail/kc/attachments/20061005/7c6f5dd6/attachment.html From matthew at veradox.com Thu Oct 5 06:19:30 2006 From: matthew at veradox.com (Matthew Wilson) Date: Thu, 05 Oct 2006 14:19:30 +0100 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> Message-ID: Perhaps... I've got a testing/development framework up and going, and a pile of relevant academic PDFs on collaborative filtering and recommender systems. I've created a team already (no submissions yet), but the rules state that users can be members of more than one team. How about "KC Perl Mongers" for our team name .... btw, the system is flawed in that once you create a password for the team, you should not change it unless you don't want anyone else to be able to join the team, even if they have the new password. (says the forums) -----Original Message----- From: "David Nicol" To: "Garrett Goebel" Cc: "Matthew Wilson" , kc at pm.org Date: Thu, 5 Oct 2006 14:13:23 -0500 Subject: Re: [Kc] meeting Tuesday Oct 10 2006 ha ha -- me too -- I can't get there until ten pm though -- anyone for a meeting-after-the-meeting, perhaps at Chubby's? > On Oct 4, 2006, at 8:05 AM, Matthew Wilson wrote: > > > Unless someone else comes up with another topic, I would like to > > discuss (preferably exclusively) the Netflix Prize. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.pm.org/pipermail/kc/attachments/20061005/7c6f5dd6/attachment-0001.html From davidnicol at gmail.com Thu Oct 5 13:21:18 2006 From: davidnicol at gmail.com (David Nicol) Date: Thu, 5 Oct 2006 15:21:18 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> Message-ID: <934f64a20610051321g68d43bc3g2f3c2ebde345b65@mail.gmail.com> I set up a team called "Kansas City" please respond to me if you would like added to it :) 10 pm at chubby's we'll draft internal team agreements; draft milestones; management-type wheel-spinning On 10/5/06, Matthew Wilson wrote: > > Perhaps... I've got a testing/development framework up and going, and a pile > of relevant academic PDFs on collaborative filtering and recommender > systems. > > I've created a team already (no submissions yet), but the rules state that > users can be members of more than one team. > > How about "KC Perl Mongers" for our team name From matthew at veradox.com Thu Oct 5 07:35:38 2006 From: matthew at veradox.com (Matthew Wilson) Date: Thu, 05 Oct 2006 15:35:38 +0100 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: <934f64a20610051321g68d43bc3g2f3c2ebde345b65@mail.gmail.com> References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> <934f64a20610051321g68d43bc3g2f3c2ebde345b65@mail.gmail.com> Message-ID: I don't know if I'll be able to join your team since I'm pretty far along with my efforts in research and implementation, and I have a lot of confidence in the overall approach I'm taking. I'll be glad to compare notes though. Depending on how things go in the next few days, I'll know just how much computing power I will be needing, so I may be looking for minority-share team members. Remember, once someone passes the 0.8563 mark (and I do believe it will happen in the next few weeks), everyone else will have 30 days to match/beat their progress before a winner is examined/judged/declared. btw, sorry my emails are dated wrongly... I'll fix it later. :) -----Original Message----- From: "David Nicol" To: "Matthew Wilson" , kcpm Date: Thu, 5 Oct 2006 15:21:18 -0500 Subject: Re: [Kc] meeting Tuesday Oct 10 2006 I set up a team called "Kansas City" please respond to me if you would like added to it :) 10 pm at chubby's we'll draft internal team agreements; draft milestones; management-type wheel-spinning On 10/5/06, Matthew Wilson wrote: > > Perhaps... I've got a testing/development framework up and going, and a pile > of relevant academic PDFs on collaborative filtering and recommender > systems. > > I've created a team already (no submissions yet), but the rules state that > users can be members of more than one team. > > How about "KC Perl Mongers" for our team name -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.pm.org/pipermail/kc/attachments/20061005/12d70c27/attachment.html From matthew at veradox.com Sat Oct 7 09:47:55 2006 From: matthew at veradox.com (SysAdmin) Date: Sat, 07 Oct 2006 11:47:55 -0500 Subject: [Kc] Netflix prize In-Reply-To: References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> <934f64a20610051321g68d43bc3g2f3c2ebde345b65@mail.gmail.com> Message-ID: <4527DA3B.3090502@veradox.com> Matthew