[Biomod-commits] Projection.raster ERROR

[Wilfried Thuiller]

Dear Pep,

Are sure to be in the right working directory? Sounds like the function does not find the models. I guess that if you run the Projection function, let's say on the original data (Sp.Env[,c("BIO1","BIO12","BIO14","BIO5","BIO6")]), this is not going to work either. Right? 
For instance, there is something wrong. In the WARNING message, it looks for repetition 4 whereas you only set up 3 evaluation (NbRunEval = 3). This is why I suspect a mix of data/workspace. 

Have you tried to plot the rasters? 

plot(Proj_CurrentRaster_QUWI_BinTSS_PA1_ANN.raster)

I'll suggest to create a new working directory, set the working directory with R (setwd()) and then re-run everything. Let me know if this is working better. 

Cheers,

Wilfried



Le 9 mars 2011 à 02:31, PEP Serra Diaz a écrit :

> 
> Dear BIOMODers,
> 
> It may be a stupid question. First time I am seriously running Projection.raster function. I get this error :
> 
> WARNING: Could not find data for model ANN evaluation repetition 1 . Probable cause : failure when running Models() 
> WARNING: Could not find data for model ANN evaluation repetition 2 . Probable cause : failure when running Models() 
> WARNING: Could not find data for model ANN evaluation repetition 3 . Probable cause : failure when running Models() 
> WARNING: Could not find data for model ANN evaluation repetition 4 . Probable cause : failure when running Models() 
> WARNING: Could not find data for model ANN evaluation repetition 1 . Probable cause : failure when running Models() 
> WARNING: Could not find data for model ANN evaluation repetition 2 . Probable cause : failure when running Models() 
> WARNING: Could not find data for model ANN evaluation repetition 3 . Probable cause : failure when running Models() 
> WARNING: Could not find data for model ANN evaluation repetition 4 . Probable cause : failure when running Models() 
> .....
> and so on for all models
> ...
> 
> RESULT: It creates projections full of NAs
> 
> 
> I run the Models function as I normally do. I checked evaluation results and different models and their outputs after running Models(). Everything seems to work ok but projection. Here it is the whole R history:
> 
> 
> Initial.State(Response=Sp.Env[,i], Explanatory=Sp.Env[,c("BIO1","BIO12","BIO14","BIO5","BIO6")], IndependentResponse=NULL, IndependentExplanatory=NULL, sp.name=naam[sp])
> 
> Models(GLM = T, TypeGLM = "quad", Test = "AIC", GBM = T, No.trees = 3000, GAM = T, CTA = T, CV.tree = 50, ANN = T, CV.ann = 2, SRE = F, FDA = T, MARS = T, RF = T, NbRunEval = 3, DataSplit = 70, Yweights=NULL, Roc=T, Optimized.Threshold.Roc=T, Kappa=T, TSS=T, KeepPredIndependent = F, VarImport=T, NbRepPA=3, strategy="random", nb.absences=5000)
> 
> 
> Projection.raster(RasterProj = CurrentStack, Proj.name='CurrentRaster', GLM = T, GBM = T, GAM = T, CTA = T, ANN = T, SRE = F, FDA=T, MARS = T, RF = T, BinRoc = F, BinKappa = F, BinTSS = T, FiltRoc = F, FiltKappa = F, FiltTSS = F, repetition.models=T, stack.out=F)
> 
> 
>> ls()
> [1] "Biomod.material"                               "Biomod.PA.data"                               
> [3] "Biomod.PA.sample"                              "CurrentBio1"                                  
> [5] "CurrentBio12"                                  "CurrentBio14"                                 
> [7] "CurrentBio5"                                   "CurrentBio6"                                  
> [9] "CurrentStack"                                  "DataBIOMOD"                                   
> [11] "Evaluation.results.Kappa"                      "Evaluation.results.Roc"                       
> [13] "Evaluation.results.TSS"                        "GBM.list"                                     
> [15] "GBM.perf"                                      "isnullYweights"                               
> [17] "naam"                                          "path"                                         
> [19] "Proj_CurrentRaster_QUWI_BinTSS_PA1_ANN.raster" "root"                                         
> [21] "Sp.Env"                                        "sp.name"                                      
> [23] "VarImportance"                                
> 
> 
> 
> 
> 
> 
> 
> 
> Pep Serra Díaz
> 
> Despatx C1/211
> Unitat de Botànica.
> Departament de Biologia Animal, Biologia Vegetal i Ecologia.
> Facultat de Biociències. Edifici C. Campus de Bellaterra
> Universitat Autònoma de Barcelona
> 08193 Cerdanyola del Vallès
> Spain
> 
> 
> _______________________________________________
> Biomod-commits mailing list
> Biomod-commits at lists.r-forge.r-project.org
> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits

--------------------------
Dr. Wilfried Thuiller
Laboratoire d'Ecologie Alpine, UMR CNRS 5553
Université Joseph Fourier
BP53, 38041 Grenoble cedex 9, France
tel: +33 (0)4 76 51 44 97
fax: +33 (0)4 76 51 42 79

Email: wilfried.thuiller at ujf-grenoble.fr
Personal website: http://www.will.chez-alice.fr
Team website: http://www-leca.ujf-grenoble.fr/equipes/emabio.htm

FP6 European MACIS project: http://www.macis-project.net
FP6 European EcoChange project: http://www.ecochange-project.eu






-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/biomod-commits/attachments/20110309/37a97d9d/attachment.htm>