similar to: Looking for packages to do Feature Selection and Classifi cation

Dear All, I've got into the habit of installing R from the precompiled Debian binaries, including many of the packages from the r-cran-* Debian packages, and later building from source (e.g., to link against Goto's BLAS, or to build patched versions, etc). I install the newly built R to the very same place (/usr/lib/R). This allows me to build and update R when I wish, AND provides the

Dear All, I found Andy Liaw's suggestion about using a NUMA (instead of SMP) kernel when running R on amd64 with > 1 CPU http://finzi.psych.upenn.edu/R/Rhelp02a/archive/35109.html A couple of questions: 1. Is this still the case with the newer dual-core opterons (e.g., the 275 et al., families) running Linux (kernel 2.6)? 2. How does this affect using Rmpi (and snow, papply, et al.)

(Apologies for double posting; I sent this to r-help and was suggested that I ask here which I should probable have done to begin with). *************** Dear All, I've got into the habit of installing R from the precompiled Debian binaries, including many of the packages from the r-cran-* Debian packages, and later building from source (e.g., to link against Goto's BLAS, or to build

Dear All, I've read Thomas Lumley's fortune "If the answer is parse() you should usually rethink the question.". But I am not sure it that also applies (and why) to other situations (Lumley's comment http://tolstoy.newcastle.edu.au/R/help/05/02/12204.html was in reply to accessing a list). Suppose I have similarly called functions, except for a postfix. E.g. f.1 <-

Dear All, I think I am confused about how I'd be able to use zlib starting with R 2.7.0. I just downloaded the latest development version, built it, etc, but I am not able to find the zlib.h that, I believe, R should place somewhere under "where/you/want/R/to/go" (from --prefix=/where/you/want/R/to/go). There seem to be entry points for zlib in the binary (e.g., grep -r gzopen ./

Dear All, How can the height of a leaf be extracted from a dendrogram? Sure, I can print it, but I am not able to, say, store it in an object. I think I understand that the height is a property of the split, not the leaf itself, but the printing functions display a "height" or "h" (which changes with "hang") and that is what I want. Obviously, the info is there

Hi All, Sorry if this is a repost (a quick browse didn't give me the answer). I wonder if there are packages that can do the feature selection and classification at the same time. For instance, I am using SVM to classify my samples, but it's easy to get overfitted if using all of the features. Thus, it is necessary to select "good" features to build an optimum hyperplane (?).

Dear All, I'd like to be able to have R store (in a list component) a compressed data set, and then write it out uncompressed. gzcon and gzfile work in exactly the opposite direction. What would be a good way to handle this? Details: ---------- We have a package that uses C; part of the C output is a large sparse matrix. This is never manipulated directly by R, but always by the C code.

Dear All, In a package, I am using ".C" to call some C functions. In one case, the number of elements of the return vectors are not known in R before the C call. (Two of the vectors are integers, the third is vector of character strings). Passing from R a vector of the maximum possible size would be a huge waste. I understand one alternative is to use ".Call", but I'd

Dear All, At least in three different GNU/Linux systems, the parallel function from the multicore package leaves defunct (zombie) R processes. For instance library(multicore) parallel(1:5) collect() After collect, the child process (with pid as given by collect) is left defunct. (If we run the last two lines of code again, the previously defunct process will be replaced by the new defunct

Dear All, I am trying to create socket clusters (using snow and snowfall) with a Windows OS. I am running Windows inside VirtualBox and VMware player (i.e., Windows is guest) from a Debian Linux host system (I've tried in two different Linux systems, an AMD x86-64 workstation and an Intel i686 laptop). However, almost always seting up the cluster fails: either R will hang forever or I will

Dear All, I am having trouble getting an R package to build and install correctly under Windows. In this package, which builds and checks OK under Linux, I use zlib (among other functions, gzprintf). As mentioned by Prof. Ripley a while back, the file "CHANGES" under src/gnuwin32 says explains that to, to use zlib, one has to set $(ZLIB_LIBS) in PKG_LIBS. I have a Makefile.win with

Dear All, I was writing a small wrapper to bootstrap a classification algorithm, but if we generate the indices in the "usual way" as: bootindex <- sample(index, N, replace = TRUE) there is a non-zero probability that all the samples belong to only one class, thus leading to problems in the fitting (or that some classes will end up with only one sample, which will be a problem

If an array has missing values in different rows, plotting using the formul= a=20 interface can produce errors. Example: fake.data <- matrix(rep(-100:100, 4), ncol =3D 4) par(mfrow =3D c(1,2)) boxplot(fake.data ~ col(fake.data)) abline(h =3D 0, lty =3D 2) boxplot(as.data.frame(fake.data)) abline(h =3D 0, lty =3D 2) ##### Add the missing data fake.data[190:200, 1] <-

Dear All, In a package, I want to use some C code where I am using a structure (as the basic element of a linked list) with flexible array members. Basically, this is a structure where the last component is an incomplete array type (e.g., Harbison & Steel, "C, a reference manual, 5th ed.", p. 159) such as: struct Sequence { struct Sequence *next; int len; unsigned int

Dear All, The "clients.txt" file of the latest Rserve package, by Simon Urbanek, says, regarding its R client, "(...) a simple R client, i.e. it allows you to connect to Rserve from R itself. It is very simple and limited, because Rserve was not primarily meant for R-to-R communication (there are better ways to do that), but it is useful for quick interactive connection to an

Dear All, I just apt-get source r-base-core and noticed that file "rules" under ./r-base-3.2.4-revised/debian contains (lines 277 to 279) --with-system-bzlib \ --with-system-pcre \ --with-system-zlib \ I wonder if these are still necessary and, in fact, when building R alpha (specifically, R-alpha_2016-03-21_r70361.tar.gz) I get a warning saying that those options are not

Dear All, For logistic regression models: is it possible to use validate (rms package) to compute bias-corrected AUC, but have variable selection with AIC use step (or stepAIC, from MASS), instead of fastbw? More details: I've been using the validate function (in the rms package, by Frank Harrell) to obtain, among other things, bootstrap bias-corrected estimates of the AUC, when variable

On Wed, 30-12-2015, at 12:44, Dirk Eddelbuettel <edd at debian.org> wrote: > On 30 December 2015 at 05:00, Dario Strbenac wrote: > | Good day, > | > | In section A.2, the manual advises "Linux users will want the urw-fonts package". However, this package only seems to be available for RedHat Linux and Fedora Linux. What about for Debian or Ubuntu ? There is no

Dear All, A 1-year postdoctoral position in Computational Biology/Bioinformatics/Evol. Biology/Statistics is available in Madrid, Spain. Brief description: Simulation and analysis of evolutionary processes in cancer. Requirements: - Postdoc younger than 30 years. - Be registered as resident ("estar empadronado") in Madrid, Spain, since 08-August-2016. - Be registed in the