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
@@ -0,0 +1,44 @@
|
|
1
|
+
\relax
|
2
|
+
\providecommand\hyper@newdestlabel[2]{}
|
3
|
+
\providecommand\HyperFirstAtBeginDocument{\AtBeginDocument}
|
4
|
+
\HyperFirstAtBeginDocument{\ifx\hyper@anchor\@undefined
|
5
|
+
\global\let\oldcontentsline\contentsline
|
6
|
+
\gdef\contentsline#1#2#3#4{\oldcontentsline{#1}{#2}{#3}}
|
7
|
+
\global\let\oldnewlabel\newlabel
|
8
|
+
\gdef\newlabel#1#2{\newlabelxx{#1}#2}
|
9
|
+
\gdef\newlabelxx#1#2#3#4#5#6{\oldnewlabel{#1}{{#2}{#3}}}
|
10
|
+
\AtEndDocument{\ifx\hyper@anchor\@undefined
|
11
|
+
\let\contentsline\oldcontentsline
|
12
|
+
\let\newlabel\oldnewlabel
|
13
|
+
\fi}
|
14
|
+
\fi}
|
15
|
+
\global\let\hyper@last\relax
|
16
|
+
\gdef\HyperFirstAtBeginDocument#1{#1}
|
17
|
+
\providecommand\HyField@AuxAddToFields[1]{}
|
18
|
+
\providecommand\HyField@AuxAddToCoFields[2]{}
|
19
|
+
\providecommand*\new@tpo@label[2]{}
|
20
|
+
\@writefile{toc}{\contentsline {section}{\numberline {1}Introduction}{1}{section.1}}
|
21
|
+
\newlabel{introduction}{{1}{1}{Introduction}{section.1}{}}
|
22
|
+
\@writefile{toc}{\contentsline {subsection}{\numberline {1.1}What does Galaaz mean}{1}{subsection.1.1}}
|
23
|
+
\newlabel{what-does-galaaz-mean}{{1.1}{1}{What does Galaaz mean}{subsection.1.1}{}}
|
24
|
+
\@writefile{toc}{\contentsline {section}{\numberline {2}Galaaz Demo}{2}{section.2}}
|
25
|
+
\newlabel{galaaz-demo}{{2}{2}{Galaaz Demo}{section.2}{}}
|
26
|
+
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Prerequisites}{2}{subsection.2.1}}
|
27
|
+
\newlabel{prerequisites}{{2.1}{2}{Prerequisites}{subsection.2.1}{}}
|
28
|
+
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Preparation}{2}{subsection.2.2}}
|
29
|
+
\newlabel{preparation}{{2.2}{2}{Preparation}{subsection.2.2}{}}
|
30
|
+
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Running the demo}{2}{subsection.2.3}}
|
31
|
+
\newlabel{running-the-demo}{{2.3}{2}{Running the demo}{subsection.2.3}{}}
|
32
|
+
\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Running other demos}{2}{subsection.2.4}}
|
33
|
+
\newlabel{running-other-demos}{{2.4}{2}{Running other demos}{subsection.2.4}{}}
|
34
|
+
\@writefile{toc}{\contentsline {section}{\numberline {3}The demo code}{3}{section.3}}
|
35
|
+
\newlabel{the-demo-code}{{3}{3}{The demo code}{section.3}{}}
|
36
|
+
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces Midwest Plot}}{4}{figure.1}}
|
37
|
+
\@writefile{toc}{\contentsline {section}{\numberline {4}An extension to the example}{4}{section.4}}
|
38
|
+
\newlabel{an-extension-to-the-example}{{4}{4}{An extension to the example}{section.4}{}}
|
39
|
+
\@writefile{toc}{\contentsline {section}{\numberline {5}Conclusion}{7}{section.5}}
|
40
|
+
\newlabel{conclusion}{{5}{7}{Conclusion}{section.5}{}}
|
41
|
+
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces Midwest Plot with `glm' function and modified theme}}{8}{figure.2}}
|
42
|
+
\newlabel{LastPage}{{}{8}{}{page.8}{}}
|
43
|
+
\xdef\lastpage@lastpage{8}
|
44
|
+
\xdef\lastpage@lastpageHy{8}
|
Binary file
|
@@ -133,7 +133,7 @@ $(document).ready(function () {
|
|
133
133
|
<div id="introduction" class="section level1">
|
134
134
|
<h1>Introduction</h1>
|
135
135
|
<p>Galaaz is a system for tightly coupling Ruby and R. Ruby is a powerful language, with a large community, a very large set of libraries and great for web development. However, it lacks libraries for data science, statistics, scientific plotting and machine learning. On the other hand, R is considered one of the most powerful languages for solving all of the above problems. Maybe the strongest competitor to R is Python with libraries such as NumPy, Panda, SciPy, SciKit-Learn and a couple more.</p>
|
136
|
-
<p>With Galaaz we do not intend to re-implement any of the scientific libraries in R, we allow for very tight coupling between the two languages to the point that the Ruby developer does not need to know that there is an R engine running. For this to happen we use new technologies provided by Oracle
|
136
|
+
<p>With Galaaz we do not intend to re-implement any of the scientific libraries in R, we allow for very tight coupling between the two languages to the point that the Ruby developer does not need to know that there is an R engine running. For this to happen we use new technologies provided by Oracle: GraalVM, TruffleRuby and FastR:</p>
|
137
137
|
<pre><code> GraalVM is a universal virtual machine for running applications written in JavaScript,
|
138
138
|
Python 3, Ruby, R, JVM-based languages like Java, Scala, Kotlin, and LLVM-based languages
|
139
139
|
such as C and C++.
