galaaz 0.4.10 → 2.0.0

data/blogs/gknit/gknit.tex

@@ -1,1358 +0,0 @@
-\documentclass[]{article}
-\usepackage{lmodern}
-\usepackage{amssymb,amsmath}
-\usepackage{ifxetex,ifluatex}
-\usepackage{fixltx2e} % provides \textsubscript
-\ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex
-  \usepackage[T1]{fontenc}
-  \usepackage[utf8]{inputenc}
-\else % if luatex or xelatex
-  \ifxetex
-    \usepackage{mathspec}
-  \else
-    \usepackage{fontspec}
-  \fi
-  \defaultfontfeatures{Ligatures=TeX,Scale=MatchLowercase}
-\fi
-% use upquote if available, for straight quotes in verbatim environments
-\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
-% use microtype if available
-\IfFileExists{microtype.sty}{%
-\usepackage{microtype}
-\UseMicrotypeSet[protrusion]{basicmath} % disable protrusion for tt fonts
-}{}
-\usepackage[margin=1in]{geometry}
-\usepackage{hyperref}
-\hypersetup{unicode=true,
-            pdftitle={How to do reproducible research in Ruby with gKnit},
-            pdfauthor={Rodrigo Botafogo; Daniel Mossé - University of Pittsburgh},
-            pdfborder={0 0 0},
-            breaklinks=true}
-\urlstyle{same}  % don't use monospace font for urls
-\usepackage{color}
-\usepackage{fancyvrb}
-\newcommand{\VerbBar}{|}
-\newcommand{\VERB}{\Verb[commandchars=\\\{\}]}
-\DefineVerbatimEnvironment{Highlighting}{Verbatim}{commandchars=\\\{\}}
-% Add ',fontsize=\small' for more characters per line
-\usepackage{framed}
-\definecolor{shadecolor}{RGB}{248,248,248}
-\newenvironment{Shaded}{\begin{snugshade}}{\end{snugshade}}
-\newcommand{\AlertTok}[1]{\textcolor[rgb]{0.94,0.16,0.16}{#1}}
-\newcommand{\AnnotationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
-\newcommand{\AttributeTok}[1]{\textcolor[rgb]{0.77,0.63,0.00}{#1}}
-\newcommand{\BaseNTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
-\newcommand{\BuiltInTok}[1]{#1}
-\newcommand{\CharTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
-\newcommand{\CommentTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textit{#1}}}
-\newcommand{\CommentVarTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
-\newcommand{\ConstantTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
-\newcommand{\ControlFlowTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{\textbf{#1}}}
-\newcommand{\DataTypeTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{#1}}
-\newcommand{\DecValTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
-\newcommand{\DocumentationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
-\newcommand{\ErrorTok}[1]{\textcolor[rgb]{0.64,0.00,0.00}{\textbf{#1}}}
-\newcommand{\ExtensionTok}[1]{#1}
-\newcommand{\FloatTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
-\newcommand{\FunctionTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
-\newcommand{\ImportTok}[1]{#1}
-\newcommand{\InformationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
-\newcommand{\KeywordTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{\textbf{#1}}}
-\newcommand{\NormalTok}[1]{#1}
-\newcommand{\OperatorTok}[1]{\textcolor[rgb]{0.81,0.36,0.00}{\textbf{#1}}}
-\newcommand{\OtherTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{#1}}
-\newcommand{\PreprocessorTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textit{#1}}}
-\newcommand{\RegionMarkerTok}[1]{#1}
-\newcommand{\SpecialCharTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
-\newcommand{\SpecialStringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
-\newcommand{\StringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
-\newcommand{\VariableTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
-\newcommand{\VerbatimStringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
-\newcommand{\WarningTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
-\usepackage{graphicx,grffile}
-\makeatletter
-\def\maxwidth{\ifdim\Gin@nat@width>\linewidth\linewidth\else\Gin@nat@width\fi}
-\def\maxheight{\ifdim\Gin@nat@height>\textheight\textheight\else\Gin@nat@height\fi}
-\makeatother
-% Scale images if necessary, so that they will not overflow the page
-% margins by default, and it is still possible to overwrite the defaults
-% using explicit options in \includegraphics[width, height, ...]{}
-\setkeys{Gin}{width=\maxwidth,height=\maxheight,keepaspectratio}
-\IfFileExists{parskip.sty}{%
-\usepackage{parskip}
-}{% else
-\setlength{\parindent}{0pt}
-\setlength{\parskip}{6pt plus 2pt minus 1pt}
-}
-\setlength{\emergencystretch}{3em}  % prevent overfull lines
-\providecommand{\tightlist}{%
-  \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}}
-\setcounter{secnumdepth}{5}
-% Redefines (sub)paragraphs to behave more like sections
-\ifx\paragraph\undefined\else
-\let\oldparagraph\paragraph
-\renewcommand{\paragraph}[1]{\oldparagraph{#1}\mbox{}}
-\fi
-\ifx\subparagraph\undefined\else
-\let\oldsubparagraph\subparagraph
-\renewcommand{\subparagraph}[1]{\oldsubparagraph{#1}\mbox{}}
-\fi
-
-%%% Use protect on footnotes to avoid problems with footnotes in titles
-\let\rmarkdownfootnote\footnote%
-\def\footnote{\protect\rmarkdownfootnote}
-
-%%% Change title format to be more compact
-\usepackage{titling}
-
-% Create subtitle command for use in maketitle
-\newcommand{\subtitle}[1]{
-  \posttitle{
-    \begin{center}\large#1\end{center}
-    }
-}
-
-\setlength{\droptitle}{-2em}
-
-  \title{How to do reproducible research in Ruby with gKnit}
-    \pretitle{\vspace{\droptitle}\centering\huge}
-  \posttitle{\par}
-    \author{Rodrigo Botafogo \\ Daniel Mossé - University of Pittsburgh}
-    \preauthor{\centering\large\emph}
-  \postauthor{\par}
-      \predate{\centering\large\emph}
-  \postdate{\par}
-    \date{29/04/2019}
-
-% usar portugues do Brasil
-% \usepackage[brazilian]{babel}
-\usepackage[utf8]{inputenc}
-
-\usepackage{geometry}
-\geometry{a4paper, top=1in}
-
-% needed for kableExtra
-\usepackage{longtable}
-\usepackage{multirow}
-\usepackage[table]{xcolor}
-\usepackage{wrapfig}
-\usepackage{float}
-\usepackage{colortbl}
-\usepackage{pdflscape}
-\usepackage{tabu}
-\usepackage{threeparttable}
-\usepackage[normalem]{ulem}
-
-\usepackage{bbm}
-\usepackage{booktabs}
-\usepackage{expex}
-
-\usepackage{graphicx}
-
-\usepackage{fancyhdr}
-% set the header and foot style
-% style 'fancy' adds the section name on the header
-% and the page number on the footer
-\pagestyle{fancy}
-
-% style 'fancyhf' leaves header and footer empty
-%\fancyhf{}
-
-% sets the left head element to \rightmark, which contains the
-% current section (\leftmark is the current chapter)
-%\fancyhead[L]{\rightmark} .
