Reproducing the Foba fit

[stephenjbarr]

James,

First, thank you so much for a great presentation. I am working on stepping through your code and cannot seem to get the foba fit to work. Attached is the message that I am getting. This is with the latest version of your code:

foba.fit<- train(TOTTCHY2~., data = meps.2011.2012.scrubbed[sample.ind,], preProcess=c("range"), method = "foba", trControl = fitControl, tuneLength=5, metric="RMSE") Loading required package: foba Error in train.default(x, y, weights = w, ...) : final tuning parameters could not be determined In addition: Warning messages: 1: In nominalTrainWorkflow(x = x, y = y, wts = weights, info = trainInfo, : There were missing values in resampled performance measures. 2: In train.default(x, y, weights = w, ...) : missing values found in aggregated results

I am not sure what to make of this. If helpful, this is my sessionInfo()

 > sessionInfo()
 R version 3.1.1 (2014-07-10)
 Platform: x86_64-unknown-linux-gnu (64-bit)

 locale:
  [1] LC_CTYPE=en_US.UTF-8          LC_NUMERIC=C                 
  [3] LC_TIME=en_US.UTF-8           LC_COLLATE=en_US.UTF-8       
  [5] LC_MONETARY=en_US.UTF-8       LC_MESSAGES=en_US.UTF-8      
  [7] LC_PAPER=en_US.UTF-8          LC_NAME=en_US.UTF-8          
  [9] LC_ADDRESS=en_US.UTF-8        LC_TELEPHONE=en_US.UTF-8     
 [11] LC_MEASUREMENT=en_US.UTF-8    LC_IDENTIFICATION=en_US.UTF-8

 attached base packages:
 [1] splines   grid      stats     graphics  grDevices utils     datasets 
 [8] methods   base     

 other attached packages:
  [1] foba_0.1        Metrics_0.1.1   MASS_7.3-35     caret_6.0-35   
  [5] ggplot2_1.0.0   FSelector_0.19  SASxport_1.5.0  Hmisc_3.14-5   
  [9] Formula_1.1-2   survival_2.37-7 lattice_0.20-29 chron_2.3-45   

 loaded via a namespace (and not attached):
  [1] acepack_1.3-3.3     BradleyTerry2_1.0-5 brglm_0.5-9        
  [4] car_2.0-21          cluster_1.15.3      codetools_0.2-9    
  [7] colorspace_1.2-4    compiler_3.1.1      digest_0.6.8       
 [10] foreach_1.4.2       foreign_0.8-61      gtable_0.1.2       
 [13] gtools_3.4.1        iterators_1.0.7     latticeExtra_0.6-26
 [16] lme4_1.1-7          Matrix_1.1-4        minqa_1.2.3        
 [19] munsell_0.4.2       nlme_3.1-117        nloptr_1.0.4       
 [22] nnet_7.3-8          plyr_1.8.1          proto_0.3-10       
 [25] randomForest_4.6-10 RColorBrewer_1.0-5  Rcpp_0.11.3        
 [28] reshape2_1.4        rJava_0.9-6         rpart_4.1-8        
 [31] RWeka_0.4-23        RWekajars_3.7.11-1  scales_0.2.4       
 [34] stringr_0.6.2       tools_3.1.1        

Thanks!

[stephenjbarr]

Note that every other line of code seems to work, just not that one.

[thejamesmarq]

Hi Stephen,

That sucks.

I'll go and try to reproduce this and see what I can work out. I'm not having the issue on my machine, so I'm wondering if it's an environment specific problem.

Out of curiosity, what distribution of linux are you using? I'm going to spin up a VM somewhere and see if I can reproduce the problem.

-James

On Wed, Apr 22, 2015 at 10:13 PM, Stephen Jeffrey Barr < notifications@github.com> wrote:

Note that every other line of code seems to work, just not that one.

— Reply to this email directly or view it on GitHub https://github.com/OpenDataMining/jamesmarq/issues/1#issuecomment-95435183 .

[stephenjbarr]

I am using Ubuntu 14.10. I am using the distribution of R from Revolution Analytics. You are on OSX right?

[stephenjbarr]

I am going to give it a try in an Ubuntu-based docker container using the stock R from Ubuntu's repos. I doubt that anything will change but I suppose it does not hurt to rule things out.

[thejamesmarq]

Right, it shouldn't really make much of a difference.

I haven't really worked much with the Revolution Analytics version of R, although I know I'll be getting access in the coming weeks. I'm not sure if it would make much of a difference, but could you try installing one of the versions from the R Foundation and re-run the code?

-James

On Thu, Apr 23, 2015 at 10:52 AM, Stephen Jeffrey Barr < notifications@github.com> wrote:

I am using Ubuntu 14.10. I am using the distribution of R from Revolution Analytics http://www.revolutionanalytics.com/revolution-r-open. You are on OSX right?

— Reply to this email directly or view it on GitHub https://github.com/OpenDataMining/jamesmarq/issues/1#issuecomment-95669167 .

[stephenjbarr]

I am trying to stock R on an Ubuntu docker container right now.

On Thu, Apr 23, 2015, at 11:13 AM, James Marquardt wrote:

Right, it shouldn't really make much of a difference.

I haven't really worked much with the Revolution Analytics version of R,

although I know I'll be getting access in the coming weeks. I'm not sure if

it would make much of a difference, but could you try installing one of the

versions from the R Foundation and re-run the code?

-James

On Thu, Apr 23, 2015 at 10:52 AM, Stephen Jeffrey Barr <

notifications@github.com> wrote:

I am using Ubuntu 14.10. I am using the distribution of R from Revolution

Analytics http://www.revolutionanalytics.com/revolution-r-open. You are

on OSX right?

—

Reply to this email directly or view it on GitHub

https://github.com/OpenDataMining/jamesmarq/issues/1#issuecomment-95669167

.

— Reply to this email directly or view it on GitHub[1].

Links:

1. https://github.com/OpenDataMining/jamesmarq/issues/1#issuecomment-95674857