I’ve finished reading this book. Though this is written in English originally, I read the translated version.
As written in review in Amazon, the book explains not only theoretical side of machine learning but also practical code. Moreover the balance of these two side was appropriate for me. Most books about machine learning can only tell me the detail of machine learning by using math and statistics or only tell me how to use machine learning tools such as scikit-learn, Theano, MLlib. I can recommend this book to novice programmer who wants to learn machine learning as their side project. Of course since the detail of scikit-learn and matplotlib is also described here, those of who is a professional data scientist using python machine learning tools in their daily work.
The most impressive part of this book was chapter 4,5,6.
- Chapter4: Preprocessing, feature engineering.
- Chapter5: Dimension reduction, compression.
- Chapter6: Model evaluation, hyper parameter tuning.
I’ve learning the basic of machine learning by myself with such as PRML and machine learning in Cousera. But I have seldom experience of solving real problems. The time when I tried to solve kaggle problem I had no good point. The reason of this bad point was mainly due to no effective preprocessing and pipeline. I’ve just learning the basic of creating pipeline and model evaluation. So now I want to try kaggle problems again and hope reach a good ranking some of the competitions.
Anyway, if you want to learn machine learning, this is the best books I’ve ever seen as your first book.
Thanks