<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix">Dear Jesus,<br>
<br>
I agree with your comment, that's why we don't want to give a mean
or a median of variables importance of all single models selected
as variable importance... <br>
<br>
As for ensemble models evaluation, we have to consider ensemble
models as "true" models.. So we have to apply the same methodology
than for the single models..<br>
We must randomise a variable, calculate all single models
predictions with this 'new set of data', combine predictions to
build our ensemble model, calculate the correlation between the
'true' predictions of our 'ensemble model' and the ones with a
randomised variable....Do it several times for all variables and
all models.... It will be really time consuming but might be
interesting in some cases.<br>
<br>
I guess that calculating variables importance according to
methodology describes above will give you a quite interpretable
value... <br>
<br>
Cheers,<br>
<br>
Damien.<br>
<br>
<br>
On 13/09/2012 09:57, Jesus wrote:<br>
</div>
<blockquote
cite="mid:CA+by4T77VnrTCVq7XsTtkeSteHrtn6buWgdpo5HFHcUhEdauww@mail.gmail.com"
type="cite"><br>
<br>
<div class="gmail_quote">On 13 September 2012 09:49, Damien
Georges <span dir="ltr"><<a moz-do-not-send="true"
href="mailto:damien.georges2@gmail.com" target="_blank">damien.georges2@gmail.com</a>></span>
wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
<div bgcolor="#FFFFFF" text="#000000">
<div>Dear Pablo,<br>
<br>
There is no way to extract variables importance from a
Ensemble model because it's not calculated yet.. We are
thinking about the way to implement it because it's a
really time consuming step.. Concerning the response
plots, the problem is the same.. <br>
I will tell you when this functionalities will be ready.<br>
<br>
Cheers,<br>
<br>
Damien. <br>
<div>
<div class="h5">Dear Damien, thanks for the responses to
this threat. I however have a question/observation
about the variables importance in a ensemble of
models. How do you really interpret the variable
importance coming from an ensemble of models? Imaging
two algorithms gave you high AUC values so they are
considered good models, but choose different
environmental variables, what would be the variable
importance result of the ensemble? I find the
interpretation of this a bit tricky. and not that
straight forward.</div>
</div>
</div>
</div>
</blockquote>
<div><br>
</div>
<div>Jesus </div>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
<div bgcolor="#FFFFFF" text="#000000">
<div>
<div>
<div class="h5">
</div>
</div>
</div>
</div>
</blockquote>
<div> </div>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
<div bgcolor="#FFFFFF" text="#000000">
<div>
<div>
<div class="h5">On 12/09/2012 17:59, Pablo Riul wrote:<br>
</div>
</div>
</div>
<div>
<div class="h5">
<blockquote type="cite">
<div style="font-size:18pt;font-family:times new
roman,new york,times,serif">
<div><span>Dear Damien,</span></div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif"><span><br>
</span></div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif"><span>Ok,
thanks! Just another thing... I'm not sure if
you received my anterior message. </span> I
tried to get the var importances of a consensus
model using something like getModelsVarImport() to
an object created by the BIOMOD_EnsembleModeling()
function but it was not possible. Is there any way
to get these information? Also, will be possible
to get the response plots for this same object?</div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif"><br>
</div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif">Cheers,</div>
<div> </div>
<div>Pablo Riul<br>
<br>
Departamento de Engenharia e Meio Ambiente<br>
Centro de Ciências Aplicadas e Educação<br>
Universidade Federal da Paraíba - Campus IV<br>
R: Mangueira s/n, Centro CEP: 58.297-000<br>
Rio Tinto - Paraíba - Brasil</div>
<div><br>
</div>
<div style="font-size:18pt;font-family:'times new
roman','new york',times,serif">
<div style="font-size:12pt;font-family:'times new
roman','new york',times,serif">
<div dir="ltr"> <font face="Arial">
<hr size="1"> <b><span
style="font-weight:bold">De:</span></b>
Damien Georges <a moz-do-not-send="true"
href="mailto:damien.georges2@gmail.com"
target="_blank"><damien.georges2@gmail.com></a><br>
<b><span style="font-weight:bold">Para:</span></b>
<a moz-do-not-send="true"
href="mailto:biomod-commits@lists.r-forge.r-project.org"
target="_blank">biomod-commits@lists.r-forge.r-project.org</a>;
Pablo Riul <a moz-do-not-send="true"
href="mailto:pabloriul@yahoo.com.br"
target="_blank"><pabloriul@yahoo.com.br></a>
<br>
