<html>
<head>
<style><!--
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 10pt;
font-family:Tahoma
}
--></style></head>
<body class='hmmessage'><div dir='ltr'>
<div>Hello Biomoders,</div><div><br></div><div>I am new to BIOMOD, and I have a couple of problems while running FDA and RF .</div><div><span style="font-size: 10pt; ">I am using the latest version of R (2.14.2) and BIOMOD V1.1-7.00 downloaded from: </span><a href="http://www.will.chez-alice.fr/Software.html" style="font-size: 10pt; ">http://www.will.chez-alice.fr/Software.html</a><span style="font-size: 10pt; "> - I am using Windows 7 (32 bit) (3GB of ram - core i3)</span></div><div><br></div><div>While running RF, I am always got this error message:</div><div><i> Error: cannot allocate vector of size 596.2 Mb</i>
</div><div><br></div><div>For FDA, it was working fine on the tutorial data but when I am trying to work on my own data, I am receiving this error:</div><div><div><i style="font-size: 10pt; "> </i><i>Error in if (min(Fit) < 0) Fit[Fit < 0] <- 0 : </i></div><div><i style="font-size: 10pt; "> m</i><i>issing value where TRUE/FALSE needed</i></div></div><div><br></div><div>I am pretty sure that there are no na values in my data using this command</div><div><i style="font-size: 10pt; "> </i><i>sum(is.na(currentclim))</i></div><div><i style="font-size: 10pt; "> </i><i>sum(is.na(species))</i> </div><div>in both cases I got 0 na values.</div><div><br></div><div>That is the code used to calibrate the models:</div><div><i>Initial.State (Response = species[,1:2], Explanatory = currentclim, IndependentResponse = species[,1:2], IndependentExplanatory = currentclim)</i></div><div><i style="font-size: 10pt; "> </i><i>Models(</i></div><div><i style="font-size: 10pt; "> </i><i>GLM = T, TypeGLM = "poly", Test = "AIC",</i></div><div><i style="font-size: 10pt; "> </i><i>GBM = T, No.trees = 2000,</i></div><div><i style="font-size: 10pt; "> </i><i>GAM = T, Spline = 3,</i></div><div><i style="font-size: 10pt; "> </i><i>CTA = F, CV.tree = 50,</i></div><div><i style="font-size: 10pt; "> </i><i>ANN = T, CV.ann = 2,</i></div><div><i style="font-size: 10pt; "> </i><i>SRE = T, quant=0.025, # requires opening R with administrative previllages.</i></div><div><i style="font-size: 10pt; "> </i><i>FDA = T,</i></div><div><i style="font-size: 10pt; "> </i><i>MARS = T,</i></div><div><i style="font-size: 10pt; "> </i><i># RF = T, </i></div><div><i style="font-size: 10pt; "> </i><i>NbRunEval = 3, DataSplit = 75, Yweights=NULL, </i></div><div><i style="font-size: 10pt; "> </i><i>Roc = T, Optimized.Threshold.Roc = T, Kappa = T, TSS=T,</i></div><div><i style="font-size: 10pt; "> </i><i>KeepPredIndependent = T, VarImport=5,</i></div><div><i style="font-size: 10pt; "> </i><i>NbRepPA=0, strategy="circles", coor=latlong,</i></div><div><i style="font-size: 10pt; "> </i><i>distance=0.125, nb.absences=1000)</i></div><div><br></div><div><br></div><div>This is the results:</div><div><i style="font-size: 10pt; ">----------------------------------- </i></div><div><div><i>Modelling summary </i></div><div><i>----------------------------------- </i></div><div><i>Number of species modelled : 2</i></div><div><i>sp1, sp2</i></div><div><i style="font-size: 10pt; ">numerical variables : bio3, bio5, bio6, bio7, bio8, bio9, bio10, bio11, bio15, bio16, bio19</i></div><div><i style="font-size: 10pt; ">number of evaluation repetitions : 3</i></div><div><i>number of pseudo-absences runs : 0</i></div><div><i>models selected : ANN, GAM, GBM, GLM, MARS, FDA, SRE</i></div><div><i>total number of model runs : 56</i></div><div><i>----------------------------------- </i></div><div><i style="font-size: 10pt; ">##### sp1 #####</i></div><div><i>Model=Artificial Neural Network </i></div><div><i> 2 Fold Cross Validation + 3 Repetitions </i></div><div><i>Calibration and evaluation phase: Nb of cross-validations: 3 </i></div><div><i>Evaluating Predictor Contributions in ANN ... </i></div><div><i>Model=GAM spline </i></div><div><i> 3 Degrees of smoothing </i></div><div><i>Evaluating Predictor Contributions in GAM ... </i></div><div><i>Model=Generalised Boosting Regression </i></div><div><i> 2000 maximum different trees and lambda Fold Cross-Validation </i></div><div><i>Evaluating Predictor Contributions in GBM ... </i></div><div><i>Model=GLM polynomial + quadratic Stepwise procedure using AIC criteria </i></div><div><i>Evaluating Predictor Contributions in GLM ... </i></div><div><i>Model=Multiple Adaptive Regression Splines </i></div><div><i>Evaluating Predictor Contributions in MARS ... </i></div><div><i>Model=Flexible Discriminant Analysis </i></div><div><i>Error in if (min(Fit) < 0) Fit[Fit < 0] <- 0 : </i></div><div><i> missing value where TRUE/FALSE needed</i></div></div><div><i><br></i></div><div><i><br></i></div><div>Thanks in advance,</div><div><span style="font-size: 10pt; ">Ahmed</span></div> </div></body>
</html>