From mestre.frederico at gmail.com Mon Sep 2 13:16:46 2013 From: mestre.frederico at gmail.com (Frederico Mestre) Date: Mon, 2 Sep 2013 12:16:46 +0100 Subject: [Biomod-commits] Variable importance Message-ID: <008b01cea7cd$ea4863b0$bed92b10$@gmail.com> Hello, I've run biomod2 and I want to get the variable importance information. I ran the function getModelsVarImport() on an object of class BIOMOD.models.out and I got, as a result, an "NA". Am I doing something wrong? How can I get variable importance? Thanks, Frederico Mestre From damien.georges2 at gmail.com Mon Sep 2 14:25:11 2013 From: damien.georges2 at gmail.com (Damien Georges) Date: Mon, 02 Sep 2013 14:25:11 +0200 Subject: [Biomod-commits] (no subject) In-Reply-To: References: Message-ID: <522483A7.9080903@gmail.com> Hi Jenny, On 14/08/2013 16:26, Jenny Williams wrote: > I am still trying to get my head around biomod2. I have run through the tutorial a few times, which works really well in a linear format. > > But, I want to see the models and assess them at every part of the process. So, I need to: > > 1: be able to re-access all the files from /.BIOMOD_DATA/ once R is closed and all the file links are lost. > e.g myBiomodModelOut You just have to load the 'formated.input.data' object within /.BIOMOD_DATA/ directory. Then object loaded (i.e myBiomodModelOut) is loaded as 'data' in your workspace. So typing smth like myBiomodModelOut <- data should let you re-run your previous script quite easily. > > 2: call the summary parameters for the models e.g GLM, I can see the files but not sure how to access them. > e.g >> myGLMs <- BIOMOD_LoadModels(myBiomodModelOut, models='GLM') > #just produces a list >> summary(myGLMs[1]) > Length Class Mode > 1 character character > #summary(GLM) doesn't work, but is the output that I am looking to find. Here objects are also loaded with standard names in your workspace. The names of objects are stored within myGLMs (just type myGLMs in your console to get it) > > 3. find the split datasets used for each of the iterations BIOMOD_Modeling options; NbRunEval for DataSplit This info are stored within calib.lines object of /.BIOMOD_DATA/ directory > > > Any help or pointers in the right direction would be greatly appreciated. > FYI the vignette does not seem to work: http://127.0.0.1:15505/library/biomod2/doc/index.html I guess that it is due to package installation issue. reinstall the package should solve it. Hope that helps, Damien. > > > > ****************** > Jenny Williams > Spatial Information Scientist, GIS Unit > Herbarium, Library, Art & Archives Directorate > Royal Botanic Gardens, Kew > Richmond, TW9 3AB, UK > > Tel: +44 (0)208 332 5277 > email: jenny.williams at kew.org > ****************** > > Film: The Forgotten Home of Coffee - Beyond the Gardens > Stories: Coffee Expedition - Ethiopia > Kew in Harapan Rainforest Sumatra > Articles: Seeing the wood for the trees > How Kew's GIS team and South East Asia botanists are working to help conserve and restore a rainforest in Sumatra. Download a pdf of this article here. > > > ________________________________ > The Royal Botanic Gardens, Kew is a non-departmental public body with exempt charitable status, whose principal place of business is at Royal Botanic Gardens, Kew, Richmond, Surrey TW9 3AB, United Kingdom. > > The information contained in this email and any attachments is intended solely for the addressee(s) and may contain confidential or legally privileged information. If you have received this message in error, please return it immediately and permanently delete it. Do not use, copy or disclose the information contained in this email or in any attachment. > > Any views expressed in this email do not necessarily reflect the opinions of RBG Kew. > > Any files attached to this email have been inspected with virus detection software by RBG Kew before transmission, however you should carry out your own virus checks before opening any attachments. RBG Kew accepts no liability for any loss or damage which may be caused by software viruses. > _______________________________________________ > 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 From damien.georges2 at gmail.com Mon Sep 2 15:08:22 2013 From: damien.georges2 at gmail.com (Damien