search

asardaes / dtwclust

R Package for Time Series Clustering Along with Optimizations for DTW
https://cran.r-project.org/package=dtwclust
GNU General Public License v3.0
254 stars 29 forks source link

Partitionial clustering, which method? #64

Closed ElliotPS1992 closed 6 months ago

ElliotPS1992 commented 1 year ago

Hello,

I am clustering a big longitudinal dataset with around 100,000 subjects. In another issue for someone else you suggested to use partitional clustering with not the PAM centroid for large datasets. This works really well and fast with for example dba or sdtw. However, I was wondering what kind of partitional clustering is used in case of dba or sdtw. For instance, K-means, K-mediods or something else?

Thank you in advance.

Kind regards, Leslie

asardaes commented 1 year ago

Hi, I'm not sure I get the question, DBA is a centroid algorithm that can be used with k-means, only using PAM counts as k-medoids.