A full-featured Ruby implementation of Naive Bayes for probabilistic classification with customizable features.
NBayes is a Ruby implementation of the Naive Bayes algorithm for probabilistic classification. It provides a full-featured toolkit for building classifiers that can handle various data types beyond text, with customizable options for smoothing, token management, and probability calculations.
Ruby developers and data practitioners who need a flexible, probabilistic classification library for tasks like text categorization, spam filtering, or general machine learning applications.
Developers choose NBayes for its comprehensive feature set, including probability outputs, customizable smoothing, and support for non-text tokens, all within a clean Ruby interface that balances flexibility with the algorithm's inherent simplicity.
A robust, full-featured Ruby implementation of Naive Bayes
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Supports all token types, not just text, allowing classification of diverse data like numerical features or categorical variables, as highlighted in the README.
Returns full probability distributions for each class instead of just predictions, enabling confidence-based decision-making, a key feature mentioned in the description.
Offers adjustable Laplacian smoothing constants and optional low-frequency token purging, providing control over model robustness and performance trade-offs.
Tied exclusively to Ruby, making it impractical for projects using other languages or requiring cross-platform ML deployments, as it adds unnecessary dependency.
The README is minimal with only basic usage and links to a 2012 blog post; last update was in 2021, indicating potential lag in bug fixes or community support.