Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

bagimpute to pmml #49

Open
YavuzDogan opened this issue Oct 26, 2018 · 1 comment
Open

bagimpute to pmml #49

YavuzDogan opened this issue Oct 26, 2018 · 1 comment

Comments

@YavuzDogan
Copy link

First of all thanks a lot for this awesome piece of work.
I failed to export a bagImputing modell which I generated with the preProcess(data, method = "bagimpute") function. Later on I found out, that there are no imputing methods implemented yet but medianInpute. Is there any development ongoing regarding different imputing methods?

@vruusmann
Copy link
Member

vruusmann commented Oct 27, 2018

Is there any development ongoing regarding different imputing methods?

It's extremely unlikely that I will be expanding support for the preProcess object by implementing model-based imputation (eg. knnImpute or bagImpute). Technically, it wouldn't be too difficult, because it can be represented in PMML as model chain where the first element is a GBM model that performs an imputation in case some value is missing, and the second element is then the "real model" element.

I'm currently looking into implementing richer workflow support using the recipes package. There's a special-purpose step for doing bagged tree imputation: https://www.rdocumentation.org/packages/recipes/versions/0.1.3/topics/step_bagimpute

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants