[Biomod-commits] Projection() Error

[Robin Engler]

Hi Brenna,

I've seen people coming-up with this error quite a number of times,
and more often than not, the problem was simply that something was
wrong with the data that they used as input of the Projection()
function. I know it sounds really basic, but I would advise you to
carefully check that data you are inputting into the projection()
function. In particular, look for:
- missing or NA values.
- is your data numeric (sometimes R automatically converts numbers to
factors when loading data!)

As I said, I know this sounds too simple but it's definitely worth to
check again your data as this is a frequent problem (and the fact that
you could make projections on 10 datasets but no the 11th would makes
me think the problem is in your projection dataset, not in your models
or the BIOMOD code).

Cheers,
Robin





I know this might sound very basic, but every time people come to me with this

On Wed, Mar 23, 2011 at 7:43 PM, Brenna Forester
<forestb at students.wwu.edu> wrote:
> Hello all,
>
> I have successfully run Projection() on 10 different climate data sets.  I
> just encountered the following error, however, while projecting using an
> eleventh data set:
>
> Error in if (sum(ProbData) != 0) { :
>   missing value where TRUE/FALSE needed
>
> I see from previous posts that this error can sometimes be avoided by
> changing FDA=F.  I did so and Projections() ran with no problems.
> Ensemble.Forecasting() also ran fine, however ProjectionBestModel() gave the
> same error as above.  I am using all models except SRE.
>
> Any feedback?  The code and version info are below.
>
> Thank you!
> Brenna
>
>> load("Rhodiola_run.Rdata")
>
>> Projection(Proj=hadc21[,3:10],Proj.name='HADC.21k',GLM = T, GBM = T, GAM =
>> T, CTA = T, ANN = T, SRE = F, FDA =T, MARS = T, RF = T, BinRoc=T,
>> BinKappa=T, BinTSS=T, FiltRoc=T, FiltKappa=T, FiltTSS=T,
>> repetition.models=T)
>
> Error in if (sum(ProbData) != 0) { :
>   missing value where TRUE/FALSE needed
>
> ## Rerun using FDA=F
>
>> Projection(Proj=hadc21[,3:10],Proj.name='HADC.21k',GLM = T, GBM = T, GAM =
>> T, CTA = T, ANN = T, SRE = F, FDA =F, MARS = T, RF = T, BinRoc=T,
>> BinKappa=T, BinTSS=T, FiltRoc=T, FiltKappa=T, FiltTSS=T,
>> repetition.models=T)
>
>> ProjectionBestModel(Proj.name='HADC.21k', Bin.trans=T,
>> Filt.trans=T,method='all')
>
> Error in if (sum(ProbData) != 0) { :
>   missing value where TRUE/FALSE needed
>
>> Ensemble.Forecasting(Proj.name= "HADC.21k", weight.method='Kappa',
>> decay='proportional', PCA.median=F, binary=T, bin.method='Kappa', Test=T,
>> repetition.models=T)
>
> Rhodiola
>
>  consensus_HADC.21k_results
> $Rhodiola
> $Rhodiola$weights
>              ANN    CTA    GAM    GBM    GLM   MARS FDA     RF SRE
> PA1       0.1373 0.1266 0.1515 0.1585 0.1191 0.1499   0 0.1569   0
> PA1_rep1  0.1359 0.1457 0.1457 0.1552 0.1171 0.1361   0 0.1644   0
>
> ## Results truncated...
>
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> I am running BIOMOD Version 1.1-5 on the following system:
>
>> version
>                _
> platform       i386-pc-mingw32
> arch           i386
> os             mingw32
> system         i386, mingw32
> status
> major          2
> minor          12.1
> year           2010
> month          12
> day            16
> svn rev        53855
> language       R
> version.string R version 2.12.1 (2010-12-16)
>
>
>
>
>
>
>
>
>
>
>
>
> _______________________________________________
> 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
>
>