Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/navdeep-g/interpretable-ml

Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.
https://github.com/navdeep-g/interpretable-ml

accountability data-mining data-science decision-trees fairness fatml gradient-boosting-machine iml interpretability interpretable interpretable-ai interpretable-machine-learning interpretable-ml lime machine-learning machine-learning-interpretability python transparency xai

Last synced: 14 days ago
JSON representation

Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.

Awesome Lists containing this project

README 

        
# Interpretable Machine Learning



##### **A collection of code, notebooks, and resources for training interpretable machine learning (ML) models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.**



##### **Want to contribute your own examples/code/resources?** Just make a pull request.



## Setup

```

cd interpretable-ml

virtualenv -p python3.6 env

source env/bin/activate

pip install -r python/jupyter-notebooks/requirements.txt



** Note: if using Ubuntu, you may have to manually install gcc. Try the following 

1. sudo apt-get update

2. sudo apt-get install gcc

3. sudo apt-get install --reinstall build-essential

```

## Contents 

* Presentations

	* [Responsible Machine Learning](https://github.com/navdeep-G/interpretable-ml/tree/master/responsible_ml_tex/rml.pdf) 

	* [Overview of Interpretable Machine Learning Techniques (incomplete list)](https://github.com/navdeep-G/interpretable-ml/tree/master/iml_tex/interpretable_ml.pdf)

	* [Discrimination in Machine Learning](https://github.com/navdeep-G/interpretable-ml/tree/master/fair_ml_tex/fair_mli.pdf)

	* [Secure Machine Learning](https://github.com/navdeep-G/interpretable-ml/tree/master/secure_ml_tex/secure_ml.pdf)

* Jupyter Notebooks

	- [Binary Classification](https://github.com/navdeep-G/interpretable-ml/tree/master/python/jupyter-notebooks/credit/binomial)

		- [Shapley, PDP, & ICE](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/binomial/xgb_credit_binary_shap_pdp_ice.ipynb)

		- [Decision Tree Surrogate and Leave One Covariate Out](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/binomial/dt_surrogate_loco.ipynb)

		- [LIME](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/binomial/lime.ipynb)

		- [Residual Analysis](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/binomial/debugging_resid_analysis_redux.ipynb)

		- [Sensitivity Analysis](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/binomial/debugging_sens_analysis_redux.ipynb)

		- [Disparate Impact Analysis](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/binomial/dia.ipynb)

		- [Disparate Impact Analysis w/ Python `datatable`](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/binomial/dia_with_datatable.ipynb)

	- [Multinomial Classification](https://github.com/navdeep-G/interpretable-ml/tree/master/python/jupyter-notebooks/credit/multinomial)

		- [Shapley, PDP, & ICE](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/multinomial/xgb_credit_multinomial_shap_pdp_ice.ipynb)

		- [Disparate Impact Analysis](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/credit/multinomial/dia_multinomial.ipynb)

- Simulated Data for Testing Purposes

	- [Binary Classfication](https://github.com/navdeep-G/interpretable-ml/tree/master/python/jupyter-notebooks/simulated/binomial)

		- [Shapley, PDP, & ICE](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/simulated/binomial/xgb_simulated_binomial_shap_pdp_ice.ipynb)

	- [Multinomial Classification]()

		- [Shapley, PDP, & ICE](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/simulated/multinomial/xgb_simulated_multinomial_shap_pdp_ice.ipynb)

		- [Shapley, PDP, ICE, & Decision Tree Surrogate](https://github.com/navdeep-G/interpretable-ml/blob/master/python/jupyter-notebooks/simulated/multinomial/xgb_simulated_multinomial_shap_pdp_ice_DT.ipynb)



## Further reading:

* Books/Articles

	* [*Responsible Machine Learning:

	Actionable Strategies for Mitigating Risks & Driving Adoption*](https://www.h2o.ai/resources/ebook/responsible-machine-learning/)

	* [*An Introduction to Machine Learning Interpretability, 2nd Edition*](https://www.h2o.ai/wp-content/uploads/2019/08/An-Introduction-to-Machine-Learning-Interpretability-Second-Edition.pdf)

	* [*A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing*](https://www.mdpi.com/2078-2489/11/3/137)

	* [*On the Art and Science of Explainable Machine Learning*](https://arxiv.org/pdf/1810.02909.pdf)

	* [*Proposals for model vulnerability and security*](https://www.oreilly.com/ideas/proposals-for-model-vulnerability-and-security)

	* [*Proposed Guidelines for the Responsible Use of Explainable Machine Learning*](https://arxiv.org/pdf/1906.03533.pdf)

	* [*Real-World Strategies for Model Debugging*](https://medium.com/@jphall_22520/strategies-for-model-debugging-aa822f1097ce)

	* [*Warning Signs: Security and Privacy in an Age of Machine Learning*](https://fpf.org/wp-content/uploads/2019/09/FPF_WarningSigns_Report.pdf)

	* [*Why you should care about debugging machine learning models*](https://www.oreilly.com/radar/why-you-should-care-about-debugging-machine-learning-models/)



## Resources

* [*Awesome Machine Learning Interpretability*](https://github.com/jphall663/awesome-machine-learning-interpretability)