No subject


Fri May 7 18:15:04 CEST 2010


h iteration.=20

> Question 3- Any suggestion?

Yes indeed.=20
First of all, I would rather use random pseudo-absence instead of SRE and s=
elect a large number of pseudo-absence. BIOMOD will automatically make sure=
 that the weighted sum of 1 equals the weighted sum of 0 (weighted prevalen=
ce =3D 0.5). We are preparing a MS with virtual data to show that this is a=
 much better solution than using SRE or anything else.=20

In the case where most of your species have less than 5000 occurrences, sel=
ected 20000 absences and it should work rather well.=20

>=20
> # i corresponds to the column where the species Presence or Absence is lo=
cated
>=20
> for (i in "spColumID") {
>=20
> Initial.State (Response=3DSp.Env[,i], Explanatory=3DSp.Env[,c(250,248,251=
,199,164,181)],IndependentResponse=3DNULL, IndependentExplanatory=3DNULL,sp=
.name=3Dnames[i])
>=20
> Models(GLM =3D T, TypeGLM =3D "quad", Test =3D "AIC", GBM =3D T, No.trees=
 =3D 3000, GAM =3D T, Spline=3D2, CTA =3D T, CV.tree =3D 50, ANN =3D T, CV.=
ann =3D 2, SRE =3D F, FDA =3D T, MARS =3D T, RF =3D T, NbRunEval =3D 1, Dat=
aSplit =3D 70, Yweights=3DNULL, Roc=3DT, Optimized.Threshold.Roc=3DT, Kappa=
=3DT, TSS=3DT, KeepPredIndependent =3D F, VarImport=3D5, NbRepPA=3D1, strat=
egy=3D"sre", coor=3DCoor, distance=3D2, nb.absences=3Dsum(Sp.Env[,i]))
>=20
> }

Depending on which OS you are on, there are different solutions. With MacOS=
 or Unic, you could use R in batch mode.=20
On Windows, what you wrote is fine excepted that you re-write everything on=
 the same .RData which is not what you want to do (it explains the confusio=
n with the number of records).=20

First of all, you should create a folder for each species in the loop, then=
 run BIOMOD in this folder, and then once Models is finished, removed every=
thing from the workspce to make sure you are using some data from the previ=
ous run.=20

It could be simply something along these lines, probably to adapt a bit wit=
h for your data and OS.=20



setwd("YOUR FOLDER WHERE YOU WANT TO STORE THE RESULS")

path =3D getwd()

for (i in "spColumID") {

#Create a folder you store the results for each species separately.
dir.create(paste(path, "/", names[i], sep=3D""))

#Set the workspace in this folder
setwd(paste(path, "/", names[i], sep=3D""))

Initial.State (Response=3DSp.Env[,i], Explanatory=3DSp.Env[,c(250,248,251,1=
99,164,181)],IndependentResponse=3DNULL, IndependentExplanatory=3DNULL,sp.n=
ame=3Dnames[i])

Models(GLM =3D T, TypeGLM =3D "quad", Test =3D "AIC", GBM =3D T, No.trees =
=3D 3000, GAM =3D T, Spline=3D2, CTA =3D T, CV.tree =3D 50, ANN =3D T, CV.a=
nn =3D 2, SRE =3D F, FDA =3D T, MARS =3D T, RF =3D T, NbRunEval =3D 1, Data=
Split =3D 70, Yweights=3DNULL, Roc=3DT, Optimized.Threshold.Roc=3DT, Kappa=
=3DT, TSS=3DT, KeepPredIndependent =3D F, VarImport=3D5, NbRepPA=3D1, strat=
egy=3D"sre", coor=3DCoor, distance=3D2, nb.absences=3Dsum(Sp.Env[,i]))

#keep the files you want to keep in a vector before deleting everything
t=3D c("path", "Sp.Env", "names")
Rem =3D ls()

#Delete everything but the object in t.
rm(list=3D(Rem[is.na(match(Rem, t))]))

}



Hope it helps,
Best
Wilfried






>=20
>=20
> Thank you very much in advance for reading such a long post with 3 Questi=
ons!
>=20
> Pep
>=20
>=20
> _______________________________________________
> 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-commi=
ts

