ClustEval clustering evaluation framework
The Dunn Index assesses the goodness of a clustering, by measuring the maximal diameter of clusters and relating it to the minimal distance between clusters. This measure is quite conservative and prone to outliers, since it bases its calculation only on minimal and maximal distances. $D = \frac{\underset{c_i \neq c_j \in C}{\text{min}}\{d(c_i,c_j)\}}{\underset{c_k \in C}{\text{max}} \{ d'(c_k) \}}$