Aglomera.Evaluation.External Namespace

Implements an external clustering evaluation criterion as a combination (weighted average) of other IExternalEvaluationCriterionTInstance, TClass.

Evaluates the given partition according to the F-measure, i.e., it measures the accuracy of the clustering by measuring the percentage of decisions that are correct (true positives + true negatives).

Evaluates the given partition according to the normalized mutual information criterion that measures the amount of information by which our knowledge about the classes increases when we are told what the clusters are.

Evaluates the given partition according to the precision criterion, given by the percentage of true positives over all positives.

Evaluates the given partition according to the purity criterion, where each cluster is assigned to its most frequent class, and then the accuracy of this assignment is measured by counting the number of correctly assigned instances and dividing by the total number of instances.

Evaluates the given partition according to the Rand index, i.e., it measures the accuracy of the clustering by measuring the percentage of decisions that are correct (true positives + true negatives).

Evaluates the given partition according to the recall criterion, given by the percentage of true positives over all relevant cases (true positives + false negatives).

Represents an interface for external criteria to evaluate how well the result of AgglomerativeClusteringAlgorithmTInstance matches the classification of instances according to a set of gold standard classes. We can think of this as supervised clustering evaluation methods, i.e., external validation methods.