-
-% sets the right head element to the page number.
-% \fancyhead[R]{\thepage}
-
-% lets the head rule disappear.
-% \renewcommand{\headrulewidth}{0pt}
-% Possible selectors for the optional argument of \fancyhead/\fancyfoot
-% are L (left), C (center) or R (right) for the position of the element
-% and E (even) or O (odd) to distinguish even and odd pages. If you omit
-% E/O the element is set for all pages.
-
-% \usepackage{lipsum}
-
-% make available command lastpage
-\usepackage{lastpage}
-
-% default fontsize 11pt better to add
-% fontsize on the yaml header
-% \usepackage[fontsize=11pt]{scrextend}
-
-% comandos para formatar uma tabela
-\usepackage{array}
-\newcolumntype{L}[1]{>{\raggedright\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
-\newcolumntype{C}[1]{>{\centering\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
-\newcolumntype{R}[1]{>{\raggedleft\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
-
-% necessário if we need to import other latex documents
-\usepackage{import}
-
-% Command to import an R variable to latex
-\newcommand{\RtoLatex}[2]{\newcommand{#1}{#2}}
-
-% 
-%\newcommand{\atraso}[1]{\color{red} \textbf {Tempo desde a Assinatura do Contrato: #1 dias}}
-\usepackage{booktabs}
-\usepackage{longtable}
-\usepackage{array}
-\usepackage{multirow}
-\usepackage{wrapfig}
-\usepackage{float}
-\usepackage{colortbl}
-\usepackage{pdflscape}
-\usepackage{tabu}
-\usepackage{threeparttable}
-\usepackage{threeparttablex}
-\usepackage[normalem]{ulem}
-\usepackage{makecell}
-\usepackage{xcolor}
-
-\begin{document}
-\maketitle
-
-\hypertarget{introduction}{%
-\section{Introduction}\label{introduction}}
-
-The idea of ``literate programming'' was first introduced by Donald
-Knuth in the 1980's (Knuth 1984). The main intention of this approach
-was to develop software interspersing macro snippets, traditional source
-code, and a natural language such as English in a document that could be
-compiled into executable code and at the same time easily read by a
-human developer. According to Knuth ``The practitioner of literate
-programming can be regarded as an essayist, whose main concern is with
-exposition and excellence of style.''
-
-The idea of literate programming evolved into the idea of reproducible
-research, in which all the data, software code, documentation, graphics
-etc. needed to reproduce the research and its reports could be included
-in a single document or set of documents that when distributed to peers
-could be rerun generating the same output and reports.
-
-The R community has put a great deal of effort in reproducible research.
-In 2002, Sweave was introduced and it allowed mixing R code with Latex
-generating high quality PDF documents. A Sweave document could include
-code, the results of executing the code, graphics and text such that it
-contained the whole narrative to reproduce the research. In 2012, Knitr,
-developed by Yihui Xie from RStudio was released to replace Sweave and
-to consolidate in one single package the many extensions and add-on
-packages that were necessary for Sweave.
-
-With Knitr, \textbf{R markdown} was also developed, an extension to the
-Markdown format. With \textbf{R markdown} and Knitr it is possible to
-generate reports in a multitude of formats such as HTML, markdown,
-Latex, PDF, dvi, etc. \textbf{R markdown} also allows the use of
-multiple programming languages such as R, Ruby, Python, etc. in the same
-document.
-
-In \textbf{R markdown}, text is interspersed with code chunks that can
-be executed and both the code and its results can become part of the
-final report. Although \textbf{R markdown} allows multiple programming
-languages in the same document, only R and Python (with the reticulate
-package) can persist variables between chunks. For other languages, such
-as Ruby, every chunk will start a new process and thus all data is lost
-between chunks, unless it is somehow stored in a data file that is read
-by the next chunk.
-
-Being able to persist data between chunks is critical for literate
-programming otherwise the flow of the narrative is lost by all the
-effort of having to save data and then reload it. Although this might,
-at first, seem like a small nuisance, not being able to persist data
-between chunks is a major issue. For example, let's take a look at the
-following simple example in which we want to show how to create a list
-and the use it. Let's first assume that data cannot be persisted between
-chunks. In the next chunk we create a list, then we would need to save
-it to file, but to save it, we need somehow to marshal the data into a
-binary format:
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{lst = R.list(}\StringTok{a: }\DecValTok{1}\NormalTok{, }\StringTok{b: }\DecValTok{2}\NormalTok{, }\StringTok{c: }\DecValTok{3}\NormalTok{)}
-\NormalTok{lst.saveRDS(}\StringTok{"lst.rds"}\NormalTok{)}
-\end{Highlighting}
-\end{Shaded}
-
-then, on the next chunk, where variable `lst' is used, we need to read
-back it's value
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{lst = R.readRDS(}\StringTok{"lst.rds"}\NormalTok{)}
-\NormalTok{puts lst}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-## $a
-## [1] 1
-## 
-## $b
-## [1] 2
-## 
-## $c
-## [1] 3
-\end{verbatim}
-
-Now, any single code has dozens of variables that we might want to use
-and reuse between chunks. Clearly, such an approach becomes quickly
-unmanageable. Probably, because of this problem, it is very rare to see
-any \textbf{R markdown} document in the Ruby community.
-
-When variables can be used accross chunks, then no overhead is needed:
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{lst = R.list(}\StringTok{a: }\DecValTok{1}\NormalTok{, }\StringTok{b: }\DecValTok{2}\NormalTok{, }\StringTok{c: }\DecValTok{3}\NormalTok{)}
-\CommentTok{# any other code can be added here}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{puts lst}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-## $a
-## [1] 1
-## 
-## $b
-## [1] 2
-## 
-## $c
-## [1] 3
-\end{verbatim}
-
-In the Python community, the same effort to have code and text in an
-integrated environment started around the first decade of 2000. In 2006
-iPython 0.7.2 was released. In 2014, Fernando Pérez, spun off project
-Jupyter from iPython creating a web-based interactive computation
-environment. Jupyter can now be used with many languages, including Ruby
-with the iruby gem (\url{https://github.com/SciRuby/iruby}). In order to
-have multiple languages in a Jupyter notebook the SoS kernel was
-developed (\url{https://vatlab.github.io/sos-docs/}).
-
-\hypertarget{gknitting-a-document}{%
-\section{gKnitting a Document}\label{gknitting-a-document}}
-
-This document describes gKnit. gKnit is based on knitr and \textbf{R
-markdown} and can knit a document written both in Ruby and/or R and
-output it in any of the available formats of \textbf{R markdown}. gKnit
-allows ruby developers to do literate programming and reproducible
-research by allowing them to have in a single document, text and code.
