[R] RPart

[ripley@stats.ox.ac.uk]

On Mon, 29 Apr 2002, dstierman wrote:

> I am using the rpart package and seem to have trouble with data sets that
> have columns with no data. I look at the column data in R and all values are
> NA. When this occurs, I get nothing back from the rpart function. Is there a
> way to get the rpart package to ignore these columns, without knowing what
> columns are empty?

That's what happens by default!

data(kyphosis)
kyphosis$dummy <- as.numeric(rep(NA, 81))

rpart(Kyphosis ~ ., data=kyphosis)

has a column with all NAs and works correctly, so I don't think your
hypothesis is the correct one.

> I have tried the na.action=na.omit and
> na.action=na.exclude, but neither one fixes the problem.

Both na.omit and na.exclude all the rows if each contains an NA!  Why are
you putting a column that is entirely NAs (and that's not empty, BTW) in
your formula?

It is easy to find and omit empty columns if you want to:

kyphosis[sapply(kyphosis, function(x) !all(is.na(x)))]

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._