--------------------------
Dr. Wilfried Thuiller
Laboratoire d'Ecologie Alpine, UMR CNRS 5553
Universit? Joseph Fourier
BP53, 38041 Grenoble cedex 9, France
tel: +33 (0)4 76 51 44 97
fax: +33 (0)4 76 51 42 79

Email: wilfried.thuiller at ujf-grenoble.fr
Home page: http://www.will.chez-alice.fr
Website: http://www-leca.ujf-grenoble.fr/equipes/tde.htm

FP6 European MACIS project: http://www.macis-project.net
FP6 European EcoChange project: http://www.ecochange-project.eu





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/biomod-commits/attachmen=
ts/20100705/cec1a13b/attachment.htm>

------------------------------

_______________________________________________
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


End of Biomod-commits Digest, Vol 15, Issue 1
*********************************************
=0A=0A=0A      
--0-1134715868-1278345945=:46390
Content-Type: text/html; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

<table cellspacing=3D"0" cellpadding=3D"0" border=3D"0" ><tr><td valign=3D"=
top" style=3D"font: inherit;"><table summary=3D"R argblock"><tbody><tr vali=
gn=3D"top"><td><code></code><br></td></tr></tbody></table>Hi all again,<br>=
<br>Can someone provide a deeper insight on how to define and create the cl=
ass 'RasterStack' needed to make the raster projections? <br><br>Best of wi=
shes,<br><br>C=E9sar<br><br><br><br>--- On <b>Mon, 5/7/10, biomod-commits-r=
equest at lists.r-forge.r-project.org <i>&lt;biomod-commits-request at lists.r-fo=
rge.r-project.org&gt;</i></b> wrote:<br><blockquote style=3D"border-left: 2=
px solid rgb(16, 16, 255); margin-left: 5px; padding-left: 5px;"><br>From: =
biomod-commits-request at lists.r-forge.r-project.org &lt;biomod-commits-reque=
st at lists.r-forge.r-project.org&gt;<br>Subject: Biomod-commits Digest, Vol 1=
5, Issue 1<br>To: biomod-commits at lists.r-forge.r-project.org<br>Date: Monda=
y, 5 July, 2010, 16:33<br><br><div class=3D"plainMail">Send Biomod-commits =
mailing list
 submissions to<br>&nbsp;&nbsp;&nbsp; <a ymailto=3D"mailto:biomod-commits at l=
ists.r-forge.r-project.org" href=3D"/mc/compose?to=3Dbiomod-commits at lists.r=
-forge.r-project.org">biomod-commits at lists.r-forge.r-project.org</a><br><br=
>To subscribe or unsubscribe via the World Wide Web, visit<br>&nbsp;&nbsp;&=
nbsp; <a href=3D"https://lists.r-forge.r-project.org/cgi-bin/mailman/listin=
fo/biomod-commits" target=3D"_blank">https://lists.r-forge.r-project.org/cg=
i-bin/mailman/listinfo/biomod-commits</a><br><br>or, via email, send a mess=
age with subject or body 'help' to<br>&nbsp;&nbsp;&nbsp; <a ymailto=3D"mail=
to:biomod-commits-request at lists.r-forge.r-project.org" href=3D"/mc/compose?=
to=3Dbiomod-commits-request at lists.r-forge.r-project.org">biomod-commits-req=
uest at lists.r-forge.r-project.org</a><br><br>You can reach the person managi=
ng the list at<br>&nbsp;&nbsp;&nbsp; <a ymailto=3D"mailto:biomod-commits-ow=
ner at lists.r-forge.r-project.org"
 href=3D"/mc/compose?to=3Dbiomod-commits-owner at lists.r-forge.r-project.org"=
>biomod-commits-owner at lists.r-forge.r-project.org</a><br><br>When replying,=
 please edit your Subject line so it is more specific<br>than "Re: Contents=
 of Biomod-commits digest..."<br><br><br>Today's Topics:<br><br>&nbsp;&nbsp=
;&nbsp;1. new raster functions (C?sar Capinha)<br>&nbsp;&nbsp;&nbsp;2. Re: =
