01_​Train_​and_​Explain_​Keras_​Network_​with_​Counterfactuals

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 KNIME with Keras.

The Component (in yellow) uses KNIME Python Integration for normalisation of features and outputs the features along with the pickled file containing the preprocessing object. The Component (in blue) can be used to select the instances to be used for Counterfactual Explainations.

Nodes

• Component Input9 ×
• Component Output9 ×
• Breakpoint5 ×
• Column Filter5 ×
• Table Row to Variable5 ×
• Show all 43 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 10 modules

Links

• Python Library for Counterfactual Instances

  docs.seldon.io/projects/alibi/en/stable/methods/CF.html
• KNIME Keras Integration

  docs.knime.com/2018-12/deep_learning_installation_guide/#keras-integration
• How to set up KNIME Python extension

  www.knime.com/blog/how-to-setup-the-python-extension
• Counterfactual - Interpretable-ml-book

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