2

I recently become familiar with Interpretable ML and I found some libraries like LIME. I would be thankful if you can suggest to me some libraries and what are the advantages of each library.

Aaron
  • 231
  • 1
  • 3
  • 9

2 Answers2

1

A couple of the most common Python packages for interpretable machine learning:

  • Lime - Can explain the prediction of any machine learning classifier.

  • SHAP - A game-theoretic approach to explain the output of any machine learning model.

  • ELI5 - Explain the weights and predictions of a variety of machine learning models.

Brian Spiering
  • 23,131
  • 2
  • 29
  • 113
0

I will suggest Dalex as it has a very easy workflow and has both Python and R APIs.

Also Interpret-ML from Microsoft has very good features.

tfkLSTM
  • 1