|
@@ -143,7 +143,7 @@ $(document).ready(function () {
|
|
143
143
|
Oracle Database, or MySQL.
|
144
144
|
|
145
145
|
GraalVM allows you to write polyglot applications with a seamless way to pass values from one
|
146
|
-
language to another. With GraalVM there is no copying or
|
146
|
+
language to another. With GraalVM there is no copying or marshaling necessary as it is with
|
147
147
|
other polyglot systems. This lets you achieve high performance when language boundaries are
|
148
148
|
crossed. Most of the time there is no additional cost for crossing a language boundary at all.
|
149
149
|
|
@@ -156,6 +156,13 @@ $(document).ready(function () {
|
|
156
156
|
|
157
157
|
With GraalVM we aim to allow developers to freely choose the right language for the task at
|
158
158
|
hand without making compromises.</code></pre>
|
159
|
+
<p>Interested readers should also check out the following sites:</p>
|
160
|
+
<ul>
|
161
|
+
<li><a href="https://www.graalvm.org/">GraalVM Home</a></li>
|
162
|
+
<li><a href="https://github.com/oracle/truffleruby">TruffleRuby</a></li>
|
163
|
+
<li><a href="https://github.com/oracle/fastr">FastR</a></li>
|
164
|
+
<li><a href="https://medium.com/graalvm/faster-r-with-fastr-4b8db0e0dceb">Faster R with FastR</a></li>
|
165
|
+
</ul>
|
159
166
|
<div id="what-does-galaaz-mean" class="section level2">
|
160
167
|
<h2>What does Galaaz mean</h2>
|
161
168
|
<p>Galaaz is the Portuguese name for “Galahad”. From Wikipedia:</p>
|
@@ -273,8 +280,8 @@ plot(gg)</code></pre>
|
|
273
280
|
<div id="an-extension-to-the-example" class="section level1">
|
274
281
|
<h1>An extension to the example</h1>
|
275
282
|
<p>If both codes are so similar, then why would one use Ruby instead of R and what good is galaaz after all?</p>
|
276
|
-
<p>Ruby is a modern OO language with numerous very useful constructs such as classes, modules, blocks, procs, etc. The example above focus on the coupling of both languages, and does not show the use of other Ruby constructs. In the following example, we will show a more complex example using other Ruby constructs. This is
|
277
|
-
<p>Let’s imagine that we work in a corporation that has its plot themes. So, it has defined a ‘CorpTheme’ module. Plots in this corporation should not have grids, numbers in labels should not use scientific notation and the
|
283
|
+
<p>Ruby is a modern OO language with numerous very useful constructs such as classes, modules, blocks, procs, etc. The example above focus on the coupling of both languages, and does not show the use of other Ruby constructs. In the following example, we will show a more complex example using other Ruby constructs. This is certainly not a very well written and robust Ruby code, but it give the idea of how Ruby and R are strongly coupled.</p>
|
284
|
+
<p>Let’s imagine that we work in a corporation that has its plot themes. So, it has defined a ‘CorpTheme’ module. Plots in this corporation should not have grids, numbers in labels should not use scientific notation and the preferred color is blue.</p>
|
278
285
|
<pre class="galaaz"><code># corp_theme.rb
|
279
286
|
# defines the corporate theme for all plots
|
280
287
|
|
@@ -427,6 +434,12 @@ sp.plot('svg')
|
|
427
434
|
<p class="caption">Midwest Plot with ‘glm’ function and modified theme</p>
|
428
435
|
</div>
|
429
436
|
</div>
|
437
|
+
<div id="conclusion" class="section level1">
|
438
|
+
<h1>Conclusion</h1>
|
439
|
+
<p>R is a very powerful language for statistical analysis, data analytics, machine learning, plotting and many other scientific applications with a very large package ecosystem. However R is often considered hard to learn and lacking modern computer languages constructs such as object oriented classes, modules, lambdas, etc. For this reason, many developers have started or switched from R to Python.</p>
|
440
|
+
