These pages serve as the official documentation for the ClusterValidityIndices.jl Julia package.

Cluster Validity Indices (CVI) tackle the problem of judging the performance of an unsupervised/clustering algorithm without the availability of truth or supervisory labels, resulting in metrics of under- or over-partitioning. Furthermore, Incremental CVIs (ICVI) are variants of these ordinarily batch algorithms that enable an online and computationally tractable method of evaluating the performance of a clustering algorithm as it clusters while being numerically equivalent to their batch counterparts.

The purpose of this package is to provide a home for the development and use of these CVIs and ICVIs. For a list of all CVIs available from the package, see the Implemented CVI List page.

See the Index for the complete list of documented functions and types.

Manual Outline

This documentation is split into the following sections:

• Background
• Basic Example
• Package Guide
• Implemented CVI List
• Contributing
• Index
• Developer Index

The Background provides an overview of the problem statement of CVIs and what they are theoretically, while Basic Example steps through an single example workflow.

The Package Guide provides a tutorial to the full usage of the package, while Examples gives many sample workflows using a variety of CVI modules. All CVIs in the package are listed in the Implemented CVI List page.

Instructions on how to contribute to the package are found in Contributing, and docstrings for every element of the package is listed in the Index. Names internal to the package are also listed under the Developer Index.

Documentation Build

This documentation was built using Documenter.jl with the following version and OS:

AdaptiveResonance v0.8.2 docs built 2023-05-18T20:58:02.433 with Julia 1.9.0 on Linux

Citation

If you make use of this project, please generate your citation with the CITATION.cff file of the repository. Alternatively, you may use the following BibTeX entry for the JOSS paper associated with the repository:

@article{Petrenko2022,
  doi = {10.21105/joss.03527},
  url = {https://doi.org/10.21105/joss.03527},
  year = {2022},
  publisher = {The Open Journal},
  volume = {7},
  number = {79},
  pages = {3527},
  author = {Sasha Petrenko and Donald C. Wunsch},
  title = {ClusterValidityIndices.jl: Batch and Incremental Metrics for Unsupervised Learning},
  journal = {Journal of Open Source Software}
}