/mlconf-2023

Workshop for ML Conference Berlin 2022

Primary LanguageJupyter NotebookMIT LicenseMIT

Workshop for ML Conference Berlin 2022

Introduction to Explainable AI

Downloadable Pre-requisites

  • Jupyter environment with *Python >= 3.9 and the following python libraries are required:
  1. requests => 2.27.1
  2. numpy=>1.22.4
  3. pandas=>1.5.3
  4. tqdm=>4.65.0
  5. scikit-learn=>1.2.2
  6. matplotlib=>3.7.1
  7. seaborn=>0.12.2
  8. catboost=>1.0.6
  9. joblib==1.2.0
  10. rulefit==0.3
  11. PDPbox==0.3.0
  12. PyALE==1.1.2
  13. imodels=>1.3.0
  14. interpret=>0.2.7
  15. alibi=>0.8.0
  16. shap=>0.40.0
  17. lime=>0.2.0.1
  18. imgaug==0.4.0
  19. PiML=>0.5.0
  20. witwidget >=1.8.1
  21. tensorflow=> 2.12.0
  22. keras=>2.12.0

(please note that Google Colab comes with all those marked with * pre-installed and code provided will come with instructions on how to install everything else)

Datasets located here: /data (M)

Additional Instructions

If you plan to run workshops code in your local machine, make sure you have a working Jupyter environment with the latest version of Python. If you don’t have one, you can install Anaconda, but please do so before the session. The code we will using is located here:

Although additional libraries can be installed quickly and usually do so without any issues, it is recommended that you install them in advance (just in case the local environment presents some problems).