galaaz 0.4.1 → 0.4.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Rakefile +29 -0
- data/bin/gknit +208 -10
- data/bin/gknit2 +14 -0
- data/bin/gknit2~ +6 -0
- data/bin/prepareR.rb +3 -0
- data/bin/prepareR.rb~ +1 -0
- data/bin/tmp.py +51 -0
- data/blogs/dev/dev.Rmd +70 -0
- data/blogs/dev/dev.Rmd~ +104 -0
- data/blogs/dev/dev.html +209 -0
- data/blogs/dev/dev.md +72 -0
- data/blogs/dev/dev_files/figure-html/bubble-1.png +0 -0
- data/blogs/dev/model.rb +41 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot.Rmd +55 -27
- data/blogs/galaaz_ggplot/galaaz_ggplot.aux +44 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot.dvi +0 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot.html +17 -4
- data/blogs/galaaz_ggplot/galaaz_ggplot.out +10 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot.pdf +0 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot.tex +630 -0
- data/blogs/galaaz_ggplot/midwest.Rmd +1 -1
- data/blogs/galaaz_ggplot/midwest_external_png +13 -0
- data/blogs/galaaz_ggplot/midwest_external_png~ +1 -0
- data/blogs/gknit/gknit.Rmd +500 -0
- data/blogs/gknit/gknit.Rmd~ +184 -0
- data/blogs/gknit/gknit.Rnd~ +17 -0
- data/blogs/gknit/gknit.html +528 -0
- data/blogs/gknit/gknit.md +628 -0
- data/blogs/gknit/gknit.pdf +0 -0
- data/blogs/gknit/gknit.tex +745 -0
- data/blogs/gknit/gknit_files/figure-html/bubble-1.png +0 -0
- data/blogs/gknit/gknit_files/figure-html/diverging_bar.png +0 -0
- data/blogs/gknit/model.rb +41 -0
- data/blogs/gknit/model.rb~ +46 -0
- data/blogs/ruby_plot/figures/dose_len.png +0 -0
- data/blogs/ruby_plot/figures/facet_by_delivery.png +0 -0
- data/blogs/ruby_plot/figures/facet_by_dose.png +0 -0
- data/blogs/ruby_plot/figures/facets_by_delivery_color.png +0 -0
- data/blogs/ruby_plot/figures/facets_by_delivery_color2.png +0 -0
- data/blogs/ruby_plot/figures/facets_with_decorations.png +0 -0
- data/blogs/ruby_plot/figures/facets_with_jitter.png +0 -0
- data/blogs/ruby_plot/figures/facets_with_points.png +0 -0
- data/blogs/ruby_plot/figures/final_box_plot.png +0 -0
- data/blogs/ruby_plot/figures/final_violin_plot.png +0 -0
- data/blogs/ruby_plot/figures/violin_with_jitter.png +0 -0
- data/blogs/ruby_plot/ruby_plot.Rmd +680 -0
- data/blogs/ruby_plot/ruby_plot.Rmd~ +215 -0
- data/blogs/ruby_plot/ruby_plot.html +563 -0
- data/blogs/ruby_plot/ruby_plot.md +731 -0
- data/blogs/ruby_plot/ruby_plot.pdf +0 -0
- data/blogs/ruby_plot/ruby_plot.tex +458 -0
- data/examples/sthda_ggplot/all.rb +0 -6
- data/examples/sthda_ggplot/two_variables_cont_bivariate/geom_hex.rb +1 -1
- data/examples/sthda_ggplot/two_variables_cont_cont/misc.rb +1 -1
- data/examples/sthda_ggplot/two_variables_disc_cont/geom_bar.rb +2 -2
- data/examples/sthda_ggplot/two_variables_disc_disc/geom_jitter.rb +0 -1
- data/lib/R/eng_ruby.R +62 -0
- data/lib/R/eng_ruby.R~ +63 -0
- data/lib/R_interface/capture_plot.rb~ +23 -0
- data/lib/{R → R_interface}/expression.rb +0 -0
- data/lib/{R → R_interface}/r.rb +10 -1
- data/lib/{R → R_interface}/r.rb~ +0 -0
- data/lib/{R → R_interface}/r_methods.rb +21 -5
- data/lib/{R → R_interface}/rbinary_operators.rb +6 -1
- data/lib/R_interface/rclosure.rb +38 -0
- data/lib/{R → R_interface}/rdata_frame.rb +0 -0
- data/lib/R_interface/rdevices.R +31 -0
- data/lib/R_interface/rdevices.rb +225 -0
- data/lib/{R/rclosure.rb → R_interface/rdevices.rb~} +3 -10
- data/lib/{R → R_interface}/renvironment.rb +0 -0
- data/lib/{R → R_interface}/rexpression.rb +0 -0
- data/lib/{R → R_interface}/rindexed_object.rb +0 -0
- data/lib/{R → R_interface}/rlanguage.rb +0 -0
- data/lib/{R → R_interface}/rlist.rb +0 -0
- data/lib/{R → R_interface}/rmatrix.rb +0 -0
- data/lib/{R → R_interface}/rmd_indexed_object.rb +0 -0
- data/lib/{R → R_interface}/robject.rb +5 -0
- data/lib/{R → R_interface}/rpkg.rb +0 -0
- data/lib/{R → R_interface}/rsupport.rb +49 -13
- data/lib/{R → R_interface}/rsupport_scope.rb +0 -0
- data/lib/{R → R_interface}/rsymbol.rb +1 -0
- data/lib/{R → R_interface}/ruby_callback.rb +0 -0
- data/lib/{R → R_interface}/ruby_extensions.rb +2 -1
- data/lib/{R → R_interface}/runary_operators.rb +0 -0
- data/lib/{R → R_interface}/rvector.rb +0 -0
- data/lib/galaaz.rb +4 -2
- data/lib/gknit.rb +27 -0
- data/lib/gknit.rb~ +26 -0
- data/lib/gknit/knitr_engine.rb +120 -0
- data/lib/gknit/knitr_engine.rb~ +102 -0
- data/lib/gknit/ruby_engine.rb +70 -0
- data/lib/gknit/ruby_engine.rb~ +72 -0
- data/lib/util/exec_ruby.rb +8 -7
- data/lib/util/inline_file.rb +70 -0
- data/lib/util/inline_file.rb~ +23 -0
- data/r_requires/ggplot.rb +1 -8
