From: zhihua li <lzhtom_at_hotmail.com>

Date: Sat 26 Mar 2005 - 17:23:04 EST

R-help@stat.math.ethz.ch mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Sat Mar 26 17:27:18 2005

Date: Sat 26 Mar 2005 - 17:23:04 EST

I didn't go into details when I asked the question for feat that I would
overly specific and blur my real goals.
The links between variables are defined as conditional probability
distributions. So if the probability distribution of a variable X's value
is conditioned on the probability distribution of the values of Y and Z, we
say Y and Z are X's parents, and in the network, there are two arrows
starting from Y and Z and poining both to X.
Clearly it's something like a bayesian network. And I do know some
packages, such as deal, can learn the bayesian networks structure from
training data. But I'm not sure if deal or other similar packages can
handle 10000 variables......

Thanks a lot for your information.

*>From: "Shelby Berkowitz" <berkowi4@msu.edu>
*

>To: "'zhihua li'" <lzhtom@hotmail.com>

*>Subject: RE: [R] learning networks with a large number of variables
*

andpre-set parents.

*>Date: Fri, 25 Mar 2005 10:00:17 -0500
**>
**>It's not really clear to me what it is you're trying to do, how you've
**>defined links between these variables, or how you're defining 'highest
**>scoring network', but for manipulating a network of that size you might
**>want to check out Pajek http://vlado.fmf.uni-lj.si/pub/networks/pajek/
**>network analysis software - there is probably a way from there to
**>extract the network you want, and you can export from it back into R for
*

>further analysis.

*>
**>HTH,
**>
**>Shelby
**>
**> >-----Original Message-----
**> >From: r-help-bounces@stat.math.ethz.ch
**> >[mailto:r-help-bounces@stat.math.ethz.ch] On Behalf Of Achim Zeileis
**> >Sent: Friday, March 25, 2005 5:41 AM
**> >To: zhihua li
**> >Cc: r-help@stat.math.ethz.ch
**> >Subject: Re: [R] learning networks with a large number of
**> >variables andpre-set parents.
**> >
**> >
**> >This is the second time within 24 hours that you cross-posted
**> >the same question to two of the R mailing lists, please read
**> >the posting guide linked at the bottom of this mail on how to
**> >properly ask your questions.
**> >
**> >As for your question: I'm not aware of an R package that would
**> >be able to do what you are looking for, but you might also ask
**> >the maintainer of the package you're specifically interested
**> >in for more details. Z
**> >
**> >
**> >
**> >On Fri, 25 Mar 2005, zhihua li wrote:
**> >
**> >> hi netters:
**> >>
**> >> I have a series of discrete variables which form a network and I
**> >> want to learn the network structure from some training data. I could
**> >> have used packages like deal but there are two problems.
**> >>
**> >> First of all, I have 10000 variables. So the possible network
**> >> structure is awfully huge, I don't know how long it will
**> >take my PC to
**> >> find the highest-scoring network..........maybe a month? Secondly, I
**> >> have some prior knowledge that only 500 out of the 10000
**> >variales are
**> >> possible parents. In another word, only those arrows startting from
**> >> the 500 variables and pointing to the remaining 99500 variables are
**> >> allowed in the network. In deal an assignment to "banlist" should
**> >> help me rule out the impossible arrows. But in my case the number of
**> >> "impossible arrows" is 500*499+99500*99549, and so the "banlist"
**> >> would get unacceptable long. Are there any methods (in deal or other
**> >> packages) to specify the parents set in advance?
**> >>
**> >> Thanks a lot!
**> >>
**> >> ______________________________________________
**> >> R-help@stat.math.ethz.ch mailing list
**> >> https://stat.ethz.ch/mailman/listinfo/r-help
**> >> PLEASE do read the posting guide!
**> >> http://www.R-project.org/posting-guide.html
**> >>
**> >
**> >______________________________________________
**> >R-help@stat.math.ethz.ch mailing list
**> >https://stat.ethz.ch/mailman/listinfo/r-help
**> >PLEASE do read
**> >the posting guide! http://www.R-project.org/posting-guide.html
**> >
**> >--
**> >No virus found in this incoming message.
**> >Checked by AVG Anti-Virus.
**> >Version: 7.0.308 / Virus Database: 266.8.1 - Release Date: 3/23/2005
**> >
**> >
**>
*

R-help@stat.math.ethz.ch mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Sat Mar 26 17:27:18 2005

*
This archive was generated by hypermail 2.1.8
: Fri 03 Mar 2006 - 03:30:56 EST
*