-
-gKnit runs atop of GraalVM, and Galaaz (an integration library between
-Ruby and R - see bellow). In gKnit, Ruby variables are persisted between
-chunks, making it an ideal solution for literate programming in this
-language. Also, since it is based on Galaaz, Ruby chunks can have access
-to R variables and Polyglot Programming with Ruby and R is quite
-natural.
-
-Galaaz has already been describe in the following posts:
-
-\begin{itemize}
-\tightlist
-\item
-  \url{https://towardsdatascience.com/ruby-plotting-with-galaaz-an-example-of-tightly-coupling-ruby-and-r-in-graalvm-520b69e21021}.\\
-\item
-  \url{https://medium.freecodecamp.org/how-to-make-beautiful-ruby-plots-with-galaaz-320848058857}
-\end{itemize}
-
-This is not a blog post on \textbf{R markdown}, and the interested user
-is directed to the following links for detailed information on its
-capabilities and use.
-
-\begin{itemize}
-\tightlist
-\item
-  \url{https://rmarkdown.rstudio.com/} or
-\item
-  \url{https://bookdown.org/yihui/rmarkdown/}
-\end{itemize}
-
-In this post, we will describe just the main aspects of \textbf{R
-markdown}, so the user can start gKnitting Ruby and R documents quickly.
-
-\hypertarget{the-yaml-header}{%
-\subsection{The Yaml header}\label{the-yaml-header}}
-
-An \textbf{R markdown} document should start with a Yaml header and be
-stored in a file with `.Rmd' extension. This document has the following
-header for gKitting an HTML document.
-
-\begin{verbatim}
----
-title: "How to do reproducible research in Ruby with gKnit"
-author: 
-    - "Rodrigo Botafogo"
-    - "Daniel Mossé - University of Pittsburgh"
-tags: [Tech, Data Science, Ruby, R, GraalVM]
-date: "20/02/2019"
-output:
-  html_document:
-    self_contained: true
-    keep_md: true
-  pdf_document:
-    includes:
-      in_header: ["../../sty/galaaz.sty"]
-    number_sections: yes
----
-\end{verbatim}
-
-For more information on the options in the Yaml header, check
-\url{https://bookdown.org/yihui/rmarkdown/html-document.html}.
-
-\hypertarget{r-markdown-formatting}{%
-\subsection{\texorpdfstring{\textbf{R Markdown}
-formatting}{R Markdown formatting}}\label{r-markdown-formatting}}
-
-Document formatting can be done with simple markups such as:
-
-\hypertarget{headers}{%
-\subsubsection{Headers}\label{headers}}
-
-\begin{verbatim}
-# Header 1
-
-## Header 2
-
-### Header 3
-\end{verbatim}
-
-\hypertarget{lists}{%
-\subsubsection{Lists}\label{lists}}
-
-\begin{verbatim}
-Unordered lists:
-
-* Item 1
-* Item 2
-    + Item 2a
-    + Item 2b
-\end{verbatim}
-
-\begin{verbatim}
-Ordered Lists
-
-1. Item 1
-2. Item 2
-3. Item 3
-    + Item 3a
-    + Item 3b
-\end{verbatim}
-
-For more R markdown formatting go to
-\url{https://rmarkdown.rstudio.com/authoring_basics.html}.
-
-\hypertarget{r-chunks}{%
-\subsubsection{R chunks}\label{r-chunks}}
-
-Running and executing Ruby and R code is actually what really interests
-us is this blog.\\
-Inserting a code chunk is done by adding code in a block delimited by
-three back ticks followed by an open curly brace (`\{') followed with
-the engine name (r, ruby, rb, include, \ldots{}), an any optional
-chunk\_label and options, as shown bellow:
-
-\begin{verbatim}
-```{engine_name [chunk_label], [chunk_options]}
-```
-\end{verbatim}
-
-for instance, let's add an R chunk to the document labeled
-`first\_r\_chunk'. This is a very simple code just to create a variable
-and print it out, as follows:
-
-\begin{verbatim}
-```{r first_r_chunk}
-vec <- c(1, 2, 3)
-print(vec)
-```
-\end{verbatim}
-
-If this block is added to an \textbf{R markdown} document and gKnitted
-the result will be:
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{vec <-}\StringTok{ }\KeywordTok{c}\NormalTok{(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{)}
-\KeywordTok{print}\NormalTok{(vec)}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-## [1] 1 2 3
-\end{verbatim}
-
-Now let's say that we want to do some analysis in the code, but just
-print the result and not the code itself. For this, we need to add the
-option `echo = FALSE'.
-
-\begin{verbatim}
-```{r second_r_chunk, echo = FALSE}
-vec2 <- c(10, 20, 30)
-vec3 <- vec * vec2
-print(vec3)     
-```
-\end{verbatim}
-
-Here is how this block will show up in the document. Observe that the
-code is not shown and we only see the execution result in a white box
-
-\begin{verbatim}
-## [1] 10 40 90
-\end{verbatim}
-
-A description of the available chunk options can be found in
-\url{https://yihui.name/knitr/}.
-
-Let's add another R chunk with a function definition. In this example, a
-vector `r\_vec' is created and a new function `reduce\_sum' is defined.
-The chunk specification is
-
-\begin{verbatim}
-```{r data_creation}
-r_vec <- c(1, 2, 3, 4, 5)
-
-reduce_sum <- function(...) {
-  Reduce(sum, as.list(...))
-}
-```
-\end{verbatim}
-
-and this is how it will look like once executed. From now on, to be
-concise in the presentation we will not show chunk definitions any
-longer.
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{r_vec <-}\StringTok{ }\KeywordTok{c}\NormalTok{(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{, }\DecValTok{4}\NormalTok{, }\DecValTok{5}\NormalTok{)}
-
-\NormalTok{reduce_sum <-}\StringTok{ }\ControlFlowTok{function}\NormalTok{(...) \{}
-  \KeywordTok{Reduce}\NormalTok{(sum, }\KeywordTok{as.list}\NormalTok{(...))}
-\NormalTok{\}}
-\end{Highlighting}
-\end{Shaded}
-
-We can, possibly in another chunk, access the vector and call the
-function as follows:
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\KeywordTok{print}\NormalTok{(r_vec)}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-## [1] 1 2 3 4 5
-\end{verbatim}
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\KeywordTok{print}\NormalTok{(}\KeywordTok{reduce_sum}\NormalTok{(r_vec))}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-## [1] 15
-\end{verbatim}
-
-\hypertarget{r-graphics-with-ggplot}{%
-\subsubsection{R Graphics with ggplot}\label{r-graphics-with-ggplot}}
-
-In the following chunk, we create a bubble chart in R using ggplot and
-include it in this document. Note that there is no directive in the code
-to include the image, this occurs automatically. The `mpg' dataframe is
-natively available to R and to Galaaz as well.