- data/r_requires/knitr.rb +27 -0
- data/r_requires/knitr.rb~ +4 -0
- data/specs/r_language.spec.rb +22 -0
- data/specs/r_plots.spec.rb +72 -0
- data/specs/r_plots.spec.rb~ +37 -0
- data/specs/tmp.rb +255 -1
- data/version.rb +1 -1
- metadata +89 -39
Binary file
|
@@ -0,0 +1,745 @@
|
|
1
|
+
\documentclass[]{article}
|
2
|
+
\usepackage{lmodern}
|
3
|
+
\usepackage{amssymb,amsmath}
|
4
|
+
\usepackage{ifxetex,ifluatex}
|
5
|
+
\usepackage{fixltx2e} % provides \textsubscript
|
6
|
+
\ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex
|
7
|
+
\usepackage[T1]{fontenc}
|
8
|
+
\usepackage[utf8]{inputenc}
|
9
|
+
\else % if luatex or xelatex
|
10
|
+
\ifxetex
|
11
|
+
\usepackage{mathspec}
|
12
|
+
\else
|
13
|
+
\usepackage{fontspec}
|
14
|
+
\fi
|
15
|
+
\defaultfontfeatures{Ligatures=TeX,Scale=MatchLowercase}
|
16
|
+
\fi
|
17
|
+
% use upquote if available, for straight quotes in verbatim environments
|
18
|
+
\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
|
19
|
+
% use microtype if available
|
20
|
+
\IfFileExists{microtype.sty}{%
|
21
|
+
\usepackage{microtype}
|
22
|
+
\UseMicrotypeSet[protrusion]{basicmath} % disable protrusion for tt fonts
|
23
|
+
}{}
|
24
|
+
\usepackage[margin=1in]{geometry}
|
25
|
+
\usepackage{hyperref}
|
26
|
+
\hypersetup{unicode=true,
|
27
|
+
pdftitle={gKnit - Ruby and R Knitting with Galaaz in GraalVM},
|
28
|
+
pdfauthor={Rodrigo Botafogo},
|
29
|
+
pdfborder={0 0 0},
|
30
|
+
breaklinks=true}
|
31
|
+
\urlstyle{same} % don't use monospace font for urls
|
32
|
+
\usepackage{color}
|
33
|
+
\usepackage{fancyvrb}
|
34
|
+
\newcommand{\VerbBar}{|}
|
35
|
+
\newcommand{\VERB}{\Verb[commandchars=\\\{\}]}
|
36
|
+
\DefineVerbatimEnvironment{Highlighting}{Verbatim}{commandchars=\\\{\}}
|
37
|
+
% Add ',fontsize=\small' for more characters per line
|
38
|
+
\usepackage{framed}
|
39
|
+
\definecolor{shadecolor}{RGB}{248,248,248}
|
40
|
+
\newenvironment{Shaded}{\begin{snugshade}}{\end{snugshade}}
|
41
|
+
\newcommand{\KeywordTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{\textbf{#1}}}
|
42
|
+
\newcommand{\DataTypeTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{#1}}
|
43
|
+
\newcommand{\DecValTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
|
44
|
+
\newcommand{\BaseNTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
|
45
|
+
\newcommand{\FloatTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
|
46
|
+
\newcommand{\ConstantTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
|
47
|
+
\newcommand{\CharTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
|
48
|
+
\newcommand{\SpecialCharTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
|
49
|
+
\newcommand{\StringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
|
50
|
+
\newcommand{\VerbatimStringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
|
51
|
+
\newcommand{\SpecialStringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
|
52
|
+
\newcommand{\ImportTok}[1]{#1}
|
53
|
+
\newcommand{\CommentTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textit{#1}}}
|
54
|
+
\newcommand{\DocumentationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
55
|
+
\newcommand{\AnnotationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
56
|
+
\newcommand{\CommentVarTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
57
|
+
\newcommand{\OtherTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{#1}}
|
58
|
+
\newcommand{\FunctionTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
|
59
|
+
\newcommand{\VariableTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
|
60
|
+
\newcommand{\ControlFlowTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{\textbf{#1}}}
|
61
|
+
\newcommand{\OperatorTok}[1]{\textcolor[rgb]{0.81,0.36,0.00}{\textbf{#1}}}
|
62
|
+
\newcommand{\BuiltInTok}[1]{#1}
|
63
|
+
\newcommand{\ExtensionTok}[1]{#1}
|
64
|
+
\newcommand{\PreprocessorTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textit{#1}}}
|
65
|
+
\newcommand{\AttributeTok}[1]{\textcolor[rgb]{0.77,0.63,0.00}{#1}}
|
66
|
+
\newcommand{\RegionMarkerTok}[1]{#1}
|
67
|
+
\newcommand{\InformationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
68
|
+
\newcommand{\WarningTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
69
|
+
\newcommand{\AlertTok}[1]{\textcolor[rgb]{0.94,0.16,0.16}{#1}}
|
70
|
+
\newcommand{\ErrorTok}[1]{\textcolor[rgb]{0.64,0.00,0.00}{\textbf{#1}}}
|
71
|
+
\newcommand{\NormalTok}[1]{#1}
|
72
|
+
\usepackage{graphicx,grffile}
|
73
|
+
\makeatletter
|
74
|
+
\def\maxwidth{\ifdim\Gin@nat@width>\linewidth\linewidth\else\Gin@nat@width\fi}