<p>With Galaaz, R programmers can almost transparently migrate from R to Ruby, since syntax is almost identical and they have fastR as the R engine. FastR, by most benchmarks, can be orders of magnitude faster than Gnu R. Further, by using Galaaz the R developer can start (slowly if needed) using all of Ruby’s constructs and libraries that nicely complement R packages.</p>
|
441
|
+
<p>For the Ruby developer, Galaaz allows the immediate use of R functions completely transparently. As shown in the second example above, class ScatterPlot completely hides all the details an R calls from the Ruby developer, furthermore Galaaz is powered by TruffleRuby that can also be orders of magnitude faster than MRI Ruby.</p>
|
442
|
+
</div>
|
430
443
|
|
431
444
|
|
432
445
|
|
@@ -0,0 +1,10 @@
|
|
1
|
+
\BOOKMARK [1][-]{section.1}{\376\377\000I\000n\000t\000r\000o\000d\000u\000c\000t\000i\000o\000n}{}% 1
|
2
|
+
\BOOKMARK [2][-]{subsection.1.1}{\376\377\000W\000h\000a\000t\000\040\000d\000o\000e\000s\000\040\000G\000a\000l\000a\000a\000z\000\040\000m\000e\000a\000n}{section.1}% 2
|
3
|
+
\BOOKMARK [1][-]{section.2}{\376\377\000G\000a\000l\000a\000a\000z\000\040\000D\000e\000m\000o}{}% 3
|
4
|
+
\BOOKMARK [2][-]{subsection.2.1}{\376\377\000P\000r\000e\000r\000e\000q\000u\000i\000s\000i\000t\000e\000s}{section.2}% 4
|
5
|
+
\BOOKMARK [2][-]{subsection.2.2}{\376\377\000P\000r\000e\000p\000a\000r\000a\000t\000i\000o\000n}{section.2}% 5
|
6
|
+
\BOOKMARK [2][-]{subsection.2.3}{\376\377\000R\000u\000n\000n\000i\000n\000g\000\040\000t\000h\000e\000\040\000d\000e\000m\000o}{section.2}% 6
|
7
|
+
\BOOKMARK [2][-]{subsection.2.4}{\376\377\000R\000u\000n\000n\000i\000n\000g\000\040\000o\000t\000h\000e\000r\000\040\000d\000e\000m\000o\000s}{section.2}% 7
|
8
|
+
\BOOKMARK [1][-]{section.3}{\376\377\000T\000h\000e\000\040\000d\000e\000m\000o\000\040\000c\000o\000d\000e}{}% 8
|
9
|
+
\BOOKMARK [1][-]{section.4}{\376\377\000A\000n\000\040\000e\000x\000t\000e\000n\000s\000i\000o\000n\000\040\000t\000o\000\040\000t\000h\000e\000\040\000e\000x\000a\000m\000p\000l\000e}{}% 9
|
10
|
+
\BOOKMARK [1][-]{section.5}{\376\377\000C\000o\000n\000c\000l\000u\000s\000i\000o\000n}{}% 10
|
Binary file
|
@@ -0,0 +1,630 @@
|
|
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={Ruby Plotting with Galaaz},
|
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{Ruby Plotting with Galaaz}
|
118
|
+
\pretitle{\vspace{\droptitle}\centering\huge}
|
119
|
+
\posttitle{\par}
|
120
|
+
\subtitle{An example of tightly coupling Ruby and R in GraalVM}
|
121
|
+
\author{Rodrigo Botafogo}
|
122
|
+
\preauthor{\centering\large\emph}
|
123
|
+
\postauthor{\par}
|
124
|
+
\predate{\centering\large\emph}
|
125
|
+
\postdate{\par}
|
126
|
+
\date{16 October 2018}
|
127
|
+
|
128
|
+
% usar portugues do Brasil
|
129
|
+
% \usepackage[brazilian]{babel}
|
130
|
+
\usepackage[utf8]{inputenc}
|
131
|
+
|
132
|
+
\usepackage{geometry}
|
133
|
+
\geometry{a4paper, top=1in}
|
134
|
+
|
135
|
+
% necessários para uso com kableExtra
|
136
|
+
\usepackage{longtable}
|
137
|
+
\usepackage{multirow}
|
138
|
+
\usepackage[table]{xcolor}
|
139
|
+
\usepackage{wrapfig}
|
140
|
+
\usepackage{float}
|
141
|
+
\usepackage{colortbl}
|
142
|
+
\usepackage{pdflscape}
|
143
|
+
\usepackage{tabu}
|
144
|
+
\usepackage{threeparttable}
|
145
|
+
\usepackage[normalem]{ulem}
|
146
|
+
|
147
|
+
\usepackage{bbm}
|
148
|
+
\usepackage{booktabs}
|
149
|
+
\usepackage{expex}
|
150
|
+
|
151
|
+
\usepackage{graphicx}
|
152
|
+
\usepackage{fancyhdr}
|
153
|
+
\pagestyle{fancy}
|
154
|
+
\fancyhf{}
|
155
|
+
|
156
|
+
\usepackage{lipsum}
|
157
|
+
|
158
|
+
% disponibilizar o comando lastpage
|
159
|
+
\usepackage{lastpage}
|
160
|
+
|
161
|
+
% tamanho do font padrão 11pt
|
162
|
+
\usepackage[fontsize=10pt]{scrextend}
|
163
|
+
|
164
|
+
% comandos para formatar uma tabela
|
165
|
+
\usepackage{array}
|
166
|
+
\newcolumntype{L}[1]{>{\raggedright\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
167
|
+
\newcolumntype{C}[1]{>{\centering\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
168
|
+
\newcolumntype{R}[1]{>{\raggedleft\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