Georges) Date: Mon, 02 Sep 2013 15:08:22 +0200 Subject: [Biomod-commits] (no subject) In-Reply-To: References: Message-ID: <52248DC6.30700@gmail.com> Dear Javier, Your scripts seem to be ok. Do you get a console error message when you make ensemble and/or projections? Is 'myExpl' a rater or a dataframe? If it is a raster you can access projected raster with get_prediction() function else you will get a data.frame that you will have to rasterize manually. Hope that helps, Damien. PS : If you don't work with the last version of the package, I recommend you to update it (**|install.packages("biomod2", repos="http://R-Forge.R-project.org")|**) That will probably solve your evaluation issue. On 23/08/2013 19:23, Javier Nori wrote: > Dear all! > > I am new with Biomod. I'm trying to perform an ensemble between results of > five algorithms ('MARS','GAM','GBM', 'MAXENT', 'GLM', 'FDA'), using > Pres-PAbs data. I have not problems to generate and project the results of > the individual models. However probably i'am making a mistake in the > emsemble of them or in the projection' script because I cannot generate the > rasters of the ensemble. In addition, I cannot obtain the values of the > evaluation index of the ensemble (*Error: Error in (function (classes, > fdef, mtable) : unable to find an inherited method for function > ?getModelsEvaluations? for signature ?"BIOMOD.EnsembleModeling.out"?*) > > Could anyone help me please? > > Thanks in advance!! > > below I attached the scripts for projection and ensemble > ** > Ensemble > myBiomodEM <- BIOMOD_EnsembleModeling( > modeling.output = myBiomodModelOut, > chosen.models = 'all', > em.by='all', > eval.metric = c('ROC'), > eval.metric.quality.threshold = c(0.8), > prob.mean = T, > prob.cv = T, > prob.ci = T, > prob.ci.alpha = 0.05, > prob.median = T, > committee.averaging = T, > prob.mean.weight = T, > prob.mean.weight.decay = 'proportional' ) > > Projection > myBiomodProj <- BIOMOD_Projection( > modeling.output = myBiomodModelOut, > new.env = myExpl, > proj.name = 'current', > selected.models = 'all', > binary.meth = 'TSS', > filtered.meth ='TSS', > cmpress = 'gzip', > clamping.mask = T, > output.format = '.img') > From damien.georges2 at gmail.com Mon Sep 2 15:43:40 2013 From: damien.georges2 at gmail.com (Damien Georges) Date: Mon, 02 Sep 2013 15:43:40 +0200 Subject: [Biomod-commits] evaluation of ensemble models In-Reply-To: <20130828201343.Horde.pq9-jag66Bn2Jk_lHPhsAw7@webmail.csic.es> References: <20130828201343.Horde.pq9-jag66Bn2Jk_lHPhsAw7@webmail.csic.es> Message-ID: <5224960C.9070207@gmail.com> Dear Raquel, For ensemble models evaluations scores are calculated as for all formal models. (see BIOMOD_Modeling help file for more details). Data use compute evaluation depends on the way you combine your models please see 'EnsembleModelingAssembly' vignette if you are interested in this point. Hope that helps, Damien. On 28/08/2013 20:13, Raquel A. Garcia wrote: > Hi, > I have a question about the ensemble function in biomod2 version > 2.1.15 - how are the evaluation scores obtained? > thanks, > Raquel > > > ................ > Raquel A. Garcia > Integrative Biology and Global Change Group | www.ibiochange.mncn.csic.es > Center for Macroecology, Evolution and Climate | www.macroecology.ku.dk > > > _______________________________________________ > 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 > From damien.georges2 at gmail.com Mon Sep 2 15:51:24 2013 From: damien.georges2 at gmail.com (Damien Georges) Date: Mon, 02 Sep 2013 15:51:24 +0200 Subject: [Biomod-commits] Variable importance In-Reply-To: <008b01cea7cd$ea4863b0$bed92b10$@gmail.com> References: <008b01cea7cd$ea4863b0$bed92b10$@gmail.com> Message-ID: <522497DC.1070007@gmail.com> Hi Frederico, Are you sure to have run some variable importance calculation at BIOMOD_Modeling step (i.e set VarImport arg to positive value (number of permutation computed))? Best, Damien On 02/09/2013 13:16, Frederico Mestre wrote: > Hello, > > > > I've run biomod2 and I want to get the variable importance information. > > > > I ran the function getModelsVarImport() on an object of class > BIOMOD.models.out and I got, as a result, an "NA". > > > > Am I doing something wrong? How can I get variable importance? > > > > Thanks, > > > > Frederico