This workflow shows how to build a hierarchy of clusters and visualize the hierarchy using the Sunburst Chart. It reads text data from a table. The data is taken from the 20 newsgroups dataset, divided into two categories, politics and sport. The data are first converted into documents, then they are preprocessed, i.e. tagged, filtered, lemmatized, etc, and later converted into document vectors. The next step is the clustering. A distance matrix is calculated using the cosine distance measure. Based on that, the documents are clustered hierarchically. To visualize the hierarchy, the Hierarchical Cluster View node is used to show the dendrogram. Furthermore the Sunburst Chart is used and the top k hierarchical levels of the clustering are shown in a radial layout.
EXAMPLES Server: 08_Other_Analytics_Types/01_Text_Processing/22_Hierarchical_Clustering_Visualization08_Other_Analytics_Types/01_Text_Processing/22_Hierarchical_Clustering_Visualization*
Download a zip-archive
* Find more about the Examples Server here.
The link will open the workflow directly in KNIME Analytics Platform (requirements: Windows; KNIME Analytics Platform must be installed with the Installer version 3.2.0 or higher). In other cases, please use the link to a zip-archive or open the provided path manually