169
|
+
|
170
|
+
% necessário para importar outros arquivos latex
|
171
|
+
\usepackage{import}
|
172
|
+
|
173
|
+
\newcommand{\RtoLatex}[2]{\newcommand{#1}{#2}}
|
174
|
+
%\newcommand{\atraso}[1]{\color{red} \textbf {Tempo desde a Assinatura do Contrato: #1 dias}}
|
175
|
+
|
176
|
+
\begin{document}
|
177
|
+
\maketitle
|
178
|
+
|
179
|
+
\section{Introduction}\label{introduction}
|
180
|
+
|
181
|
+
Galaaz is a system for tightly coupling Ruby and R. Ruby is a powerful
|
182
|
+
language, with a large community, a very large set of libraries and
|
183
|
+
great for web development. However, it lacks libraries for data science,
|
184
|
+
statistics, scientific plotting and machine learning. On the other hand,
|
185
|
+
R is considered one of the most powerful languages for solving all of
|
186
|
+
the above problems. Maybe the strongest competitor to R is Python with
|
187
|
+
libraries such as NumPy, Panda, SciPy, SciKit-Learn and a couple more.
|
188
|
+
|
189
|
+
With Galaaz we do not intend to re-implement any of the scientific
|
190
|
+
libraries in R, we allow for very tight coupling between the two
|
191
|
+
languages to the point that the Ruby developer does not need to know
|
192
|
+
that there is an R engine running. For this to happen we use new
|
193
|
+
technologies provided by Oracle: GraalVM, TruffleRuby and FastR:
|
194
|
+
|
195
|
+
\begin{verbatim}
|
196
|
+
GraalVM is a universal virtual machine for running applications written in JavaScript,
|
197
|
+
Python 3, Ruby, R, JVM-based languages like Java, Scala, Kotlin, and LLVM-based languages
|
198
|
+
such as C and C++.
|
199
|
+
|
200
|
+
GraalVM removes the isolation between programming languages and enables interoperability in a
|
201
|
+
shared runtime. It can run either standalone or in the context of OpenJDK, Node.js,
|
202
|
+
Oracle Database, or MySQL.
|
203
|
+
|
204
|
+
GraalVM allows you to write polyglot applications with a seamless way to pass values from one
|
205
|
+
language to another. With GraalVM there is no copying or marshaling necessary as it is with
|
206
|
+
other polyglot systems. This lets you achieve high performance when language boundaries are
|
207
|
+
crossed. Most of the time there is no additional cost for crossing a language boundary at all.
|
208
|
+
|
209
|
+
Often developers have to make uncomfortable compromises that require them to rewrite
|
210
|
+
their software in other languages. For example:
|
211
|
+
|
212
|
+
* “That library is not available in my language. I need to rewrite it.”
|
213
|
+
* “That language would be the perfect fit for my problem, but we cannot run it in our environment.”
|
214
|
+
* “That problem is already solved in my language, but the language is too slow.”
|
215
|
+
|
216
|
+
With GraalVM we aim to allow developers to freely choose the right language for the task at
|
217
|
+
hand without making compromises.
|
218
|
+
\end{verbatim}
|
219
|
+
|
220
|
+
Interested readers should also check out the following sites:
|
221
|
+
|
222
|
+
\begin{itemize}
|
223
|
+
\tightlist
|
224
|
+
\item
|
225
|
+
\href{https://www.graalvm.org/}{GraalVM Home}
|
226
|
+
\item
|
227
|
+
\href{https://github.com/oracle/truffleruby}{TruffleRuby}
|
228
|
+
\item
|
229
|
+
\href{https://github.com/oracle/fastr}{FastR}
|
230
|
+
\item
|
231
|
+
\href{https://medium.com/graalvm/faster-r-with-fastr-4b8db0e0dceb}{Faster
|
232
|
+
R with FastR}
|
233
|
+
\end{itemize}
|
234
|
+
|
235
|
+
\subsection{What does Galaaz mean}\label{what-does-galaaz-mean}
|
236
|
+
|
237
|
+
Galaaz is the Portuguese name for ``Galahad''. From Wikipedia:
|
238
|
+
|
239
|
+
\begin{verbatim}
|
240
|
+
Sir Galahad (sometimes referred to as Galeas or Galath),
|
241
|
+
in Arthurian legend, is a knight of King Arthur's Round Table and one of the three
|
242
|
+
achievers of the Holy Grail. He is the illegitimate son of Sir Lancelot and Elaine of
|
243
|
+
Corbenic, and is renowned for his gallantry and purity as the most perfect of all knights.
