[jira] [Created] (IGNITE-10747) [ML] Add NaN (missing) value support into Decision Tree training

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

[jira] [Created] (IGNITE-10747) [ML] Add NaN (missing) value support into Decision Tree training

Anton Vinogradov (Jira)
Anton Dmitriev created IGNITE-10747:
---------------------------------------

             Summary: [ML] Add NaN (missing) value support into Decision Tree training
                 Key: IGNITE-10747
                 URL: https://issues.apache.org/jira/browse/IGNITE-10747
             Project: Ignite
          Issue Type: Improvement
          Components: ml
    Affects Versions: 2.8
            Reporter: Anton Dmitriev
            Assignee: Alexey Platonov
             Fix For: 2.8


As result of integration with XGBoost our DecisionTree model now supports NaN (missing) values. Would be great to support these values in out DecisionTree classification/regression trainers as well.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)