similar to: EM unsupervised clustering

Hello All... I gave a task to my students that involved using mclust to look for clusters in some bivariate data of isotopes vs various mining locations. They discovered something I didn?t expect; the data (called tur) is appended below. p <- qplot(x = dD, y = dCu65, data = tur, color = mine) print(p) # simple bivariate plot of the data; looks fine mod1 <- Mclust(tur[,2:3]) mod1$G mod2

Dear list members, I am using Mclust in order to deconvolute a distribution that I believe is a sum of two gaussians. First I can make a model: > my.data.model = Mclust(my.data, modelNames=c("E"), warn=T, G=1:3) But then, when I try to plot the result, I get the following error: > mclust1Dplot(my.data.model, parameters = my.data.model$parameters, what = "density")

Hi, I'm trying to use the library mclust for gaussian mixture on a numeric vector. The function Mclust(data,G=3) is working fine but the fitting is not optimal and is using modelNames="E". When I'm trying Mclust(data,G=3,modelName="V") I have the following message: Error in if (Sumry$G > 1) ans[c(orderedNames, "z")] else ans[orderedNames] : argument is

My question is with respect to mCLUST and the values of BIC and log likelihood. The relevant part of my R script is: ######################### BEGIN MDS ANALYSIS ######################### #load data data <- read.table("Ecoli33_Barry.dis", header = TRUE, row.names = 1) #perform MDS Scaling mds <- metaMDS(data, k = Dimensions, trymax = 20, autotransform =TRUE, noshare = 0.1,

Hi, I'm trying to use the library mclust for gaussian mixture on a numeric vector. The function Mclust(data,G=3) is working fine but the fitting is not optimal and is using modelNames="E". When I'm trying Mclust(data,G=3,modelName="V") I have the following message: Error in if (Sumry$G > 1) ans[c(orderedNames, "z")] else ans[orderedNames] : argument is

Are there R packages that allow for dynamic clustering, i.e. where the number of clusters are not predefined? I have a list of numbers that falls in either 2 or just 1 cluster. Here an example of one that should be clustered into two clusters: two <- c(1,2,3,2,3,1,2,3,400,300,400) and here one that only contains one cluster and would therefore not need to be clustered at all. one <-

Hi, I got the same problem like http://tolstoy.newcastle.edu.au/R/devel/04/11/1204.html R crashes when I use the em function from the mclust package on univariate data and on a special case on bivariate data (when the matrix is not provided as written in the manual). It seems as if the problem is the format of the data to be analyzed. Operating System: Windows XP (SP2) R version: R-2.0.1 The

hi, When I try to use the function coordProj {mclust} " coordProj(diabetes[,-1],dimens=c(2,3),what="uncertainy",uncertainty=diabetesModel$uncertainty,parameters=diabetesModel$parameters) " to identify uncertainty, it errors and send this warning message: " Warning message: In coordProj(diabetes[, -1], dimens = c(2, 3), what = "uncertainy", : what

I'm running Mclust 3.0 in R-2.7.0 and have run into a situation where the optimal number of clusters, 12, seems to be greater than the number of colors available to Mclust. The code below, which demonstrates errors, does not if the max no of clusters is set at 10. sessionInfo, after a restart of R and loading of packages, follows the output. Is this a known problem with Mclust? Can I

Buen día, no sé si estoy utilizando bien la lista, es la primera vez. Si lo hago mal me corrigen por favor. Sobre tu comentario Pedro, muchas gracias. Lo qeu entiendo con tu sugerencia de set.seed es qeu de esa forma fijas los resultados, pero no estoy seguro si otra agrupación funcione mejor. Es decir me interesa un método de agrupación que genere la "mejor" agrupación y como los

K-means recluster data with given cluster centers Dear R user, I have several large data sets. Over time additional new data sets will be created. I want to cluster all the data in a similar/ identical way with the k-means algorithm. With the first data set I will find my cluster centers and save the cluster centers to a file [1]. This first data set is huge, it is guarantied that cluster

Hi, My questions concern the function 'mclustBIC' which compute BIC for a range of clusters of several models on the given data and the other function 'mclustModel' which choose the best model and the best number of cluster accordind to the results of the previous cited function. 1) When trying the following example (see ?mclustModel), I get negative BIC computed by

Thanks to all for the input. rgentlem at jimmy.harvard.edu said: >If you really want help -- no, I just thought I'd waste some bandwidth. :-) >If on the other hand you >just want some reassurance that Splus is indeed a commerical package oh gee, thanks, I wasn't sure about that. When I had said: >> R can't handle files named x. If I can use Splus, should I just

An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20091125/6a78f78b/attachment-0001.pl>

Hello everyone. I have a few MCLUST questions and I was hoping someone could help me out. If you’re an MCLUST user, they will likely be pretty easy to answer. Thanks in advance for any help. Ken What are the pros/cons of starting a finite mixture model at the “m” step versus the “e” step (where “m” is the maximization step and “e” is the expectation step of the EM algorithm)? In

---------- Forwarded message ---------- From: niharika singhal <niharikasinghal1990 at gmail.com> Date: Sun, Aug 27, 2017 at 11:57 AM Subject: Re: Find maxima of a function To: "David Winsemius [via R]" <ml+s789695n4745009h56 at n4.nabble.com>, "Ismail SEZEN [via R]" <ml+s789695n4744993h60 at n4.nabble.com>, Ulrik Stervbo <ulrik.stervbo at gmail.com>

I have not followed the history of this thread, but I am quite flummoxed as to why the OP is rewriting code to estimate parameters from an univariate Gaussian mixture model when alternatives such as EMCluster (which generally appears to handle initialization better than MClust) exist. Or perhaps there is more to it in which case I apologize. But I thought that I would make the OP aware of the

Dear Niharika, As I said before, the problem is basically an optimization issue. You should isolate the problematic part from the rest of your study. Sometimes, more information does not help to solution. All the answers from us (Ulrik, David, me) are more or less are correct to find a maximum point. Newton?s method is also correct. But after answers, you only say, it didn?t find the right

I keep on receiving the message below after submitting the following line using the mclust package. m2 is a 99 X 1 column vector. * em(modelName = "E", m2, mu = c(25, 50), sigmasq=10, pro = c(0.4, 0.6)) Error in as.double.default(data) : (list) object cannot be coerced to double. Why do I receive this error? Thank, Brian C. Newquist Research Statistician

Hi All, I need to fit a mutlivariate normal model to a dataset in order to obtain the mean and covariance parameters. I see that the MVN function in the MCLUST package can do this, however when I try to run even the simplest example provided in the documentation, as below, I get the following error: n <- 1000 set.seed(0) x <- rnorm(n, mean = -1, sd = 2) mvn(modelName = "X", x)