Evaluation of the cluster quality with indicators
cammarano opened this issue · comments
Supposing to start from an unlabeled dataset featured by N features, I want to perform a clustering. I don't have a testing sample (labels) and ground truth is not available. I don't see a tool for evaluating the clustering quality, for instance to provide silhouette coefficients.
Is there a way to perform this kind of analysis?
Hey @cammarano, yeah so far all the clustering metrics and reports require the ground-truth. I would love to implement something like a silhouette score some day.