similar to: MDL - Fayyad & Irani Discretization

Dear R-helpers: I am interested in discretization methods for numerical attributes, as they are reported in the 'machine learning' community. For example, the work of Fayyad & Irani (IJCAI-93), Kononenko, entropy-based approaches, MDL principle, the C4.5 approach, etc. I am especially interested in those methods that take a factor as goal target into account for discretizing

I've been trough the R documentation for about half an hour and it's not clear to me how to do this: I need to format to character a series of integers from 1 to 1000, and I like them to look like "0001" "0002", "0059", "0123" and so on. Padded with zeroes to have four digits. Cheers! Mario. r-help-request at r-project.org wrote: > Send

Hi, Is anybody using Copula package for fitting copulas to own data? I have two marginals Log Normal with (parameters 1.17 and 0.76) and Gamma ( 2.7 and 1.05) Which package I should use to fit Gumbel and Clayton Copulas? Thanks, fayyad [[alternative HTML version deleted]]

When I want to install "dprep" and I always get information: > install.packages("dprep") Warning in install.packages("dprep") : argument 'lib' is missing: using 'C:\Users\Documents/R/win-library/2.8' --- Please select a CRAN mirror for use in this session --- Warning message: package ?dprep? is not available I have tried a lot of mirror...

Hi! I want to use one method "combinations" from "gtools" package but in my code I must use also "dprep" method where is method "combinations" too. Mayby I show you result my help function: Help on topic 'combinations' was found in the following packages: Package Library dprep /usr/lib64/R/library gtools

Hello All, I am trying to carry out variable reduction. I do not have information about the dependent variable, and have only the X variables as it were. In selecting variables I wish to keep, I have considered the following criteria. 1) Percentage of missing value in each column/variable 2) Variance of each variable, with a cut-off value. I recently came across Weka and found that there is an

Hi, I am doing some research on feature selection for classfication problem using genetic algorithm in a wrapper approach. I am wondering if there is some package which is already built for this purpose. I was advised before about dprep package but I don't think it used GA there (if I am wrong, please correct me!) Thanks, Ed

Full_Name: Kang Yousan Version: 2.5.0 OS: Windows XP Submission from: (NULL) (211.137.211.67) There is a bug in function distancia() in package dprep. See the description below. > distancia 1 function (x, y) 2 { 3 if (class(y) == "matrix") { 4 distancia = drop(sqrt(colSums((x - t(y))^2))) 5 distancia = t(distancia) 6 } 7 else distancia =

Dear R experts, I have a large database made up of mixed data types (numeric, character, factor, ordinal factor) with missing values, and I am looking for a package that would help me impute the missing values using ?either the mean if numerical or the mode if character/factor. I maybe could use replace like this: df$var[is.na(df$var)] <- mean(df$var, na.rm = TRUE) And go through all the many

Dear All, I'm now working on Archimedean copulas and try to test the goodness of fit. Which packages I should use? I have Clayton copula with parameter (5.35) and Frank (19.5). I found this build function wrote by Yan and Ivan via R Packages, but I'm not sure the matrix for x? Please advice. e.g gofCopula(claytonCopula(1),x) Thank you Regards, Fayyad [[alternative HTML version

Dear r-users, Any such a way that we can compute SPI using kernel function (nonparametric approach) without assuming any parametric distributions? Any existing package for above method using R? Thank you for your help. Fayyad [[alternative HTML version deleted]]

Hi All, Are there any package to check the GOF for nonparametric copulas using R? Fayyad [[alternative HTML version deleted]]

Hi, there: After I upgraded my R to 2.4.1, it is my first time of trying to use MASS and found the following error message: > install.packages("MASS") --- Please select a CRAN mirror for use in this session --- trying URL 'http://cran.cnr.Berkeley.edu/bin/macosx/universal/contrib/2.4/VR_7.2-33.tgz' Content type 'application/x-gzip' length 995260 bytes opened URL

hello, are there functions to detecte outlying observations in samples? thanks. ___________________________________________________________________________ [[alternative HTML version deleted]]

We are seeing the message " PRI Error on span 1: Received MDL/TEI management message, but configured for mode other than PTMP" on one of our Asterisk boxes on a PRI. A Google search turns up a number of hits for this error, but they are all for BRI not PRI. I'm reasonably sure there are no recent updates or config changes. Running Asterisk 1.4.37. We can update to 1.4.44 if it

Hello, I have successfully installed MDL ISIS Draw 2.5 (a program used in chemistry) under Wine (0.9.12 in Debian). Now, I need to install an addon (AutoNom2000, which is used to give IUPAC names of compounds) for this program. (This addon requires Windows 2000/XP; Wine was configured to "mimic" Windows 98 by default). When I try to run its installer, I get the following:

I have 2 ISDN BRI boxes, each with 4 spans, where the first one is configured as CPE, the second one as NET(so I don't need real lines for developing and testing). Once in a while I do see the following libpri error messages simultaneously on both boxes: PRI Span: 1 TEI=0 MDL-ERROR (A): Got supervisory frame with F=1 in state 7(Multi-frame established) PRI Span: 2 TEI=0 MDL-ERROR (A): Got

Hi, there: I have a variable whose distribution is far from normal and its qqnorm is S-shape, like a logisitic plot. My purpose is to discretize it into 2 or 3 classes. (basically, a transformation from quantative to discrete). I am wondering if there is a good way to do that. thanks, Ed

There has been a recent thread on R-help on this, which resurrected concepts from bug reports PR#1228 and PR#6743. Since the discussion has included a lot of erroneous 'information' based on misunderstandings of floating-point computations, this is an attempt to set the record straight and explain the solutions adopted. The problem was that var(rep(0.02, 10)) was observed to be (on

Hi. The dprep library has at least three different methods for outlier detection: baysout, mahaout, robout. I wanted to test them on a very simple data set: vrmat<-cbind((1:22),c(8,14,14,17,21,20,27,23,25,33,31,32,30,36,37,40,42,44,52,61,81,265)) As you can see by eyeballing this, the last point is a very good outlier candidate, and maybe the second to last point, too. Anyway, I