|
244
|
+
Emerging quite late in the medieval Arthurian tradition, Sir Galahad first appears in the
|
245
|
+
Lancelot–Grail cycle, and his story is taken up in later works such as the Post-Vulgate
|
246
|
+
Cycle and Sir Thomas Malory's Le Morte d'Arthur. His name should not be mistaken with
|
247
|
+
Galehaut, a different knight from Arthurian legend.
|
248
|
+
\end{verbatim}
|
249
|
+
|
250
|
+
\section{Galaaz Demo}\label{galaaz-demo}
|
251
|
+
|
252
|
+
\subsection{Prerequisites}\label{prerequisites}
|
253
|
+
|
254
|
+
\begin{itemize}
|
255
|
+
\tightlist
|
256
|
+
\item
|
257
|
+
GraalVM (\textgreater{}= rc7)
|
258
|
+
\item
|
259
|
+
TruffleRuby
|
260
|
+
\item
|
261
|
+
FastR
|
262
|
+
\end{itemize}
|
263
|
+
|
264
|
+
The following R packages will be automatically installed when necessary,
|
265
|
+
but could be installed prior to the demo if desired:
|
266
|
+
|
267
|
+
\begin{itemize}
|
268
|
+
\tightlist
|
269
|
+
\item
|
270
|
+
ggplot2
|
271
|
+
\item
|
272
|
+
gridExtra
|
273
|
+
\end{itemize}
|
274
|
+
|
275
|
+
Installation of R packages requires a development environment. In Linux,
|
276
|
+
the gnu compiler and tools should be enough. I am not sure what is
|
277
|
+
needed on the Mac.
|
278
|
+
|
279
|
+
In order to run the `specs' the following Ruby package is necessary:
|
280
|
+
|
281
|
+
\begin{itemize}
|
282
|
+
\tightlist
|
283
|
+
\item
|
284
|
+
gem install rspec
|
285
|
+
\end{itemize}
|
286
|
+
|
287
|
+
\subsection{Preparation}\label{preparation}
|
288
|
+
|
289
|
+
\begin{itemize}
|
290
|
+
\tightlist
|
291
|
+
\item
|
292
|
+
gem install galaaz
|
293
|
+
\end{itemize}
|
294
|
+
|
295
|
+
\subsection{Running the demo}\label{running-the-demo}
|
296
|
+
|
297
|
+
The ggplot for this demos was extracted from:
|
298
|
+
\url{http://r-statistics.co/Top50-Ggplot2-Visualizations-MasterList-R-Code.html}.
|
299
|
+
|
300
|
+
On the console do
|
301
|
+
|
302
|
+
\begin{verbatim}
|
303
|
+
> galaaz master_list:scatter_plot
|
304
|
+
\end{verbatim}
|
305
|
+
|
306
|
+
\subsection{Running other demos}\label{running-other-demos}
|
307
|
+
|
308
|
+
Doing on the console
|
309
|
+
|
310
|
+
\begin{verbatim}
|
311
|
+
> galaaz -T
|
312
|
+
\end{verbatim}
|
313
|
+
|
314
|
+
will show a list with all available demos. To run any of the demos in
|
315
|
+
the list, substitute the call to `rake' to `galaaz'. For instance, one
|
316
|
+
of the examples in the list is `rake sthda:bar'. In order to run this
|
317
|
+
example just do `galaaz sthda:bar'. Doing `galaaz sthda:all' will run
|
318
|
+
all demos in the sthda cathegory. Some of the examples require `rspec'
|
319
|
+
do be available. To install `rspec' just do `gem install rspec'.
|
320
|
+
|
321
|
+
\section{The demo code}\label{the-demo-code}
|
322
|
+
|
323
|
+
The following is the Ruby code and plot for the above example. There is
|
324
|
+
a small difference between the code in the example and the code bellow.
|
325
|
+
If the example is ran, the plot will appear on the screen, bellow, we
|
326
|
+
generate an `svg' image and then include it in this document. In order
|
327
|
+
to generate and image, the R.svg device is used. To generate the plot on
|
328
|
+
the screen, use the R.awt device, as commented on the code.
