[Biomod-commits] Re : error message Ensemble.Forecasting function

[Bruno Lafourcade]

Hi Manuela and other BIOMODers,


I am very puzzled with this one. I have encounetered it several times before and it seems to come from
various possibilities and I haven't yet figured out how to solve it completely. 

I believe some of the operations that the function is to be doing areencountering absent data, at least that's what I came up with.
I would advise you to try and switch on/off some of the arguments. Ibelieve "binary" and "Test" would surely make a difference if
switched off.

Also, maybe just setting "repetition.models" to TRUE might skip the problem even if the others are kept as FALSE. It is a late 
improvement and might not totally be bug free on the overall of the function.

Thanks for reporting any advances.
Bruno

 

 

-------
Bruno Lafourcade
Statistical tools engineer

Laboratoire d'Ecologie Alpine, bureau 308
CNRS - UMR 5553, 2233 rue de la piscine
38400 Saint Martin d'Hères
-------
 

 

-----E-mail d'origine-----
De : mdamen at uniroma3.it
A : biomod-commits at r-forge.wu-wien.ac.at
Envoyé le : Jeudi, 3 Décembre 2009 15:24
Sujet : [Biomod-commits] error message Ensemble.Forecasting function


Dear all,

I encountered a problem with the Ensemble.Forecasting() function.

I am working on 1 species (678 obs. - 10 variables).

I get models with the function:
Models(GLM=T, TypeGLM="poly", Test="AIC", GBM=T, No.trees = 5000, GAM= T,
CTA=T, CV.tree =50, ANN=T, CV.ann=3, SRE=F, Perc025=TRUE, Perc05=FALSE,
MDA=T, MARS=T, RF=T, NbRunEval = 3, DataSplit = 80, VarImport=5, Roc = T, 
      Optimized.Threshold.Roc = T, Kappa = F, TSS = F)

... then I projected the models:
Projection (Proj = pres[,4:13], Proj.name="pres", GLM = T, GBM = T, GAM = T,
CTA = T, ANN = T, SRE = F, Perc025 = T, Perc05 = F, MDA =T, MARS = T, RF =
T, BinRoc = T, BinKappa = F, BinTSS = F, FiltRoc = F, FiltKappa = F,
FiltTSS = F, repetition.models = F)

finally the Ensemble.Forecasting function -

Ensemble.Forecasting(Proj.name= "pres", weight.method = "Roc", decay = 1.6,
                    PCA.median = F, binary = T, bin.method = "Roc",
                    Test = T, repetition.models = F)

gave me this error:

Errore in if (sum(ProbData) != 0) { :
  valore mancante dove è richiesto TRUE/FALSE

(The english translation of the second line is: "missig value where
TRUE/FALSE is required")

What is wrong?
I would be very grateful for any help

Manuela

-- 
Manuela D'Amen
PhD student
Lab Zoology and Animal Biology
Department of Environmental Biology
University of Roma Tre, Rome, Italy


_______________________________________________
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/20091207/7d19161e/attachment.htm