hyunsooseol / snowcluster

This module allows users to analyze k-means & hierarchical clustering, and visualize results of Principal Component, Correspondence Analysis, Discriminant analysis, Decision tree, Multidimensional scaling, Multiple Factor Analysis, Machine learning, and Prophet analysis.

snowCluster

This module allows users to analyze k-means and hierarchical clustering,Correspondence Analysis, Multiple Factor Analysis, Factor analysis of mixed data, Discriminant Analysis, Multidimensional Scaling, Univariate time series, and various visualization results.

snowCluster module can be installed and used in R as a standard R packages.

Installation

At the moment, snowCluster is not in CRAN yet, so you need to install it via devtools library(jmv)

library(haven)

library(jmvReadWrite)

library(jmvconnect)

devtools::install_github("hyunsooseol/snowCluster")

snowcluster's Issues

Request for a Guide for Jamovi SnowCluster

Hi Prof Hyunsoo, I am new to machine learning. May I know if you have a guide or glossary for your SnowCluster package? I have researched the technical short forms such as "svmlinear" and "rf" using Google. It will be enormously helpful if you have a resource to advise me on how to use your SnowCluster package. Let me know if you have a resource somewhere. Thank you very much in advance.

Discriminant analysis SnowCluster

The plots will not work (just spin forever) is this a jamovi update issue?

Save k-means clusters in data

Hello,
I would like to make a request: currently, using the module "Multidimensional scaling plot", it is not possible to save the k-means clusters into the dataset as an actual variable.
I would like to have this possibility, if possible.

Thanks a lot!

Cluster Dendrogram shows only 9 characters for nominal variable names

I would love to have at least 10 characters..

Discriminant Analysis

Cant plot results of - [ ] @ #> Diacriminant Analysis

snowCluster Decision Tree

I tried to use the decision tree model for my analysis, and this error occurred:

:1:5: unexpected symbol 1:20. will ^

error message: "more clusters than distinct data points"

Hi there,

Thank you in advance for your help on this issue. I am not the strongest statistician, so I hope this question makes sense.

I am attempting to run a k-means cluster analysis using the snowCluster module in JAMOVI. All of my variables are continuous, and it's only when I add some of the variables to the analysis that this error pops up. I am trying to run a cluster analysis with 3 clusters. I am not sure how to fix this. Any help is appreciated!

Saving cluster membership as nominal

Thank you for the package! It makes my life so much easier :-)
When saving a cluster membership, is it possible to specify that the new variable should be of type Nominal, not Continuous? A variable of type Continous cannot be used to split in exploratory analysis.

snowcluster jamovi

je n'arrive pas a faire de cluster avec le module que j'ai installer cluster : snowcluster 7.3.3

non-metric MDS

Thanks a lot for this module. I have been looking for the possibility of multidimensional analysis in Jamovi for a long time. Do you plan to include non-metric MDS in future versions?

Error: Duplicate 'row.names' are not allowed

In my data the rows aren't named,so having duplicates is impossible. I get this when using the analyses in snowCluster such as Hierachrical Clustering and PCA plot. My data are attached. When "County" is the label variable this error doesn't occur, but when other Labels such as "3Regions" is selected, the error pops up.
WEKA data.csv

snowCluster::caret does not work in ubuntu system

Hi ,
The machine learning part of the package, snowCluster::caret can run well in R (windows).
However, in R (ubuntu), or in Rstudio (cloud version), we got no results (empty tables or figures).
How can we run it in a Linux evironment?
Thanks
James

Univariate time series Problem

Hi,
I want to use ARIMA or Prophet module for my population forecasting research. But when I add the variables, I receive this message. I can't find any "newbie-friendly" tutorial for this extension. Also, can you explain to me about using this extension?
My data (ss-1)
Error message (ss-2, ss-3)
My file (poppr.omv)

Best regards.

poppr_.zip

More cluster centers than distinct data points using Snow Cluster add-in to Jamovi

I am experiencing a problem with Snow Cluster K-means clustering using Jamovi. My Jamovi dataset has 5800+ records, each with 5 variables to base the clusters on. There are 2 issues, firstly that optimal number of clusters always seems to be 1, which makes no sense given the diversity of data. The main issue is that I get the error "more cluster centers than distinct data points" whenever the number of clusters selected exceeds the number of variables entered (5), so it works fine selecting 2, 3, 4, 5 clusters, but if I enter 6 for the number of clusters, I immediately get this error. I get the same error using a smaller data set of 50 records. Working out clustering in Excel, I come up with 10 clusters. Please advice on what might be causing this problem so I can fix it. Source data is available if requested. I have seen remarks on this error relating to programming in r, but I am not writing or adjusting the code, just using Jamovi to drive the Snow Clustering. I am running on an iMac Pro M4 with 64GB memory, Mac Monterey OS, with Jamovi 2.3.28 (latest stable). I can provide the data if needed.

more cluster centers than distinct data points with Jamovi and Snow Cluster K-means

This is a request for advice on how to overcome an issue I am having with Snow Cluster K-means clustering. I am working with a dataset of 5800+ stores, where previously I have run PCA Analysis which distilled down to 4 resulting components, representing Population, Income, Store Size, and State/Climate. I am also including Sales Volume as a further variable into the clustering mix. The component values were saved to the store data. There are 2 issues, firstly that optimal number of clusters always seems to be 1, which makes no sense given the diversity of stores. However the main issue is that I get the error "more cluster centers than distinct data points" whenever the number of clusters selected exceeds the number of variables entered (5), so it works fine selecting 2, 3, 4, 5 clusters, but if I enter 6 for the number of clusters, I immediately get this error. Please advice on what might be causing this problem so I can fix it. Source data is available if requested.

교수님 안녕하세요, 군집분석 관련하여 여쭙고자 합니다.

사진에서와 같이 Centroids of clusters Table와 plot of means across clusters 군집 평균이 반대로 제시되는데 제가 해석을 잘못한 것일까요?

감사합니다!

Problems with the extension snowCluster package

Hello Professor Hyunsooseol

I have the version jamovi-2.4.8.0-win64 installed and I would like to use the snowCluster package. However, it is not available and I get an error message. I have thought about installing the most recent version jamovi-2.4.11.0-win64. Could you confirm if this could solve the installation and operation problem of the snowCluster extension with this new version?

Please, you can alternatively replay to [email protected]

Many thanks in advances

Michael

LDA in SnowCluster not showing the results

Hi!

I am using snowCluster for linear discriminant analysis but the results are not loading. I am using MacOS and installed the jamovi latest version.

Subscript out of Bounds

Hello! I have built today snowCluster to run LDA with my data. However, the error message "subscript fuori limite" (italian for: "subscript out of Bounds") appears. I have also tried with Iris Data but it shows same error. However, results are visible. Can I consider them as correct? I am using macOS Ventura, Jamovi version 2.3.21.0, snowCluster 7.1.2. Thanks!

settings for Hierarchical Clustering Dendrogram

Hi. I assume that the Hierarchical Clustering Dendogram is to be used as an attractive and convenient version of hierarchical clustering, whereas the Hierarchical clustering method gives a choice of settings. Can I assume that the Hierarchical Clustering Dendogram runs along the default settings of the other tool, i.e. standardized data, Euclidean distance and Ward D2 clustering?

I'm currently working on the second editions of my statistics books using jamovi, including a chapter on cluster analysis, so I would be grateful for your help with this.

Cole