Interactive Exploration of Large Dendrograms with Prototypes

Hierarchical clustering is one of the standard methods taught for identifying and exploring underlying structures that may be present within a dataset. Students are shown examples in which dendrogram, visual representation hierarchical clustering, reveals clear structure. However, practice, data analysts today frequently encounter datasets whose large scale undermines usefulness dendrogram as visualization tool. Densely packed branches obscure structure, overlapping labels impossible to read. In this article we new workflow performing via R package called protoshiny aims restore its former role being an effective versatile Our proposal leverages interactivity combined with ability label internal nodes representative point (called prototype). After presenting workflow, provide three case studies demonstrate utility.