Summary

In this chapter, we took an ambitious step toward understanding some of the most important and useful concepts in ML. We looked over the various terms used to describe the field as it relates to the domain of AI, examined the main areas of ML and the governing categories of supervised and unsupervised learning, and then proceeded to explore the full process of developing an ML model for a given dataset.

While developing our model, we explored many useful steps. We explored and preprocessed the data to remove inconsistencies and missing values. We also examined the data in great detail, and we subsequently addressed issues relating to multicollinearity. Next, we developed a Gaussian Naïve Bayes classification model, which operated with a robust 95% rate of accuracy – on our first try too! Finally, we looked at one of the most common ways data scientists hand over their fully trained models to data engineers to move ML models into production.

Although we took...