ClusterKit: High-performance UMAP and clustering for Ruby
ClusterKit brings state-of-the-art dimensionality reduction and clustering algorithms to Ruby through native Rust bindings. Run UMAP, PCA, K-means, and HDBSCAN directly in your Ruby process with performance matching Python’s scikit-learn - no Python required.
What makes it special:
- Native Rust performance via Magnus FFI (2-3x faster with parallel processing)
- Reproducible results with seed support
- Handles extreme data ranges without crashing (fixed the notorious box_size panic)
- Works seamlessly with Ruby arrays and Numo::NArray
Perfect for data visualization, density-based clustering, anomaly detection, and exploratory data analysis - all without leaving Ruby or shelling out to Python.
- GitHub: https://github.com/cpetersen/clusterkit
- RubyGems: https://rubygems.org/gems/clusterkit
Post a comment