Wilson wrote: > Remember, once someone passes the 0.8563 mark (and I do believe it > will happen in the next few weeks), everyone else will have 30 days to > match/beat their progress before a winner is examined/judged/declared. Oops; I was wrong on that - the 30 days don't start until 90 days from the start of the contest. -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/x-pkcs7-signature Size: 2852 bytes Desc: S/MIME Cryptographic Signature Url : http://mail.pm.org/pipermail/kc/attachments/20061007/3f51c22d/attachment.bin From ggoebel at goebel.ws Sat Oct 7 10:22:48 2006 From: ggoebel at goebel.ws (Garrett Goebel) Date: Sat, 7 Oct 2006 12:22:48 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> <934f64a20610051321g68d43bc3g2f3c2ebde345b65@mail.gmail.com> Message-ID: <64703218-13F4-4A3F-9645-EA6F50668806@goebel.ws> On Oct 5, 2006, at 9:35 AM, Matthew Wilson wrote: > I don't know if I'll be able to join your team since I'm pretty far > along with my efforts in research and implementation, and I have a > lot of confidence in the overall approach I'm taking. I'll be glad > to compare notes though. Depending on how things go in the next > few days, I'll know just how much computing power I will be > needing, so I may be looking for minority-share team members. > > > Remember, once someone passes the 0.8563 mark (and I do believe it > will happen in the next few weeks), everyone else will have 30 days > to match/beat their progress before a winner is examined/judged/ > declared. > I'm not so sure it'll be beaten. There has yet to be an entry on the leaderboard that matches Cinematch... I too would like to have done a more "people with similar tastes" style ratings projection, but the data set of ~100 million ratings using 480,000 unique customer id's... doesn't lend itself very well to that approach. That and I somehow doubt that the people at Netflix are incompetent. I.e., they say that there are a lot of approaches that they aren't using. But that doesn't mean that they haven't explored and rejected those routes. Myself, I've dumped the training set data into a database. And am trying to figure out the right questions to ask... I do think someone will get the $50,000 progress prize. But I also doubt that it'll be me. I expect a team strong in mathematics and statistics will find a way to finesse small improvements on Cinematch. Enough to justify the progress bounty. I wish there was more documentation on the approach Cinematch takes and the alternative approaches. The progress bounty might be had by anyone who stumbles upon a better balance of approaches, but I doubt anyone will manage the million dollar prize without a novel approach. cheers, Garrett From matthew at veradox.com Sat Oct 7 10:28:54 2006 From: matthew at veradox.com (Matthew Wilson) Date: Sat, 07 Oct 2006 12:28:54 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: <64703218-13F4-4A3F-9645-EA6F50668806@goebel.ws> References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> <934f64a20610051321g68d43bc3g2f3c2ebde345b65@mail.gmail.com> <64703218-13F4-4A3F-9645-EA6F50668806@goebel.ws> Message-ID: <4527E3D6.2060702@veradox.com> > I too would like to have done a more "people with similar tastes" > style ratings projection, but the data set of ~100 million ratings > using 480,000 unique customer id's... doesn't lend itself very well to > that approach. > > That and I somehow doubt that the people at Netflix are incompetent. > I.e., they say that there are a lot of approaches that they aren't > using. But that doesn't mean that they haven't explored and rejected > those routes. > > Myself, I've dumped the training set data into a database. And am > trying to figure out the right questions to ask... > > I do think someone will get the $50,000 progress prize. But I also > doubt that it'll be me. I expect a team strong in mathematics and > statistics will find a way to finesse small improvements on Cinematch. > Enough to justify the progress bounty. > > I wish there was more documentation on the approach Cinematch takes > and the alternative approaches. The progress bounty might be had by > anyone who stumbles upon a better balance of approaches, but I doubt > anyone will manage the million dollar prize without a novel approach. > > cheers, > > Garrett On Cinematch's approach: *Technology Review:* Before building a better recommendation system, it would be useful to understand your current approach. How does Cinematch