We are very proud to present our book Practical Data Science with R 2nd Edition. This is the book for you if you are a data scientist, want to be a data scientist, or want to work with data scientists. This is a good “what next” book for analysts and programmers wanting to know more about machine learning and data wrangling.
Our goal is to present data science from a pragmatic, practice-oriented viewpoint. The book will complement other analytics, statistics, machine learning, data science and R books with the following features:
- This book teaches you how to work as a data scientist. Learn how important listening, collaboration, honest presentation, and iteration are to what we do.
- The key emphasis of the book is process: collecting requirements, loading data, examining data, building models, validating models, documenting and deploying models to production.
- We provide over 10 significant example datasets, and demonstrate the concepts that we discuss with fully worked exercises using standard R methods. We feel that this approach allows us to illustrate what we really want to teach and to demonstrate all the preparatory steps necessary to any real-world project. Every result and almost every graph in the book is given as a fully worked example.
- This book is careful with statistics, but presents topics in the context and order a practitioner worries about them. For example we emphasize construction of predictive models and model evaluation and prediction over the more standard topics of summary statistics and packaged procedures (such as ANOVA).
In support of Practical Data Science with R 2nd Edition we are providing:
- Table of contents, and a free example chapter available from the Manning book page .
- A public repository of data sets (under a Creative Commons Attribution-NonCommercial 3.0 Unported License where possible).
- Downloadable example code.
Please order now on the Manning book page.
Some of the features new to the 2nd edition include:
- A chapter on advanced data preparation using the vtreat package.
- Regularization methods.
- Model explainability.
- More on data manipulation and data wrangling.
- Using xgboost / gradient boosting.
For more about the book please check out:
Also, Win-Vector LLC is available to help with your data science projects or training. We would love to work with you.