main.tex

\documentclass[twoside,a5paper,10pt,openright]{memoir}
% \setstocksize{230mm}{160mm}
\setlrmarginsandblock{23mm}{20mm}{*}
\setulmarginsandblock{20mm}{20mm}{*}
\checkandfixthelayout

\usepackage[utf8]{inputenc}
\usepackage[english]{babel}
\usepackage[style=authoryear,maxbibnames=99,giveninits=true,backref=true]{biblatex}
\addbibresource{references.bib}

\usepackage{amsmath}
\usepackage{mathtools}
\usepackage{blkarray}
\usepackage[colorlinks]{hyperref}
\usepackage{fontspec}
\usepackage{xltxtra}
\usepackage{sourcesanspro}
\usepackage{unicode-math}
\usepackage{graphicx}
\usepackage[super]{nth}
\usepackage{booktabs}
\usepackage{csquotes}
\usepackage{multirow}
\usepackage[table]{xcolor}
\usepackage{titletoc}
\usepackage[noend,noline,linesnumbered]{algorithm2e}
\usepackage[automake]{glossaries-extra}
\usepackage{orcidlink}
\usepackage{fontawesome5}
\usepackage{nicefrac}
\usepackage{cancel}

\DeclareMathOperator*{\argmax}{arg\,max}
\DeclareMathOperator*{\argmin}{arg\,min}
\DeclareMathOperator{\Prob}{P}
\DeclareMathOperator{\E}{E}
\DeclareMathOperator{\Var}{Var}
\DeclareMathOperator{\sign}{sign}

\usepackage[Bjornstrup]{fncychap} % must come before cleveref to avoid break appendix name
\usepackage{cleveref}
\newcommand\pcref[1]{(\cref{#1})}

\usepackage{tikz}
\usetikzlibrary{shapes, arrows.meta, positioning, shapes.geometric}
\usetikzlibrary{fit}
\usetikzlibrary {datavisualization.formats.functions}
\usepackage{pgfplots}
\makeatletter
\newcommand{\gnuplotResult}{}
\newcommand*{\gnuplotInvnorm}[2][\jobname.gnuplot]{%
  \immediate\write18{gnuplot -e "set print '#1'; print invnorm(#2)"}%
  \IfFileExists{#1}{%
    \renewcommand{\gnuplotResult}{\input{#1}}%
  }{%
    \PackageError{gnuplotInvnorm}{File `#1' not found}{%
      The file `#1' could not be found. Maybe you need to enable \write18.%
    }%
  }%
}%
\newcommand*{\gnuplotNorm}[2][\jobname.gnuplot]{%
  \immediate\write18{gnuplot -e "set print '#1'; print norm(#2)"}%
  \IfFileExists{#1}{%
    \renewcommand{\gnuplotResult}{\input{#1}}%
  }{%
    \PackageError{gnuplotNorm}{File `#1' not found}{%
      The file `#1' could not be found. Maybe you need to enable \write18.%
    }%
  }%
}%
\def\pgfdvmathinvnorm#1#2{%
  % Remove prefix "1Y" and suffix "]" in #2
  \gnuplotInvnorm{#2}%
  \let#1=\gnuplotResult%
}%
\makeatother

\tikzset{%
  decision/.style={draw, diamond, text centered, minimum height=0.5cm, minimum width=1cm},
  block/.style={rectangle, draw, text width=6em, text centered, rounded corners, minimum height=3em},
  mediumblock/.style={rectangle, draw, text width=3em, text centered, rounded corners, minimum height=2em},
  darkblock/.style={block, fill=gray, text=white},
  smallblock/.style={rectangle, rounded corners, draw, font=\tiny, minimum height=1em, inner sep=2pt},
  smalldarkblock/.style={smallblock, fill=gray, text=white},
  darkcircle/.style={draw, circle, fill=gray, text centered, text=white},
  smallcircle/.style={draw, circle, text centered, font=\tiny},
  smalldarkcircle/.style={smallcircle, fill=gray, text=white},
  line/.style={draw, -latex},
  dline/.style={draw, latex-latex},
  bigarrow/.style={draw, -latex, line width=3pt, gray}}

\usepackage{titling}
\usepackage[most]{tcolorbox}
\usepackage{xhfill}

\usepackage{qrcode}
\newcommand{\linkwithqr}[1]{%
  \begin{minipage}{0.8\textwidth}
    \url{#1}
  \end{minipage}
  \hfill
  \begin{minipage}{0.15\textwidth}
    \qrcode[height=\textwidth]{#1}
  \end{minipage}
}

