shapash and interpret

Both tools provide explainability and interpretability capabilities for machine learning models, but Shapash is designed for user-friendliness and development of reliable models, while InterpretML focuses on fitting inherently interpretable models and explaining black-box models, suggesting they are **competitors** offering different approaches to the same core problem.

shapash
70
Verified
interpret
67
Established
Maintenance 13/25
Adoption 11/25
Maturity 25/25
Community 21/25
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 21/25
Stars: 3,150
Forks: 373
Downloads:
Commits (30d): 3
Language: Jupyter Notebook
License: Apache-2.0
Stars: 6,813
Forks: 778
Downloads:
Commits (30d): 44
Language: C++
License: MIT
No risk flags
No Package No Dependents

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.

machine-learning-auditing model-explanation data-science-communication predictive-analytics AI-transparency

About interpret

interpretml/interpret

Fit interpretable models. Explain blackbox machine learning.

This project helps data scientists, analysts, and domain experts understand why their machine learning models make certain predictions. You input your trained model and data, and it outputs clear explanations, showing how different factors influence predictions globally and for individual cases. This is useful for anyone who needs to trust, debug, or explain their models to stakeholders or for regulatory compliance.

model-debugging regulatory-compliance fairness-auditing AI-explainability predictive-analytics

Scores updated daily from GitHub, PyPI, and npm data. How scores work