Replying to quite old thread..but its awesome
RWeka package is quite good in dissecting the tree in more than 2 parts.
As someone said J48 which is implementation of C4.5 and thus ID3 will be
helpful.
Also to plot you may have to rage a war like situation.
Let us knoe if you face any problem
Here is the complete dataset:
Outlook TempHumidityWindy Class
Sunny 2 2 Yes Play
Sunny 2 1 Yes Don't Play
Sunny 3 1 No Don't Play
Sunny 2 1 No Don't Play
Sunny 1 2 No Play
Overcast2
@Above,
Thanks. That certainly helps.
I understand that the rpart splits only in binary. Is there any support in R
to make the split have more than 2 nodes?
Cheers,
Jagdeesh
--
View this message in context:
http://r.789695.n4.nabble.com/Rpart-query-tp2991198p2991643.html
Sent from the R help m
On Mon, 11 Oct 2010, jagdeesh_mn wrote:
Hi,
Being a novice this is my first usage of R.
I am trying to use rpart for building a decision tree in R. And I have the
following dataframe
Outlook TempHumidityWindy Class
Sunny 75 70 Yes Play
Sunny 80 90 Y
Or now Im pretty sure of it as when I took your dataset and used the magic
way of ctrl-c ctrl-v to make some more observations I get a decision tree.
--
View this message in context:
http://r.789695.n4.nabble.com/Rpart-query-tp2991198p2991469.html
Sent from the R help mailing list archive at Nab
My guess is that you have two few observations is your dataset for rpart to
determin a "safe" dissision.
--
View this message in context:
http://r.789695.n4.nabble.com/Rpart-query-tp2991198p2991461.html
Sent from the R help mailing list archive at Nabble.com.
___
Dont know if it will work but you can try ctree from the party package
require(party)
bla <- ctree(Class ~ Outlook + Temp + Humidity + Windy, data=dataframe)
plot(bla)
//Joel
--
View this message in context:
http://r.789695.n4.nabble.com/Rpart-query-tp2991198p2991417.html
Sent from the R help
Hi,
Being a novice this is my first usage of R.
I am trying to use rpart for building a decision tree in R. And I have the
following dataframe
Outlook TempHumidityWindy Class
Sunny 75 70 Yes Play
Sunny 80 90 Yes Don't Play
Sunny 85 85
8 matches
Mail list logo