|
75
|
+
\def\maxheight{\ifdim\Gin@nat@height>\textheight\textheight\else\Gin@nat@height\fi}
|
76
|
+
\makeatother
|
77
|
+
% Scale images if necessary, so that they will not overflow the page
|
78
|
+
% margins by default, and it is still possible to overwrite the defaults
|
79
|
+
% using explicit options in \includegraphics[width, height, ...]{}
|
80
|
+
\setkeys{Gin}{width=\maxwidth,height=\maxheight,keepaspectratio}
|
81
|
+
\IfFileExists{parskip.sty}{%
|
82
|
+
\usepackage{parskip}
|
83
|
+
}{% else
|
84
|
+
\setlength{\parindent}{0pt}
|
85
|
+
\setlength{\parskip}{6pt plus 2pt minus 1pt}
|
86
|
+
}
|
87
|
+
\setlength{\emergencystretch}{3em} % prevent overfull lines
|
88
|
+
\providecommand{\tightlist}{%
|
89
|
+
\setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}}
|
90
|
+
\setcounter{secnumdepth}{5}
|
91
|
+
% Redefines (sub)paragraphs to behave more like sections
|
92
|
+
\ifx\paragraph\undefined\else
|
93
|
+
\let\oldparagraph\paragraph
|
94
|
+
\renewcommand{\paragraph}[1]{\oldparagraph{#1}\mbox{}}
|
95
|
+
\fi
|
96
|
+
\ifx\subparagraph\undefined\else
|
97
|
+
\let\oldsubparagraph\subparagraph
|
98
|
+
\renewcommand{\subparagraph}[1]{\oldsubparagraph{#1}\mbox{}}
|
99
|
+
\fi
|
100
|
+
|
101
|
+
%%% Use protect on footnotes to avoid problems with footnotes in titles
|
102
|
+
\let\rmarkdownfootnote\footnote%
|
103
|
+
\def\footnote{\protect\rmarkdownfootnote}
|
104
|
+
|
105
|
+
%%% Change title format to be more compact
|
106
|
+
\usepackage{titling}
|
107
|
+
|
108
|
+
% Create subtitle command for use in maketitle
|
109
|
+
\newcommand{\subtitle}[1]{
|
110
|
+
\posttitle{
|
111
|
+
\begin{center}\large#1\end{center}
|
112
|
+
}
|
113
|
+
}
|
114
|
+
|
115
|
+
\setlength{\droptitle}{-2em}
|
116
|
+
|
117
|
+
\title{gKnit - Ruby and R Knitting with Galaaz in GraalVM}
|
118
|
+
\pretitle{\vspace{\droptitle}\centering\huge}
|
119
|
+
\posttitle{\par}
|
120
|
+
\author{Rodrigo Botafogo}
|
121
|
+
\preauthor{\centering\large\emph}
|
122
|
+
\postauthor{\par}
|
123
|
+
\predate{\centering\large\emph}
|
124
|
+
\postdate{\par}
|
125
|
+
\date{19 October 2018}
|
126
|
+
|
127
|
+
% usar portugues do Brasil
|
128
|
+
% \usepackage[brazilian]{babel}
|
129
|
+
\usepackage[utf8]{inputenc}
|
130
|
+
|
131
|
+
\usepackage{geometry}
|
132
|
+
\geometry{a4paper, top=1in}
|
133
|
+
|
134
|
+
% necessários para uso com kableExtra
|
135
|
+
\usepackage{longtable}
|
136
|
+
\usepackage{multirow}
|
137
|
+
\usepackage[table]{xcolor}
|
138
|
+
\usepackage{wrapfig}
|
139
|
+
\usepackage{float}
|
140
|
+
\usepackage{colortbl}
|
141
|
+
\usepackage{pdflscape}
|
142
|
+
\usepackage{tabu}
|
143
|
+
\usepackage{threeparttable}
|
144
|
+
\usepackage[normalem]{ulem}
|
145
|
+
|
146
|
+
\usepackage{bbm}
|
147
|
+
\usepackage{booktabs}
|
148
|
+
\usepackage{expex}
|
149
|
+
|
150
|
+
\usepackage{graphicx}
|
151
|
+
\usepackage{fancyhdr}
|
152
|
+
\pagestyle{fancy}
|
153
|
+
\fancyhf{}
|
154
|
+
|
155
|
+
\usepackage{lipsum}
|
156
|
+
|
157
|
+
% disponibilizar o comando lastpage
|
158
|
+
\usepackage{lastpage}
|
159
|
+
|
160
|
+
% tamanho do font padrão 11pt
|
161
|
+
\usepackage[fontsize=10pt]{scrextend}
|
162
|
+
|
163
|
+
% comandos para formatar uma tabela
|
164
|
+
\usepackage{array}
|
165
|
+
\newcolumntype{L}[1]{>{\raggedright\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
166
|
+
\newcolumntype{C}[1]{>{\centering\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
167
|
+
\newcolumntype{R}[1]{>{\raggedleft\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
168
|
+
|
169
|
+
% necessário para importar outros arquivos latex
|
170
|
+
\usepackage{import}
|
171
|
+
|
172
|
+
\newcommand{\RtoLatex}[2]{\newcommand{#1}{#2}}
|
173
|
+
%\newcommand{\atraso}[1]{\color{red} \textbf {Tempo desde a Assinatura do Contrato: #1 dias}}
|
174
|
+
|
175
|
+
\begin{document}
|
176
|
+
\maketitle
|
177
|
+
|
178
|
+
\section{Introduction}\label{introduction}
|
179
|
+
|
180
|
+
The idea of ``literate programming'' was first introduced by Donald
|
181
|
+
Knuth in the 1980's. The main intention of this approach was to develop
|
182
|
+
software interspersing macro snippets, traditional source code, and a
|
183
|
+
natural language such as English that could be compiled into executable
|
184
|
+
code and at the same time easily read by a human developer. According to
|
185
|
+
Knuth ``The practitioner of literate programming can be regarded as an
|
186
|
+
essayist, whose main concern is with exposition and excellence of
|
187
|
+
style.''
