03_​Global_​Feature_​Importance

0 ×

In the example, the Credit Scoring data set is partitioned to training and test samples. Then, the black box model (Neural Network) is trained on the standardly pre-processed training data using the AutoML component. The Workflow Object capturing the pre-processing and the model is provided as one of the inputs for the Global Feature Importance component.

The Global Feature Importance component is then used to inspect the global model behavior using three Global Surrogate models (Generalized Linear Model, Decision Tree, and Random Forest) and Permutation Feature Importance explainability technique.

Nodes

• Column Filter135 ×
• Rule Engine Variable94 ×
• Column Rename89 ×
• Component Input87 ×
• Component Output87 ×
• Show all 141 nodes

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Data Generation
• FeatureKNIME Deep Learning - Keras Integration
• FeatureKNIME Ensemble Learning Wrappers
• FeatureKNIME H2O Machine Learning Integration
• Show all 14 modules

Links

• KNIME Integrated Deployment - KNIME.com

  www.knime.com/integrated-deployment
• Molnar, Christoph. "Interpretable machine learning. A Guide for Making Black Box Models Explainable", 2019.

  christophm.github.io/interpretable-ml-book/
• Give Me Some Credit - Kaggle data set

  www.kaggle.com/c/GiveMeSomeCredit/