October 2017
Beginner to intermediate
572 pages
26h 1m
English
In this recipe, we demonstrate how to use the silhouette plot to validate clusters. You can first retrieve the silhouette information, which shows cluster sizes, the average silhouette widths, and individual silhouette widths. The silhouette coefficient is a value ranging from 0 to 1; the closer to 1, the better the quality of the cluster.
Lastly, we use the plot function to draw a silhouette plot. The left-hand side of the plot shows the number of horizontal lines, which represent the number of clusters. The right-hand column shows the mean similarity of the plot of its own cluster minus the mean similarity of the next similar cluster. The average silhouette width is presented at the bottom of the plot.
Read now
Unlock full access