The rest of this book will cover several advanced topics. Some of the things we discuss really are advanced topics, which are often useful in data science but which many data scientists never need. Deep learning is a good example of this.
In other cases though, we will be fleshing out topics that we've already discussed. There will be less in the way of nuts-and-bolts code and more abstract theory. The big reason for this is that standard techniques often don't work for one reason or another. For example, you might need to adjust how a machine learning model works in order to accommodate outliers in a particular way. If this happens, you will have to revisit the assumptions that the standard techniques are based on and devise new techniques that work for your situation.