imbs-hl / ranger

A Fast Implementation of Random Forests
http://imbs-hl.github.io/ranger/
776 stars 192 forks source link

Accommodating different data types? #501

Open cjvanlissa opened 4 years ago

cjvanlissa commented 4 years ago

It seems to me that it should be possible to apply classification to variables of the type character and logical by converting them to factor and back, and regression to variables of the type Date by converting it to integer and back. Possibly other types as well.

Would you be interested in implementing this, or accepting a pull request that implements it?

cjvanlissa commented 4 years ago

Hmmm.. I see in the code that character and logical are already supported.. still I get an error. Will do some debugging. This idea might still be valid for Date though!

mnwright commented 4 years ago

A PR for Date outcomes is very welcome. Please also post your issues with characters and logicals.