<b><span style="font-weight:bold">Enviadas:</span></b>
Quarta-feira, 12 de Setembro de 2012 10:52<br>
<b><span style="font-weight:bold">Assunto:</span></b>
Re: [Biomod-commits] Warning in
BIOMOD_FormatingData<br>
</font> </div>
<br>
<div>
<div>
<div>Dear Pablo,<br>
<br>
Don't worry about it.. It's just a warning
indicating that some function of raster
package have changed of names.. <br>
I took this into account in the last
biomod2 version so warnings will disappear
when you'll update the package .<br>
<br>
Best,<br>
<br>
Damien <br>
<br>
On 12/09/2012 14:46, Pablo Riul wrote:<br>
</div>
<blockquote type="cite">
<div
style="font-size:18pt;font-family:'times
new roman','new york',times,serif">
<div><span>Dear list,</span></div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif"><span><br>
</span></div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif"><span>I
updated my packages and I'm now
using raster 2.0-12. When I created
myBiomodData using the
BIOMOD_FormatingData function I
received the warning below:</span></div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif"><span><br>
</span></div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif"><span>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;color:#1c39f6"><span
style="color:#99228d">> </span>myBiomodData
<-
BIOMOD_FormatingData(resp.var =
myResp,expl.var = myExpl,resp.xy =
myRespXY,<a moz-do-not-send="true"
href="http://resp.name"
target="_blank">resp.name</a> =
myRespName,PA.nb.rep =
1,PA.nb.absences =
1000,PA.strategy = 'random')</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;min-height:19.0px"><br>
</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px Monaco">-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Mhisp Data Formating
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;min-height:19.0px"><br>
</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px Monaco"> !
No data has been set aside for
modeling evaluation</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px Monaco"> >
Pseudo Absences Selection
checkings...</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px Monaco"> >
random pseudo absences selection</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px Monaco"> >
Pseudo absences are selected in
explanatory variables</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px Monaco">-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Done
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;color:#ff1f17">Warning
message:</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;color:#ff1f17">In .local(x,
rcl, ...) :</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;color:#ff1f17"> raster
function "reclass" has been
deprecated and will be removed
from the package;</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;color:#ff1f17">Please use
"reclassify" instead</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;color:#ff1f17"><br>
</div>
<div style="margin:0.0px 0.0px 0.0px
0.0px;font:14.2px
Monaco;color:#ff1f17"><br>
</div>
</span></div>
<div>Its not a problem now, but maybe in
next updates of package raster the
reclass function may be not available
anymore.</div>
<div><br>
</div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif">Cheers,</div>
<div
style="font-style:normal;font-size:24px;background-color:transparent;font-family:'times
new roman','new york',times,serif"> </div>
<div>Pablo Riul<br>
<br>
Departamento de Engenharia e Meio
Ambiente<br>
Centro de Ciências Aplicadas e
Educação<br>
Universidade Federal da Paraíba -
Campus IV<br>
R: Mangueira s/n, Centro CEP:
58.297-000<br>
Rio Tinto - Paraíba - Brasil</div>
</div>
<br>
<fieldset></fieldset>
<br>
<pre>_______________________________________________
Biomod-commits mailing list
<a moz-do-not-send="true" rel="nofollow" href="mailto:Biomod-commits@lists.r-forge.r-project.org" target="_blank">Biomod-commits@lists.r-forge.r-project.org</a>
<a moz-do-not-send="true" rel="nofollow" href="https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits" target="_blank">https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits</a></pre>
</blockquote>
<br>
</div>
</div>
<br>
<br>
</div>
</div>
</div>
</blockquote>
<br>
</div>
</div>
</div>
<br>
_______________________________________________<br>
Biomod-commits mailing list<br>
<a moz-do-not-send="true"
href="mailto:Biomod-commits@lists.r-forge.r-project.org">Biomod-commits@lists.r-forge.r-project.org</a><br>
<a moz-do-not-send="true"
href="https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits"
target="_blank">https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits</a><br>
</blockquote>
</div>
<br>
</blockquote>
<br>
</body>
</html>