work? *Jim Bennett:* First, you collect 100 million user ratings for about 18,000 movies. Take any two movies and find the people who have rated both of them. Then look to see if the people who rate one of the movies highly rate the other one highly, if they liked one and not the other, or if they didn't like either movie. Based on their ratings, Cinematch sees whether there's a correlation between those people. Now, do this for all possible pairs of 65,000 movies. from http://www.technologyreview.com/read_article.aspx?id=17587&ch=biztech I have a bundle of 30ish PDFs that thoroughly describe all publicly known alternative approaches. It's taken me about 10 hours with Google Scholar to get them all. Ask me for it offlist if you'd like a .zip of them. -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/x-pkcs7-signature Size: 2852 bytes Desc: S/MIME Cryptographic Signature Url : http://mail.pm.org/pipermail/kc/attachments/20061007/fb8bdf8a/attachment.bin From matthew at veradox.com Sun Oct 8 15:54:02 2006 From: matthew at veradox.com (Matthew Wilson) Date: Sun, 08 Oct 2006 17:54:02 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: <64703218-13F4-4A3F-9645-EA6F50668806@goebel.ws> References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> <934f64a20610051321g68d43bc3g2f3c2ebde345b65@mail.gmail.com> <64703218-13F4-4A3F-9645-EA6F50668806@goebel.ws> Message-ID: <4529818A.6030808@veradox.com> > I wish there was more documentation on the approach Cinematch takes > and the alternative approaches. The progress bounty might be had by > anyone who stumbles upon a better balance of approaches, but I doubt > anyone will manage the million dollar prize without a novel approach. More on the method Cinematch might use... http://appft1.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&u=%2Fnetahtml%2FPTO%2Fsearch-adv.html&r=1&p=1&f=G&l=50&d=PG01&S1=20050125307&OS=20050125307&RS=20050125307 -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/x-pkcs7-signature Size: 2852 bytes Desc: S/MIME Cryptographic Signature Url : http://mail.pm.org/pipermail/kc/attachments/20061008/3fd5f975/attachment.bin From ggoebel at goebel.ws Sun Oct 8 18:40:04 2006 From: ggoebel at goebel.ws (Garrett Goebel) Date: Sun, 8 Oct 2006 20:40:04 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: <4529818A.6030808@veradox.com> References: <4722ED96-F200-48E7-AA93-2E65C50DAFC6@goebel.ws> <934f64a20610051213w542e61bbw13d933af3a71d573@mail.gmail.com> <934f64a20610051321g68d43bc3g2f3c2ebde345b65@mail.gmail.com> <64703218-13F4-4A3F-9645-EA6F50668806@goebel.ws> <4529818A.6030808@veradox.com> Message-ID: <55299273-2E6C-49A1-8B6E-6F2C816FC649@goebel.ws> Hmm... Didn't Linus Torvalds make a good argument that software developers shouldn't read patents, because then they can't be guilty of knowingly violating them? On Oct 8, 2006, at 5:54 PM, Matthew Wilson wrote: > >> I wish there was more documentation on the approach Cinematch >> takes and the alternative approaches. The progress bounty might be >> had by anyone who stumbles upon a better balance of approaches, >> but I doubt anyone will manage the million dollar prize without a >> novel approach. > > More on the method Cinematch might use... > > http://appft1.uspto.gov/netacgi/nph-Parser? > Sect1=PTO2&Sect2=HITOFF&u=%2Fnetahtml%2FPTO%2Fsearch- > adv.html&r=1&p=1&f=G&l=50&d=PG01&S1=20050125307&OS=20050125307&RS=2005 > 0125307 > _______________________________________________ > kc mailing list > kc at pm.org > http://mail.pm.org/mailman/listinfo/kc From stephenclouse at gmail.com Sun Oct 8 21:13:34 2006 From: stephenclouse at gmail.com (Stephen Clouse) Date: Sun, 8 Oct 2006 23:13:34 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: References: Message-ID: <5d0ee2170610082113v5eaf9da7s722a2a93cca70ba2@mail.gmail.com> Sadly, I will have to skip this month's meeting. I've got four out-of-town visitors colliding here tomorrow night. -- Stephen Clouse -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.pm.org/pipermail/kc/attachments/20061008/58fd7c7a/attachment.html From davidnicol at gmail.com Mon Oct 9 23:27:27 2006 From: davidnicol at gmail.com (David Nicol) Date: Tue, 10 Oct 2006 01:27:27 -0500 Subject: [Kc] draft bylaws of Kansas City netflixprize team Message-ID: <934f64a20610092327u503b03f2xa321fb94a8cb93b9@mail.gmail.com> On 10/7/06, Matthew Wilson wrote: > It's taken me about 10 hours Dave's Proposal: * the Kansas City netflixprize (NFP) team will be abbreviated