new raster functions (Wilfried Thuiller)<br>&nbsp;&nbsp;&nbsp;3. memory err=
or- again... (PEP Serra Diaz)<br>&nbsp;&nbsp;&nbsp;4. Re: memory error- aga=
in... (Wilfried Thuiller)<br><br><br>--------------------------------------=
--------------------------------<br><br>Message: 1<br>Date: Mon, 5 Jul 2010=
 12:05:33 +0000 (GMT)<br>From: C?sar Capinha &lt;<a ymailto=3D"mailto:nrevi=
stada at yahoo.co.uk" href=3D"/mc/compose?to=3Dnrevistada at yahoo.co.uk">nrevist=
ada at yahoo.co.uk</a>&gt;<br>Subject: [Biomod-commits] new raster functions<b=
r>To: <a ymailto=3D"mailto:biomod-commits at lists.r-forge.r-project.org"
 href=3D"/mc/compose?to=3Dbiomod-commits at lists.r-forge.r-project.org">biomo=
d-commits at lists.r-forge.r-project.org</a><br>Message-ID: &lt;<a ymailto=3D"=
mailto:394679.98688.qm at web27405.mail.ukl.yahoo.com" href=3D"/mc/compose?to=
=3D394679.98688.qm at web27405.mail.ukl.yahoo.com">394679.98688.qm at web27405.ma=
il.ukl.yahoo.com</a>&gt;<br>Content-Type: text/plain; charset=3D"iso-8859-1=
"<br><br>Hi all,<br><br>I'm trying to make some projections of predictions =
and I would very much benefit from using the new BIOMOD capabilities for pr=
ojecting directly to raster files. Still, I've downloaded the latest versio=
n (windows) and it seems to come without the CHM helpfile. I'm not about th=
e syntax of these new functions. <br><br>Can someone provide insights on th=
em?<br><br>Best Wishes,<br>C?sar Capinha<br><br><br><br>&nbsp; &nbsp; &nbsp=
; <br>-------------- next part --------------<br>An HTML attachment was scr=
ubbed...<br>URL: &lt;<a
 href=3D"http://lists.r-forge.r-project.org/pipermail/biomod-commits/attach=
ments/20100705/7a728d20/attachment-0001.htm" target=3D"_blank">http://lists=
.r-forge.r-project.org/pipermail/biomod-commits/attachments/20100705/7a728d=
20/attachment-0001.htm</a>&gt;<br><br>------------------------------<br><br=
>Message: 2<br>Date: Mon, 5 Jul 2010 14:16:10 +0200<br>From: Wilfried Thuil=
ler &lt;<a ymailto=3D"mailto:wilfried.thuiller at ujf-grenoble.fr" href=3D"/mc=
/compose?to=3Dwilfried.thuiller at ujf-grenoble.fr">wilfried.thuiller at ujf-gren=
oble.fr</a>&gt;<br>Subject: Re: [Biomod-commits] new raster functions<br>To=
: C?sar Capinha &lt;<a ymailto=3D"mailto:nrevistada at yahoo.co.uk" href=3D"/m=
c/compose?to=3Dnrevistada at yahoo.co.uk">nrevistada at yahoo.co.uk</a>&gt;<br>Cc=
: <a ymailto=3D"mailto:biomod-commits at r-forge.wu-wien.ac.at" href=3D"/mc/co=
mpose?to=3Dbiomod-commits at r-forge.wu-wien.ac.at">biomod-commits at r-forge.wu-=
wien.ac.at</a><br>Message-ID: &lt;<a
 ymailto=3D"mailto:36D7AE5F-2430-4A14-96AE-E81DCBE11A6E at ujf-grenoble.fr" hr=
ef=3D"/mc/compose?to=3D36D7AE5F-2430-4A14-96AE-E81DCBE11A6E at ujf-grenoble.fr=
">36D7AE5F-2430-4A14-96AE-E81DCBE11A6E at ujf-grenoble.fr</a>&gt;<br>Content-T=
ype: text/plain; charset=3D"iso-8859-1"<br><br>Dear C?sar,<br>If you type t=
his, does it work?<br><br>?Projection.raster<br><br>Wilfried<br><br><br>Le =
5 juil. 2010 ? 14:05, C?sar Capinha a ?crit :<br><br>&gt; Hi all,<br>&gt; <=
br>&gt; I'm trying to make some projections of predictions and I would very=
 much benefit from using the new BIOMOD capabilities for projecting directl=
y to raster files. Still, I've downloaded the latest version (windows) and =
it seems to come without the CHM helpfile. I'm not about the syntax of thes=
