shapash and awesome-machine-learning-interpretability
One is a user-friendly library for explainability and interpretability in machine learning, while the other is a curated list of resources for responsible machine learning, making them complementary in the sense that the latter could list the former as an awesome resource.
About shapash
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
This project helps data scientists and machine learning engineers understand why their predictive models make certain decisions. It takes a trained machine learning model and its input data, then generates easy-to-understand visualizations and reports that explain the model's behavior. The output helps both technical and non-technical stakeholders gain trust and insights into the model's predictions.
About awesome-machine-learning-interpretability
jphall663/awesome-machine-learning-interpretability
A curated list of awesome responsible machine learning resources.
This project offers a curated collection of resources for anyone grappling with the ethical implications and responsible deployment of machine learning. It provides guidance, educational materials, and technical references to help you understand and address fairness, transparency, and accountability issues in AI systems. The primary users are professionals who work with or are impacted by AI, such as HR managers, legal experts, policymakers, and project managers, who need to navigate the complexities of AI ethics and governance.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work