|
188
|
+
|
189
|
+
The idea of literate programming envolved into the idea of reproducible
|
190
|
+
research, in which all the data, software code, documentation, graphics
|
191
|
+
etc. needed to reproduce the research and its reports could be included
|
192
|
+
in a single document or set of documents that when distributed to peers
|
193
|
+
could be rerun generating the same output and reports.
|
194
|
+
|
195
|
+
The R community has put a great deal of effort in reproducible research.
|
196
|
+
In 2002, Sweave was introduced and it allowed mixing R code with Latex
|
197
|
+
generating hight quality PDF documents. Those documents could include
|
198
|
+
the code, the result of executing the code, graphics and text. This
|
199
|
+
contained the whole narrative to reproduce the research. But Sweave had
|
200
|
+
many problems and in 2012, Knitr, developed by Yihui Xie from RStudio
|
201
|
+
was released, solving many of the long lasting problems from Sweave and
|
202
|
+
including in one single package many extensions and add-on packages that
|
203
|
+
were necessary for Sweave.
|
204
|
+
|
205
|
+
With Knitr, R markdown was also developed, an extension the the Markdown
|
206
|
+
format. With R markdown and Knitr it is possible to generate reports in
|
207
|
+
a multitude of formats such as HTML, markdown, Latex, PDF, dvi, etc. R
|
208
|
+
markdown also allows the use of multiple programming languages in the
|
209
|
+
same document. In R markdown text is interspersed with code chunks that
|
210
|
+
can be executed and both the code as the result of executing the code
|
211
|
+
can become part of the final report. Although R markdown allows multiple
|
212
|
+
programming languages in the same document, only R and Python (with the
|
213
|
+
reticulate package) can persist variables between chunks. For other
|
214
|
+
languages, such as Ruby, every chunk will start a new process and thus
|
215
|
+
all data is lost between chunks, unless it is somehow stored in a data
|
216
|
+
file that is read by the next chunk.
|
217
|
+
|
218
|
+
Being able to persist data between chunks is critical for literate
|
219
|
+
programming otherwise the flow of the narrative is lost by all the
|
220
|
+
effort of having to save data and then reload it. Probably, because of
|
221
|
+
this impossibility, it is very rare to see any R markdown document
|
222
|
+
document in the Ruby community.
|
223
|
+
|
224
|
+
In the Python community, the same effort to have code and text in an
|
225
|
+
integrated environment started also on the first decade of 2000. In 2006
|
226
|
+
iPython 0.7.2 was released. In 2014, Fernando Pérez, spun off project
|
227
|
+
Jupyter from iPython creating a web-based interactive computation
|
228
|
+
environment. Jupyter can now be used with many languages, including Ruby
|
229
|
+
with the iruby gem (\url{https://github.com/SciRuby/iruby}). I am not
|
230
|
+
sure if multiple languages can be used in a Jupyter notebook.
|
231
|
+
|
232
|
+
\section{gKnitting a Document}\label{gknitting-a-document}
|
233
|
+
|
234
|
+
This document describes gKnit. gKnit uses Knitr and R markdown to knit a
|
235
|
+
document in Ruby or R and output it in any of the available formats for
|
236
|
+
R markdown. The only difference between gKnit and normal Knitr documents
|
237
|
+
is that gKnit runs atop of GraalVM, and Galaaz (an integration library
|
238
|
+
between Ruby and R). Another blog post on Galaaz and its integration
|
239
|
+
with ggplot2 can be found at:
|
240
|
+
\url{https://towardsdatascience.com/ruby-plotting-with-galaaz-an-example-of-tightly-coupling-ruby-and-r-in-graalvm-520b69e21021}.
|
241
|
+
With Galaaz, gKnit can knit documents in Ruby and R and both Ruby and R
|
242
|
+
execute on the same process and memory, variables, classes, etc. will be
|
243
|
+
preserved between chunks of code.
|
244
|
+
|
245
|
+
This is not a blog post on rmarkdown, and the interested user is
|
246
|
+
directed to
|
247
|
+
|
248
|
+
\begin{itemize}
|
249
|
+
\tightlist
|
250
|
+
\item
|
251
|
+
\url{https://rmarkdown.rstudio.com/} or
|
252
|
+
\item
|
253
|
+
\url{https://bookdown.org/yihui/rmarkdown/} for detailed information
|
254
|
+
on its capabilities and use.
|
255
|
+
\end{itemize}
|
256
|
+
|
257
|
+
Here, we will describe quickly the main aspects of R markdown, so the
|
258
|
+
user can start gKnitting Ruby and R documents quickly.
|
259
|
+
|
260
|
+
\subsection{The Yaml header}\label{the-yaml-header}
|
261
|
+
|
262
|
+
An R markdown document should start with a Yaml header and be stored in
|
263
|
+
a file with `.Rmd' extension. This document has the following header for
|
264
|
+
gKitting an HTML document.
