The goal seems to be to bring reasonably well-informed people to an advanced understanding of regression and ANOVA techniques (linear models). The book does serve that purpose, as the book explains each element with sufficient technical precision to fully understand what is happening without trailing into mathematical statistics more than necessary.

Many data analysts get their start working in Microsoft Excel, as it is a relatively inexpensive graphical interface with nearly unlimited learning resources. After some time, you may find that you want more flexibility in your analysis, but learning a programming language like R can be a daunting challenge.

The R book is 880 pages long and it covers just about everything you can do in base R, with some packages introduced.

This book takes a general approach, teaching the reader how to implement a wide variety of machine-learning techniques.

You can expect to learn about basic neural networks that solve a regression or classification problem, as well as advanced topics. These advanced topics include image classification (like MNIST), natural language processing, and general time-series models.

This book illustrates a method of using the traditional deep learning based multi-class classification techniques to hide message in a matrix of seemingly random numbers.

I start from the very beginning of assigning variables, and end with multi-class classification with deep learning models.