[R] Error in riv package

David Winsemius dwinsemius at comcast.net
Tue Aug 16 21:47:50 CEST 2016


> On Aug 16, 2016, at 11:07 AM, Shivi Bhatia <shivipmp82 at gmail.com> wrote:
> 
> HI Team,
> 
> I am working to reduce the # of predictor variables from the model using
> woe and iv values. For this i am using riv package. However i am having a
> hard time installing this package:
> 
> install_github("riv","tomasgreif")
> install.packages("DBI",dependencies=TRUE)
> 
> The error i receive is :
> *Username parameter is deprecated. Please use tomasgreif/riv *

No. You did not get an error message. It was clearly labeled a :Warning message". Here is the full console output from that call:

> install_github("riv","tomasgreif")
Downloading GitHub repo tomasgreif/riv at master
from URL https://api.github.com/repos/tomasgreif/riv/zipball/master
Installing woe
'/Library/Frameworks/R.framework/Resources/bin/R' --no-site-file --no-environ  \
  --no-save --no-restore --quiet CMD INSTALL  \
  '/private/var/folders/yq/m3j1jqtj6hq6s5mq_v0jn3s80000gn/T/Rtmp6YDYoj/devtoolsadc32ead1a82/tomasgreif-woe-43fcf26'  \
  --library='/Library/Frameworks/R.framework/Versions/3.3/Resources/library'  \
  --install-tests 

* installing *source* package ‘woe’ ...
** R
** data
*** moving datasets to lazyload DB
** demo
** preparing package for lazy loading
** help
*** installing help indices
** building package indices
** testing if installed package can be loaded
* DONE (woe)
Warning message:
Username parameter is deprecated. Please use tomasgreif/riv 


It's just telling you to use this next time:

install_github("tomasgreif/riv")

I will lay long odds that you already have the package installed.

I cannot comment on what this package purports to do. I'm somewhat suspicious that it is statistically suspect.

-- 
David.

> 
> The other approach i have to use the library(InformationValue). I have this
> as below:
> WOE(X=SFDC1$support_cat, Y=SFDC1$survey)
> WOETable(X=SFDC1$support_cat, Y=SFDC1$survey)
> IV(X=SFDC1$support_cat, Y=SFDC1$survey)
> 
> This package assists me achieve what i am looking for but here i need to
> add one independent variable at a time to see whether it is predictive or
> not. Is there a way i can add all variables at a go or have to add one by
> one,
> 
> For the above package (riv) i have seen an example which helps to take the
> entire data range and  predictive the power of each predictor. The link for
> the same is:
> https://www.r-bloggers.com/r-credit-scoring-woe-information-value-in-woe-
> package/
> 
> Thanks, Shivi
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

David Winsemius
Alameda, CA, USA



More information about the R-help mailing list