Reference books on machine learning with R
In the previous article, I gave a brief overview of machine learning. In this article, I would like to discuss specific examples of “machine learning as a toolbox”. One of the options for these approaches is to use the R language and its libraries.
The R language is a programming language and development environment for statistical analysis, and is a relatively old tool created in 1993 by the University of Auckland, New Zealand. R is a relatively old tool created in 1993 by the University of Auckland, New Zealand. Its features include simple and fast handling of vectors, matrices, etc., which makes it easy to construct mathematical processing algorithms and fast processing. Also, since the main purpose of the software is to perform calculations, relatively simple programming is possible. Because of these features, it is used by research institutes all over the world, and a large number of libraries (packages) have been created and released, with 17029 packages registered as of 2021/02/01. The number of libraries is less than half that of Python, but considering that it is a language specialized for statistical analysis, I think it is safe to say that there is a sufficient amount.
A number of reference books have been published. Japanese books include “Machine Learning with R,” translated from Brett Lantz’s book, and “Minna no R: A New Textbook for Data Analysis and Statistical Analysis,” translated from Jared P. Lander’s book. In foreign books, I have translated “R In a nutshell second edition” by O’Reilly, “Statistical Analysis with R Beginner’s Guide” and “Big Data Analytics with R and Hadoop” by Packet. An Introduction to Statistical Learning:with Applications in R” by Springer, and others.
The table of contents for “Machine Learning with R” is as follows:
Chapter 1: Introduction to Machine Learning,
Chapter 2: Managing and Understanding Data,
Chapter 3: Lazy Learning – Classification Using Nearest Neighbor Methods,
Chapter 4: Probabilistic Learning – Classification Using Simple Bayes,
Chapter 5: Divide-and-Conquer – Classification Using Decision Trees and Classification Rules,
Chapter 6: Predicting Numerical Data – Regression Methods,
Chapter 7: Black Box methods – neural networks and support vector machines,
Chapter 8: Detecting patterns – shopping cart analysis using correlation rules,
Chapter 9: Detecting groups of data – clustering using the k-means method,
Chapter 10: Evaluating model performance,
Chapter 11: Improving model performance, and
Chapter 12: Specialized topics in machine learning.
As you can see from the contents of the table of contents, there is a lot to learn. As you can see from the contents of the table of contents, the book focuses on examples for specific tasks, making it an ideal textbook to use first.
In “Everybody’s R: A New Textbook for Data Analysis and Statistical Analysis,” you’ll find
Chapter 1: Getting R,
Chapter 2: The R Environment,
Chapter 3: R Packages,
Chapter 4: R Basics,
Chapter 5: Advanced Data Structures,
Chapter 6: Getting Data into R,
Chapter 7: Statistical Graphs,
Chapter 8: Writing R Functions,
Chapter 9: Control Statements,
Chapter 10: Loops. Methods,
Chapter 11: Grouping Operations,
Chapter 12: Data Formatting,
Chapter 13: String Manipulation,
Chapter 14: Probability Distributions,
Chapter 15: Basic Statistics,
Chapter 16: Linear Models,
Chapter 17: Generalized Linear Models,
Chapter 18: Model Evaluation,
Chapter 19: Regularization and Reduction (Shrinkage),
Chapter 20: Nonlinear Models,
Chapter 21: Time Series and Autocorrelation,
Chapter 22: Clustering
Chapter 21: Time Series and Autocorrelation,
Chapter 22: Clustering,
Chapter 23: Reproducibility with the knitr Package Report and Slide Show, and
Chapter 24: Building the R Package.
Compared to “Machine Learning with R”, this book is more like a dictionary of R. I think it is a good reference book to read after you are able to use R to some extent.
In this article, I introduced the outline of R. In the next article, I will introduce the actual code. In the next article, I would like to introduce the actual code.
コメント