similar to: Kohonen Package

All, The kohonen predict function is returning NA for SOM predictions regardless of data used... even the package example for a SOM using wine data is returning NA's Does anyone have a working example SOM. Also, what is the purpose of trainY, what would be the dependent data for an unsupervised SOM? As may be apparent to you by my questions, I am very new to kohonen maps and am very grateful

Hi All, I am making a serious effort to try to learn R, but one hurdle I am facing is that I need to "see" the data as I walk through the examples in the packages. For instance, many examples on the web start by a command like data("wines"). How can I actually view what the dataset looks like prior to transformations and analysis? I have tried to use edit() , print, and

I have a data set with 10 variables, and about 8000 instances (or objects/rows/samples). In addition I have one more ('class') variable that I have about 10 instances for, but for which I wish to impute values for. I am a little confused how to go about doing this, mostly as I'm not well-versed in it. Do I train the SOM with a data object that contains just the first 10 variables

Hi, I'm trying to utilize the kohonen package to build SOM's. However, trying this on my data I get the error: "Argument data should be numeric" when running the som(data.train, grid = somgrid(6, 6, "hexagonal")) function. As you see, there is a problem with the data type of data.train which is a list. When I try to convert it to "numeric" I get the error:

I would really like some or any advice on how I can improve (or fix??) the following analysis. I hope I have provided a completely runnable code - it doesn't produce any errors for me. The resulting plot at the end shows a pretty poor correlation (just speaking visually here) to the test set. How can I improve the performance of the mapping and prediction? Here are some of the data

Hi all, I am new to R, but with the help I have received thus,I have already been able to work through a bunch of questions on my own in just a few days. I imagine my questions are relatively simple, but here she goes. 1) I am using a package where one of the objects generated represents X/Y coordinates for each observation. I have been able to plot my row names onto the graph using text()

HI, Dear R community, I am using the following codes to do the som. I tried to label the notes by the majority vote. either through mapping or prediction. I attached my output, the left one dont have any labels in the note, the right one has more than one label in each note. I need to have only one label for each note either by majority vote or prediction. Can anyone give some suggestions or

Hi Everyone, I was hoping someone could help me with the settings for Tinn-R. I see in the screen shots that it has syntax help, or something similar (tips on what functions, etc). I can not seem to get this to turn on in the program, and I am wondering if I have to set up a few options. I quickly read through the help and could not figure it out. Many thanks! - Brock P.S. It appears as

Hi All, I am new to R, but it has been a lot of fun learning as I go and have been blow away by what it can do. Came across this example and wanted to see if ggplot2 or some other visualization package could make this sort of graphic.

Hi. Three years ago, I've read the question of availability of SOM library for R using Kohonen's SOM_PAK in this mailing-list. This answer was no availability. And no package dealing with SOM in CRAN. Is this situation same? Could you tell me availability this library? Best Regards.

This was sent to me personally but was probably meant for R-help. -------- Original Message -------- Subject: Re: [R] Kohonen Package Date: Mon, 1 Mar 2010 14:45:13 +1000 From: Martin <labadz at gmail.com> To: ehlers at ucalgary.ca Hi Any idea if the kohonen package can produce umatrices with hexagons and component planes as found in various publications? Cheers Martin Martin Labadz

Hi Everyone, I am relatively new to R, but I want to try to learn how to use it and potentially replace the other commercial packages I have learned to use over the years. That said, I need to get at data in databases, more specifically, MySQL. I installed the RMySQL package without error, but when I try to load it, I get the following error: > library(RMySQL) Loading required package: DBI

Hi all, Can anyone help me setup this package so I can use it. I am getting errors with the Rgraphviz package and have tried a number of ways to get this to work. Any help will be greatly appreciated! I am sorta new to R but have been actively trying to get into using it as my main analysis software. Thanks, Brock [[alternative HTML version deleted]]

Hola, alguien me puede decir cómo descargar la librería "kohonen", pues lo he intentado con download.packages y no hay forma. No sé si es porque pongo mal el directorio de destino o porque esa librería esta dentro de otra y no la localizo. Ya he usado en otras ocasiones el comando download.packages y no me había dado problemas gracias [[alternative HTML version deleted]]

hi all, i would like to apply the kohonen 's algorithm (SOM). Somebody knows if there is an available script ? thanks -- ------- Olivier MARTIN -------- _______________________________ _______________________________ CEA 17, rues des martyrs LETI/DSYS/SCSI Bur 225 olivier.martin at cea.fr 04 76 88 47 61 (bur.) 04 76 88 57 87 (fax.) ---------------------- 06 08 67 93 42 (pers.)

Hi All, I am experimenting with using binary data (1, 0) in the kohonen package. I would like either 1 or 0 to be mapped in SOM, but the package gives me 1 or 0 (as expected), but something in between. I am not scaling the binary data, but still there are in-between values. Can anybody suggest a way to keep the data binary, even in the SOM plot? Thanks a lot. George

Hi everyone, I have successfully created and analyzed my network data. I am new to R, and Network Analysis too, but I want to color my vertex based on some of the centrality measures calculated. Can someone point me in the right direction? Again, I am new to R, but given how powerful R appears to be, I figure this is probably pretty easy to do, I just wish I could figure it out. Many thanks

Hi everyone, This is my first posting and I am just starting to fumble my way thru R. I have been working thru the Arules package, and I used to be able to use the image function and I get the following message: Error in image.default(basket2) : 'z' must be a matrix I used to be able to plot the image. I only started to get this error when I tried to add x and y axis labels.

Hi everybody! I try to implements Self-Organizing Maps with R and the Kohonen package. I have made an algorithm that try differents width and height. For each step, Silhouette index, Davies-Bouldin index and Dunn index are computed. However, there is always after severals minutes a *Runtime error* appears on the window: Microsoft visual c++ runtime library "this application has requested

somfunc<- function (file) { aa_som<-scale(file) final.som<-som(data=aa_som, rlen=10000, grid=somgrid(5,4, "hexagonal")) pdf(file="/home/cdu/changbin/file.pdf") #output graphic file. plot(final.som, main="Unsupervised SOM") dev.off() } I have many different files, if I want output pdf file with the same name as for each dataset I feed to the function