search

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.
http://www.sthda.com/english/wiki/factoextra-r-package-easy-multivariate-data-analyses-and-elegant-visualization
8 stars 2 forks source link

K-means clustering does not work for k >= 3 #31

Closed cristinagarciamata closed 1 week ago

cristinagarciamata commented 2 weeks ago

K-means clustering works as usual when the number of clusters is set to 2 (k=2), but as soon as I try to change the k to a higher number, the analysis does not run (see picture). I have tried it on various other devices, but the module keeps getting stuck (and I know it worked like two weeks ago).

Capture04

hyunsooseol commented 2 weeks ago

Hi cristinagarciamata

Could you attach .omv file that produces error in here?

Kind Regards Seol

cristinagarciamata commented 2 weeks ago

Hi Seol,

here is the .omv files with the error. Thanks for your quick reply! I had to change the name of the file ending to .omv.txt because GitHub did not let me attach .omv files.

Kind regards Cristina

KMeans_Problem.omv.txt

hyunsooseol commented 2 weeks ago

Hi cristinagarciamata

Oh. You should attach the file as zip file here cause I can not open txt file.

Kind Regards Seol

cristinagarciamata commented 2 weeks ago

Hi @hyunsooseol

thanks for the hint. Here is the attached file as zip: KMeans_Problem.omv.zip

Kind Regards Cristina

hyunsooseol commented 2 weeks ago

Hi cristinagarciamata

This is not an error of module. In general, the number of variables should be greater than the number of clusters.

Kind Regards Seol

cristinagarciamata commented 1 week ago

Oh, thanks for the clarification!

As one of the plots recommended k=5 for my data, I thought it might be possible to calculate it.