A Minimal Book Example

Grégoire Virepinte
2018-07-24
2
Contents

Introduction 5
Why this book? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Why write this in English? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
What to find here? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5

1 Prerequisites 7

2 Model Selection 9
2.1 The Bias-Variance Trade-Off . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.2 Cross-validation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.3 The use of information criteria . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.4 Bootstrap . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.5 ROC Curve . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9

3 Regression 11
3.1 Linear regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.2 Logistic regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.3 Polynomial regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.4 Constraints: Ridge, Lasso, Elastic Net . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.5 Non-linear regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.6 Random and fixed effects . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11

4 Missing values 13

5 Gradient boosting 15
5.1 Fundamental idea . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
5.2 Basic algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
5.3 An implementation of XGBoost . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

6 Random Forest 17
6.1 Idea . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
6.2 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17

3
4 CONTENTS
Introduction

Why this book?

The basic aim of this book is to collect a few revision cards about Machine Learning. Those are mainly
things that I have learned during the past year and forgotten not long after, which really is a shame.

Why write this in English?

There a few reasons for that:
• I could potentially publish this in the future, one day, which means that I might as well write it in
English from the very beginning,
• I have been burned enough times with UTF-8-incompatible encoding (accents missing, that sort of
thing), and I don’t want that to happen again.
• Most of the Machine Learning vocabulary seems to be in English anyway, and I don’t want to have to
resort to Frenglish.
• Because I can.

What to find here?

This should be the basic idea of the book:
• A succint mathematical description of the concepts mentionned in the book,
• A special emphasis on the conditions of application if I can find some, because I always seem to have
problems with those,
• An example in R with the proper code and libraries.

5
6 CONTENTS
Chapter 1

Prerequisites

This is a sample book written in Markdown. You can use anything that Pandoc’s Markdown supports,
e.g., a math equation a2 + b2 = c2 .
The bookdown package can be installed from CRAN or Github:
install.packages("bookdown")
# or the development version
# devtools::install_github("rstudio/bookdown")

Remember each Rmd file contains one and only one chapter, and a chapter is defined by the first-level
heading #.
To compile this example to PDF, you need XeLaTeX. You are recommended to install TinyTeX (which
includes XeLaTeX): https://yihui.name/tinytex/.

7
8 CHAPTER 1. PREREQUISITES
Chapter 2

Model Selection

2.1 The Bias-Variance Trade-Off

2.2 Cross-validation

2.3 The use of information criteria

2.4 Bootstrap

2.5 ROC Curve

You can label chapter and section titles using {#label} after them, e.g., we can reference Chapter ??. If
you do not manually label them, there will be automatic labels anyway, e.g., Chapter ??.
Figures and tables with captions will be placed in figure and table environments, respectively.
par(mar = c(4, 4, .1, .1))
plot(pressure, type = 'b', pch = 19)

Reference a figure by its code chunk label with the fig: prefix, e.g., see Figure 2.1. Similarly, you can
reference tables generated from knitr::kable(), e.g., see Table 2.1.
knitr::kable(
head(iris, 20), caption = 'Here is a nice table!',
booktabs = TRUE
)

You can write citations, too. For example, we are using the bookdown package (Xie, 2018) in this sample
book, which was built on top of R Markdown and knitr (Xie, 2015).

9
10 CHAPTER 2. MODEL SELECTION

800
600
pressure

400
200
0

0 50 100 150 200 250 300 350

temperature

Figure 2.1: Here is a nice figure!

Table 2.1: Here is a nice table!

Sepal.Length Sepal.Width Petal.Length Petal.Width Species

5.1 3.5 1.4 0.2 setosa
4.9 3.0 1.4 0.2 setosa
4.7 3.2 1.3 0.2 setosa
4.6 3.1 1.5 0.2 setosa
5.0 3.6 1.4 0.2 setosa
5.4 3.9 1.7 0.4 setosa
4.6 3.4 1.4 0.3 setosa
5.0 3.4 1.5 0.2 setosa
4.4 2.9 1.4 0.2 setosa
4.9 3.1 1.5 0.1 setosa
5.4 3.7 1.5 0.2 setosa
4.8 3.4 1.6 0.2 setosa
4.8 3.0 1.4 0.1 setosa
4.3 3.0 1.1 0.1 setosa
5.8 4.0 1.2 0.2 setosa
5.7 4.4 1.5 0.4 setosa
5.4 3.9 1.3 0.4 setosa
5.1 3.5 1.4 0.3 setosa
5.7 3.8 1.7 0.3 setosa
5.1 3.8 1.5 0.3 setosa
Chapter 3

Regression

3.1 Linear regression

3.2 Logistic regression

3.3 Polynomial regression

3.4 Constraints: Ridge, Lasso, Elastic Net

3.5 Non-linear regression

3.6 Random and fixed effects

11
12 CHAPTER 3. REGRESSION
Chapter 4

Missing values

13
14 CHAPTER 4. MISSING VALUES
Chapter 5

Gradient boosting

5.1 Fundamental idea

5.2 Basic algorithm

5.3 An implementation of XGBoost

15
16 CHAPTER 5. GRADIENT BOOSTING
Chapter 6

Random Forest

6.1 Idea

6.2 Implementation

17
18 CHAPTER 6. RANDOM FOREST
Bibliography

Xie, Y. (2015). Dynamic Documents with R and knitr. Chapman and Hall/CRC, Boca Raton, Florida, 2nd
edition. ISBN 978-1498716963.
Xie, Y. (2018). bookdown: Authoring Books and Technical Documents with R Markdown. R package version
0.7.

19