Machine Learning with R. Second Edition. by Brett Lantz. Published by Packt
This book is perfect for newbies. I really enjoyed reading it. It covers all the basic Algorithms. None of them in real depth, but it provides an easy-reading map of the several points in the machine learning world. In its guts, we can find the following chapters,
- Chapter 1: Introducing of Machine Learning
- Chapter 2: Managing and Understanding Data
- Chapter 3: Lazy Learning - Classification Using Nearest Neighbors
- Chapter 4: Probabilistic Learning Classification
- Chapter 5: Divide and Conquer - Classification using Decision Tree and Rules
- Chapter 6: Forecasting Numeric Data - Regression Methods
- Chapter 7: Black Box Methods - Neural Networks and Support Vector Machines
- Chapter 8: Finding Patterns - Market Basket Analysis Using Association Rules
- Chapter 9: Finding Groups of Data - Clustering with k-means
- Chapter 10: Evaluating Model Performance
- Chapter 11: Improving Model Performance
- Chapter 12: Specialized Machine Learning Topics
I really recommend this book to start gaining knowledge of the different concepts. The explanations are done in a plain language and go very straight to the point. So, it is not difficult to follow for someone starting in data science/Analysis.
All the theoretical points are explained following a test case as an example. The test cases are coded with R, so you can start to familiarise with some of the most important packages.
One thing that I really liked is the structures explanation of each one of the algorithms. For each chapter, the author explains first, the basic structure of each algorithm, considering some basic maths or statistics, if needed. To that, follows the strengths and weaknesses and there is a very nice and useful table that sums up the package and R coding that later is developed.
Regarding the test cases or examples, though are used to start your friendship with R, are so ready prepared that can give a bad assumption that machine learning processes are easy to code.
But at my point of knowledge, I already have found and suffered, some not easy data pre-processes. Considering that it is said that 80% of the work of a data scientist is preparing the data for building the model, this book fails in pointing out that part. Even because that last fact, I do really recommend this book. My punctuation is 7 out of 10.
Wanna buy it? Here you can (that is not an affiliate marketing link)