similar to: bug (?!) in "pam()" clustering from fpc package ?

Hello Martin Maechler and All, A simple question (I hope): How can I compute the "sum of the dissimilarities" that appears in the pam command (from the cluster package) ? Is it the "manhattan" distance (such as the one implemented by "dist") ? I am asking since I am running clustering on a dataset. I found 7 medoids with the pam command, and from it I have the

Hello R-community: Much of the time I want to use loops to look at graphs, etc. For example, I have 25 plots, for which the names are m.1$medoids, m.2$medoids, ..., m.25$medoids. I want to index the object number (1:25) as below (just to show concept). for (i in 1:25){ plot(m.i$medoids) } I've tried the following, with negative results for ...

Hi i am using prediction.strength with k-medoids algorithms. There are simple examples like prediction.strength(iriss,2,3,M=3,method="pam") I wrote my code like prediction.strength(data,2,6,M=10,clustermethod=pamkCBI,DIST,krange=2:6,diss=TRUE,usepam=TRUE) because i am using the dissimilarity matrix instead of the data itself for the clustering algorithms. But then i got this error

Hello, When using PAM (partitioning around medoids), I would like to skip the build-step and give the fonction my own medoids. Do you know if it is possible, and how ? Thank you very much. Isabel

I am using the PAM algorithm in the CLUSTER library. When I allow PAM to seed the medoids using the default __build__ algorithm things work well: > pam(stats.table, metric="euclidean", stand=TRUE, k=5) But I have some clusters from a Hierarchical analysis that I would like to use as seeds for the PAM algorithm. I can't figure what the mediod argument wants. When I put in the

Hello all, I am using the clustering functions in R in order to work with large masses of binary time series data, however the clustering functions do not seem able to fit this size of practical problem. Library 'hclust' is good (though it may be sub par for this size of problem, thus doubly poor for this application) in that I do not want to make assumptions about the number of

Dear R helpers, I have a large data set with 36 variables and about 50.000 cases. The variabels represent labour market status during 36 months, there are 8 different variable values (e.g. Full-time Employment, Student,...) Only cases with at least one change in labour market status is included in the data set. To analyse sub sets of the data, I have used daisy in the cluster-package to create

Greetings, I have had good success using the clara() function to perform a simple cluster analysis on a large dataset (1 million+ records with 9 variables). Since the clara function is a wrapper to pam(), which will accept known medoid data - I am wondering if this too is possible with clara() ... The documentation does not suggest that this is possible. Essentially I am trying to

HI R users With clara function I get a data frame (maybe this is not the exact word, I'm new to R) with the following variables: > names(myclara) [1] "sample" "medoids" "i.med" "clustering" "objective" [6] "clusinfo" "diss" "call" "silinfo" "data" I want to

Hello everyone, I need to do k-medoids clustering for data which consists of 50,000 observations. I have computed distances between the observations separately and tried to use those with pam(). I got the "cannot allocate vector of length" error and I realize this job is too memory intensive. I am at a bit of a loss on what to do at this point. I can't use clara(), because I

Dear R user, Can you please help me. How do I convert part of a cluster analysis output under the heading “Clustering vector” as shown below, showing the clusters to which each respondent belongs to:      [1] 1 1 2 2 1 2 1 2 1 1 2 2 1 2 2 2 2 1 1 1 1 2 2 1 2 2 1 2 2 2 2 2 2 2 2 1 2   [38] 2 1 1 2 2 2 2 2 1 2 1 2 2 2 2 1 2 1 2 2 1 2 2 2 2 2 2 1 2 1 2 2 2 1 1 2 2   [75] 2 1 2 2 2 2 2 2 2 1 1 2

Hola. Yo en vez de utilizar análisis cluster que impliquen distancias, probaría con un kmedias o con un pam (partition around medoids) pero utilizando muestras, la función clara de la librería cluster puede ayudarte. Pego el details de la ayuda de 'clara' Details clara is fully described in chapter 3 of Kaufman and Rousseeuw (1990). Compared to other partitioning methods such as pam,

I am using some functions from package clusterSim to evaluate the best clusters layout. Here is the features vector I am using to cluater 12 signals: > alpha.vec [1] 0.8540039 0.8558350 0.8006592 0.8066406 0.8322754 0.8991699 0.8212891 [8] 0.8815918 0.9050293 0.9174194 0.8613281 0.8425293 In the following I pasted an excerpt of my program:

El inconveniente con un K-medias, es que se tiene que se tiene que pre definir el número de segmentos, pero eso es algo con lo q no cuento. La solución de Javier me parece q sería la única opción. Atte. Ricardo Alva Valiente -----Mensaje original----- De: R-help-es [mailto:r-help-es-bounces en r-project.org] En nombre de javier.ruben.marcuzzi en gmail.com Enviado el: miércoles, 29 de abril de

Dear R users, When I run the following code, R crashes: require(cclust) x <- matrix(c(0,0,0,1.5,1,-1), ncol=2, byrow=TRUE) cclust(x, centers=x[2:3,], dist="manhattan", method="kmeans") While this works: cclust(x, centers=x[2:3,], dist="euclidean", method="kmeans") I'm posting this here because I am not sure if it is a bug. I've been searching

Dear all, I have a problem when using some classification functions (Kmeans, PAM, FANNY...) with a distance matrix, and i would to understand how it proceeds for the positioning of centroids after one execution step. In fact, in the classical formulation of the algorithm, after each step, to re-position the center, it calculates the distance between any elements of the old cluster and its

Buen aporte?excelente!! Atte. Ricardo Alva Valiente De: Jose Luis Cañadas Reche [mailto:canadasreche en gmail.com] Enviado el: miércoles, 29 de abril de 2015 12:51 PM Para: Alva Valiente, Ricardo (RIAV); 'javier.ruben.marcuzzi en gmail.com'; R-help-es en r-project.org Asunto: Re: [R-es] cantidad de datos Podrías hacer varios kmedias con diferente número de clusters y comprobar como

Dear All, I'm dealing with a case, where 'manhattan' distance of each of 100 vectors is calculated from 10000 other vectors. For achieving this, following 4 scenarios are tested: 1) scenario 1: > x<-read.table("query.vec") > v<-read.table("query.vec2") > d<-matrix(nrow=nrow(v),ncol=nrow(x)) > for (i in 1:nrow(v)){ + d[i,]<-

Hi All, For the function "bclust"(e1071), the argument "base.method" is explained as "must be the name of a partitioning cluster function returning a list with the same components as the return value of 'kmeans'. In my understanding, there are three partitioning cluster functions in R, which are "clara, pam, fanny". Then I check each of them to

Hello list, I am new to R, so if the question is rather silly, please ignore it. I was wondering wether it would be possible to use the models generated by pam, clara and the like as predictors? Scanning through the available documentation shed no light (for me) upon the subject. Regards, Renald