e new functions. <br>&gt; <br>&gt; Can someone provide insights on them?<br=
>&gt; <br>&gt; Best Wishes,<br>&gt; C?sar Capinha<br>&gt; <br>&gt; ________=
_______________________________________<br>&gt; Biomod-commits mailing
 list<br>&gt; <a ymailto=3D"mailto:Biomod-commits at lists.r-forge.r-project.o=
rg" href=3D"/mc/compose?to=3DBiomod-commits at lists.r-forge.r-project.org">Bi=
omod-commits at lists.r-forge.r-project.org</a><br>&gt; <a href=3D"https://lis=
ts.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits" target=3D=
"_blank">https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomo=
d-commits</a><br><br>--------------------------<br>Dr. Wilfried Thuiller<br=
>Laboratoire d'Ecologie Alpine, UMR CNRS 5553<br>Universit? Joseph Fourier<=
br>BP53, 38041 Grenoble cedex 9, France<br>tel: +33 (0)4 76 51 44 97<br>fax=
: +33 (0)4 76 51 42 79<br><br>Email: <a ymailto=3D"mailto:wilfried.thuiller=
@ujf-grenoble.fr" href=3D"/mc/compose?to=3Dwilfried.thuiller at ujf-grenoble.f=
r">wilfried.thuiller at ujf-grenoble.fr</a><br>Home page: <a href=3D"http://ww=
w.will.chez-alice.fr" target=3D"_blank">http://www.will.chez-alice.fr</a><b=
r>Website: <a href=3D"http://www-leca.ujf-grenoble.fr/equipes/tde.htm"
 target=3D"_blank">http://www-leca.ujf-grenoble.fr/equipes/tde.htm</a><br><=
br>FP6 European MACIS project: <a href=3D"http://www.macis-project.net" tar=
get=3D"_blank">http://www.macis-project.net</a><br>FP6 European EcoChange p=
roject: <a href=3D"http://www.ecochange-project.eu" target=3D"_blank">http:=
//www.ecochange-project.eu</a><br><br><br><br><br><br>-------------- next p=
art --------------<br>An HTML attachment was scrubbed...<br>URL: &lt;<a hre=
f=3D"http://lists.r-forge.r-project.org/pipermail/biomod-commits/attachment=
s/20100705/55d7a47f/attachment-0001.htm" target=3D"_blank">http://lists.r-f=
orge.r-project.org/pipermail/biomod-commits/attachments/20100705/55d7a47f/a=
ttachment-0001.htm</a>&gt;<br><br>------------------------------<br><br>Mes=
sage: 3<br>Date: Mon, 05 Jul 2010 15:47:22 +0100<br>From: PEP Serra Diaz &l=
t;<a ymailto=3D"mailto:Josep.Serra at uab.cat" href=3D"/mc/compose?to=3DJosep.=
Serra at uab.cat">Josep.Serra at uab.cat</a>&gt;<br>Subject: [Biomod-commits] mem=
ory error-
 again...<br>To: <a ymailto=3D"mailto:biomod-commits at r-forge.wu-wien.ac.at"=
 href=3D"/mc/compose?to=3Dbiomod-commits at r-forge.wu-wien.ac.at">biomod-comm=
its at r-forge.wu-wien.ac.at</a><br>Message-ID: &lt;<a ymailto=3D"mailto:9e9e8=
098525c.4c31fe8a at uab.es" href=3D"/mc/compose?to=3D9e9e8098525c.4c31fe8a at uab=
.es">9e9e8098525c.4c31fe8a at uab.es</a>&gt;<br>Content-Type: text/plain; char=
set=3Dus-ascii<br><br><br>Dear BIOMODers,<br><br>I have a hughe dataset (mo=
re or less 70000 rows) and the error is, of course: cannot allocate vector =
size of 459.1 MB. (I already increased memory.limt ()&nbsp; )<br><br>In tha=
t huge DF many species are recorded, so I though creating a litle loop so I=
 could go species by species and therefore would not load a huge dataset (Q=
uestion 1- Is that making any sense?). In each species model, presences and=
 absences are equaled, so we keep prevalence constant, and the strategy of =
PseudoA selection is SRE. (see script below)<br><br>For the first species (=
only
 4500 presences) R retrieves this memory error when computing RF, which I c=