\newcommand{\aurl}{google.com}
\newenvironment{parwithqr}[1]{%
  \renewcommand\aurl{#1}%
  \noindent%
  \begin{minipage}{0.75\textwidth}%
}{%
  \end{minipage}%
  \hfill%
  \begin{minipage}{0.20\textwidth}%
    \qrcode[height=\textwidth]{\aurl}%
  \end{minipage}%
}
\newenvironment{lparwithqr}[1]{%
  \renewcommand\aurl{#1}%
  \noindent%
  \begin{minipage}{0.20\textwidth}%
    \qrcode[height=\textwidth]{\aurl}%
  \end{minipage}%
  \hfill%
  \begin{minipage}{0.75\textwidth}%
}{%
  \end{minipage}%
}

\nonfrenchspacing

\setsecnumdepth{subsection}
\maxtocdepth{subsection}

\babelhyphenation[english]{par-a-digm}

\newtcolorbox[auto counter, number within=chapter, crefname={algorithm}{algorithms}]{algobox}[2][]{%
  float=thbp, base={Algorithm \thetcbcounter: #2},
  colframe=black!20!white, #1,
  before upper={\begin{algorithm}[H]},
  after upper={\end{algorithm}}}

\input{glossary}

\begin{document}

\setmathfont{STIXTwoMath}[
  Extension={.otf},
  Path={./fonts/},
  Scale=1]

\setmainfont{STIXTwoText}[
  Extension={.otf},
  Path={./fonts/},
  UprightFont={*-Regular},
  BoldFont={*-Bold},
  ItalicFont={*-Italic},
  BoldItalicFont={*-BoldItalic}]

\setmonofont{CourierPrime}[
  Extension={.ttf},
  Path={./fonts/},
  UprightFont={*-Regular},
  BoldFont={*-Bold},
  ItalicFont={*-Italic},
  BoldItalicFont={*-BoldItalic},
  Scale=0.9]

\newcommand{\code}[1]{\colorbox{black!10!white}{\texttt{#1}}}

%\setsansfont{SourceSansPro}

\urlstyle{rm}

\tcbset {
  base/.style={
    arc=0mm,
    bottomtitle=0.5mm,
    boxrule=0mm,
    colbacktitle=black!20!white,
    coltitle=black,
    left=2.5mm,
    leftrule=1mm,
    right=3.5mm,
    title={#1},
    toptitle=0.75mm,
    lower separated=false,
  }
}

\newtcbtheorem[auto counter, number within=chapter]{defbox}{Definition}{
  float=h!,
  colframe=black!20!white,
  description delimiters parenthesis,
  label type=definition,
  base
}{def}

\newtcolorbox{mainbox}[1]{
  float=ht,
  spread outwards=-2mm,
  spread inwards=-2mm,
  %spread downwards,
  colframe=black!20!white,
  fonttitle=\bfseries,
  base={#1},
  left=16mm,
  right=19mm,
}

\newtcolorbox{hlbox}[1]{
  float=h,
  colframe=black!20!white,
  fonttitle=\bfseries,
  base={#1},
}

\newtcolorbox[blend into=figures]{figurebox}[2][]{%
  float=thbp, base={#2},
  colframe=black!20!white,
  every float=\centering, #1}

\newtcolorbox[blend into=tables]{tablebox}[2][]{%
  float=thbp, base={#2},
  colframe=black!20!white,
  every float=\centering, #1}

\newcommand\boxsubtitle[1]{%
  \vspace{0.5em}
  \noindent\xrfill[0.5ex]{1pt}[black!20]\phantom{x}\textbf{#1}\phantom{x}\xrfill[0.5ex]{1pt}[black!20]%
  \vspace{0.5em}
}

\renewcommand{\vec}[1]{\mathbf{#1}}

\title{Data science project: an inductive learning approach}
\author{Filipe A. N. Verri}

