[Biomod-commits] error message in running the models

[Wilfried Thuiller]

Dear Emilie,

Thank you for your email. 

First of all, you have 73 variables which is way too much for most of the models included in BIOMOD. Either you make a pre-selection by removing highlightly correlated ones (for instance you can combine your temperature variable by calculating seasonal mean instead of monthly variables which are correlated in time. Same of precip and sdmav. If you can go down to 10-12 variables, it would be enough. OR you only use the techniques that can handle such a high number of variables (random forest, GBM). 

Could you please send me your data (off-list) to see what is going on with your data (the first 100 rows will be sufficient). 
Just a suggestion. Could you switch off ANN to see if the other models work? 

Best
Wilfried


Le 16 févr. 2012 à 23:20, Emilie Roy-Dufresne a écrit :

> confirm 18ee744ad3977b59039ac17e53e4bc7c154780d9 
>  
> Hi!
> I having some issues while trying to run the BioMod script in R. I keep getting this error message while I run the different models provided my BioMod with my data. What does it mean?
> 
> > Models(GLM=T,TypeGLM="poly",Test="AIC",GBM=T,No.trees=2000,GAM=T,Spline=3,CTA=T,CV.tree=50,ANN=T,CV.ann=2,SRE=T,quant=0.025,FDA=T,MARS=T,RF=T,NbRunEval=3,DataSplit=70,Yweights=NULL,Roc=T,Optimized.Threshold.Roc=T,Kappa=T,TSS=T,KeepPredIndependent=T,VarImport=5,NbRepPA=2,strategy="sre",coor=My.Data[,2:3],distance=2,nb.absences=100)
>  
> -----------------------------------
> Modelling summary
> -----------------------------------
> Number of species modelled :          1
> peromyscus
>  
> numerical variables :                 photo01, photo02, photo03, photo04, photo05, photo09, photo10, photo11, photo12, allqcland, recancover, tminavg01, tminavg02, tminavg03, tminavg04, tminavg05, tminavg06, tminavg07, tminavg08, tminavg09, tminavg10, tminavg11, tminavg12, tmaxavg01, tmaxavg02, tmaxavg03, tmaxavg04, tmaxavg05, tmaxavg06, tmaxavg07, tmaxavg08, tmaxavg09, tmaxavg10, tmaxavg11, tmaxavg12, trngavg, precavg01, precavg02, precavg03, precavg04, precavg05, precavg06, precavg07, precavg08, precavg09, precavg10, precavg11, precavg12, sdmavg01, sdmavg02, sdmavg03, sdmavg04, sdmavg05, sdmavg06, sdmavg07, sdmavg08, sdmavg09, sdmavg10, sdmavg11, sdmavg12, wlenavg, wpravg, wtmnavg, wtmxavg
>  
>  
> number of evaluation repetitions :    3
> number of pseudo-absences runs :      2
> models selected :                     ANN, CTA, GAM, GBM, GLM, MARS, FDA, RF, SRE
> total number of model runs :          72
> -----------------------------------
>  
>  
> #####                  peromyscus                    #####
> #####             pseudo-absence run 1                       #####
> Model=Artificial Neural Network
>          2 Fold Cross Validation + 3 Repetitions
> Calibration and evaluation phase: Nb of cross-validations:  3
> Error in parse(text = paste("Target[Samp$calibration]", paste(.scopeExpSyst(Input[1:10,  :
>   <text>:2:0: unexpected end of input
> 1: 12 + tmaxavg01 + tmaxavg02 + tmaxavg03 + tmaxavg04 + tmaxavg05 + tmaxavg06 + tmaxavg07 + tmaxavg08 + tmaxavg09 + tmaxavg10 + tmaxavg11 + tmaxavg12 + trngavg + precavg01 + precavg02 + precavg03
>   ^
> 
> Thank you,
> ____________________________________
> Emilie Roy-Dufresne
> M. Sc. Candidate Geography Department - McGill - Biogeography studies
> Guide en tourisme d'aventure
> 
> 
> 
> _______________________________________________
> 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

ERC Starting Grant TEEMBIO project: http://www.will.chez-alice.fr/Research.html
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/20120217/4867f8ca/attachment-0001.html>