Giters

stekhoven / missForest

missForest is a nonparametric, mixed-type imputation method for basically any type of data for the statistical software R.

Home Page:http://stat.ethz.ch/CRAN/web/packages/missForest/index.html

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Updates on saving forests

hiltbrd opened this issue · comments

commented

Hi,
I was wondering about the status of the update regarding the saving of missForest objects to predict on? I find random forest imputation to win out over other methods but often need to use the preprocessing imputation on new data in production.

Thanks,
Dave

commented

Thank you for all the work on this fantastic tool -- wanted to bump this issue up for the exact same use case. We really like missForest but would like to use an already fit imputation model for new incoming observations.