Re: [R] Constructing a symmetric matrix with library(corpcor)

vec2sm( r, diag = FALSE, order=rr ) Next time please make an effort to post using plain text format, as your HTML-formatted email got rather messed up coming through this plain-text mailing list. You might find a reading of The R Inferno informative on the subject of F vs. FALSE. -- Sent

[R] Constructing a symmetric matrix with library(corpcor)

I like to compose a symmetric matrix in the pattern as shown below (for 3 x 3 and 4 x 4). For a symmetric matrix of order 5, the result does not seem right. Help? It is possible to write a two-level do loop for the task, but I suppose that is less efficient. > library(corpcor)> r <- 1:3; r[1] 1

Re: [R] Help required for Rcmdr

Not sure what C+ software is, but with regard to C or C++ compilers the short answer is probably not. The true answer is that it may depend on your unspecified operating system and on what packages you want to use. If you are on windows you can install most packages from zip files with no

Re: [R] Question On Regex and DataFrame

Hi kalyan, It is a bit difficult to work out what you want to do. However, there are some things I can suggest. The gsub function is useful for changing strings not assigning new values. If you want to delete a column of a data frame if there are any NA values, you first want to check for NA

Re: [R] Question On Regex and DataFrame

Inline beow. On Sunday, February 21, 2016, kalyan chakravarty < kalyanchakravarty...@gmail.com> wrote: > Hi, > I am new to R and learning the basics.so i came to know that data frame can > store any data type as oppose to matrix which stores only numeric.My > question is False. You need to

[R] Question On Regex and DataFrame

Hi, I am new to R and learning the basics.so i came to know that data frame can store any data type as oppose to matrix which stores only numeric.My question is 1.)How to replace a particular pattern with new pattern in data frame.I tried something like x =

Re: [R] Help required for Rcmdr

Dear Sirs, just wanted to check whether C+ or C++ software is required to be in the installed in the laptop in order to use Rcmdr regards sekhar On Wed, Feb 10, 2016 at 10:17 PM, Fox, John wrote: > Dear Sekhar, > > > -Original Message- > > From: Sekhar Venkatesan

Re: [R] Why CLARA clustering method does not give the same classes as when I do clustering manually?

By the way, I have to say that I am dealing with missing values and that is why I am using clara or I may use pam, as kmeans (which is very good at dealing with large datasets) cannot handle missing values. Behnam. From: David L Carlson

Re: [R] Why CLARA clustering method does not give the same classes as when I do clustering manually?

Clara uses the Euclidean distance. Why you get different results can only be said if you provide a reproducible code example for both what you did in clara and what you did "manually". Best wishes, Christian *** --- *** Christian Hennig University College London, Department of Statistical

Re: [R] Why CLARA clustering method does not give the same classes as when I do clustering manually?

I do not think this is quite true. When the medoids are not specified, pam/clara looks for a good initial set (build phase) and then finds a local minimum of the objective function (swap phase). Both pam/clara and kmeans can find local minima that are not the global minimum. If the build phase

Re: [R] How a clustering algorithm in R can end up with negative silhouette values?

Each observation is assigned to the closest medoid, a single observation. An observation that is between two medoids will be assigned to the closer one even if its distances to members of the other cluster are closer on average (but the medoid of that cluster is slightly farther away). If the

Re: [R] Multivariate multiple linear regression question

Ok. Will do thank you. I do apologize for the spam. That was done in error. On Feb 21, 2016 12:10 AM, "Bert Gunter" wrote: > Sorry, but please do not multiple post. That's spam. > > This is a list about the R programming language, not about statistical > methods. While

Re: [R] How to create an executable file from R GUI?

Oh, thanks Peter, good example for Mac, but indeed not working on Windows. For a completely cross-platform solution (that is, including Windows which is what Zahra wants), I believe shiny is the right tool. So Zahra, if you want to use shiny, you need to look at their own tutorials, step by step,

Re: [R] Multivariate multiple linear regression question

Sorry, but please do not multiple post. That's spam. This is a list about the R programming language, not about statistical methods. While there is often some overlap, your questions are entirely statistical and therefore OT here( at least imo). Try a statistical list like stats.stackexchange.com