Mestre > > > > _______________________________________________ > 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 From mestre.frederico at gmail.com Tue Sep 10 00:10:05 2013 From: mestre.frederico at gmail.com (Frederico Mestre) Date: Mon, 9 Sep 2013 23:10:05 +0100 Subject: [Biomod-commits] BIOMOD_ConvertOldRun Message-ID: <001501ceada9$592d43a0$0b87cae0$@gmail.com> Hello: I?m trying to convert to biomod2 an old BIOMOD project by using BIOMOD_ConvertOldRun(). However I get this message: myspecies run convertion... BIOMOD.formated.data creation BIOMOD.Model.Options creation Converting Models ComputedError in FUN("myspecies"[[1L]], ...) : models directory doesn't exist! But I?ve got a models folder in the working directory. I don?t know what happened. Any help? Thanks, Frederico From damien.georges2 at gmail.com Tue Sep 10 11:16:30 2013 From: damien.georges2 at gmail.com (Damien Georges) Date: Tue, 10 Sep 2013 11:16:30 +0200 Subject: [Biomod-commits] BIOMOD_ConvertOldRun In-Reply-To: <001501ceada9$592d43a0$0b87cae0$@gmail.com> References: <001501ceada9$592d43a0$0b87cae0$@gmail.com> Message-ID: <522EE36E.3030702@gmail.com> Dear Frederico, Are you sure to give to BIOMOD_ConvertOldRun() the right object? Could you please send me the lines of code you use? Best, Damien. PS: Is re-runing the models within biomod2 is too time consuming? If it's not, I encourage you to redo the modeling procedure in case of this bug persists. On 10/09/2013 00:10, Frederico Mestre wrote: > Hello: > > > > I'm trying to convert to biomod2 an old BIOMOD project by using > BIOMOD_ConvertOldRun(). > > > > However I get this message: > > > > myspecies run convertion... > > BIOMOD.formated.data creation > > BIOMOD.Model.Options creation > > Converting Models ComputedError in FUN("myspecies"[[1L]], ...) : > models directory doesn't exist! > > > > But I?ve got a models folder in the working directory. I don't know what > happened. > > > > Any help? > > > > Thanks, > > > > Frederico > > > > > > _______________________________________________ > 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 From javiernori at gmail.com Thu Sep 26 22:30:25 2013 From: javiernori at gmail.com (Javier Nori) Date: Thu, 26 Sep 2013 17:30:25 -0300 Subject: [Biomod-commits] (no subject) In-Reply-To: <52248DC6.30700@gmail.com> References: <52248DC6.30700@gmail.com> Message-ID: Dear Deamien: Thank you very much for your answer! myExpl are rasters --- myExpl<-stack("D:/prueba/ACA/bio1","D:/ .....---I don't understand how to use the function 'getprediction' with these rasters. after some adjustments in the script, I do not get any errors (console or warning). However, although I can create the raster for all the individual projections, I'm unable to generate the total consensus files. My list of files: > list.files("Bammody/proj_current/") [1] "Bammody.current.projection.out" [2] "proj_current_Bammody.img" [3] "proj_current_Bammody.img.aux.xml" [4] "proj_current_Bammody_TSSbin.img" [5] "proj_current_Bammody_TSSbin.img.aux.xml" [6] "proj_current_ClampingMask.img" [7] "proj_current_ClampingMask.img.aux.xml" I'm probably forgetting some lines in my script. I would like to send you the files and maybe you can help me find the 'mistake'. Would that be possible? Thanks in advance Javier. 2013/9/2 Damien Georges > Dear Javier, > > Your scripts seem to be ok. > Do you get a console error message when you make ensemble and/or > projections? > > Is 'myExpl' a rater or a dataframe? If it is a raster you can access > projected raster with get_prediction() function else you will get a > data.frame that you will have to rasterize manually. > > Hope that helps, > Damien. > > PS : If you don't work with the last version of the package, I recommend > you to update it (* install.packages("biomod2", repos= > "http://R-Forge.R-project.org" )*) That > will probably solve your evaluation issue. > > > On 23/08/2013 19:23, Javier Nori wrote: > > Dear all! > > I am new with Biomod. I'm trying to perform an ensemble between results of > five algorithms ('MARS','GAM','GBM', 'MAXENT', 'GLM', 'FDA'), using > Pres-PAbs data. I have not problems to generate and project the results of > the individual models. However probably i'am making a mistake in the > emsemble of them or in the projection' script because I cannot generate the > rasters of the ensemble. In addition, I cannot obtain the values of the > evaluation index of the ensemble (*Error: Error in (function (classes, > fdef, mtable) : unable to find an inherited method for function > ?getModelsEvaluations? for signature ?"BIOMOD.EnsembleModeling.out"?