[R] how to extract the variables used in decision tree

[David Winsemius]

On May 11, 2010, at 6:49 PM, Changbin Du wrote:

> HI, Dear R community,
>
> How to extract the variables actually used in tree construction? I  
> want to
> extract these variables and combine other variable as my features in  
> next
> step model building.

help(package=rpart, rpart.object)


>
>> printcp(fit.dimer)
>

Perhaps:

fit.dimer$terms


> Classification tree:
> rpart(formula = outcome ~ ., data = p_df, method = "class")
>
> Variables actually used in tree construction:
> [1] CT DP DY FC NE NW QT SK TA WC WD WG WW YG
>
> Root node error: 608/1743 = 0.34882
>
> n= 1743
>
>        CP nsplit rel error  xerror     xstd
> 1 0.185033      0   1.00000 1.00000 0.032726
> 2 0.052632      2   0.62993 0.65132 0.028773
> 3 0.026316      4   0.52467 0.58059 0.027596
> 4 0.025768      5   0.49836 0.57072 0.027419
> 5 0.019737      8   0.42105 0.56086 0.027239
> 6 0.018092      9   0.40132 0.55263 0.027087
> 7 0.013158     12   0.34704 0.52796 0.026616
> 8 0.011513     13   0.33388 0.50000 0.026056
> 9 0.010000     15   0.31086 0.48520 0.025748
>
>
> THanks so much!
>
> -- 
> Sincerely,
> Changbin
> --
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

David Winsemius, MD
West Hartford, CT