This is a hands-on introduction to the enhanced Automatic Machine Learning (AutoML) functionality provided by Driverless AI. We introduce you to data visualization for predictive models, automated feature engineering and model optimization using an adaptive evolutionary approach, automatic report generation, machine learning interpretability, and one-click model deployment, all using H2O.ai Driverless AI.
By the end of this training, the attendee will be able to
- Import data into Driverless AI
- Create summary statistics for all data columns/features imported
- Create data visualizations, including scatterplots, outlier plots, skewed variable plots, missing data plots, parallel coordinate plots, radar plots, heatmaps, and data transform recommendations.
- Split data into training and test sets
- Adjust Accuracy, Time, and Interpretability knob settings to create different predictive modeling recipes and perform model tuning
- Create a Project for comparing and scoring multiple models in a leaderboard framework
- Run model diagnostics on a new dataset to get AUC, RMSE, logloss, and other measures of model fit
- Download and review the automatic model report
- Download model predictions
- Create feature importance values, partial dependence and ICE plots, LIME plots, Shapley values, and other measures for interpreting models
- Deploy a model into a REST API
This course assumes some familiarity with statistical or machine learning modeling.