|
265
|
+
|
266
|
+
\begin{verbatim}
|
267
|
+
---
|
268
|
+
title: "gKnit - Ruby and R Knitting with Galaaz in GraalVM"
|
269
|
+
author: "Rodrigo Botafogo"
|
270
|
+
tags: [Galaaz, Ruby, R, TruffleRuby, FastR, GraalVM, knitr, gknit]
|
271
|
+
date: "29 October 2018"
|
272
|
+
output:
|
273
|
+
html_document:
|
274
|
+
keep_md: true
|
275
|
+
---
|
276
|
+
\end{verbatim}
|
277
|
+
|
278
|
+
For more information on the options in the Yaml header, check
|
279
|
+
\url{https://bookdown.org/yihui/rmarkdown/html-document.html}.
|
280
|
+
|
281
|
+
\subsection{R Markdown formatting}\label{r-markdown-formatting}
|
282
|
+
|
283
|
+
Document formating can be done with simple markups such as:
|
284
|
+
|
285
|
+
\subsubsection{Headers}\label{headers}
|
286
|
+
|
287
|
+
\begin{verbatim}
|
288
|
+
# Header 1
|
289
|
+
|
290
|
+
## Header 2
|
291
|
+
|
292
|
+
### Header 3
|
293
|
+
\end{verbatim}
|
294
|
+
|
295
|
+
\subsubsection{Lists}\label{lists}
|
296
|
+
|
297
|
+
\begin{verbatim}
|
298
|
+
Unordered lists:
|
299
|
+
|
300
|
+
* Item 1
|
301
|
+
* Item 2
|
302
|
+
+ Item 2a
|
303
|
+
+ Item 2b
|
304
|
+
\end{verbatim}
|
305
|
+
|
306
|
+
\begin{verbatim}
|
307
|
+
Ordered Lists
|
308
|
+
|
309
|
+
1. Item 1
|
310
|
+
2. Item 2
|
311
|
+
3. Item 3
|
312
|
+
+ Item 3a
|
313
|
+
+ Item 3b
|
314
|
+
\end{verbatim}
|
315
|
+
|
316
|
+
Please, go to \url{https://rmarkdown.rstudio.com/authoring_basics.html},
|
317
|
+
for more R markdown formating.
|
318
|
+
|
319
|
+
\subsection{Code Chunks}\label{code-chunks}
|
320
|
+
|
321
|
+
Running and executing Ruby and R code is actually what really interests
|
322
|
+
us is this blog. Inserting a code chunk is done by adding code in a
|
323
|
+
block delimited by three back ticks followed by a block with the engine
|
324
|
+
name (r, ruby, rb, include, others), an optional chunk\_label and
|
325
|
+
optional options, as shown bellow:
|
326
|
+
|
327
|
+
\begin{verbatim}
|
328
|
+
```{engine_name [chunk_label], [chunk_options]}
|
329
|
+
```
|
330
|
+
\end{verbatim}
|
331
|
+
|
332
|
+
for instance, let's add an R chunk to the document labeled
|
333
|
+
`first\_r\_chunk'. In this case, the code should not be shown in the
|
334
|
+
document, so the option `echo=FALSE' was added.
|
335
|
+
|
336
|
+
\begin{verbatim}
|
337
|
+
```{r first_r_chunk, echo = FALSE}
|
338
|
+
```
|
339
|
+
\end{verbatim}
|
340
|
+
|
341
|
+
A description of the available chunk options can be found in the
|
342
|
+
documentation cited above.
|
343
|
+
|
344
|
+
For including a Ruby chunk, just change the name of the engine to ruby
|
345
|
+
as follows:
|
346
|
+
|
347
|
+
\begin{verbatim}
|
348
|
+
```{ruby first_ruby_chunk}
|
349
|
+
```
|
350
|
+
\end{verbatim}
|
351
|
+
|
352
|
+
In this example, the ruby chunk is called `first\_ruby\_chunk'. One
|
353
|
+
important aspect of chunk labels is that they cannot be duplicate. If a
|
354
|
+
chunk label is duplicate, the knitting will stop with an error.
|
355
|
+
|
356
|
+
\subsubsection{R chunks}\label{r-chunks}
|
357
|
+
|
358
|
+
Let's now add an R chunk to this document. In this example, a vector
|
359
|
+
`r\_vec' is created and a new function `redundat\_sum' is defined. The
|
360
|
+
chunk specification is
|
361
|
+
|
362
|
+
\begin{verbatim}
|
363
|
+
```{r data_creation}
|
364
|
+
r_vec <- c(1, 2, 3, 4, 5)
|
365
|
+
|
366
|
+
redef_sum <- function(...) {
|
367
|
+
Reduce(sum, as.list(...))
|
368
|
+
}
|
369
|
+
```
|
370
|
+
\end{verbatim}
|
371
|
+
|
372
|
+
and this is how it will look like once executed. From now on, we will
|
373
|
+
not show the chunk definition any longer.
