[MATH-1519] Implement the Calinski-Harabasz clusters evaluator

• Type: New Feature
• Status: Resolved
• Priority: Major
• Resolution: Done
• Labels: features
• Assignee: Unassigned
• Reporter: Chen Tao
• Created: 09/Mar/20 02:27
• Updated: 10/Mar/20 02:36
• Resolved: 10/Mar/20 02:35

Description

It is also known as the Variance Ratio Criterion.
The Calinsk-iHarabasz score is defined as ratio between the within-cluster dispersion and the between-cluster dispersion, can be used to evaluate the model, where a higher Calinski-Harabasz score relates to a model with better defined clusters.
For more information, please read:
https://scikit-learn.org/stable/modules/generated/sklearn.metrics.calinski_harabasz_score.html
https://www.tandfonline.com/doi/abs/10.1080/03610927408827101

Issue Links

• is related to: MATH-1515 Enhance clustering API
• links to: GitHub Pull Request #123