-
-For the reader not knowledgeable of ggplot, ggplot is a graphics library
-based on ``the grammar of graphics'' (Wilkinson 2005). The idea of the
-grammar of graphics is to build a graphics by adding layers to the plot.
-More information can be found in
-\url{https://towardsdatascience.com/a-comprehensive-guide-to-the-grammar-of-graphics-for-effective-visualization-of-multi-dimensional-1f92b4ed4149}.
-
-In the plot bellow the `mpg' dataset from base R is used. ``The data
-concerns city-cycle fuel consumption in miles per gallon, to be
-predicted in terms of 3 multivalued discrete and 5 continuous
-attributes.'' (Quinlan, 1993)
-
-First, the `mpg' dataset if filtered to extract only cars from the
-following manumactures: Audi, Ford, Honda, and Hyundai and stored in the
-`mpg\_select' variable. Then, the selected dataframe is passed to the
-ggplot function specifying in the aesthetic method (aes) that
-`displacement' (disp) should be plotted in the `x' axis and `city
-mileage' should be on the `y' axis. In the `labs' layer we pass the
-`title' and `subtitle' for the plot. To the basic plot `g', geom\_jitter
-is added, that plots cars from the same manufactures with the same color
-(col=manufactures) and the size of the car point equal its high way
-consumption (size = hwy). Finally, a last layer is plotter containing a
-linear regression line (method = ``lm'') for every manufacturer.
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\CommentTok{# load package and data}
-\KeywordTok{library}\NormalTok{(ggplot2)}
-\KeywordTok{data}\NormalTok{(mpg, }\DataTypeTok{package=}\StringTok{"ggplot2"}\NormalTok{)}
-
-\NormalTok{mpg_select <-}\StringTok{ }\NormalTok{mpg[mpg}\OperatorTok{$}\NormalTok{manufacturer }\OperatorTok{%in%}\StringTok{ }\KeywordTok{c}\NormalTok{(}\StringTok{"audi"}\NormalTok{, }\StringTok{"ford"}\NormalTok{, }\StringTok{"honda"}\NormalTok{, }\StringTok{"hyundai"}\NormalTok{), ]}
-
-\CommentTok{# Scatterplot}
-\KeywordTok{theme_set}\NormalTok{(}\KeywordTok{theme_bw}\NormalTok{())  }\CommentTok{# pre-set the bw theme.}
-\NormalTok{g <-}\StringTok{ }\KeywordTok{ggplot}\NormalTok{(mpg_select, }\KeywordTok{aes}\NormalTok{(displ, cty)) }\OperatorTok{+}\StringTok{ }
-\StringTok{  }\KeywordTok{labs}\NormalTok{(}\DataTypeTok{subtitle=}\StringTok{"mpg: Displacement vs City Mileage"}\NormalTok{,}
-       \DataTypeTok{title=}\StringTok{"Bubble chart"}\NormalTok{)}
-
-\NormalTok{g }\OperatorTok{+}\StringTok{ }\KeywordTok{geom_jitter}\NormalTok{(}\KeywordTok{aes}\NormalTok{(}\DataTypeTok{col=}\NormalTok{manufacturer, }\DataTypeTok{size=}\NormalTok{hwy)) }\OperatorTok{+}\StringTok{ }
-\StringTok{  }\KeywordTok{geom_smooth}\NormalTok{(}\KeywordTok{aes}\NormalTok{(}\DataTypeTok{col=}\NormalTok{manufacturer), }\DataTypeTok{method=}\StringTok{"lm"}\NormalTok{, }\DataTypeTok{se=}\NormalTok{F)}
-\end{Highlighting}
-\end{Shaded}
-
-\includegraphics{/home/rbotafogo/desenv/galaaz/blogs/gknit/gknit_files/figure-latex/bubble-1.png}
-
-\hypertarget{ruby-chunks}{%
-\subsubsection{Ruby chunks}\label{ruby-chunks}}
-
-Including a Ruby chunk is just as easy as including an R chunk in the
-document: just change the name of the engine to `ruby'. It is also
-possible to pass chunk options to the Ruby engine; however, this version
-does not accept all the options that are available to R chunks. Future
-versions will add those options.
-
-\begin{verbatim}
-```{ruby first_ruby_chunk}
-```
-\end{verbatim}
-
-In this example, the ruby chunk is called `first\_ruby\_chunk'. One
-important aspect of chunk labels is that they cannot be duplicated. If a
-chunk label is duplicated, gKnit will stop with an error.
-
-In the following chunk, variable `a', `b' and `c' are standard Ruby
-variables and `vec' and `vec2' are two vectors created by calling the
-`c' method on the R module.
-
-In Galaaz, the R module allows us to access R functions transparently.
-The `c' function in R, is a function that concatenates its arguments
-making a vector.
-
-It should be clear that there is no requirement in gknit to call or use
-any R functions. gKnit will knit standard Ruby code, or even general
-text without any code.
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{a = [}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{]}
-\NormalTok{b = }\StringTok{"US$ 250.000"}
-\NormalTok{c = }\StringTok{"The 'outputs' function"}
-
-\NormalTok{vec = R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{)}
-\NormalTok{vec2 = R.c(}\DecValTok{10}\NormalTok{, }\DecValTok{20}\NormalTok{, }\DecValTok{30}\NormalTok{)}
-\end{Highlighting}
-\end{Shaded}
-
-In the next block, variables `a', `vec' and `vec2' are used and printed.
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{puts a}
-\NormalTok{puts vec * vec2}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-## 1
-## 2
-## 3
-## [1] 10 40 90
-\end{verbatim}
-
-Note that `a' is a standard Ruby Array and `vec' and `vec2' are vectors
-that behave accordingly, where multiplication works as expected.
-
-\hypertarget{accessing-r-from-ruby}{%
-\subsubsection{Accessing R from Ruby}\label{accessing-r-from-ruby}}
-
-One of the nice aspects of Galaaz on GraalVM, is that variables and
-functions defined in R, can be easily accessed from Ruby. This next
-chunk, reads data from R and uses the `reduce\_sum' function defined
-previously. To access an R variable from Ruby the `\textasciitilde{}'
-function should be applied to the Ruby symbol representing the R
-variable. Since the R variable is called `r\_vec', in Ruby, the symbol
-to acess it is `:r\_vec' and thus `\textasciitilde{}:r\_vec' retrieves
-the value of the variable.
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{puts ~}\StringTok{:r_vec}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-## [1] 1 2 3 4 5
-\end{verbatim}
-
-In order to call an R function, the `R.' module is used as follows
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{puts R.reduce_sum(~}\StringTok{:r_vec}\NormalTok{)}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-## [1] 15
-\end{verbatim}
-
-\hypertarget{ruby-plotting}{%
-\subsubsection{Ruby Plotting}\label{ruby-plotting}}
-
-We have seen an example of plotting with R. Plotting with Ruby does not
-require anything different from plotting with R. In the following
-example, we plot a diverging bar graph using the `mtcars' dataframe from
-R. This data was extracted from the 1974 Motor Trend US magazine, and
-comprises fuel consumption and 10 aspects of automobile design and
-performance for 32 automobiles (1973--74 models). The ten aspects are:
-
-\begin{itemize}
-\tightlist
-\item
-  mpg: Miles/(US) gallon
-\item
-  cyl: Number of cylinders
-\item
-  disp: Displacement (cu.in.)
-\item
-  hp: Gross horsepower
-\item
-  drat: Rear axle ratio
-\item
-  wt: Weight (1000 lbs)
-\item
-  qsec: 1/4 mile time
-\item
-  vs: Engine (0 = V-shaped, 1 = straight)
-\item
-  am: Transmission (0 = automatic, 1 = manual)
-\item
-  gear: Number of forward gears
-\item
-  carb: Number of carburetors
-\end{itemize}
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\CommentTok{# copy the R variable :mtcars to the Ruby mtcars variable}
-\NormalTok{mtcars = ~}\StringTok{:mtcars}
-
-\CommentTok{# create a new column 'car_name' to store the car names so that it can be}
-\CommentTok{# used for plotting. The 'rownames' of the data frame cannot be used as}
-\CommentTok{# data for plotting}
-\NormalTok{mtcars.car_name = R.rownames(}\StringTok{:mtcars}\NormalTok{)}
-
-\CommentTok{# compute normalized mpg and add it to a new column called mpg_z}
-\CommentTok{# Note that the mean value for mpg can be obtained by calling the 'mean'}
-\CommentTok{# function on the vector 'mtcars.mpg'.  The same with the standard}
-\CommentTok{# deviation 'sd'.  The vector is then rounded to two digits with 'round 2'}
-\NormalTok{mtcars.mpg_z = ((mtcars.mpg - mtcars.mpg.mean)/mtcars.mpg.sd).round }\DecValTok{2}
-
-\CommentTok{# create a new column 'mpg_type'. Function 'ifelse' is a vectorized function}
-\CommentTok{# that looks at every element of the mpg_z vector and if the value is below}
-\CommentTok{# 0, returns 'below', otherwise returns 'above'}
-\NormalTok{mtcars.mpg_type = (mtcars.mpg_z < }\DecValTok{0}\NormalTok{).ifelse(}\StringTok{"below"}\NormalTok{, }\StringTok{"above"}\NormalTok{)}
-
-\CommentTok{# order the mtcar data set by the mpg_z vector from smaler to larger values}
-\NormalTok{mtcars = mtcars[mtcars.mpg_z.order, }\StringTok{:all}\NormalTok{]}
-
-\CommentTok{# convert the car_name column to a factor to retain sorted order in plot}
-\NormalTok{mtcars.car_name = mtcars.car_name.factor }\StringTok{levels: }\NormalTok{mtcars.car_name}
-
-\CommentTok{# let's look at the first records of the final data frame}
-\NormalTok{puts mtcars.head}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-##                      mpg cyl disp  hp drat    wt  qsec vs am gear carb
-## Cadillac Fleetwood  10.4   8  472 205 2.93 5.250 17.98  0  0    3    4
-## Lincoln Continental 10.4   8  460 215 3.00 5.424 17.82  0  0    3    4
-## Camaro Z28          13.3   8  350 245 3.73 3.840 15.41  0  0    3    4
-## Duster 360          14.3   8  360 245 3.21 3.570 15.84  0  0    3    4
-## Chrysler Imperial   14.7   8  440 230 3.23 5.345 17.42  0  0    3    4
-## Maserati Bora       15.0   8  301 335 3.54 3.570 14.60  0  1    5    8
-##                                car_name mpg_z mpg_type
-## Cadillac Fleetwood   Cadillac Fleetwood -1.61    below
-## Lincoln Continental Lincoln Continental -1.61    below
-## Camaro Z28                   Camaro Z28 -1.13    below
-## Duster 360                   Duster 360 -0.96    below
-## Chrysler Imperial     Chrysler Imperial -0.89    below
-## Maserati Bora             Maserati Bora -0.84    below
-\end{verbatim}
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{require }\StringTok{'ggplot'}
-
-\NormalTok{puts mtcars.ggplot(E.aes(}\StringTok{x: :car_name}\NormalTok{, }\StringTok{y: :mpg_z}\NormalTok{, }\StringTok{label: :mpg_z}\NormalTok{)) +}
-\NormalTok{     R.geom_bar(E.aes(}\StringTok{fill: :mpg_type}\NormalTok{), }\StringTok{stat: 'identity'}\NormalTok{, }\StringTok{width: }\FloatTok{0.5}\NormalTok{) +}
-\NormalTok{     R.scale_fill_manual(}\StringTok{name: 'Mileage'}\NormalTok{,}
-                         \StringTok{labels: }\NormalTok{R.c(}\StringTok{'Above Average'}\NormalTok{, }\StringTok{'Below Average'}\NormalTok{),}
-                         \StringTok{values: }\NormalTok{R.c(}\StringTok{'above'}\NormalTok{: }\StringTok{'#00ba38'}\NormalTok{, }\StringTok{'below'}\NormalTok{: }\StringTok{'#f8766d'}\NormalTok{)) +}
-\NormalTok{     R.labs(}\StringTok{subtitle: "Normalised mileage from 'mtcars'"}\NormalTok{,}
-            \StringTok{title: "Diverging Bars"}\NormalTok{) + }
-\NormalTok{     R.coord_flip}
-\end{Highlighting}
-\end{Shaded}
-
-\includegraphics{/home/rbotafogo/desenv/galaaz/blogs/gknit/gknit_files/figure-latex/diverging_bar.pdf}
-
-\hypertarget{inline-ruby-code}{%
-\subsubsection{Inline Ruby code}\label{inline-ruby-code}}
-
-When using a Ruby chunk, the code and the output are formatted in blocks
-as seen above. This formatting is not always desired. Sometimes, we want
-to have the results of the Ruby evaluation included in the middle of a
-phrase. gKnit allows adding inline Ruby code with the `rb' engine. The
-following chunk specification will create and inline Ruby text:
-
-\begin{verbatim}
-This is some text with inline Ruby accessing variable 'b' which has value:
-```{rb puts b}
-```
-and is followed by some other text!
-\end{verbatim}
-
-This is some text with inline Ruby accessing variable `b' which has
-value: US\$ 250.000 and is followed by some other text!
-
-Note that it is important not to add any new line before of after the
-code block if we want everything to be in only one line, resulting in
-the following sentence with inline Ruby code.
-
-\hypertarget{the-outputs-function}{%
-\subsubsection{The `outputs' function}\label{the-outputs-function}}
-
-He have previously used the standard `puts' method in Ruby chunks in
-order produce output. The result of a `puts', as seen in all previous
-chunks that use it, is formatted inside a white box that follows the
-code block. Many times however, we would like to do some processing in
-the Ruby chunk and have the result of this processing generate and
-output that is ``included'' in the document as if we had typed it in
-\textbf{R markdown} document.
