Description: In this challenge, your goal is to see which features are the most important in predicting the quality of wine. After doing this analysis, you should create a visualization that shows the features' importances in order.
Solution Summary: I solve this challenge by comparing the root mean squared error obtained with an AutoML regression model over a subset of the data, and over the whole data with feature value permutations -- one feature at a time. In the end, our conclusion is that alcohol content is likely the most important feature that determines wine quality.
To use this workflow in KNIME, download it from the below URL and open it in KNIME:
Download WorkflowDeploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.
Try NodePit Runner!