ClustEval clustering evaluation framework
The Rand Index is the ratio of pairs of objects correctly clustered out of all possible pairs. This measure estimates the likelihood of an element being correctly classified. This measure is based on the pairwise approach to calculate TP,TN,FP and FN. $R = \frac{TP+TN}{TP+FP+FN+TN}$ In the binary classification background we have two classes that we want to distinguish: positive and negative. In this scenario there are four possible outcomes: