Expose offset_column in AutoML

h2oai / h2o-3

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

Apache License 2.0

6.85k stars 2k forks source link

All the algorithms, aside from RF, support {{offset_column}} so we should expose this to the user in AutoML. We should probably just skip Random Forest if this is enabled.

We should also note that this cannot be supported in mutliclass by default, since the Stacked Ensemble metalearner is GLM and multiclass offset_column is not supported in GLM. We could throw an error and suggest to the user to change the metaleraner algorithm (or we will change it automatically) to something that does support it.

Current blocker is that GLM MOJO does not support offset column, so let’s fix this first: [https://h2oai.atlassian.net/browse/PUBDEV-8548|https://h2oai.atlassian.net/browse/PUBDEV-8548|smart-link]

h2oai / h2o-3

Expose offset_column in AutoML #7116