I don't see much why to use random forest with only one predictive variable!
Recall that random forest grow trees with a random subset of variables in
competition for growing each node of the trees in the forest... How do you
make such a random subset with only one predictive variable? there is no
I agree with you about the less practical meaning of this sample of
the extreme case. I am just curious about the grammar syntax of
randomForest.
Thanks.
Hui
On Tue, Apr 13, 2004 at 05:29:06PM +0200, Philippe Grosjean wrote:
I don't see much why to use random forest with only one predictive
With only one `x' variable, RF will be identical to bagging.
This looks like a bug. I will check it out.
Andy
From: Hui Han
I agree with you about the less practical meaning of this sample of
the extreme case. I am just curious about the grammar syntax of
randomForest.
Thanks.
Hui
On Tue, 13 Apr 2004, Hui Han wrote:
Hi,
I am doing feature selection for my dataset. The following is
the extreme case where only one feature is left. But I got
the error below. So my question is that do I have to use
more than one features?
sample.subset
udomain.edu hpclass
1