Generate unsupervised labels by identifying structure in feature space or an embedded representation.
Clustering groups observations according to patterns in the selected analytical space.
Ounias can cluster the original selected features or a lower-dimensional representation generated by an embedding method.
Choose whether the clustering method operates directly on selected features or on a generated embedding.
Cluster observations directly using the selected dataset features.
Cluster observations using coordinates produced by an embedding method.
Different clustering methods make different assumptions about group shape, density, and membership.
Partitions observations around a selected number of cluster centers.
Models observations as a mixture of probabilistic distributions.
Finds dense regions while allowing some observations to remain unassigned.
Extends density-based clustering across varying density levels.
Builds a hierarchical grouping by progressively combining observations or clusters.
Uses relationships between observations to identify potentially nonlinear group structure.
