RE: [igraph] dendrograms from communities

[Glazko, Galina V]

Dear Gabor,

thank you! now I see.
Is there an implementation of Hierarchical Random Graph
fitting procedures in iGraph?

best regards
Galina

________________________________________
From: address@hidden address@hidden On Behalf Of Gábor Csárdi address@hidden
Sent: Tuesday, March 08, 2011 2:56 PM
To: Help for igraph users
Cc: Glazko, Galina V
Subject: Re: [igraph] dendrograms from communities

Dear Galina,

On Tue, Mar 8, 2011 at 3:31 PM, Glazko, Galina V <address@hidden> wrote:
> Dear friends,
>
>
>
> I have two simple questions about the construction of the dendrograms from
> communities:
>
>
>
> 1.       What is the algorithm for tree inference in this case, could
> someone refer me to the original publication?

I am not sure what you mean by "inference" here, this word has a well
defined meaning in statistics, but probably you mean just extracting
the tree from the results of the community detection functions. So
there is no inference here, not in the statistical sense.

A nice paper that really does inference is this, in case you are interested:
http://www.nature.com/nature/journal/v453/n7191/abs/nature06830.html

> 2.       Is it possible to infer a tree structure from communities, found
> with the algorithm fastgreedy.community?

In any case, the community structure detection algorithms in igraph
belong to two groups. Some explicitly detect a tree structure
(fast-greedy, walktrap), others (e.g. spinglass) don't. For the ones
that do,

For walktrap, just call as.dendrogram on the results. For fast-greedy, see:
http://lists.gnu.org/archive/html/igraph-help/2010-11/msg00060.html

Best Regards,
Gabor

>
>
> I would appreciate your help
>
> Thank you!
>
> Best regards
>
> Galina
>
> Confidentiality Notice: This e-mail message, including any attachments,
> is for the sole use of the intended recipient(s) and may contain
> confidential and privileged information.  Any unauthorized review,
> use, disclosure or distribution is prohibited.  If you are not the
> intended recipient, please contact the sender by reply
> e-mail and destroy all copies of the original message..
> _______________________________________________
> igraph-help mailing list
> address@hidden
> http://lists.nongnu.org/mailman/listinfo/igraph-help
>
>



--
Gabor Csardi <address@hidden>     UNIL DGM
Confidentiality Notice: This e-mail message, including any attachments,
is for the sole use of the intended recipient(s) and may contain
confidential and privileged information.  Any unauthorized review,
use, disclosure or distribution is prohibited.  If you are not the 
intended recipient, please contact the sender by reply
e-mail and destroy all copies of the original message..