Summary 

In this chapter, we understood the various functionality that H2O Flow has to offer. After getting comfortable with the web UI, we started implementing our ML pipeline. We imported and parsed the Heart Failure Prediction dataset. We understood the various operations that can be performed on the dataframe, understood the metadata and statistics of the dataframe, and prepared the dataset to later train, validate, and predict models.

Then, we trained models on the dataframe using AutoML. We understood the various parameters that needed to be input to correctly configure AutoML. We trained models using AutoML and understood the leaderboard. Then, we dived deeper into the details of the models trained and tried our best to understand their characteristics.

Once our model was trained, we performed predictions on it and then explored the prediction output by combining it with the original dataframe so that we could compare the predicted values.

In the next chapter,...