|
374
|
+
|
375
|
+
\begin{Shaded}
|
376
|
+
\begin{Highlighting}[]
|
377
|
+
\NormalTok{r_vec <-}\StringTok{ }\KeywordTok{c}\NormalTok{(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{, }\DecValTok{4}\NormalTok{, }\DecValTok{5}\NormalTok{)}
|
378
|
+
|
379
|
+
\NormalTok{redef_sum <-}\StringTok{ }\ControlFlowTok{function}\NormalTok{(...) \{}
|
380
|
+
\KeywordTok{Reduce}\NormalTok{(sum, }\KeywordTok{as.list}\NormalTok{(...))}
|
381
|
+
\NormalTok{\}}
|
382
|
+
\end{Highlighting}
|
383
|
+
\end{Shaded}
|
384
|
+
|
385
|
+
We can, possibly in another chunk, access the vector and call the
|
386
|
+
function as follows:
|
387
|
+
|
388
|
+
\begin{Shaded}
|
389
|
+
\begin{Highlighting}[]
|
390
|
+
\KeywordTok{print}\NormalTok{(r_vec)}
|
391
|
+
\end{Highlighting}
|
392
|
+
\end{Shaded}
|
393
|
+
|
394
|
+
\begin{verbatim}
|
395
|
+
## [1] 1 2 3 4 5
|
396
|
+
\end{verbatim}
|
397
|
+
|
398
|
+
\begin{Shaded}
|
399
|
+
\begin{Highlighting}[]
|
400
|
+
\KeywordTok{print}\NormalTok{(}\KeywordTok{redef_sum}\NormalTok{(r_vec))}
|
401
|
+
\end{Highlighting}
|
402
|
+
\end{Shaded}
|
403
|
+
|
404
|
+
\begin{verbatim}
|
405
|
+
## [1] 15
|
406
|
+
\end{verbatim}
|
407
|
+
|
408
|
+
\subsubsection{Ruby chunks}\label{ruby-chunks}
|
409
|
+
|
410
|
+
In the same way that an R chunk was created, let's now create a Ruby
|
411
|
+
chunk. One important aspect of Ruby is that in Ruby every evaluation of
|
412
|
+
a chunk occurs on its own local scope, so, creating a variable in a
|
413
|
+
chunk will be out of scope in the next chunk. To make sure that
|
414
|
+
variables are available between chunks, they should be made global.
|
415
|
+
|
416
|
+
In this chunk, variable `\$a', `\$b' and `\$c' are standard Ruby
|
417
|
+
variables and `\$vec' and `\$vec2' are two vectors created by a call to
|
418
|
+
FastR. It should be clear that there is no requirement in gknit to call
|
419
|
+
or use R functions. gKnit will knit standard Ruby code, or even general
|
420
|
+
text without code.
|
421
|
+
|
422
|
+
\begin{Shaded}
|
423
|
+
\begin{Highlighting}[]
|
424
|
+
\DataTypeTok{$a}\NormalTok{ = [}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{]}
|
425
|
+
\DataTypeTok{$b}\NormalTok{ = }\StringTok{"US$ 250.000"}
|
426
|
+
\DataTypeTok{$c}\NormalTok{ = }\StringTok{"Inline text in a Heading"}
|
427
|
+
|
428
|
+
\DataTypeTok{$vec}\NormalTok{ = R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{)}
|
429
|
+
\DataTypeTok{$vec2}\NormalTok{ = R.c(}\DecValTok{10}\NormalTok{, }\DecValTok{20}\NormalTok{, }\DecValTok{30}\NormalTok{)}
|
430
|
+
\end{Highlighting}
|
431
|
+
\end{Shaded}
|
432
|
+
|
433
|
+
In this next block, variables `\$a', `\$vec' and `\$vec2' are used and
|
434
|
+
printed.
|
435
|
+
|
436
|
+
\begin{Shaded}
|
437
|
+
\begin{Highlighting}[]
|
438
|
+
\NormalTok{puts }\DataTypeTok{$a}
|
439
|
+
\NormalTok{puts }\DataTypeTok{$vec}\NormalTok{ * }\DataTypeTok{$vec2}
|
440
|
+
\end{Highlighting}
|
441
|
+
\end{Shaded}
|
442
|
+
|
443
|
+
\begin{verbatim}
|
444
|
+
## 1
|
445
|
+
## 2
|
446
|
+
## 3
|
447
|
+
## [1] 10 40 90
|
448
|
+
\end{verbatim}
|
449
|
+
|
450
|
+
\subsubsection{Accessing R from Ruby}\label{accessing-r-from-ruby}
|
451
|
+
|
452
|
+
One of the nice aspects of Galaaz on GraalVM, is that variables and
|
453
|
+
functions defined in R, can be easily accessed from Ruby. This next
|
454
|
+
chunk, reads data from R and uses the `redef\_fun' function defined
|
455
|
+
previously. To access an R variable from Ruby the `\textasciitilde{}'
|
456
|
+
function shoud be applied to the Ruby symbol representing the R
|
457
|
+
variable. Since the R variable is called `r\_vec', in Ruby, the symbol
|
458
|
+
to acess it is `:r\_vec' and thus `\textasciitilde{}:r\_vec' retrieves
|
459
|
+
the value of the variable.
|
460
|
+
|
461
|
+
\begin{Shaded}
|
462
|
+
\begin{Highlighting}[]
|
463
|
+
\NormalTok{puts ~}\StringTok{:r_vec}
|
464
|
+
\end{Highlighting}
|
465
|
+
\end{Shaded}
|
466
|
+
|
467
|
+
\begin{verbatim}
|
468
|
+
## [1] 1 2 3 4 5
|
469
|
+
\end{verbatim}
|
470
|
+
|
471
|
+
In order to call an R function, the `R.' module is used as follows
|
472
|
+
|
473
|
+
\begin{Shaded}
|
474
|
+
\begin{Highlighting}[]
|
475
|
+
\NormalTok{puts R.redef_sum(}\DataTypeTok{$vec}\NormalTok{)}
|
476
|
+
\end{Highlighting}
|
477
|
+
\end{Shaded}
|
478
|
+
|
479
|
+
\begin{verbatim}
|
480
|
+
## [1] 6
|
481
|
+
\end{verbatim}
|
482
|
+
|
483
|
+
\subsubsection{Inline Ruby code}\label{inline-ruby-code}
|
484
|
+
|
485
|
+
Knitr allows inserting R inline by adding `r code` . Unfortunately, this
|
486
|
+
is not possible with Ruby code as there is no provision in knitr for
|
487
|
+
adding this kind of inline engine. However, gKnit allows adding inline
|
488
|
+
Ruby code with the `rb' engine. The following text will create and
|
489
|
+
inline Ruby text:
|
490
|
+
|
491
|
+
\begin{verbatim}
|
492
|
+
This is some text with inline Ruby accessing variable \$b which has value:
|
493
|
+
```{rb puts $b}
|
494
|
+
```
|
495
|
+
and is followed by some other text!