|
329
|
+
|
330
|
+
\begin{Shaded}
|
331
|
+
\begin{Highlighting}[]
|
332
|
+
\NormalTok{require }\StringTok{'galaaz'}
|
333
|
+
\NormalTok{require }\StringTok{'ggplot'}
|
334
|
+
|
335
|
+
\CommentTok{# load package and data}
|
336
|
+
\NormalTok{R.options(}\StringTok{scipen: }\DecValTok{999}\NormalTok{) }\CommentTok{# turn-off scientific notation like 1e+48}
|
337
|
+
\NormalTok{R.theme_set(R.theme_bw) }\CommentTok{# pre-set the bw theme.}
|
338
|
+
|
339
|
+
\NormalTok{midwest = ~}\StringTok{:midwest}
|
340
|
+
\CommentTok{# midwest <- read.csv("http://goo.gl/G1K41K") # bkup data source}
|
341
|
+
|
342
|
+
\CommentTok{# R.awt # run the awt device if the plot should show on the screen}
|
343
|
+
\NormalTok{R.svg }\CommentTok{# run the svg device if an image should be generated}
|
344
|
+
|
345
|
+
\CommentTok{# Scatterplot}
|
346
|
+
\NormalTok{gg = midwest.ggplot(E.aes(}\StringTok{x: :area}\NormalTok{, }\StringTok{y: :poptotal}\NormalTok{)) + }
|
347
|
+
\NormalTok{ R.geom_point(E.aes(}\StringTok{col: :state}\NormalTok{, }\StringTok{size: :popdensity}\NormalTok{)) + }
|
348
|
+
\NormalTok{ R.geom_smooth(}\StringTok{method: "loess"}\NormalTok{, }\StringTok{se: }\DecValTok{false}\NormalTok{) + }
|
349
|
+
\NormalTok{ R.xlim(R.c(}\DecValTok{0}\NormalTok{, }\FloatTok{0.1}\NormalTok{)) + }
|
350
|
+
\NormalTok{ R.ylim(R.c(}\DecValTok{0}\NormalTok{, }\DecValTok{500000}\NormalTok{)) + }
|
351
|
+
\NormalTok{ R.labs(}\StringTok{subtitle: "Area Vs Population"}\NormalTok{, }
|
352
|
+
\StringTok{y: "Population"}\NormalTok{, }
|
353
|
+
\StringTok{x: "Area"}\NormalTok{, }
|
354
|
+
\StringTok{title: "Scatterplot"}\NormalTok{, }
|
355
|
+
\StringTok{caption: "Source: midwest"}\NormalTok{)}
|
356
|
+
|
357
|
+
\NormalTok{R.png(}\StringTok{'midwest.png'}\NormalTok{) }\CommentTok{# this line is not necessary with the awt device}
|
358
|
+
\NormalTok{puts gg}
|
359
|
+
|
360
|
+
\NormalTok{R.dev__off }\CommentTok{# R.dev__off turns off the device. If using awt, the plot}
|
361
|
+
\CommentTok{# window will be closed}
|
362
|
+
\end{Highlighting}
|
363
|
+
\end{Shaded}
|
364
|
+
|
365
|
+
\begin{figure}
|
366
|
+
\centering
|
367
|
+
\includegraphics[width=0.70000\textwidth]{midwest.png}
|
368
|
+
\caption{Midwest Plot}
|
369
|
+
\end{figure}
|
370
|
+
|
371
|
+
In R, the code to generate this plot is the following
|
372
|
+
|
373
|
+
\begin{Shaded}
|
374
|
+
\begin{Highlighting}[]
|
375
|
+
\CommentTok{# install.packages("ggplot2")}
|
376
|
+
\CommentTok{# load package and data}
|
377
|
+
\KeywordTok{options}\NormalTok{(}\DataTypeTok{scipen=}\DecValTok{999}\NormalTok{) }\CommentTok{# turn-off scientific notation like 1e+48}
|
378
|
+
\KeywordTok{library}\NormalTok{(ggplot2)}
|
379
|
+
\KeywordTok{theme_set}\NormalTok{(}\KeywordTok{theme_bw}\NormalTok{()) }\CommentTok{# pre-set the bw theme.}
|
380
|
+
\KeywordTok{data}\NormalTok{(}\StringTok{"midwest"}\NormalTok{, }\DataTypeTok{package =} \StringTok{"ggplot2"}\NormalTok{)}
|
381
|
+
\CommentTok{# midwest <- read.csv("http://goo.gl/G1K41K") # bkup data source}
|
382
|
+
|
383
|
+
\CommentTok{# Scatterplot}
|
384
|
+
\NormalTok{gg <-}\StringTok{ }\KeywordTok{ggplot}\NormalTok{(midwest, }\KeywordTok{aes}\NormalTok{(}\DataTypeTok{x=}\NormalTok{area, }\DataTypeTok{y=}\NormalTok{poptotal)) }\OperatorTok{+}\StringTok{ }
|
385
|
+
\StringTok{ }\KeywordTok{geom_point}\NormalTok{(}\KeywordTok{aes}\NormalTok{(}\DataTypeTok{col=}\NormalTok{state, }\DataTypeTok{size=}\NormalTok{popdensity)) }\OperatorTok{+}\StringTok{ }
