SeldonIO / alibi
Algorithms for explaining machine learning models
☆2,475Updated 2 weeks ago
Alternatives and similar repositories for alibi:
Users that are interested in alibi are comparing it to the libraries listed below
- Interpretability and explainability of data and machine learning models☆1,676Updated last month
- Algorithms for outlier, adversarial and drift detection☆2,336Updated last week
- Generate Diverse Counterfactual Explanations for any machine learning model.☆1,392Updated 4 months ago
- Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).☆1,443Updated 3 weeks ago
- Fit interpretable models. Explain blackbox machine learning.☆6,438Updated this week
- Source code/webpage/demos for the What-If Tool☆943Updated 6 months ago
- XAI - An eXplainability toolbox for machine learning☆1,158Updated 3 years ago
- Code for "High-Precision Model-Agnostic Explanations" paper☆799Updated 2 years ago
- A Python package to assess and improve fairness of machine learning models.☆2,035Updated this week
- A library for debugging/inspecting machine learning classifiers and explaining their predictions☆2,771Updated 2 years ago
- Interpret Community extends Interpret repository with additional interpretability techniques and utility functions to handle real-world d…☆427Updated last month
- python partial dependence plot toolbox☆852Updated 6 months ago
- OmniXAI: A Library for eXplainable AI☆908Updated 8 months ago
- Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.☆2,367Updated 3 months ago
- moDel Agnostic Language for Exploration and eXplanation☆1,414Updated last month
- Feature engineering package with sklearn like functionality☆2,021Updated last week
- Extra blocks for scikit-learn pipelines.☆1,314Updated last week
- Hummingbird compiles trained ML models into tensor computation for faster inference.☆3,415Updated 2 months ago
- Bias Auditing & Fair ML Toolkit☆713Updated last week
- ☆913Updated 2 years ago
- 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models☆2,861Updated last week
- Model interpretability and understanding for PyTorch☆5,156Updated this week
- Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code. We are look…☆428Updated 7 months ago
- Fast SHAP value computation for interpreting tree-based models☆537Updated last year
- Natural Gradient Boosting for Probabilistic Prediction☆1,691Updated last week
- A machine learning package for streaming data in Python. The other ancestor of River.☆773Updated last year
- A curated list of awesome responsible machine learning resources.☆3,747Updated this week
- Visual analysis and diagnostic tools to facilitate machine learning model selection.☆4,328Updated last month
- Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, …☆675Updated 9 months ago
- A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitig…☆2,556Updated 3 months ago