You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
With the addition of Decision Tree Graphviz visualizations and given that some Learners already implement the RanksFeatures interface which provides a method to output the importance scores of each feature in the training set, we could start to build out a separate section of the User Guide dedicated to model explainability.
I think a good place to start would be an Introduction, a Feature Importances section, and a Decision Tree visualization section. We could move the Feature Importances section over from the Training page (https://github.com/RubixML/ML/blob/master/docs/training.md#feature-importances). We should also include an image (png) of an example Decision Tree graph.
With the addition of Decision Tree Graphviz visualizations and given that some Learners already implement the RanksFeatures interface which provides a method to output the importance scores of each feature in the training set, we could start to build out a separate section of the User Guide dedicated to model explainability.
I think a good place to start would be an Introduction, a Feature Importances section, and a Decision Tree visualization section. We could move the Feature Importances section over from the Training page (https://github.com/RubixML/ML/blob/master/docs/training.md#feature-importances). We should also include an image (png) of an example Decision Tree graph.
The page should be written in markdown like the rest of them see https://github.com/RubixML/ML/tree/master/docs.
The text was updated successfully, but these errors were encountered: