Re: Problem reading a graph file

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Re: Problem reading a graph file

Marc Marí Dell'Olmo-2
I obtain this message:


Error: C stack usage is too close to the limit



Marc Marí-Dell'Olmo
CIBER Epidemiología y Salud Pública
Servei de Sistemes d'Informació Sanitària (SeSIS)
Agència de Salut Pública de Barcelona
Pl. Lesseps 1. 08023 Barcelona
Tel. 93 2027775 | Fax. 93 3686943
www.aspb.cat


El 15 de marzo de 2012 13:35, Marc Marí Dell'Olmo <[hidden email]> escribió:

> I am analysing a lot of cities, and with the testing version I have the
> problem that INLA not works for some of them. I think that cities that do
> not work are those with a lot of areas and, therefore, with big graph
> files. For example I am working with cities with more than 3000 areas... is
> it possible??
>
> Marc Marí-Dell'Olmo
> CIBER Epidemiología y Salud Pública
> Servei de Sistemes d'Informació Sanitària (SeSIS)
> Agència de Salut Pública de Barcelona
> Pl. Lesseps 1. 08023 Barcelona
> Tel. 93 2027775 | Fax. 93 3686943
> www.aspb.cat
>
>
> El 15 de marzo de 2012 13:24, help help <[hidden email]> escribió:
>
> It's fixed in the testing version
>> On Mar 15, 2012 1:23 PM, "Marc Marí Dell&apos;Olmo" <[hidden email]>
>> wrote:
>>
>>> Hello!
>>>
>>> I have a simple problem. I am using the R version 2.14.1 with the last
>>> stable version of INLA (not the testing version) and windows 7 with 64bits.
>>> Today I have rerunned some BYM models with the last version of INLA and I
>>> have obtained errors. These models had already run with previous
>>> versions of INLA (and previous versions of R) and I had not received any
>>> errors.
>>>
>>> I have tried to find the problem and I think that now the graph file is
>>> not being read correctly. My graph has no disconnected components but
>>> INLA thinks that I have 3 disconnected components. Have you changed the format
>>> through which the neighbourhood matrix is specified?
>>>
>>> I attach my graph file in order you can check this problem.
>>>
>>> > aux <- inla.read.graph("W:/bratislava.inla")
>>> > summary(aux)
>>>         n =  17
>>>         ncc =  3
>>>         nnbs = (names)  2 3 4 5 6 7
>>>                (count)  2 4 5 2 2 2
>>>
>>>
>>> ___
>>> this summary shoud be:
>>>      n =  17
>>>         ncc =  1
>>>         nbs = (names)  2 3 4 5 6 7
>>>               (count)  2 4 5 2 2 2
>>>
>>>
>>>
>>> Thank you very much!
>>>
>>> Marc Marí-Dell'Olmo
>>> CIBER Epidemiología y Salud Pública
>>> Servei de Sistemes d'Informació Sanitària (SeSIS)
>>> Agència de Salut Pública de Barcelona
>>> Pl. Lesseps 1. 08023 Barcelona
>>> Tel. 93 2027775 | Fax. 93 3686943
>>> www.aspb.cat
>>>
>>
>
        [[alternative HTML version deleted]]


______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Problem reading a graph file

Uwe Ligges-3


On 15.03.2012 13:47, Marc Marí Dell'Olmo wrote:
> I obtain this message:
>
>
> Error: C stack usage is too close to the limit

Using the function inla.read.graph?
Then please ask the corresponding package maintainer.

Uwe Ligges

>
>
> Marc Marí-Dell'Olmo
> CIBER Epidemiología y Salud Pública
> Servei de Sistemes d'Informació Sanitària (SeSIS)
> Agència de Salut Pública de Barcelona
> Pl. Lesseps 1. 08023 Barcelona
> Tel. 93 2027775 | Fax. 93 3686943
> www.aspb.cat
>
>
> El 15 de marzo de 2012 13:35, Marc Marí Dell'Olmo<[hidden email]>  escribió:
>
>> I am analysing a lot of cities, and with the testing version I have the
>> problem that INLA not works for some of them. I think that cities that do
>> not work are those with a lot of areas and, therefore, with big graph
>> files. For example I am working with cities with more than 3000 areas... is
>> it possible??
>>
>> Marc Marí-Dell'Olmo
>> CIBER Epidemiología y Salud Pública
>> Servei de Sistemes d'Informació Sanitària (SeSIS)
>> Agència de Salut Pública de Barcelona
>> Pl. Lesseps 1. 08023 Barcelona
>> Tel. 93 2027775 | Fax. 93 3686943
>> www.aspb.cat
>>
>>
>> El 15 de marzo de 2012 13:24, help help<[hidden email]>  escribió:
>>
>> It's fixed in the testing version
>>> On Mar 15, 2012 1:23 PM, "Marc Marí Dell&apos;Olmo"<[hidden email]>
>>> wrote:
>>>
>>>> Hello!
>>>>
>>>> I have a simple problem. I am using the R version 2.14.1 with the last
>>>> stable version of INLA (not the testing version) and windows 7 with 64bits.
>>>> Today I have rerunned some BYM models with the last version of INLA and I
>>>> have obtained errors. These models had already run with previous
>>>> versions of INLA (and previous versions of R) and I had not received any
>>>> errors.
>>>>
>>>> I have tried to find the problem and I think that now the graph file is
>>>> not being read correctly. My graph has no disconnected components but
>>>> INLA thinks that I have 3 disconnected components. Have you changed the format
>>>> through which the neighbourhood matrix is specified?
>>>>
>>>> I attach my graph file in order you can check this problem.
>>>>
>>>>> aux<- inla.read.graph("W:/bratislava.inla")
>>>>> summary(aux)
>>>>          n =  17
>>>>          ncc =  3
>>>>          nnbs = (names)  2 3 4 5 6 7
>>>>                 (count)  2 4 5 2 2 2
>>>>
>>>>
>>>> ___
>>>> this summary shoud be:
>>>>       n =  17
>>>>          ncc =  1
>>>>          nbs = (names)  2 3 4 5 6 7
>>>>                (count)  2 4 5 2 2 2
>>>>
>>>>
>>>>
>>>> Thank you very much!
>>>>
>>>> Marc Marí-Dell'Olmo
>>>> CIBER Epidemiología y Salud Pública
>>>> Servei de Sistemes d'Informació Sanitària (SeSIS)
>>>> Agència de Salut Pública de Barcelona
>>>> Pl. Lesseps 1. 08023 Barcelona
>>>> Tel. 93 2027775 | Fax. 93 3686943
>>>> www.aspb.cat
>>>>
>>>
>>
>
> [[alternative HTML version deleted]]
>
>
>
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.