Summary

Congratulations! We finally made it to the end of a very dense, yet very informative chapter. In this chapter, we learned quite a few different things. In the first half of this chapter, we explored the realm of classification and demonstrated the application of a number of models using the single-cell RNA dataset – a classical application in the field of biotechnology and life sciences. We learned about a number of different models, including KNNs, SVMs, decision trees, random forests, and XGBoost. We then moved our data and code to GCP, where we stored our data in BigQuery, and provisioned a notebook instance to run our code in. In addition, we learned how to automate some of the manual and labor-intensive parts of the model development process as it pertains to the protein classification dataset using auto-sklearn. Finally, we took advantage of GCP's AutoML application to develop a classification model for our dataset.

In the second half of this chapter, we...