Random forest with categorical variables

[fcas80]

In running a random forest model with the random forest package, do independent categorical variables need to be converted to factors? Does the dependent categorical variable need to be converted to a factor?

I would think the dependent variable does. I'm not as sure about the independent variables. Thank you.

[GreyMerchant]

Hello @fcas80,

You can see here that they do in fact convert the dependent categorical variable to a factor in the vignette here: https://htmlpreview.github.io/?https://github.com/geneticsMiNIng/BlackBoxOpener/blob/master/randomForestExplainer/inst/doc/randomForestExplainer.html

I would assume you will have to do the same for the independent variables as it otherwise won't know that it should treat it in that way.

[Max]

Yes for the outcome data. It slightly depends on the implementation but most of those that I have seem require a factor.

For the predictors (independent variables), that's up to you. This is extensively discussed here. For example:

[fcas80]

GreyMerchant, thanks for your reply. In the vignette you shared, the author does convert the dependent variable to a factor, but he does not convert any independent variables to factors.