02_​Counterfactual_​Explanations_​for_​Keras

0 ×

This application is a simple example of using Conterfactual Explanations (Python) component to identify the Counterfactual Instances for a Binary classification model trained in Keras outside KNIME eg: Python IDE, Google Colab or Jupyter Notebook.

The Python object reader load the pickled Python object which is used for nomalisation of features, while the Network Reader node reads the keras model trained outside of KNIME. The component (in blue) can be used to select the instances to be used for Counterfactual Explanations.

Nodes

• Component Input5 ×
• Component Output5 ×
• Conda Environment Propagation5 ×
• Breakpoint4 ×
• Rule Engine Variable3 ×
• Show all 28 nodes

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Basic File System Connectors
• FeatureKNIME Data Generation
• FeatureKNIME Deep Learning - Keras Integration
• FeatureKNIME Deep Learning - TensorFlow 2 Integration
• Show all 8 modules

Links

• Python Library for Counterfactual Instances

  docs.seldon.io/projects/alibi/en/stable/methods/CF.html
• How to set up Python-KNIME extension

  www.knime.com/blog/how-to-setup-the-python-extension
• KNIME Keras Integration

  docs.knime.com/2018-12/deep_learning_installation_guide/#keras-integration
• Counterfactual -Interpretable-ml-book

  christophm.github.io/interpretable-ml-book/counterfactual.html