Model explanations in Azure Machine Learning
Studio include multiple visualizations
that you can use to explore
feature importance. The first visualization on the explanations tab for a run shows global feature importance. You can use the slider to
show only the top-k features. Switching to the summary
importance visualization shows the distribution of
individual importance, values for each feature
across the test dataset. You can view the features
as a swarm plot, shown above, a box plot, or a violin plot. Selecting an individual
data point shows the local feature importance for the case to which the
data point belongs.