DiCE

Getting Started:

  • Diverse Counterfactual Explanations (DiCE) for ML

Notebooks:

  • Quick introduction to generating counterfactual explanations using DiCE
  • Defining meta data
  • Loading trained ML model
  • Generate diverse counterfactuals
  • Advanced options to customize Counterfactual Explanations
  • Generate feasible counterfactual explanations using a VAE
  • Adding feasibility constraints

Package:

  • dice_ml package
DiCE
  • »
  • <no title>
  • View page source

Example notebooks

Notebooks:

  • Quick introduction to generating counterfactual explanations using DiCE
    • Preliminaries: Loading a dataset and a ML model trained over it
    • Generating counterfactual examples using DiCE
    • Generating feature attributions (local and global) using DiCE
    • Working with deep learning models (TensorFlow and PyTorch)
    • More resources: What’s next?
  • Defining meta data
  • Loading trained ML model
  • Generate diverse counterfactuals
  • Advanced options to customize Counterfactual Explanations
    • Loading dataset
    • 1. Loading a custom ML model
    • Generate diverse counterfactuals
    • 2. Changing feature weights
    • 3. Trading off between proximity and diversity goals
  • Generate feasible counterfactual explanations using a VAE
    • Loading dataset
    • Loading the ML model
    • Generate counterfactuals using a VAE model
  • Adding feasibility constraints
    • ModelApprox
    • Initilize the Model and Explainer for FeasibleModelApprox
Next Previous

© Copyright 2020, Ramaravind, Amit, Chenhao

Built with Sphinx using a theme provided by Read the Docs.