|
496
|
+
\end{verbatim}
|
497
|
+
|
498
|
+
The result of executing the above ckunk is the following sentence with
|
499
|
+
inline Ruby code
|
500
|
+
|
501
|
+
This is some text with inline Ruby accessing variable \$b which has
|
502
|
+
value: US\$ 250.000 and is followed by some other text!
|
503
|
+
|
504
|
+
In an inline block, it is possible to execute multiple Ruby statements
|
505
|
+
by adding a semicolom between them:
|
506
|
+
|
507
|
+
\begin{verbatim}
|
508
|
+
Multiple statements in the 'rb' engine use semicolom:
|
509
|
+
```{rb puts $a, puts $b}
|
510
|
+
```
|
511
|
+
\end{verbatim}
|
512
|
+
|
513
|
+
Multiple statements in the `rb' engine use semicolom: 1 2 3 US\$ 250.000
|
514
|
+
|
515
|
+
\subsubsection{Inline text in a Heading}\label{inline-text-in-a-heading}
|
516
|
+
|
517
|
+
Sometimes one wants to add an inline text in a heading. To do that in
|
518
|
+
Ruby the whole heading needs to be returned by the inline Ruby engine.
|
519
|
+
For example the heading above, was created by the following chunk:
|
520
|
+
|
521
|
+
\begin{verbatim}
|
522
|
+
```{rb puts "### #{$c}"}
|
523
|
+
```
|
524
|
+
\end{verbatim}
|
525
|
+
|
526
|
+
Remember that variable `\$\c' was defined in a previous Ruby chunk and
|
527
|
+
is now being used to create the section heading for this section.
|
528
|
+
|
529
|
+
\subsubsection{Including Ruby files}\label{including-ruby-files}
|
530
|
+
|
531
|
+
R is a language that was created to be easy and fast for statisticians
|
532
|
+
to use. It was not a language to be used for developing large systems.
|
533
|
+
Of course, there are large systems and libraries in R, but the focus of
|
534
|
+
the language is for developing statistical models and distribute that to
|
535
|
+
peers.
|
536
|
+
|
537
|
+
Ruby on the other hand, is a language for large software development.
|
538
|
+
Systems written in Ruby will have dozens or hundreds of files. In order
|
539
|
+
to document a large system with literate programming we cannot expect
|
540
|
+
the developer to add all the files in a single `.Rmd' file. gKnit
|
541
|
+
provides the `include' chunk engine to include a Ruby file as if it had
|
542
|
+
being typed in the `.Rmd' file.
|
543
|
+
|
544
|
+
To include a file the following chunk should be created, whre is the
|
545
|
+
name of the file to be include and where the extension, if it is `.rb',
|
546
|
+
does not need to be added. If the `relative' option is not included,
|
547
|
+
then it is treated as TRUE. When `relative' is true, `require\_relative'
|
548
|
+
semantics is used to load the file, when false, Ruby's \$LOAD\_PATH is
|
549
|
+
searched to find the file and it is 'require'd.
|
550
|
+
|
551
|
+
\begin{verbatim}
|
552
|
+
```{include <filename>, relative = <TRUE/FALSE>}
|
553
|
+
```
|
554
|
+
\end{verbatim}
|
555
|
+
|
556
|
+
Here we include file `model.rb' which is in the same directory of this
|
557
|
+
blog. This code uses R `caret' package to split a dataset in a train and
|
558
|
+
test sets.
|
559
|
+
|
560
|
+
\begin{verbatim}
|
561
|
+
```{include model}
|
562
|
+
```
|
563
|
+
\end{verbatim}
|
564
|
+
|
565
|
+
\begin{verbatim}
|
566
|
+
require 'galaaz'
|
567
|
+
|
568
|
+
# Loads the R 'caret' package. If not present, installs it
|
569
|
+
R.install_and_loads 'caret'
|
570
|
+
|
571
|
+
class Model
|
572
|
+
|
573
|
+
attr_reader :data
|
574
|
+
attr_reader :test
|
575
|
+
attr_reader :train
|
576
|
+
|
577
|
+
#==========================================================
|
578
|
+
#
|
579
|
+
#==========================================================
|
580
|
+
|
581
|
+
def initialize(data, percent_train:, seed: 123)
|
582
|
+
|
583
|
+
R.set__seed(seed)
|
584
|
+
@data = data
|
585
|
+
@percent_train = percent_train
|
586
|
+
@seed = seed
|
587
|
+
|
588
|
+
end
|
589
|
+
|
590
|
+
#==========================================================
|
591
|
+
#
|
592
|
+
#==========================================================
|
593
|
+
|
594
|
+
def partition(field)
|
595
|
+
|
596
|
+
train_index =
|
597
|
+
R.createDataPartition(@data.send(field), p: @percet_train,
|
598
|
+
list: false, times: 1)
|
599
|
+
@train = @data[train_index, :all]
|
600
|
+
@test = @data[-train_index, :all]
|
601
|
+
|
602
|
+
end
|
603
|
+
|
604
|
+
end
|
605
|
+
\end{verbatim}
|
606
|
+
|
607
|
+
\begin{Shaded}
|
608
|
+
\begin{Highlighting}[]
|
609
|
+
\NormalTok{mtcars = ~}\StringTok{:mtcars}
|
610
|
+
\NormalTok{model = }\DataTypeTok{Model}\NormalTok{.new(mtcars, }\StringTok{percent_train: }\FloatTok{0.8}\NormalTok{)}
