[R-sig-Geo] data.frame methods for maxlike and maxent

[Tim Howard]

You can create the model using data contained in a data.frame but then -- because you are creating a species distribution model - you still need the raster stack to actually run the prediction and make the map representing the model. And your raster stack still needs to have those environmental variables, even if you are dealing with seasonal data and time is another factor. Perhaps I'm not understanding your scenario. 

At any rate, the SDM vignette that comes with dismo shows you how to use randomPoints to extract the values from a raster stack to a data.frame, which you then can use to create your model. (page 26 in here: http://cran.r-project.org/web/packages/dismo/vignettes/sdm.pdf ).  Is that what you are asking?

Tim
 
----------
Date: Thu, 08 Aug 2013 20:11:22 +1000
From: Gerardo Martin <gerardommc at gmail.com>
To: r-sig-geo at r-project.org 
Subject: [R-sig-Geo] data.frame methods for maxlike and maxent
Message-ID: <52036ECA.6010200 at gmail.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

Hi all. I'm trying to implement some species distribution models with my 
data sets. Because of the nature of the organisms i'm working with I 
need specifically to fit models with data contained in a data.frame 
instead of providing the x,y locations to be sampled from a rasterStack.
Firstly i've found one way of doing it with dismo's maxent 
implementation, by providing a vector with 1's ans 0's, 0 values 
correspond to values extracted with randomPonints. However, I haven't 
found a way of providing the data.fame as background data, instead of 
pseudoabsences as described.
Secondly, I also want to fit a maxlike model, but haven't found if 
there's a data.frame method. Like I said, I can't do it with the 
traditional rasterStack method, because the information to fit the model 
is seasonal.

Any help is really appreciated.

Regards

Gerardo



_______________________________________________
R-sig-Geo mailing list
R-sig-Geo at r-project.org 
https://stat.ethz.ch/mailman/listinfo/r-sig-geo 


End of R-sig-Geo Digest, Vol 120, Issue 8