Partial Dependence Plot with a Custom Model

This is an example for visualizing a partial dependence plot and an ICE curves plot in KNIME.
An XGBoost model was picked, but any model and its set of Learner and Predictor nodes can be used.

- Read the dataset about wines
- Partition the data in train and test
- Create the samples via the apposite shared component Partial Dependence Pre-processing
- Score the samples using the predictor node and a trained model
- Visualize the Partial Dependence/ICE Plot and customize it directly in the View (Execute > Right Click > Open View)
- Apply and Close to save the custom in-view settings

External resources

• Christoph Molnar - Interpretable Machine Learning - A Guide for Making Black Box Models Explainable - 5.1 Partial Dependence Plot (PDP)
• Data Source: UCI - Wine Quality Data Set