[Biomod-commits] error: number of columns of result is not a multiple of vector length (arg 1)

[Damien Georges]

Hi Kumar,

Are you sure your Independent variable are in the rigth format?
e.g:
     - have you both presences and absences in your IndependentResponse 
var? ,
     - did you removed all NAs from your IndependentExplanatory?

You can easily check it printing your variables summaries (i.e 
summary(Expl.VarTest) )

Best,

Damien.

On 16/07/2012 03:05, Kumar Mainali wrote:
> Hello BIOMODellers,
>
> I am working on BIOMOD v 1.1-7.02 in R 2.14.1 and am trying to run 
> four models with independent test data. After running the first model 
> for a while, it gives me the following error message and it stops: 
> "number of columns of result is not a multiple of vector length (arg 
> 1)". Just to see what would happen, I used the same dataset used in 
> building model to test it. This time, there was no error message.
>
> Thanks in advance.
> - Kumar
>
> Initial.State(Response = Resp.Var, sp.name <http://sp.name> = 
> "Something", Explanatory = Expl.Var,
>
> IndependentResponse = Resp.VarTest, IndependentExplanatory = Expl.VarTest)
>
>
> > Models(GLM = T, TypeGLM = "poly", Test = "AIC",
>
> + GBM = T, No.trees = 5000,
>
> + GAM = T, Spline = 3, CTA = F, CV.tree = 50,
>
> + ANN = F, CV.ann = 2,
>
> + SRE = F, quant=0.025,
>
> + FDA = F,
>
> + MARS = F,
>
> + RF = T,
>
> + NbRunEval = 1, DataSplit = 100, Yweights=NULL,
>
> + Roc = T, Optimized.Threshold.Roc = T, Kappa = T, TSS=T,
>
> + KeepPredIndependent = T, VarImport=T,
>
> + NbRepPA=1, strategy="random", coor=LatLong, nb.absences=2329)
>
> ##### pseudo-absence run 1                 #####
>
> Model=GAM spline
>
> 3  Degrees of smoothing
>
> Evaluating Predictor Contributions in  GAM ...
>
> Error in KappaStat(Misc) : subscript out of bounds
>
> In addition: Warning message:
>
> In rbind(Misc, a) :
>
> number of columns of result is not a multiple of vector length (arg 1)
>
>
> > Evaluation.results.Kappa
>
> $Something_PA1
>
> Cross.validation indepdt.data total.score Cutoff Sensitivity Specificity
>
> GAM NA           NA          NA NA          NA          NA
>
> GBM NA           NA          NA NA          NA          NA
>
> GLM NA           NA          NA NA          NA          NA
>
> RF NA           NA          NA NA          NA          NA
>
> > Evaluation.results.Roc
>
> $Something_PA1
>
> Cross.validation indepdt.data total.score Cutoff Sensitivity Specificity
>
> GAM NaN         <NA>       0.817 493.52      74.168 74.109
>
> GBM <NA>         <NA>        <NA> <NA>        <NA>        <NA>
>
> GLM <NA>         <NA>        <NA> <NA>        <NA>        <NA>
>
> RF <NA>         <NA>        <NA> <NA>        <NA>        <NA>
>
>
> -- 
> Section of Integrative Biology
> University of Texas at Austin
> Austin, Texas 78712, USA
>
>
> _______________________________________________
> 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


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/biomod-commits/attachments/20120716/e2dbcbee/attachment-0001.html>