https://community.databricks.com/t5/machine-learning/what-is-the-preview-feature-for-auto-ml/m-p/19870#M1089 <P>What is the preview feature for Auto ML</P> Fri, 25 Jun 2021 13:16:56 GMT User16826994223 2021-06-25T13:16:56Z https://community.databricks.com/t5/machine-learning/what-is-the-preview-feature-for-auto-ml/m-p/19870#M1089 <P>What is the preview feature for Auto ML</P> Fri, 25 Jun 2021 13:16:56 GMT https://community.databricks.com/t5/machine-learning/what-is-the-preview-feature-for-auto-ml/m-p/19870#M1089 User16826994223 2021-06-25T13:16:56Z https://community.databricks.com/t5/machine-learning/what-is-the-preview-feature-for-auto-ml/m-p/19871#M1090 <P>A - AutoML public preview features</P><P>The Databricks AutoML Public Preview parallelizes training over <A href="https://scikit-learn.org/stable/" alt="https://scikit-learn.org/stable/" target="_blank">sklearn</A> and <A href="https://xgboost.readthedocs.io/en/latest/" alt="https://xgboost.readthedocs.io/en/latest/" target="_blank">xgboost</A> models for classification (binary and multiclass) and regression problems. We support datasets with numerical, categorical and timestamp features and automatically handle one-hot encoding and null imputation. Trained models are <A href="https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html" alt="https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html" target="_blank">sklearn pipelines</A> such that all data preprocessing is wrapped with the model for inference.</P> Fri, 25 Jun 2021 13:17:16 GMT https://community.databricks.com/t5/machine-learning/what-is-the-preview-feature-for-auto-ml/m-p/19871#M1090 User16826994223 2021-06-25T13:17:16Z