annot understand for a DF of 9000 rows (P+A), and I even the number of repe=
titions is set to 1.<br><br>Secondly, I checked that BIOMOD creates an obje=
ct: Biomod.PA.data with 40000 records aprox. I assume that these are the pr=
esences and the ALL absences selected outside the SurfaceRange (strategy se=
lected), and later on BIOMOD will select the number of absences indicated (=
=3DNumber of Presences in this case). Question 2- Is this correct or is it =
loading ALL absences outside the range? (maybe that's why it retrieves an e=
rror.) <br><br>Question 3- Any suggestion?<br><br># i corresponds to the co=
lumn where the species Presence or Absence is located<br><br>for (i in "spC=
olumID") {<br><br>Initial.State (Response=3DSp.Env[,i], Explanatory=3DSp.En=
v[,c(250,248,251,199,164,181)],IndependentResponse=3DNULL, IndependentExpla=
natory=3DNULL,sp.name=3Dnames[i])<br><br>Models(GLM =3D T, TypeGLM =3D "qua=
d", Test
 =3D "AIC", GBM =3D T, No.trees =3D 3000, GAM =3D T, Spline=3D2, CTA =3D T,=
 CV.tree =3D 50, ANN =3D T, CV.ann =3D 2, SRE =3D F, FDA =3D T, MARS =3D T,=
 RF =3D T, NbRunEval =3D 1, DataSplit =3D 70, Yweights=3DNULL, Roc=3DT, Opt=
imized.Threshold.Roc=3DT, Kappa=3DT, TSS=3DT, KeepPredIndependent =3D F, Va=
rImport=3D5, NbRepPA=3D1, strategy=3D"sre", coor=3DCoor, distance=3D2, nb.a=
bsences=3Dsum(Sp.Env[,i]))<br><br>}<br><br><br>Thank you very much in advan=
ce for reading such a long post with 3 Questions!<br><br>Pep<br><br><br><br=
><br>------------------------------<br><br>Message: 4<br>Date: Mon, 5 Jul 2=
010 17:33:32 +0200<br>From: Wilfried Thuiller &lt;<a ymailto=3D"mailto:wilf=
ried.thuiller at ujf-grenoble.fr" href=3D"/mc/compose?to=3Dwilfried.thuiller at u=
jf-grenoble.fr">wilfried.thuiller at ujf-grenoble.fr</a>&gt;<br>Subject: Re: [=
Biomod-commits] memory error- again...<br>To: PEP Serra Diaz &lt;<a ymailto=
=3D"mailto:Josep.Serra at uab.cat" href=3D"/mc/compose?to=3DJosep.Serra at uab.ca=
t">Josep.Serra at uab.cat</a>&gt;<br>Cc: <a
 ymailto=3D"mailto:biomod-commits at r-forge.wu-wien.ac.at" href=3D"/mc/compos=
e?to=3Dbiomod-commits at r-forge.wu-wien.ac.at">biomod-commits at r-forge.wu-wien=
.ac.at</a><br>Message-ID: &lt;<a ymailto=3D"mailto:096790AC-CF60-4B41-872F-=
ED5A12F4BF80 at ujf-grenoble.fr" href=3D"/mc/compose?to=3D096790AC-CF60-4B41-8=
72F-ED5A12F4BF80 at ujf-grenoble.fr">096790AC-CF60-4B41-872F-ED5A12F4BF80 at ujf-=
grenoble.fr</a>&gt;<br>Content-Type: text/plain; charset=3D"iso-8859-1"<br>=
<br>Dear Pep,<br><br>&gt; In that huge DF many species are recorded, so I t=
hough creating a litle loop so I could go species by species and therefore =
would not load a huge dataset (Question 1- Is that making any sense?). In e=
ach species model, presences and absences are equaled, so we keep prevalenc=
e constant, and the strategy of PseudoA selection is SRE. (see script below=
)<br><br>It does make sense to run BIOMOD species by species. This what I a=
m usually doing when using grid systems. <br><br>&gt; For the first species=
 (only
 4500 presences) R retrieves this memory error when computing RF, which I c=
annot understand for a DF of 9000 rows (P+A), and I even the number of repe=
titions is set to 1.<br>&gt; <br>&gt; Secondly, I checked that BIOMOD creat=
es an object: Biomod.PA.data with 40000 records aprox. I assume that these =
