similar to: tree construction crashes (PR#1698)

Dear All, We came across a problem when using the "tree" package to analyze our data set. First, in the "tree" function, if we use the default value "mindev=0.01", the resulting regression tree has a single node. So, we set "mindev=0", and obtain a tree with 931 terminal nodes. However, when we further use the "cv.tree" function to run a 10-fold

I have a problem with running the tree package (dec.8, 2001) for R. The problem is, it will only give me 5/6 terminal node and then stop, while using Splus's tree on the same data with the same specification give me hundreds of nodes. Here's a little more background info: R-1.4.1 Solaris 5.7 rpart (most recent version) tree (..) Splus 6.0 Solaris 5.7 tree

Estimados compañeros hace unos días instale la versión última de R (3.4.1) en windows 10 y hoy me tiene loco el siguiente error cuando ejecuto predict para un árbol de clasificación-regresión. El problema da incluso con el ejemplo del comando predict library(tree) data(shuttle, package="MASS") shuttle.tr <- tree(use ~ ., shuttle, subset=1:253, mindev=1e-6,

Hi, all, I am wondering if it is possible to set parameters of 'rpart' and 'tree' such that they will produce the exact same tree? Thanks. Auston Wei Statistical Analyst Department of Biostatistics and Applied Mathematics The University of Texas MD Anderson Cancer Center Tel: 713-563-4281 Email: wwei@mdanderson.org [[alternative HTML version deleted]]

Hi. I'm trying to get a tree, that fits all the lines of the training set ( a tree with no error in classification) data(iris) tree.control(150,mindev=3D-1,minsize=3D2) ir.tr <- tree(Species ~., iris) ir.tr summary(ir.tr) I'm trying to use this as a test, but it still have some examples that are classified wrongly... Anyone could tell me what's the problem?

Hi. I'm using the tree package to fit one tree from a training set. I'm using the command: hm.tr <-tree(X1~.,teste2, mindev = 0, minsize = 2) and i get the error: Error in "row.names<-.data.frame"(*tmp*, value = fit$node[1:n]) : duplicate row.names are not allowed the frameset, has 180 columns and 16000 rows. The

For the package at http://www.cs.cas.cz/~savicky/R-devel/something_0.0.0.tar.gz which is a minor part of some other package only to demonstrate the problem, i get (under R version 2.11.0 Under development 2009-12-12 r50714 and also under R-2.9.2, openSUSE 11.1 (x86_64) and CentOS release 5.2) R CMD check something_0.0.0.tar.gz ... * checking Rd files ... OK * checking Rd metadata ...

Full_Name: Petr Savicky Version: 2.4.0 OS: Fedora Core release 2 Submission from: (NULL) (62.24.91.47) the error is > binom.test(0.56*10000,10000) Error in binom.test(0.56 * 10000, 10000) : 'x' must be nonnegative and integer while > binom.test(5600,10000) yields correct result. The same error occurrs for > binom.test(0.57*10000,10000)

Gracias Carlos miraré el fix y en su defecto intentaré mandar un mensaje al autor. De todas las maneras espero que alguien lo pruebe en windows 10 Saludos, Juan El 24/09/2017 a las 20:32, Carlos Ortega escribió: > Hola Juan Antonio, > > Acabo de instalar "tree" en Mac OSX y no aparece este error... > > > shuttle1 <- shuttle[254:256, ]  # 3 missing cases >

I am using tree() in the library tree to learn regression trees. Once in a while I am getting the error "Tree is too big". From the same data set, but with randomized subsets I am learning several tree model and in the end of the day I would like to look at some of the properties across trees. My problem: I have for loop containing a call to tree(). However, since tree() returns an

Dear R developers, I am using R under Linux, but I would like to share an extension package with some Windows users. The package contains only data and .R scripts. There is no src directory. So, I think I do not need a Windows machine with C compiler, "make", "sh" and "perl". If I am wrong, please tell me. I tried the following approaches (after verifying the

I have a C function, which performs a transformation of a large integer matrix. The matrix may be of size 1.6GB, so I can have only one copy in RAM and have to modify it in place. This is possible using .Call and works fine. For debugging, I need two copies of a smaller matrix and modify only one of them. This may also be done, for example, by A <- some integer matrix B <- A +

The help page for function identical says: 'identical' sees 'NaN' as different from 'as.double(NA)', but all 'NaN's are equal (and all 'NA' of the same type are equal). However, we have x <- NaN y <- as.double(NA) x # [1] NaN y # [1] NA identical(x,y) # [1] TRUE In my opinion, NaN and as.double(NA) should be distinguished as the

When i unpack R-devel_2010-01-05.tar.bz2 and run ./configure on two Linux machines, i get the error message configure: creating ./config.status config.status: creating Makeconf config.status: creating Makefile config.status: creating doc/Makefile config.status: creating doc/html/Makefile config.status: creating doc/manual/Makefile config.status: creating etc/Makefile

configure and make run OK, but make check failed for R version 2.5.1 RC (2007-06-26 r42068) on graphics with error: > ## The following two examples use latin1 characters: these may not > ## appear correctly (or be omitted entirely). > plot(1:10, 1:10, main = "text(...) examples\n~~~~~~~~~~~~~~", + sub = "R is GNU ?, but not ? ...") Error in title(...) :

Full_Name: Steve Ellison Version: 2.4.1 OS: Windows, Linux Submission from: (NULL) (194.73.101.157) bxp() allows specifcation of box locations with at=, but neither adjusts xlim= to fit at nor does it respect xlim provided explicitly. This is because bxp() now includes explicit xlim as c(0.5, n+0.5), without checking for explicitly supplied xlim (or ylim if horizontal). This also prevents

Hi, I'm looking for an "easy" way to setup a decision tree. This is *not* any kind of regression, but a very simple DAG with probability on each edge and a value at each node. I just need a way to input the graph and calculate the expected value at each end node. The whole thing could be done with a calculator and pencil, but it would be nice to have everything in R. I can't

As others already mentioned, in your example you are first creating an integer matrix and the coercing it to a double matrix by assigning (double) 1 to element [1,1]. However, even when correcting for this mistake, there is an extra copy created when using matrix(). Try this in a fresh vanilla R session: > print(gc()) used (Mb) gc trigger (Mb) max used (Mb) Ncells 136684 3.7

In R-2.10.0, the development version, function as.factor() uses 17 digit precision for conversion of numeric values to character type. This is very good for the consistency of the resulting factor, however, i expect that people will complain about, for example, as.factor(0.3) being [1] 0.29999999999999999 Levels: 0.29999999999999999 I suggest to extend the "Warning" section of

While I'm building 3.0, I thought I would ask if anyone has seen the following with TOT: Unable to schedule 'Dominator Tree Construction' required by 'Module Verifier' Unable to schedule pass UNREACHABLE executed at <root>/llvm/lib/VMCore/PassManager.cpp:1223! Abort This code was working with TOT ~3 weeks ago. This is a code generator, and execution library (the IR C++