|
611
|
+
\NormalTok{model.partition(}\StringTok{:mpg}\NormalTok{)}
|
612
|
+
\NormalTok{puts model.train.head}
|
613
|
+
\NormalTok{puts model.test.head}
|
614
|
+
\end{Highlighting}
|
615
|
+
\end{Shaded}
|
616
|
+
|
617
|
+
\begin{verbatim}
|
618
|
+
## mpg cyl disp hp drat wt qsec vs am gear carb
|
619
|
+
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
|
620
|
+
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
|
621
|
+
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
|
622
|
+
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
|
623
|
+
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
|
624
|
+
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
|
625
|
+
## mpg cyl disp hp drat wt qsec vs am gear carb
|
626
|
+
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
|
627
|
+
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
|
628
|
+
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
|
629
|
+
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
|
630
|
+
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
|
631
|
+
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
|
632
|
+
\end{verbatim}
|
633
|
+
|
634
|
+
\subsubsection{Documenting Gems}\label{documenting-gems}
|
635
|
+
|
636
|
+
\begin{verbatim}
|
637
|
+
# Copyright (c) 2017 Oracle and/or its affiliates. All rights reserved. This
|
638
|
+
# code is released under a tri EPL/GPL/LGPL license. You can use it,
|
639
|
+
# redistribute it and/or modify it under the terms of the:
|
640
|
+
#
|
641
|
+
# Eclipse Public License version 1.0, or
|
642
|
+
# GNU General Public License version 2, or
|
643
|
+
# GNU Lesser General Public License version 2.1.
|
644
|
+
|
645
|
+
warn "#{File.basename(__FILE__)}: warning: callcc is obsolete; use Fiber instead"
|
646
|
+
|
647
|
+
class Continuation
|
648
|
+
def initialize
|
649
|
+
@fiber = Fiber.current
|
650
|
+
end
|
651
|
+
|
652
|
+
def call
|
653
|
+
if Fiber.current != @fiber
|
654
|
+
raise 'continuation called across fiber'
|
655
|
+
end
|
656
|
+
raise 'Continuations are unsupported on TruffleRuby'
|
657
|
+
end
|
658
|
+
end
|
659
|
+
|
660
|
+
module Kernel
|
661
|
+
def callcc
|
662
|
+
yield Continuation.new
|
663
|
+
end
|
664
|
+
module_function :callcc
|
665
|
+
end
|
666
|
+
\end{verbatim}
|
667
|
+
|
668
|
+
\subsection{Converting to PDF}\label{converting-to-pdf}
|
669
|
+
|
670
|
+
One of the beauties of knitr is that the same input can be converted to
|
671
|
+
many different outputs. One very useful format, is, of course, PDF. In
|
672
|
+
order to converted an R markdown file to PDF it is necessary to have
|
673
|
+
LaTeX installed on the system. We will not explain here how to install
|
674
|
+
LaTeX as there are plenty of documents on the web showing how to
|
675
|
+
proceed.
|
676
|
+
|
677
|
+
gKnit comes with a simple LaTeX style file for gknitting this blog as a
|
678
|
+
PDF document. Here is the Yaml header to generate this blog in PDF
|
679
|
+
format instead of HTML:
|
680
|
+
|
681
|
+
\begin{verbatim}
|
682
|
+
---
|
683
|
+
title: "gKnit - Ruby and R Knitting with Galaaz in GraalVM"
|
684
|
+
author: "Rodrigo Botafogo"
|
685
|
+
tags: [Galaaz, Ruby, R, TruffleRuby, FastR, GraalVM, knitr, gknit]
|
686
|
+
date: "29 October 2018"
|
687
|
+
output:
|
688
|
+
pdf_document:
|
689
|
+
includes:
|
690
|
+
in_header: ["../../sty/galaaz.sty"]
|
691
|
+
number_sections: yes
|
692
|
+
---
|
693
|
+
\end{verbatim}
|
694
|
+
|
695
|
+
\section{Conclusion}\label{conclusion}
|
696
|
+
|
697
|
+
\section{Installing gKnit}\label{installing-gknit}
|
698
|
+
|
699
|
+
\subsection{Prerequisites}\label{prerequisites}
|
700
|
+
|
701
|
+
\begin{itemize}
|
702
|
+
\tightlist
|
703
|
+
\item
|
704
|
+
GraalVM (\textgreater{}= rc7)
|
705
|
+
\item
|
706
|
+
TruffleRuby
|
707
|
+
\item
|
708
|
+
FastR
|
709
|
+
\end{itemize}
|
710
|
+
|
711
|
+
The following R packages will be automatically installed when necessary,
|
712
|
+
but could be installed prior to using gKnit if desired:
|
713
|
+
|
714
|
+
\begin{itemize}
|
715
|
+
\tightlist
|
716
|
+
\item
|
717
|
+
ggplot2
|
718
|
+
\item
|
719
|
+
gridExtra
|
720
|
+
\item
|
721
|
+
knitr
|
722
|
+
\end{itemize}
|
723
|
+
|
724
|
+
Installation of R packages requires a development environment and can be
|
725
|
+
time consuming. In Linux, the gnu compiler and tools should be enough. I
|
726
|
+
am not sure what is needed on the Mac.
|
727
|
+
|
728
|
+
\subsection{Preparation}\label{preparation}
|
729
|
+
|
730
|
+
\begin{itemize}
|
731
|
+
\tightlist
|
732
|
+
\item
|
733
|
+
gem install galaaz
|
734
|
+
\end{itemize}
|
735
|
+
|
736
|
+
\subsection{Usage}\label{usage}
|
737
|
+
|
738
|
+
\begin{itemize}
|
739
|
+
\tightlist
|
740
|
+
\item
|
741
|
+
gknit {[}filename{]}
|
742
|
+
\end{itemize}
|
743
|
+
|
744
|
+
|
745
|
+
\end{document}
|