-
-For example, suppose we want to create a new heading in our document,
-but the heading phrase is the result of some code processing: maybe it's
-the first line of a file we are going to read. Method `outputs' adds its
-output as if typed in the \textbf{R markdown} document.
-
-Take now a look at variable `c' (it was defined in a previous block
-above) as `c = ``The `outputs' function''. ``The `outputs' function'' is
-actually the name of this section and it was created using the 'outputs'
-function inside a Ruby chunk.
-
-The ruby chunk to generate this heading is:
-
-\begin{verbatim}
-```{ruby heading}
-outputs "### #{c}"
-```
-\end{verbatim}
-
-The three `\#\#\#' is the way we add a Heading 3 in \textbf{R markdown}.
-
-\hypertarget{html-output-from-ruby-chunks}{%
-\subsubsection{HTML Output from Ruby
-Chunks}\label{html-output-from-ruby-chunks}}
-
-We've just seen the use of method `outputs' to add text to the the
-\textbf{R markdown} document. This technique can also be used to add
-HTML code to the document. In \textbf{R markdown}, any html code typed
-directly in the document will be properly rendered.\\
-Here, for instance, is a table definition in HTML and its output in the
-document:
-
-\begin{verbatim}
-<table style="width:100%">
-  <tr>
-    <th>Firstname</th>
-    <th>Lastname</th> 
-    <th>Age</th>
-  </tr>
-  <tr>
-    <td>Jill</td>
-    <td>Smith</td> 
-    <td>50</td>
-  </tr>
-  <tr>
-    <td>Eve</td>
-    <td>Jackson</td> 
-    <td>94</td>
-  </tr>
-</table>
-\end{verbatim}
-
-Firstname
-
-Lastname
-
-Age
-
-Jill
-
-Smith
-
-50
-
-Eve
-
-Jackson
-
-94
-
-But manually creating HTML output is not always easy or desirable,
-specially if we intend the document to be rendered in other formats, for
-example, as Latex. Also, The above table looks ugly. The `kableExtra'
-library is a great library for creating beautiful tables. Take a look at
-\url{https://cran.r-project.org/web/packages/kableExtra/vignettes/awesome_table_in_html.html}
-
-In the next chunk, we output the `mtcars' dataframe from R in a nicely
-formatted table. Note that we retrieve the mtcars dataframe by using
-`\textasciitilde{}:mtcars'.
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{R.install_and_loads(}\StringTok{'kableExtra'}\NormalTok{)}
-\NormalTok{outputs (~}\StringTok{:mtcars}\NormalTok{).kable.kable_styling}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{table}[H]
-\centering
-\begin{tabular}{l|r|r|r|r|r|r|r|r|r|r|r}
-\hline
-  & mpg & cyl & disp & hp & drat & wt & qsec & vs & am & gear & carb\\
-\hline
-Mazda RX4 & 21.0 & 6 & 160.0 & 110 & 3.90 & 2.620 & 16.46 & 0 & 1 & 4 & 4\\
-\hline
-Mazda RX4 Wag & 21.0 & 6 & 160.0 & 110 & 3.90 & 2.875 & 17.02 & 0 & 1 & 4 & 4\\
-\hline
-Datsun 710 & 22.8 & 4 & 108.0 & 93 & 3.85 & 2.320 & 18.61 & 1 & 1 & 4 & 1\\
-\hline
-Hornet 4 Drive & 21.4 & 6 & 258.0 & 110 & 3.08 & 3.215 & 19.44 & 1 & 0 & 3 & 1\\
-\hline
-Hornet Sportabout & 18.7 & 8 & 360.0 & 175 & 3.15 & 3.440 & 17.02 & 0 & 0 & 3 & 2\\
-\hline
-Valiant & 18.1 & 6 & 225.0 & 105 & 2.76 & 3.460 & 20.22 & 1 & 0 & 3 & 1\\
-\hline
-Duster 360 & 14.3 & 8 & 360.0 & 245 & 3.21 & 3.570 & 15.84 & 0 & 0 & 3 & 4\\
-\hline
-Merc 240D & 24.4 & 4 & 146.7 & 62 & 3.69 & 3.190 & 20.00 & 1 & 0 & 4 & 2\\
-\hline
-Merc 230 & 22.8 & 4 & 140.8 & 95 & 3.92 & 3.150 & 22.90 & 1 & 0 & 4 & 2\\
-\hline
-Merc 280 & 19.2 & 6 & 167.6 & 123 & 3.92 & 3.440 & 18.30 & 1 & 0 & 4 & 4\\
-\hline
-Merc 280C & 17.8 & 6 & 167.6 & 123 & 3.92 & 3.440 & 18.90 & 1 & 0 & 4 & 4\\
-\hline
-Merc 450SE & 16.4 & 8 & 275.8 & 180 & 3.07 & 4.070 & 17.40 & 0 & 0 & 3 & 3\\
-\hline
-Merc 450SL & 17.3 & 8 & 275.8 & 180 & 3.07 & 3.730 & 17.60 & 0 & 0 & 3 & 3\\
-\hline
-Merc 450SLC & 15.2 & 8 & 275.8 & 180 & 3.07 & 3.780 & 18.00 & 0 & 0 & 3 & 3\\
-\hline
-Cadillac Fleetwood & 10.4 & 8 & 472.0 & 205 & 2.93 & 5.250 & 17.98 & 0 & 0 & 3 & 4\\
-\hline
-Lincoln Continental & 10.4 & 8 & 460.0 & 215 & 3.00 & 5.424 & 17.82 & 0 & 0 & 3 & 4\\
-\hline
-Chrysler Imperial & 14.7 & 8 & 440.0 & 230 & 3.23 & 5.345 & 17.42 & 0 & 0 & 3 & 4\\
-\hline
-Fiat 128 & 32.4 & 4 & 78.7 & 66 & 4.08 & 2.200 & 19.47 & 1 & 1 & 4 & 1\\
-\hline
-Honda Civic & 30.4 & 4 & 75.7 & 52 & 4.93 & 1.615 & 18.52 & 1 & 1 & 4 & 2\\
-\hline
-Toyota Corolla & 33.9 & 4 & 71.1 & 65 & 4.22 & 1.835 & 19.90 & 1 & 1 & 4 & 1\\
-\hline
-Toyota Corona & 21.5 & 4 & 120.1 & 97 & 3.70 & 2.465 & 20.01 & 1 & 0 & 3 & 1\\
-\hline
-Dodge Challenger & 15.5 & 8 & 318.0 & 150 & 2.76 & 3.520 & 16.87 & 0 & 0 & 3 & 2\\
-\hline
-AMC Javelin & 15.2 & 8 & 304.0 & 150 & 3.15 & 3.435 & 17.30 & 0 & 0 & 3 & 2\\
-\hline
-Camaro Z28 & 13.3 & 8 & 350.0 & 245 & 3.73 & 3.840 & 15.41 & 0 & 0 & 3 & 4\\
-\hline
-Pontiac Firebird & 19.2 & 8 & 400.0 & 175 & 3.08 & 3.845 & 17.05 & 0 & 0 & 3 & 2\\
-\hline
-Fiat X1-9 & 27.3 & 4 & 79.0 & 66 & 4.08 & 1.935 & 18.90 & 1 & 1 & 4 & 1\\
-\hline
-Porsche 914-2 & 26.0 & 4 & 120.3 & 91 & 4.43 & 2.140 & 16.70 & 0 & 1 & 5 & 2\\
-\hline
-Lotus Europa & 30.4 & 4 & 95.1 & 113 & 3.77 & 1.513 & 16.90 & 1 & 1 & 5 & 2\\
-\hline
-Ford Pantera L & 15.8 & 8 & 351.0 & 264 & 4.22 & 3.170 & 14.50 & 0 & 1 & 5 & 4\\
-\hline
-Ferrari Dino & 19.7 & 6 & 145.0 & 175 & 3.62 & 2.770 & 15.50 & 0 & 1 & 5 & 6\\
-\hline
-Maserati Bora & 15.0 & 8 & 301.0 & 335 & 3.54 & 3.570 & 14.60 & 0 & 1 & 5 & 8\\
-\hline
-Volvo 142E & 21.4 & 4 & 121.0 & 109 & 4.11 & 2.780 & 18.60 & 1 & 1 & 4 & 2\\
-\hline
-\end{tabular}
-\end{table}
-
-\hypertarget{including-ruby-files-in-a-chunk}{%
-\subsubsection{Including Ruby files in a
-chunk}\label{including-ruby-files-in-a-chunk}}
-
-R is a language that was created to be easy and fast for statisticians
-to use. As far as I know, it was not a language to be used for
-developing large systems. Of course, there are large systems and
-libraries in R, but the focus of the language is for developing
-statistical models and distribute that to peers.