\hypersetup{%
  pdftitle={\thetitle},
  pdfsubject={Data science},
  pdfauthor={\theauthor},
  pdfkeywords={data science, statistics, machine learning, databases},
  urlcolor=black!60,
  linkcolor=black,
  citecolor=black,}

\begin{titlingpage}
  \begin{tikzpicture}[remember picture, overlay]
    \fill[black!80] (current page.south west) rectangle (current page.north east);
    \node[anchor=south east, inner sep=0mm] at (current page.south east) {%
      \reflectbox{\includegraphics[width=\paperwidth]{images/bard2.jpg}}%
    };
    \node[white,anchor=north, yshift=-25mm](title) at (current page.north) {\HUGE\sffamily\uppercase{Data science project}};
    \node[white,anchor=north, inner sep=5mm] at (title.south) {\LARGE\sffamily\uppercase{an inductive learning approach}};
    \node[anchor=south west, inner sep=11mm] at (current page.south west) {\HUGE\sffamily\uppercase{F.A.N. Verri}};
  \end{tikzpicture}
\end{titlingpage}

\newpage
\clearpage
\newpage
\frontmatter
\thispagestyle{empty}
\begin{tikzpicture}[remember picture, overlay]
  \node[anchor=south east, inner sep=8mm] at (current page.south east) {%
    \reflectbox{\includegraphics[height=0.3\paperheight]{images/toucan_bw.png}}%
  };
  \node[anchor=south west, inner sep=10mm] at (current page.south west)
    {\large\sffamily Version 0.1 ``\textit{Audacious Hatchling}''};
    % {\large\sffamily Version 1.0 ``\textit{Tropical Toucan}''};
  \node[anchor=south east, inner sep=10mm] at (current page.south east) {\large\sffamily\today};
  \node[anchor=north, yshift=-25mm](title) at (current page.north) {\HUGE\sffamily\uppercase{Data science project}};
  \node[anchor=north, inner sep=5mm](subtitle) at (title.south) {\LARGE\sffamily\uppercase{an inductive learning approach}};
  \node[anchor=north, inner sep=5mm] at (subtitle.south) {\Large\sffamily\uppercase{Filipe A. N. Verri}};
\end{tikzpicture}

\newpage
\mbox{}
\vfill

{
  \footnotesize\noindent\color{red}
  \textbf{Disclaimer:} This version is a work in progress.  Proofreading and professional editing are
  still pending.
}

\vspace{0.5cm}
{
\footnotesize\noindent
The book is typeset with \XeTeX{} using the Memoir class.  All figures are
original and created with Ti\textit{k}Z.  Proudly written in
\href{https://neovim.io/}{Neovim} with the assistance of
\href{https://github.com/features/copilot}{GitHub Copilot}.
Book cover image was created with the assistance of
\href{https://gemini.google.com}{Gemini} and \href{https://openai.com/dall-e-2}{DALL·E 2}.
We use the beautiful \href{https://www.stixfonts.org/}{STIX fonts} for text and math.
Some icons are from \href{https://fontawesome.com/}{Font Awesome 5} by Dave Gandy.
}

\vspace{0.5cm}
{
\footnotesize\noindent
Scripture quotations are from The ESV® Bible (The Holy Bible, English Standard Version®),
copyright © 2001 by Crossway, a publishing ministry of Good News Publishers. Used by
permission. All rights reserved.
}

\vspace{0.5cm}
{
\footnotesize\noindent
\thetitle{} © 2023--\the\year{} by \theauthor{}~\orcidlink{0000-0002-8240-5129} is licensed under
Attribution-NonCommercial-NoDerivatives 4.0 International. To view a copy of this license,
visit
\href{http://creativecommons.org/licenses/by-nc-nd/4.0/}{creativecommons.org/licenses/by-nc-nd/4.0}.
}

\thispagestyle{empty}
\newpage

\thispagestyle{empty}

% Dedication page
\begin{center}
  \vspace{0.2\textheight}
  \itshape
  To my wife, for inspiring and supporting me to write this book.

  \vfill
  \raggedleft Above all, God be praised.
\end{center}

\newpage

\thispagestyle{empty}
\phantom{foo}
\newpage

\tableofcontents
\thispagestyle{empty}

\input{foreword}
\input{about}
% \input{courses}

\mainmatter
\input{history}
\input{data}
\input{project}
\input{structured}
\input{handling}
% \input{exploratory} TODO
\input{inductive}
\input{preprocess}
\input{planning}
% \input{ethics} TODO

\renewcommand{\theHchapter}{A\arabic{chapter}} % workaround for hyperref
\appendix
\input{preliminaries}
\input{machines}

\backmatter
\printbibliography
\printglossary

\end{document}