to KCNFPT * KCNFPT is a cooperative effort to win a progress prize in the NFP contest * in the event of winning a prize, proceeds will be divided by share weight * share weight is a linear function of hours worked for KCNFPT, so that the sum of all participant's share weights is 1 * hours worked are cumulative and nonrevocable * to add submitted hours worked to your total they must be approved by holders of over half of the share weight before your submission, i.e. hours approval motions require 50% share weight to carry * you're not allowed to work more than 30 hours a week on KCNFPT unless you're currently unemployed, in which case you may work up to 60 hours a week on it * hours are submitted weekly through the KCNFPT hours submission mechanism, which will probably be a web interface by Dave but might just be the mailing list * that's the KCNFPT mailing list, which has not been set up yet * on joining KCNFPT, a new participant must declare how many hours they've put into their work on the NFP before joining, and that becomes their initial hours tally * people who leave the team are not eligible for a share, but leaving the team can be blocked by a 10% share * joining and leaving motions require a 90% approval by share weight to carry * amending these bylaws, which are the contract under which the team operates as a team,requires full consensus without abstention (although a 90% majority can kick the blocks out to achieve that) subject to debate: * participants may leave KCNFPT, but if they leave they may not use methods developed within the KCNFPT process in their own NFP submissions or in the NFP submissions of other teams; it is expected that multiple NFP teams may be used to allow submission of results for scoring more often than would otherwise be allowed, and if any team including participating kcnfpt members wins, it will be as if kcnfpt had won * there will be a non-disclosure agreement to prevent leaking of team-proprietary methods before the contest is over (or we give up) *********************** Executive summary: The team will attempt to support Matthew Wilson, and possibly other capable and motivated heros who may appear, by discussing direction and strategy and by spiking possibile improvements. Time invested in the team equals weight of your share in the event we win something. Even without winning, the collaborative experience will be worthwhile as an example of a collaborative experience if nothing else. The potential upside beyond the contest at hand is the forming of an execution-capable software engineering team who are willing and able to work for deferred reward, who may then seek future projects with greater expected reward/effort ratios. From matthew at veradox.com Tue Oct 10 00:07:28 2006 From: matthew at veradox.com (Matthew Wilson) Date: Tue, 10 Oct 2006 08:07:28 +0100 Subject: [Kc] draft bylaws of Kansas City netflixprize team In-Reply-To: <934f64a20610092327u503b03f2xa321fb94a8cb93b9@mail.gmail.com> References: <934f64a20610092327u503b03f2xa321fb94a8cb93b9@mail.gmail.com> Message-ID: Well put. You must be in B-school or something. Looking forward to the meeting tonight, especially since I've never been in a bar. The place we're meeting after Planet Sub is a bar, right? Even without winning, the collaborative experience will be worthwhile as an example of a collaborative experience if nothing else. The potential upside beyond the contest at hand is the forming of an execution-capable software engineering team who are willing and able to work for deferred reward, who may then seek future projects with greater expected reward/effort ratios. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.pm.org/pipermail/kc/attachments/20061010/5286de0c/attachment.html From matthew at veradox.com Tue Oct 10 00:16:44 2006 From: matthew at veradox.com (Matthew Wilson) Date: Tue, 10 Oct 2006 08:16:44 +0100 Subject: [Kc] draft bylaws of Kansas City netflixprize team In-Reply-To: References: <934f64a20610092327u503b03f2xa321fb94a8cb93b9@mail.gmail.com> Message-ID: Where is the Chubby's at which we're meeting, anyway? -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.pm.org/pipermail/kc/attachments/20061010/5f86c64a/attachment.html From djgoku at gmail.com Tue Oct 10 12:55:04 2006 From: djgoku at gmail.com (djgoku) Date: Tue, 10 Oct 2006 14:55:04 -0500 Subject: [Kc] meeting Tuesday Oct 10 2006 In-Reply-To: References: Message-ID: <99dd19c90610101255n10124d69u5c4a73d92cbede@mail.gmail.com> On 10/4/06, Matthew Wilson wrote: > > Unless someone else comes up with another topic, I would like to discuss > (preferably exclusively) the Netflix Prize. 