# 5. Pattern Clustering

The sub graphs, which were generated within the [Pattern Detection](4_Frequent_Subgraph_Mining.md) step, are used
as input for this step.
The **Graph Set Clustering** step aims at clustering similar patterns (sub graphs) into groups.
These groups/clusters can be viewed in the next step in
the [Collaboration Pattern Repository](6_Collaboration_Pattern_Repository.md).

## Execute graph set clustering

These different clustering algorithms can be executed:

- **Partitioning**: Autodetect the number of clusters by searching for distinct graphs
- **Hierarchical**: Definition of the number of clusters, Cluster Division Selector and Cluster Representative Seeder (
  high calculation times)
<!-- Not working atm - **Density-Based**: Autodetect the number of clusters by searching for near graphs -->

![Clustering](img/clustering.gif)