July 2017
Beginner to intermediate
715 pages
17h 3m
English
Content preview from Java: Data Science Made Easy
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
Start your free trial
Unsupervised Evaluation
Lastly, there are unsupervised evaluation scores for assessing the quality of clustering when no labels are known.
We already mentioned one such metric: distortion, which is the sum of distances between each item and its closest centroid. There are other metrics such as:
- Maximal pairwise distance within clusters
- Mean pairwise distance
- Sum of squared pairwise distances
These and some other metrics are also implemented in JSAT and you will find them in the jsat.clustering.evaluation.intra package.