Clustering: Silhouette Coefficient or Performance for Agglomerative Clustering Solution
btibert
New Altair Community Member
Is it possible to review a cluster solution via the Silhouette Coeffecient? I know that we have a performance operator for centroid-based approaches, but I was hoping to present my students with a form of "performance" for a fit based on agglomerative clustering.
For example: https://rstudio-pubs-static.s3.amazonaws.com/284508_1faa54c2fb684ad689eccc0bcaa3b528.html#silhouette-coefficient
Context: For larger datasets, the dendrogram output in RM is hard to read, especially in the absence of interactivity and labels on the records. It would be outside the scope of my course to have my students use a python operator, unfortunately, so curious if there is already a solution that I am missing
For example: https://rstudio-pubs-static.s3.amazonaws.com/284508_1faa54c2fb684ad689eccc0bcaa3b528.html#silhouette-coefficient
Context: For larger datasets, the dendrogram output in RM is hard to read, especially in the absence of interactivity and labels on the records. It would be outside the scope of my course to have my students use a python operator, unfortunately, so curious if there is already a solution that I am missing
Tagged:
0