|
386
|
+
\StringTok{ }\KeywordTok{geom_smooth}\NormalTok{(}\DataTypeTok{method=}\StringTok{"loess"}\NormalTok{, }\DataTypeTok{se=}\NormalTok{F) }\OperatorTok{+}\StringTok{ }
|
387
|
+
\StringTok{ }\KeywordTok{xlim}\NormalTok{(}\KeywordTok{c}\NormalTok{(}\DecValTok{0}\NormalTok{, }\FloatTok{0.1}\NormalTok{)) }\OperatorTok{+}\StringTok{ }
|
388
|
+
\StringTok{ }\KeywordTok{ylim}\NormalTok{(}\KeywordTok{c}\NormalTok{(}\DecValTok{0}\NormalTok{, }\DecValTok{500000}\NormalTok{)) }\OperatorTok{+}\StringTok{ }
|
389
|
+
\StringTok{ }\KeywordTok{labs}\NormalTok{(}\DataTypeTok{subtitle=}\StringTok{"Area Vs Population"}\NormalTok{, }
|
390
|
+
\DataTypeTok{y=}\StringTok{"Population"}\NormalTok{, }
|
391
|
+
\DataTypeTok{x=}\StringTok{"Area"}\NormalTok{, }
|
392
|
+
\DataTypeTok{title=}\StringTok{"Scatterplot"}\NormalTok{, }
|
393
|
+
\DataTypeTok{caption =} \StringTok{"Source: midwest"}\NormalTok{)}
|
394
|
+
|
395
|
+
\KeywordTok{plot}\NormalTok{(gg)}
|
396
|
+
\end{Highlighting}
|
397
|
+
\end{Shaded}
|
398
|
+
|
399
|
+
Note that both codes are very similar. The Ruby code requires the use of
|
400
|
+
``R.'' before calling any functions, for instance R function
|
401
|
+
`geom\_point' becomes `R.geom\_point' in Ruby. R named parameters such
|
402
|
+
as (col = state, size = popdensity), become in Ruby (col: :state, size:
|
403
|
+
:popdensity).
|
404
|
+
|
405
|
+
One last point that needs to be observed is the call to the `aes'
|
406
|
+
function. In Ruby instead of doing `R.aes', we use `E.aes'. The
|
407
|
+
explanation of why E.aes is needed is an advanced topic in R and depends
|
408
|
+
on what is know as Non-standard Evaluation (NSE) in R. In short,
|
409
|
+
function `aes' is lazily evaluated in R, i.e., in R when calling
|
410
|
+
geom\_point(aes(col=state, size=popdensity)), function geom\_point
|
411
|
+
receives as argument something similar to a string containing
|
412
|
+
`aes(col=state, size=popdensity)', and the aes function will be
|
413
|
+
evaluated inside the geom\_point function. In Ruby, there is no Lazy
|
414
|
+
evaluation and doing R.aes would try to evaluate aes immediately. In
|
415
|
+
order to delay the evaluation of function aes we need to use E.aes. The
|
416
|
+
interested reader on NSE in R is directed to
|
417
|
+
\url{http://adv-r.had.co.nz/Computing-on-the-language.html}.
|
418
|
+
|
419
|
+
\section{An extension to the example}\label{an-extension-to-the-example}
|
420
|
+
|
421
|
+
If both codes are so similar, then why would one use Ruby instead of R
|
422
|
+
and what good is galaaz after all?
|
423
|
+
|
424
|
+
Ruby is a modern OO language with numerous very useful constructs such
|
425
|
+
as classes, modules, blocks, procs, etc. The example above focus on the
|
426
|
+
coupling of both languages, and does not show the use of other Ruby
|
427
|
+
constructs. In the following example, we will show a more complex
|
428
|
+
example using other Ruby constructs. This is certainly not a very well
|
429
|
+
written and robust Ruby code, but it give the idea of how Ruby and R are
|
430
|
+
strongly coupled.
|
431
|
+
|
432
|
+
Let's imagine that we work in a corporation that has its plot themes.
|
433
|
+
So, it has defined a `CorpTheme' module. Plots in this corporation
|
434
|
+
should not have grids, numbers in labels should not use scientific
|
435
|
+
notation and the preferred color is blue.