are the presences and the ALL absences selected outside the SurfaceRange (s=
trategy selected), and later on BIOMOD will select the number of absences i=
ndicated (=3DNumber of Presences in this case). Question 2- Is this correct=
 or is it loading ALL absences outside the range? (maybe that's why it retr=
ieves an error.) <br><br>However, it will much more powerful to also create=
 a workspace and data folder to store the results for each species. <br>Fro=
m what I understand from your code, everything will be re-written at each i=
teration. <br><br>&gt; Question 3- Any suggestion?<br><br>Yes indeed. <br>F=
irst of all, I would rather use random pseudo-absence instead of SRE
 and select a large number of pseudo-absence. BIOMOD will automatically mak=
e sure that the weighted sum of 1 equals the weighted sum of 0 (weighted pr=
evalence =3D 0.5). We are preparing a MS with virtual data to show that thi=
s is a much better solution than using SRE or anything else. <br><br>In the=
 case where most of your species have less than 5000 occurrences, selected =
20000 absences and it should work rather well. <br><br>&gt; <br>&gt; # i co=
rresponds to the column where the species Presence or Absence is located<br=
>&gt; <br>&gt; for (i in "spColumID") {<br>&gt; <br>&gt; Initial.State (Res=
ponse=3DSp.Env[,i], Explanatory=3DSp.Env[,c(250,248,251,199,164,181)],Indep=
endentResponse=3DNULL, IndependentExplanatory=3DNULL,sp.name=3Dnames[i])<br=
>&gt; <br>&gt; Models(GLM =3D T, TypeGLM =3D "quad", Test =3D "AIC", GBM =
=3D T, No.trees =3D 3000, GAM =3D T, Spline=3D2, CTA =3D T, CV.tree =3D 50,=
 ANN =3D T, CV.ann =3D 2, SRE =3D F, FDA =3D T, MARS =3D T, RF =3D T, NbRun=
Eval =3D 1, DataSplit =3D 70,
 Yweights=3DNULL, Roc=3DT, Optimized.Threshold.Roc=3DT, Kappa=3DT, TSS=3DT,=
 KeepPredIndependent =3D F, VarImport=3D5, NbRepPA=3D1, strategy=3D"sre", c=
oor=3DCoor, distance=3D2, nb.absences=3Dsum(Sp.Env[,i]))<br>&gt; <br>&gt; }=
<br><br>Depending on which OS you are on, there are different solutions. Wi=
th MacOS or Unic, you could use R in batch mode. <br>On Windows, what you w=
rote is fine excepted that you re-write everything on the same .RData which=
 is not what you want to do (it explains the confusion with the number of r=
ecords). <br><br>First of all, you should create a folder for each species =
in the loop, then run BIOMOD in this folder, and then once Models is finish=
ed, removed everything from the workspce to make sure you are using some da=
ta from the previous run. <br><br>It could be simply something along these =
lines, probably to adapt a bit with for your data and OS. <br><br><br><br>s=
etwd("YOUR FOLDER WHERE YOU WANT TO STORE THE RESULS")<br><br>path =3D getw=
d()<br><br>for (i
 in "spColumID") {<br><br>#Create a folder you store the results for each s=
pecies separately.<br>dir.create(paste(path, "/", names[i], sep=3D""))<br><=
br>#Set the workspace in this folder<br>setwd(paste(path, "/", names[i], se=
p=3D""))<br><br>Initial.State (Response=3DSp.Env[,i], Explanatory=3DSp.Env[=
,c(250,248,251,199,164,181)],IndependentResponse=3DNULL, IndependentExplana=
tory=3DNULL,sp.name=3Dnames[i])<br><br>Models(GLM =3D T, TypeGLM =3D "quad"=
, Test =3D "AIC", GBM =3D T, No.trees =3D 3000, GAM =3D T, Spline=3D2, CTA =
=3D T, CV.tree =3D 50, ANN =3D T, CV.ann =3D 2, SRE =3D F, FDA =3D T, MARS =