*) > > Could anyone help me please? > > Thanks in advance!! > > below I attached the scripts for projection and ensemble > ** > Ensemble > myBiomodEM <- BIOMOD_EnsembleModeling( > modeling.output = myBiomodModelOut, > chosen.models = 'all',em.by='all', > eval.metric = c('ROC'), > eval.metric.quality.threshold = c(0.8), > prob.mean = T,prob.cv = T,prob.ci = T, > prob.ci.alpha = 0.05, > prob.median = T, > committee.averaging = T, > prob.mean.weight = T, > prob.mean.weight.decay = 'proportional' ) > > Projection > myBiomodProj <- BIOMOD_Projection( > modeling.output = myBiomodModelOut, > new.env = myExpl,proj.name = 'current', > selected.models = 'all', > binary.meth = 'TSS', > filtered.meth ='TSS', > cmpress = 'gzip', > clamping.mask = T, > output.format = '.img') > > > > > -- *************************************************************************** Javier Nori Centro de Zoolog?a Aplicada - F.C.E.F.y.N. Universidad Nacional de C?rdoba From javiernori at gmail.com Thu Sep 26 22:32:47 2013 From: javiernori at gmail.com (Javier Nori) Date: Thu, 26 Sep 2013 17:32:47 -0300 Subject: [Biomod-commits] problems to create totalconsensus files Message-ID: Dear Deamien: Thank you very much for your answer! myExpl are rasters --- myExpl<-stack("D:/prueba/ACA/ bio1","D:/ .....---I don't understand how to use the function 'getprediction' with these rasters. after some adjustments in the script, I do not get any errors (console or warning). However, although I can create the raster for all the individual projections, I'm unable to generate the total consensus files. My list of files: > list.files("Bammody/proj_current/") [1] "Bammody.current.projection.out" [2] "proj_current_Bammody.img" [3] "proj_current_Bammody.img.aux.xml" [4] "proj_current_Bammody_TSSbin.img" [5] "proj_current_Bammody_TSSbin.img.aux.xml" [6] "proj_current_ClampingMask.img" [7] "proj_current_ClampingMask.img.aux.xml" I'm probably forgetting some lines in my script. I would like to send you the files and maybe you can help me find the 'mistake'. Would that be possible? Thanks in advance Javier. -- *************************************************************************** Javier Nori Centro de Zoolog?a Aplicada - F.C.E.F.y.N. Universidad Nacional de C?rdoba From damien.georges2 at gmail.com Fri Sep 27 08:57:14 2013 From: damien.georges2 at gmail.com (Damien Georges) Date: Fri, 27 Sep 2013 08:57:14 +0200 Subject: [Biomod-commits] problems to create totalconsensus files In-Reply-To: References: Message-ID: <52452C4A.4010504@gmail.com> Dear Javier, Did you work with the "Bammody.current.projection.out" object as BIOMOD_EnsembleForecasting arg? Are you still working in the same directory than the one you made your analysis? As you suggest, I guess that you should send me your script (and your data if it is not to heavy) offline. I'll try to have a look on it and tell you what's going wrong. Best, Damien. On 26/09/2013 22:32, Javier Nori wrote: > Dear Deamien: > Thank you very much for your answer! > myExpl are rasters --- myExpl<-stack("D:/prueba/ACA/ > bio1","D:/ .....---I don't understand how to use the function > 'getprediction' with these rasters. > > after some adjustments in the script, I do not get any errors (console or > warning). However, although I can create the raster for all the individual > projections, I'm unable to generate the total consensus files. My list of > files: > >> list.files("Bammody/proj_current/") > [1] "Bammody.current.projection.out" > [2] "proj_current_Bammody.img" > [3] "proj_current_Bammody.img.aux.xml" > [4] "proj_current_Bammody_TSSbin.img" > [5] "proj_current_Bammody_TSSbin.img.aux.xml" > [6] "proj_current_ClampingMask.img" > [7] "proj_current_ClampingMask.img.aux.xml" > > I'm probably forgetting some lines in my script. I would like to send you > the files and maybe you can help me find the 'mistake'. Would that be > possible? > > Thanks in advance > Javier. >