3 of the 4 code snippets posted > so far on the forums are in perl. The other is in ruby. I wish I had time to go to this, but I have a research paper due on Friday. jonathan From ggoebel at goebel.ws Tue Oct 10 19:56:12 2006 From: ggoebel at goebel.ws (Garrett Goebel) Date: Tue, 10 Oct 2006 21:56:12 -0500 Subject: [Kc] Fwd: NetPrize: Apophenia statistical libarary References: <60AEB60B-B9F3-40C9-B04F-F7E6C38CCCD2@goebel.ws> Message-ID: > For those interested in the NetFlix NetPrize... > > http://apophenia.sourceforge.net/ > > is an open source statistical library based on GSL (Gnu Scientific > Library) and SQLite... > From djgoku at gmail.com Tue Oct 10 20:45:32 2006 From: djgoku at gmail.com (djgoku) Date: Tue, 10 Oct 2006 22:45:32 -0500 Subject: [Kc] draft bylaws of Kansas City netflixprize team In-Reply-To: References: <934f64a20610092327u503b03f2xa321fb94a8cb93b9@mail.gmail.com> Message-ID: <99dd19c90610102045v4627ab6fpac228c521cc95782@mail.gmail.com> On 10/10/06, Matthew Wilson wrote: > > Where is the Chubby's at which we're meeting, anyway? I went to Chubby's on Broadway til about 10:15PM not sure this is the correct place, but didn't see any KCPMers their. google maps link? From djgoku at gmail.com Thu Oct 12 13:28:50 2006 From: djgoku at gmail.com (djgoku) Date: Thu, 12 Oct 2006 15:28:50 -0500 Subject: [Kc] KCPM IRC Channel In-Reply-To: <20060712182058.GA25701@mooresystems.com> References: <99dd19c90607121115n236f4fe7u393315c0c30b18ab@mail.gmail.com> <20060712182058.GA25701@mooresystems.com> Message-ID: <99dd19c90610121328g43e0ea23jb4fe09c1d0b64cd4@mail.gmail.com> On 7/12/06, Andrew Moore wrote: > On Wed, Jul 12, 2006 at 01:15:09PM -0500, djgoku wrote: > > Would there be any interest of having a #KCPM IRC channel? > > I occasionally lurk on #perl on irc.perl.org. I'd open a window in > #kcpm on that network or something like that if there were anyone else > there. Reading the FAQ for irc.perl.org they don't have nick/chan serv protection. So I have created/registered a #KCPM channel on irc.freenode.org. jonathan From matthew at veradox.com Thu Oct 12 08:25:44 2006 From: matthew at veradox.com (Matthew Wilson) Date: Thu, 12 Oct 2006 16:25:44 +0100 Subject: [Kc] KCPM IRC Channel In-Reply-To: <99dd19c90610121328g43e0ea23jb4fe09c1d0b64cd4@mail.gmail.com> References: <99dd19c90607121115n236f4fe7u393315c0c30b18ab@mail.gmail.com> <20060712182058.GA25701@mooresystems.com> <99dd19c90610121328g43e0ea23jb4fe09c1d0b64cd4@mail.gmail.com> Message-ID: My work's proxy won't let me tunnel irc through it, unless I ssh out through it to another machine first, which I'm not supposed to do. Does anyone know of an ajax IRC client/webapp? -----Original Message----- From: djgoku To: kcpm Date: Thu, 12 Oct 2006 15:28:50 -0500 Subject: Re: [Kc] KCPM IRC Channel On 7/12/06, Andrew Moore wrote: > On Wed, Jul 12, 2006 at 01:15:09PM -0500, djgoku wrote: > > Would there be any interest of having a #KCPM IRC channel? > > I occasionally lurk on #perl on irc.perl.org. I'd open a window in > #kcpm on that network or something like that if there were anyone else > there. Reading the FAQ for irc.perl.org they don't have nick/chan serv protection. So I have created/registered a #KCPM channel on irc.freenode.org. jonathan _______________________________________________ kc mailing list kc at pm.org http://mail.pm.org/mailman/listinfo/kc [http://mail.pm.org/mailman/listinfo/kc] -------------- next part -------------- An HTML attachment was scrubbed... URL: http://mail.pm.org/pipermail/kc/attachments/20061012/b5ded0e2/attachment.html From djgoku at gmail.com Thu Oct 12 14:49:06 2006 From: djgoku at gmail.com (djgoku) Date: Thu, 12 Oct 2006 16:49:06 -0500 Subject: [Kc] KCPM IRC Channel In-Reply-To: References: <99dd19c90607121115n236f4fe7u393315c0c30b18ab@mail.gmail.com> <20060712182058.GA25701@mooresystems.com> <99dd19c90610121328g43e0ea23jb4fe09c1d0b64cd4@mail.gmail.com> Message-ID: <99dd19c90610121449s6cdcd665i3a3e11dec6b3ee06@mail.gmail.com> On 10/12/06, Matthew Wilson wrote: > > > My work's proxy won't let me tunnel irc through it, unless I ssh out through > it to another machine first, which I'm not supposed to do. Does anyone know > of an ajax IRC client/webapp? You could find a CGI IRC client. Would anyone think it is worth to have a http://kcpm.org.