shapash
Model explainer
Provides visualizations and explanations to help understand machine learning model interactions and decisions
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
3k stars
37 watching
335 forks
Language: Jupyter Notebook
last commit: about 1 month ago
Linked from 3 awesome lists
ethical-artificial-intelligenceexplainabilityexplainable-mlinterpretabilitylimemachine-learningpythonshaptransparency
josephmisiti/awesome-machine-learning
altamiracorp/awesome-xaiRelated projects:
| Repository | Description | Stars |
|---|---|---|
 shap/shap | Provides an algorithm to explain the output of machine learning models using game theory and Shapley values. | 23,077 |
 jphall663/interpretable_machine_learning_with_python | Teaching software developers how to build transparent and explainable machine learning models using Python | 673 |
 bgreenwell/fastshap | Provides an efficient approach to computing Shapley values for explaining machine learning model predictions. | 116 |
 trekhleb/homemade-machine-learning | Practices implementing popular machine learning algorithms from scratch to gain a deeper understanding of their mathematics | 23,191 |
 h2oai/mli-resources | Provides tools and techniques for interpreting machine learning models | 483 |
 interpretml/interpret | An open-source package for explaining machine learning models and promoting transparency in AI decision-making | 6,324 |
 dfki-interactive-machine-learning/arasif | Provides sentence embeddings for Arabic languages using pre-trained word embeddings and Smooth Inverse Frequency algorithm | 5 |
| interpretml/dice | Provides counterfactual explanations for machine learning models to facilitate interpretability and understanding. | 1,373 |
 csinva/imodels | An open-source package that provides interpretable machine learning models compatible with scikit-learn. | 1,406 |
 christophm/interpretable-ml-book | A comprehensive resource for explaining the decisions and behavior of machine learning models. | 4,811 |
 mostafa-samir/how-machine-learning-works | An implementation of Manning Publications' How Machine Learning Works book in Python using Jupyter Notebook | 4 |
| h2oai/article-information-2019 | A framework for building and evaluating machine learning systems with high accuracy and interpretability, particularly in human-centered applications. | 13 |
 ethicalml/xai | An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance | 1,135 |
 trusted-ai/aix360 | A toolkit for explaining complex AI models and data-driven insights | 1,641 |
 giskard-ai/giskard | Automates the detection of performance, bias, and security issues in AI applications | 4,125 |