-
-Ruby on the other hand, is a language for large software development.
-Systems written in Ruby will have dozens, hundreds or even thousands of
-files. To document a large system with literate programming, we cannot
-expect the developer to add all the files in a single `.Rmd' file. gKnit
-provides the `include' chunk engine to include a Ruby file as if it had
-being typed in the `.Rmd' file.
-
-To include a file, the following chunk should be created, where is the
-name of the file to be included and where the extension, if it is `.rb',
-does not need to be added. If the `relative' option is not included,
-then it is treated as TRUE. When `relative' is true, ruby's
-`require\_relative' semantics is used to load the file, when false,
-Ruby's \$LOAD\_PATH is searched to find the file and it is 'require'd.
-
-\begin{verbatim}
-```{include <filename>, relative = <TRUE/FALSE>}
-```
-\end{verbatim}
-
-Bellow we include file `model.rb', which is in the same directory of
-this blog.\\
-This code uses R `caret' package to split a dataset in a train and test
-sets. The `caret' package is a very important a useful package for doing
-Data Analysis, it has hundreds of functions for all steps of the Data
-Analysis workflow. To use `caret' just to split a dataset is like using
-the proverbial cannon to kill the fly. We use it here only to show that
-integrating Ruby and R and using even a very complex package as `caret'
-is trivial with Galaaz.
-
-A word of advice: the `caret' package has lots of dependencies and
-installing it in a Linux system is a time consuming operation. Method
-`R.install\_and\_loads' will install the package if it is not already
-installed and can take a while.
-
-\begin{verbatim}
-```{include model}
-```
-\end{verbatim}
-
-\begin{verbatim}
-require 'galaaz'
-
-# Loads the R 'caret' package.  If not present, installs it 
-R.install_and_loads 'caret'
-
-class Model
-  
-  attr_reader :data
-  attr_reader :test
-  attr_reader :train
-
-  #==========================================================
-  #
-  #==========================================================
-  
-  def initialize(data, percent_train:, seed: 123)
-
-    R.set__seed(seed)
-    @data = data
-    @percent_train = percent_train
-    @seed = seed
-    
-  end
-
-  #==========================================================
-  #
-  #==========================================================
-
-  def partition(field)
-
-    train_index =
-      R.createDataPartition(@data.send(field), p: @percet_train,
-                            list: false, times: 1)
-    @train = @data[train_index, :all]
-    @test = @data[-train_index, :all]
-    
-  end
-  
-end
-\end{verbatim}
-
-\begin{Shaded}
-\begin{Highlighting}[]
-\NormalTok{mtcars = ~}\StringTok{:mtcars}
-\NormalTok{model = }\DataTypeTok{Model}\NormalTok{.new(mtcars, }\StringTok{percent_train: }\FloatTok{0.8}\NormalTok{)}
-\NormalTok{model.partition(}\StringTok{:mpg}\NormalTok{)}
-\NormalTok{puts model.train.head}
-\NormalTok{puts model.test.head}
-\end{Highlighting}
-\end{Shaded}
-
-\begin{verbatim}
-##                    mpg cyl  disp  hp drat    wt  qsec vs am gear carb
-## Datsun 710        22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
-## Hornet 4 Drive    21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
-## Hornet Sportabout 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
-## Merc 240D         24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
-## Merc 280          19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
-## Merc 280C         17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
-##                mpg cyl  disp  hp drat    wt  qsec vs am gear carb
-## Mazda RX4     21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
-## Mazda RX4 Wag 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
-## Valiant       18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
-## Duster 360    14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
-## Merc 230      22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
-## Merc 450SE    16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
-\end{verbatim}
-
-\hypertarget{documenting-gems}{%
-\subsubsection{Documenting Gems}\label{documenting-gems}}
-
-gKnit also allows developers to document and load files that are not in
-the same directory of the `.Rmd' file.
-
-Here is an example of loading the `find.rb' file from TruffleRuby. In
-this example, relative is set to FALSE, so Ruby will look for the file
-in its \$LOAD\_PATH, and the user does not need to no it's directory.
-
-\begin{verbatim}
-```{include find, relative = FALSE}
-```
-\end{verbatim}
-
-\begin{verbatim}
-# frozen_string_literal: true
-#
-# find.rb: the Find module for processing all files under a given directory.
-#
-
-#
-# The +Find+ module supports the top-down traversal of a set of file paths.
-#
-# For example, to total the size of all files under your home directory,
-# ignoring anything in a "dot" directory (e.g. $HOME/.ssh):
-#
-#   require 'find'
-#
-#   total_size = 0
-#
-#   Find.find(ENV["HOME"]) do |path|
-#     if FileTest.directory?(path)
-#       if File.basename(path)[0] == ?.
-#         Find.prune       # Don't look any further into this directory.
