Search papers, labs, and topics across Lattice.
This paper introduces SCPP, an open-source Python library designed to standardize and simplify the implementation of soft clustering algorithms. By providing a scikit-learn-compatible interface, SCPP facilitates model training, evaluation, and benchmarking across a diverse array of soft clustering techniques, including fuzzy and probabilistic methods. The library integrates 40 algorithms and offers comprehensive documentation and testing, enhancing reproducibility and extensibility in clustering research.
SCPP streamlines soft clustering research by unifying 40 algorithms under a single, user-friendly framework that promotes reproducibility and extensibility.
In this paper, we present SCPP (Soft Clustering Python Package), an open-source Python framework for soft clustering. SCPP establishes a canonical, scikit-learn-compatible estimator interface that standardizes model training, prediction, membership representation, evaluation, and benchmarking across heterogeneous soft clustering methods, including fuzzy, probabilistic, graph-based, matrix factorization, and deep learning methods. The framework currently integrates 40 representative algorithms together with a comprehensive benchmarking comprising datasets, clustering quality metrics, and standardized runtime, memory, and scalability evaluation. SCPP further provides extensive documentation, practical examples, automated testing, and seamless integration with the scientific Python ecosystem, enabling reproducible experimentation and straightforward extension with new algorithms. The source code is publicly available at https://github.com/soft-clustering/soft-clustering.
