Survival Analysis with Python, -- by Avishek Nag.

I got this book to review, via a group of data scientists. I was very curious and interested because survival analysis is one of those cases that has been a part of medical statistics for a while and with the AI/DS hype cycle going hard after Machine Learning(ML) it has been ignored.

So here are the pros:

* -- Pretty math-heavy, uses quite a bunch of equations and algebraic manipulation to show some of the results

* -- the Nice balance of code and math. Yes despite the book not shying away from math, It strikes a balance among a combo of math, code and simple plain English explanation.

* -- It has a nice amount of explanatory text setting up the problem, where and when it can be (and often is) ignored and replaced with a looser defined problem(Aka constraint relaxation in the discrete math space).

Okay now for the con:

* -- For someone who's interested in math at the theorems and proof level, it feels like the author decided to leave out the most interesting parts to avoid scaring mathphobes.

* -- Following up on the above, I feel like the book is pretty small and would have loved some more digging into the theorems, their assumptions for proof and how it affects the problem and its prediction.

In summary, I feel this is a great book to jump into basic survival analysis(strictest version of the problem, ) from a statistical viewpoint. And since it provides python examples, there's a nice jumping-off point if you have a hands-on problem to solve. In addition, because of the mathy nature of the book, it also provides some sense/way of reasoning with your model's eventual predictions.

Thanks to Avishek Nag for the book and the opportunity to review it.