-#       else
-#         next
-#       end
-#     else
-#       total_size += FileTest.size(path)
-#     end
-#   end
-#
-module Find
-
-  #
-  # Calls the associated block with the name of every file and directory listed
-  # as arguments, then recursively on their subdirectories, and so on.
-  #
-  # Returns an enumerator if no block is given.
-  #
-  # See the +Find+ module documentation for an example.
-  #
-  def find(*paths, ignore_error: true) # :yield: path
-    block_given? or return enum_for(__method__, *paths, ignore_error: ignore_error)
-
-    fs_encoding = Encoding.find("filesystem")
-
-    paths.collect!{|d| raise Errno::ENOENT, d unless File.exist?(d); d.dup}.each do |path|
-      path = path.to_path if path.respond_to? :to_path
-      enc = path.encoding == Encoding::US_ASCII ? fs_encoding : path.encoding
-      ps = [path]
-      while file = ps.shift
-        catch(:prune) do
-          yield file.dup.taint
-          begin
-            s = File.lstat(file)
-          rescue Errno::ENOENT, Errno::EACCES, Errno::ENOTDIR, Errno::ELOOP, Errno::ENAMETOOLONG
-            raise unless ignore_error
-            next
-          end
-          if s.directory? then
-            begin
-              fs = Dir.children(file, encoding: enc)
-            rescue Errno::ENOENT, Errno::EACCES, Errno::ENOTDIR, Errno::ELOOP, Errno::ENAMETOOLONG
-              raise unless ignore_error
-              next
-            end
-            fs.sort!
-            fs.reverse_each {|f|
-              f = File.join(file, f)
-              ps.unshift f.untaint
-            }
-          end
-        end
-      end
-    end
-    nil
-  end
-
-  #
-  # Skips the current file or directory, restarting the loop with the next
-  # entry. If the current file is a directory, that directory will not be
-  # recursively entered. Meaningful only within the block associated with
-  # Find::find.
-  #
-  # See the +Find+ module documentation for an example.
-  #
-  def prune
-    throw :prune
-  end
-
-  module_function :find, :prune
-end
-\end{verbatim}
-
-\hypertarget{converting-to-pdf}{%
-\subsection{Converting to PDF}\label{converting-to-pdf}}
-
-One of the beauties of knitr is that the same input can be converted to
-many different outputs. One very useful format, is, of course, PDF. In
-order to converted an \textbf{R markdown} file to PDF it is necessary to
-have LaTeX installed on the system. We will not explain here how to
-install LaTeX as there are plenty of documents on the web showing how to
-proceed.
-
-gKnit comes with a simple LaTeX style file for gknitting this blog as a
-PDF document. Here is the Yaml header to generate this blog in PDF
-format instead of HTML:
-
-\begin{verbatim}
----
-title: "gKnit - Ruby and R Knitting with Galaaz in GraalVM"
-author: "Rodrigo Botafogo"
-tags: [Galaaz, Ruby, R, TruffleRuby, FastR, GraalVM, knitr, gknit]
-date: "29 October 2018"
-output:
-  pdf\_document:
-    includes:
-      in\_header: ["../../sty/galaaz.sty"]
-    number\_sections: yes
----
-\end{verbatim}
-
-\hypertarget{conclusion}{%
-\section{Conclusion}\label{conclusion}}
-
-In order to do reproducible research, one of the main basic tools needed
-is a systhem that allows ``literate programming'' where text, code and
-possibly a set of files can be compiled onto a report that can be easily
-distributed to peers. Peers should be able to use this same set of files
-to rerun the compilation by their own obtaining the exact same original
-report. gKnit is such a system for Ruby and R. It uses \textbf{R
-Markdown} to integrate text and code chunks, where code chunks can
-either be part of the \textbf{R Markdwon} file or be imported from files
-in the system. Ideally, in reproducible research, all the files needed
-to rebuild a report should be easilly packed together (in the same
-zipped directory) and distributed to peers for reexecution.
-
-One of the promises of Oracle's GraalVM is that users/developers will be
-able to use the best tool for their task at hand, independently of the
-programming language the tool was written on. We developed and
-implemented Galaaz atop the GraalVM and Truffle interop messages and the
-time and effort to wrap Ruby over R - Galaaz - or to wrap Knitr with
-gKnit was a fraction of a fraction of a fraction (one man effort for a
-couple of hours a day, for approximately six months) of the time require
-to implement the original tools. Trying to reimplement all R packages in
-Ruby would require the same effort it is taking Python to implement
-NumPy, Pandas and all supporting libraries and it is unlikely that this
-effort would ever be done. GraalVM has allowed Ruby to profit ``almost
-for free'' from this huge set of libraries and tools that make R one of
-the most used languages for data analysis and machine learning.
-
-More interesting than wrapping the R libraries with Ruby, is that Ruby
-adds value to R, by allowing developers to use powerful and modern
-constructs for code reuse that are not the strong points of R. As shown
-in this blog, R and Ruby can easily communicate and R can be structured
-in classes and modules in a way that greatly expands its power and
-readability.
-
-\hypertarget{installing-gknit}{%
-\section{Installing gKnit}\label{installing-gknit}}
-
-\hypertarget{prerequisites}{%
-\subsection{Prerequisites}\label{prerequisites}}
-
-\begin{itemize}
-\tightlist
-\item
-  GraalVM (\textgreater{}= rc8)
-\item
-  TruffleRuby
-\item
-  FastR
-\end{itemize}
-
-The following R packages will be automatically installed when necessary,
-but could be installed prior to using gKnit if desired:
-
-\begin{itemize}
-\tightlist
-\item
-  ggplot2
-\item
-  gridExtra
-\item
-  knitr
-\end{itemize}
-
-Installation of R packages requires a development environment and can be
-time consuming. In Linux, the gnu compiler and tools should be enough. I
-am not sure what is needed on the Mac.
-
-\hypertarget{preparation}{%
-\subsection{Preparation}\label{preparation}}
-
-\begin{itemize}
-\tightlist
-\item
-  gem install galaaz
-\end{itemize}
-
-\hypertarget{usage}{%
-\subsection{Usage}\label{usage}}
-
-\begin{itemize}
-\tightlist
-\item
-  gknit \textless{}filename\textgreater{}
-\end{itemize}
-
-\hypertarget{references}{%
-\section*{References}\label{references}}
-\addcontentsline{toc}{section}{References}
-
-\hypertarget{refs}{}
-\leavevmode\hypertarget{ref-Knuth:literate_programming}{}%
-Knuth, Donald E. 1984. ``Literate Programming.'' \emph{Comput. J.} 27
-(2). Oxford, UK: Oxford University Press: 97--111.
-\url{https://doi.org/10.1093/comjnl/27.2.97}.
-
-\leavevmode\hypertarget{ref-Wilkinson:grammar_of_graphics}{}%
-Wilkinson, Leland. 2005. \emph{The Grammar of Graphics (Statistics and
-Computing)}. Berlin, Heidelberg: Springer-Verlag.
-
-
-\end{document}