<html><body><div style="color:#000; background-color:#fff; font-family:arial, helvetica, sans-serif;font-size:10pt"><div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-size: 13px; font-family: arial, helvetica, sans-serif; ">Hi all,</span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-size: small; font-family: arial, helvetica, sans-serif; "><br></span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-size: small; font-family: arial, helvetica, sans-serif; ">I am trying to run the MaxEnt tutorial datasets (presences + backgroung points with localities, bioclimatic variables and one categorical variable for Bradypus Variegatus) in BIOMOD and am facing some trouble:</span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-size: small; font-family: arial, helvetica, sans-serif; "><br></span></div><div
style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-size: small; font-family: arial, helvetica, sans-serif; ">1)</span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-size: small; font-family: arial, helvetica, sans-serif; "><br></span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-family: arial, helvetica, sans-serif; font-size: 13px; "><div class="MsoNormal"><span lang="ES">Models(GLM = T, TypeGLM = "poly", Test = "AIC",</span></div><div class="MsoNormal"><span lang="ES">+ GBM = T, No.trees = 2000,</span></div><div class="MsoNormal"><span lang="ES">+ GAM = T,Spline = 3, CTA = T, CV.tree = 50,</span></div><div class="MsoNormal"><span lang="ES">+ ANN = T, CV.ann = 2,</span></div><div class="MsoNormal"><span lang="ES">+ SRE = T, quant=0.025,</span></div><div class="MsoNormal"><span lang="ES">+ FDA = T,</span></div><div class="MsoNormal"><span
lang="ES">+ MARS = T,</span></div><div class="MsoNormal"><span lang="ES">+ RF = T,</span></div><div class="MsoNormal"><span lang="ES">+ NbRunEval = 3, DataSplit = 80, Yweights=NULL,</span></div><div class="MsoNormal"><span lang="ES">+ Roc = T, Optimized.Threshold.Roc = T, Kappa = T, TSS=T,</span></div><div class="MsoNormal"><span lang="ES">+ KeepPredIndependent = T, VarImport=5,</span></div><div class="MsoNormal"><span lang="ES">+ NbRepPA=2, strategy="circles", coor=LatLong,</span></div><div class="MsoNormal"><span lang="ES">+ distance=2, nb.absences=1000)</span></div><div class="MsoNormal"><span lang="ES"><br></span></div><div class="MsoNormal"><span lang="ES">Even though BIOMOD warns me about MARS' and SRE's inability to handle categorical variables:</span></div><div class="MsoNormal"><span lang="ES"><br></span></div><div class="MsoNormal"><span lang="ES"></span></div><div class="MsoNormal"><span lang="ES">MARS model was shut down, it cannot run on
factorial variables : ecoreg</span></div><div class="MsoNormal"><span lang="ES">SRE model was shut down, it cannot run on factorial variables : ecoreg</span></div><div class="MsoNormal"><span lang="ES"><br></span></div><div class="MsoNormal"><span lang="ES"></span></div><div class="MsoNormal"><span lang="ES">I do not get any warnings for all the rest (ANN, CTA, GAM, GBM, GLM, FDA, RF). Nevertheless, the “ models”<i> </i>folder only contains results for CTA and ANN.</span></div><div class="MsoNormal"><span lang="ES"><br></span></div><div class="MsoNormal"><span lang="ES">2)</span></div><div class="MsoNormal">No Biomod.PA.sample$Sp1$PA1 object is generated after running the models.</div><div class="MsoNormal"><br></div><div class="MsoNormal">3)</div></span><div class="MsoNormal"><span lang="EN-US">I have no predictions in my pred folder.<o:p></o:p></span></div><div></div><div></div></div><div style="font-family: 'Times New Roman'; font-size:
medium; "><span style="font-size: small; font-family: arial, helvetica, sans-serif; "><br></span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-family: arial, helvetica, sans-serif; font-size: 13px; ">4)</span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-family: arial, helvetica, sans-serif; font-size: 13px; "><div class="MsoNormal"><span lang="ES">I want to evaluate the importance of each variable according to the procedure described in BIOMOD tutorial, 2012 p.30:</span></div><div class="MsoNormal"><span lang="ES"><o:p> </o:p></span></div><div class="MsoNormal"><span lang="ES">model <- glm(Sp281 ~ Var1 + Var2 + Var3 + Var4 + Var5 + Var6 + Var7, data=Sp.Env)</span></div><div class="MsoNormal"><span lang="ES">Pred <- predict(model, Expl.Var, type="response")</span></div><div class="MsoNormal"><span lang="EN-US">Expl.Var2 <-
Expl.Var<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US">Expl.Var2[,</span><span lang="EN-US">'</span><span lang="EN-US">Var1</span><span lang="EN-US">'</span><span lang="EN-US">] <- sample(Expl.Var[,</span><span lang="EN-US">'</span><span lang="EN-US">Var1</span><span lang="EN-US">'</span><span lang="EN-US">])<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US">Pred2 <- predict(model, Expl.Var2, type="response")<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US">par(mfrow=c(1,2))<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US">level.plot(Pred, LatLong, show.scale=F, cex=0.8)<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US">level.plot(Pred2, LatLong, show.scale=F, cex=0.8)<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></div><div class="MsoNormal"><span lang="EN-US">First of all, does someone have to go through the whole procedure
of typing the code above for each model and for each variable, and to use the predict() function each time? According to the tutorial “once the models are trained (i.e. calibrated), a standard prediction is made. Then, one of the variables is randomized and a new prediction is made.” I thought that BIOMOD was following this procedure automatically. If yes, how? If not, </span><span lang="EN-US">how can I load CTA, ANN (and all the rest of the models in general) the same way glm is loaded in the code above (i.e. glm</span><span lang="ES">(Sp281 ~ Var1 + Var2 + Var3 + Var4 + Var5 + Var6 + Var7, data=Sp.Env))?</span><span lang="EN-US"><o:p></o:p></span></div><div class="MsoNormal"><span lang="ES"><br></span></div></span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-size: small; font-family: arial, helvetica, sans-serif; ">Cheers,</span></div><div style="font-family: 'Times New Roman'; font-size: medium;
"><span style="font-size: small; font-family: arial, helvetica, sans-serif; "><br></span></div><div style="font-family: 'Times New Roman'; font-size: medium; "><span style="font-family: arial, helvetica, sans-serif; font-size: 13px; ">Andreas</span></div></div></div></body></html>