=3D T, RF =3D T, NbRunEval =3D 1, DataSplit =3D 70, Yweights=3DNULL, Roc=3D=
T, Optimized.Threshold.Roc=3DT, Kappa=3DT, TSS=3DT, KeepPredIndependent =3D=
 F, VarImport=3D5, NbRepPA=3D1, strategy=3D"sre", coor=3DCoor, distance=3D2=
, nb.absences=3Dsum(Sp.Env[,i]))<br><br>#keep the files you want to keep in=
 a vector before deleting everything<br>t=3D c("path", "Sp.Env", "names")<b=
r>Rem =3D ls()<br><br>#Delete everything but the object in
 t.<br>rm(list=3D(Rem[is.na(match(Rem, t))]))<br><br>}<br><br><br><br>Hope =
it helps,<br>Best<br>Wilfried<br><br><br><br><br><br><br>&gt; <br>&gt; <br>=
&gt; Thank you very much in advance for reading such a long post with 3 Que=
stions!<br>&gt; <br>&gt; Pep<br>&gt; <br>&gt; <br>&gt; ____________________=
___________________________<br>&gt; Biomod-commits mailing list<br>&gt; <a =
ymailto=3D"mailto:Biomod-commits at lists.r-forge.r-project.org" href=3D"/mc/c=
ompose?to=3DBiomod-commits at lists.r-forge.r-project.org">Biomod-commits at list=
s.r-forge.r-project.org</a><br>&gt; <a href=3D"https://lists.r-forge.r-proj=
ect.org/cgi-bin/mailman/listinfo/biomod-commits" target=3D"_blank">https://=
lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits</a><br>=
<br>--------------------------<br>Dr. Wilfried Thuiller<br>Laboratoire d'Ec=
ologie Alpine, UMR CNRS 5553<br>Universit? Joseph Fourier<br>BP53, 38041 Gr=
enoble cedex 9, France<br>tel: +33 (0)4 76 51 44 97<br>fax: +33 (0)4 76 51 =
42
 79<br><br>Email: <a ymailto=3D"mailto:wilfried.thuiller at ujf-grenoble.fr" h=
ref=3D"/mc/compose?to=3Dwilfried.thuiller at ujf-grenoble.fr">wilfried.thuille=
r at ujf-grenoble.fr</a><br>Home page: <a href=3D"http://www.will.chez-alice.f=
r" target=3D"_blank">http://www.will.chez-alice.fr</a><br>Website: <a href=
=3D"http://www-leca.ujf-grenoble.fr/equipes/tde.htm" target=3D"_blank">http=
://www-leca.ujf-grenoble.fr/equipes/tde.htm</a><br><br>FP6 European MACIS p=
roject: <a href=3D"http://www.macis-project.net" target=3D"_blank">http://w=
ww.macis-project.net</a><br>FP6 European EcoChange project: <a href=3D"http=
://www.ecochange-project.eu" target=3D"_blank">http://www.ecochange-project=
.eu</a><br><br><br><br><br><br>-------------- next part --------------<br>A=
n HTML attachment was scrubbed...<br>URL: &lt;<a href=3D"http://lists.r-for=
ge.r-project.org/pipermail/biomod-commits/attachments/20100705/cec1a13b/att=
achment.htm"
 target=3D"_blank">http://lists.r-forge.r-project.org/pipermail/biomod-comm=
its/attachments/20100705/cec1a13b/attachment.htm</a>&gt;<br><br>-----------=
-------------------<br><br>_______________________________________________<=
br>Biomod-commits mailing list<br><a ymailto=3D"mailto:Biomod-commits at lists=
.r-forge.r-project.org" href=3D"/mc/compose?to=3DBiomod-commits at lists.r-for=
ge.r-project.org">Biomod-commits at lists.r-forge.r-project.org</a><br><a href=
=3D"https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-com=
mits" target=3D"_blank">https://lists.r-forge.r-project.org/cgi-bin/mailman=
/listinfo/biomod-commits</a><br><br><br>End of Biomod-commits Digest, Vol 1=
5, Issue 1<br>*********************************************<br></div></bloc=
kquote></td></tr></table><br>=0A=0A=0A=0A      
--0-1134715868-1278345945=:46390--


More information about the Biomod-commits mailing list