Spatial clusters with equal number of objects (2)

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

Spatial clusters with equal number of objects (2)

maurizio
Hello everybody,
is there an easy way to cluster spatial objects (polygons in my case, a
grid of 500mx500m cells) with an equal number of objects per cluster?
I tried to attach an example of what I mean but I think the message was
never delivered.
Regards

--
Maurizio Marchi
Skype ID: maurizioxyz
linux user 552742

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
Reply | Threaded
Open this post in threaded view
|

Re: Spatial clusters with equal number of objects (2)

Marcelino de la Cruz Rot
Hello Maurizio,

If they are cells in a grid, they are already as much clustered as they
could be ;-p.

Please, be more specific.

Cheers,

Marcelino


El 31/10/2017 a las 11:57, Maurizio Marchi escribió:
> Hello everybody,
> is there an easy way to cluster spatial objects (polygons in my case, a
> grid of 500mx500m cells) with an equal number of objects per cluster?
> I tried to attach an example of what I mean but I think the message was
> never delivered.
> Regards
>

--
Marcelino de la Cruz Rot
Depto. de Biología y Geología
Física y Química Inorgánica
Universidad Rey Juan Carlos
Móstoles España

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
Reply | Threaded
Open this post in threaded view
|

Re: Spatial clusters with equal number of objects (2)

Tim Keitt-3
In reply to this post by maurizio
http://www.keittlab.org/

On Tue, Oct 31, 2017 at 5:57 AM, Maurizio Marchi <[hidden email]
> wrote:

> Hello everybody,
> is there an easy way to cluster spatial objects (polygons in my case, a
> grid of 500mx500m cells) with an equal number of objects per cluster?
>

If you mean maximally compact clusters, that is proven NP complexity, so
you would have to resort to heuristic search or greedy approximations. One
approach is to place points sequentially up to n with each point maximally
distant from all previous points then assign nearest neighbors.

I wonder if igraph has something that would suit the problem?

THK

I tried to attach an example of what I mean but I think the message was

> never delivered.
> Regards
>
> --
> Maurizio Marchi
> Skype ID: maurizioxyz
> linux user 552742
>
>         [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> [hidden email]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
Reply | Threaded
Open this post in threaded view
|

Re: Spatial clusters with equal number of objects (2)

Levi John Wolf
ClustGeo <https://arxiv.org/pdf/1707.03897.pdf> may be of interest, but
most things I've seen in this space are in Python, like Clusterpy & the
Python Spatial Analysis Library's MaxP algorithm.

You can call it from R using reticulated.

On Tue, Oct 31, 2017 at 7:18 PM Tim Keitt <[hidden email]> wrote:

> http://www.keittlab.org/
>
> On Tue, Oct 31, 2017 at 5:57 AM, Maurizio Marchi <
> [hidden email]
> > wrote:
>
> > Hello everybody,
> > is there an easy way to cluster spatial objects (polygons in my case, a
> > grid of 500mx500m cells) with an equal number of objects per cluster?
> >
>
> If you mean maximally compact clusters, that is proven NP complexity, so
> you would have to resort to heuristic search or greedy approximations. One
> approach is to place points sequentially up to n with each point maximally
> distant from all previous points then assign nearest neighbors.
>
> I wonder if igraph has something that would suit the problem?
>
> THK
>
> I tried to attach an example of what I mean but I think the message was
> > never delivered.
> > Regards
> >
> > --
> > Maurizio Marchi
> > Skype ID: maurizioxyz
> > linux user 552742
> >
> >         [[alternative HTML version deleted]]
> >
> > _______________________________________________
> > R-sig-Geo mailing list
> > [hidden email]
> > https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> >
>
>         [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> [hidden email]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>
--
Levi John Wolf
Lecturer in Quantitatve Human Geography | University of Bristol
Associate Member | Center for Multilevel Modeling, University of Bristol
Visiting Fellow | Center for Spatial Data Science, University of Chicago
ljwolf.org

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
Reply | Threaded
Open this post in threaded view
|

Re: Spatial clusters with equal number of objects (2)

maurizio
Thanks, I'll check it out!

On Tue, 31 Oct 2017 at 21:49, Levi John Wolf <[hidden email]>
wrote:

> ClustGeo <https://arxiv.org/pdf/1707.03897.pdf> may be of interest, but
> most things I've seen in this space are in Python, like Clusterpy & the
> Python Spatial Analysis Library's MaxP algorithm.
>
> You can call it from R using reticulated.
>
> On Tue, Oct 31, 2017 at 7:18 PM Tim Keitt <[hidden email]> wrote:
>
>> http://www.keittlab.org/
>>
>> On Tue, Oct 31, 2017 at 5:57 AM, Maurizio Marchi <
>> [hidden email]
>> > wrote:
>>
>> > Hello everybody,
>> > is there an easy way to cluster spatial objects (polygons in my case, a
>> > grid of 500mx500m cells) with an equal number of objects per cluster?
>> >
>>
>> If you mean maximally compact clusters, that is proven NP complexity, so
>> you would have to resort to heuristic search or greedy approximations. One
>> approach is to place points sequentially up to n with each point maximally
>> distant from all previous points then assign nearest neighbors.
>>
>> I wonder if igraph has something that would suit the problem?
>>
>> THK
>>
>> I tried to attach an example of what I mean but I think the message was
>> > never delivered.
>> > Regards
>> >
>> > --
>> > Maurizio Marchi
>> > Skype ID: maurizioxyz
>> > linux user 552742
>> >
>> >         [[alternative HTML version deleted]]
>> >
>> > _______________________________________________
>> > R-sig-Geo mailing list
>> > [hidden email]
>> > https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>> >
>>
>>         [[alternative HTML version deleted]]
>>
>> _______________________________________________
>> R-sig-Geo mailing list
>> [hidden email]
>> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>>
> --
> Levi John Wolf
> Lecturer in Quantitatve Human Geography | University of Bristol
> Associate Member | Center for Multilevel Modeling, University of Bristol
> Visiting Fellow | Center for Spatial Data Science, University of Chicago
> ljwolf.org
>
--
Maurizio Marchi
Skype ID: maurizioxyz
linux user 552742

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo