On Jun 16, 2010, at 1:05 PM, Andrej wrote:
Sorry, I apologize. Below is the minimal example.
library(RWeka)
model <- J48(as.factor(Species)~., data = iris)
model
J48 pruned tree
------------------
Petal.Width <= 0.6: setosa (50.0)
Petal.Width > 0.6
| Petal.Width <= 1.7
| | Petal.Length <= 4.9: versicolor (48.0/1.0)
| | Petal.Length > 4.9
| | | Petal.Width <= 1.5: virginica (3.0)
| | | Petal.Width > 1.5: versicolor (3.0/1.0)
| Petal.Width > 1.7: virginica (46.0/1.0)
Number of Leaves : 5
Size of the tree : 9
So, the task is to extract the number of leases.
methods(print) # print.Weka_classifier has asterisk
getAnywhere(print.Weka_classifier)
The task performed by print.Weka_classifier is handled outside of R in
the invisible Java call.
str(model)
As a mostly uninformed guess after looking at the output of
str(model), you might get satisfaction with:
> nrow(attr(model$terms, "factors"))
[1] 5
But I am not really sure because the documentation is so sketchy about
the structure of the returned object. It appears the authors expect a
lot more knowledge about Weka trees than I have.
--
David
Andrej
On Jun 16, 6:58 pm, David Winsemius <dwinsem...@comcast.net> wrote:
Publicly produce something we can work with. I have no idea how to
create an example that will match such an object.
?dput
?dump
Read Posting Guide.
--
David.
On Jun 16, 2010, at 12:54 PM, Andrej wrote:
Thanks David for your fast reply, but now I realized tat "string" is
of type:
class(string)
[1] "jobjRef"
attr(,"package")
[1] "rJava"
so I get an error when i try with gsub or sub:
sub("^.+\\t(\\d+)\\n.+$", "\\1", string)
Error in as.character.default(x) :
no method for coercing this S4 class to a vector
I think that there should be trivial solution, but... Any further
idea?
Regards, Andrej
On Jun 16, 6:47 pm, David Winsemius <dwinsem...@comcast.net> wrote:
On Jun 16, 2010, at 12:04 PM, Andrej wrote:
Dear all,
I'm trying to filter out the "number of leaves" (it should be 1 in
the
example below) from the following string:
string
[1] "Java-Object{J48 pruned tree\n------------------\n: 0
(15.0/3.0)\n
\nNumber of Leaves : \t1\n\nSize of the tree : \t1\n}"
Any idea how to do that as simple as possible? Thanks in advance
for
any advice.
?sub # or ?gsub if you need more than one pattern matched (they
are
on the same page).
This should find the first occurrence of digits following a tab
terminated by a line feed and then return only the digits:
string <- "Java-Object{J48 pruned tree\n------------------\n: 0
(15.0/3.0)\n \nNumber of Leaves : \t1\n\nSize of the tree :
\t1\n}"
sub("^.+\\t(\\d+)\\n.+$", "\\1", string)
[1] "1"
The parens within the search pattern are matched to "\\1". Need to
double backslashed within patterns.
Regards, Andrej
--
David Winsemius, MD
West Hartford, CT
______________________________________________
r-h...@r-project.org mailing listhttps://stat.ethz.ch/mailman/
listinfo/r-help
PLEASE do read the posting guidehttp://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
______________________________________________
r-h...@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guidehttp://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
David Winsemius, MD
West Hartford, CT
______________________________________________
r-h...@r-project.org mailing listhttps://stat.ethz.ch/mailman/
listinfo/r-help
PLEASE do read the posting guidehttp://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
______________________________________________
R-help@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
______________________________________________
R-help@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.