|
436
|
+
|
437
|
+
\begin{Shaded}
|
438
|
+
\begin{Highlighting}[]
|
439
|
+
\CommentTok{# corp_theme.rb}
|
440
|
+
\CommentTok{# defines the corporate theme for all plots}
|
441
|
+
|
442
|
+
\KeywordTok{module} \DataTypeTok{CorpTheme}
|
443
|
+
|
444
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
445
|
+
\CommentTok{# Defines the plot theme (visualization). In this theme we remove major and minor}
|
446
|
+
\CommentTok{# grids, borders and background. We also turn-off scientific notation.}
|
447
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
448
|
+
|
449
|
+
\KeywordTok{def} \DecValTok{self}\NormalTok{.global_theme}
|
450
|
+
|
451
|
+
\NormalTok{ R.options(}\StringTok{scipen: }\DecValTok{999}\NormalTok{) }\CommentTok{# turn-off scientific notation like 1e+48}
|
452
|
+
|
453
|
+
\CommentTok{# remove major grids}
|
454
|
+
\NormalTok{ global_theme = R.theme(}\StringTok{panel__grid__major: }\NormalTok{E.element_blank())}
|
455
|
+
\CommentTok{# remove minor grids}
|
456
|
+
\NormalTok{ global_theme = global_theme + R.theme(}\StringTok{panel__grid__minor: }\NormalTok{E.element_blank)}
|
457
|
+
\CommentTok{# remove border}
|
458
|
+
\NormalTok{ global_theme = global_theme + R.theme(}\StringTok{panel__border: }\NormalTok{E.element_blank)}
|
459
|
+
\CommentTok{# remove background}
|
460
|
+
\NormalTok{ global_theme = global_theme + R.theme(}\StringTok{panel__background: }\NormalTok{E.element_blank)}
|
461
|
+
\CommentTok{# Change axis font}
|
462
|
+
\NormalTok{ global_theme = global_theme +}
|
463
|
+
\NormalTok{ R.theme(}\StringTok{axis__text: }\NormalTok{E.element_text(}\StringTok{size: }\DecValTok{8}\NormalTok{, }\StringTok{color: "#000080"}\NormalTok{))}
|
464
|
+
\CommentTok{# change color of axis titles}
|
465
|
+
\NormalTok{ global_theme = global_theme +}
|
466
|
+
\NormalTok{ R.theme(}\StringTok{axis__title: }\NormalTok{E.element_text(}
|
467
|
+
\StringTok{color: "#000080"}\NormalTok{, }
|
468
|
+
\StringTok{face: "bold"}\NormalTok{,}
|
469
|
+
\StringTok{size: }\DecValTok{8}\NormalTok{,}
|
470
|
+
\StringTok{hjust: }\DecValTok{1}\NormalTok{))}
|
471
|
+
\KeywordTok{end}
|
472
|
+
|
473
|
+
\KeywordTok{end}
|
474
|
+
\end{Highlighting}
|
475
|
+
\end{Shaded}
|
476
|
+
|
477
|
+
We now define a ScatterPlot class:
|
478
|
+
|
479
|
+
\begin{Shaded}
|
480
|
+
\begin{Highlighting}[]
|
481
|
+
\CommentTok{# ScatterPlot.rb}
|
482
|
+
\CommentTok{# creates a scatter plot and allow some configuration}
|
483
|
+
|
484
|
+
\KeywordTok{class} \DataTypeTok{ScatterPlot}
|
485
|
+
|
486
|
+
\OtherTok{attr_accessor} \StringTok{:title}
|
487
|
+
\OtherTok{attr_accessor} \StringTok{:subtitle}
|
488
|
+
\OtherTok{attr_accessor} \StringTok{:caption}
|
489
|
+
\OtherTok{attr_accessor} \StringTok{:x_label}
|
490
|
+
\OtherTok{attr_accessor} \StringTok{:y_label}
|
491
|
+
|
492
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
493
|
+
\CommentTok{# Initialize the plot with the data and the x and y variables}
|
494
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
495
|
+
|
496
|
+
\KeywordTok{def}\NormalTok{ initialize(data, x:, y:)}
|
497
|
+
\OtherTok{@data}\NormalTok{ = data}
|
498
|
+
\OtherTok{@x}\NormalTok{ = x}
|
499
|
+
\OtherTok{@y}\NormalTok{ = y}
|
500
|
+
\KeywordTok{end}
|
501
|
+
|
502
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
503
|
+
\CommentTok{# Define groupings by color and size}
|
504
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
505
|
+
|
506
|
+
\KeywordTok{def}\NormalTok{ group_by(color:, size:)}
|
507
|
+
\OtherTok{@color_by}\NormalTok{ = color}
|
508
|
+
\OtherTok{@size_by}\NormalTok{ = size}
|
509
|
+
\KeywordTok{end}
|
510
|
+
|
511
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
512
|
+
\CommentTok{# Add a smoothing line, and if confidence is true the add a confidence interval, if}
|
513
|
+
\CommentTok{# false does not add the confidence interval}
|
514
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
515
|
+
|
516
|
+
\KeywordTok{def}\NormalTok{ add_smoothing_line(method:, }\StringTok{confidence: }\DecValTok{true}\NormalTok{)}
|
517
|
+
\OtherTok{@method}\NormalTok{ = method}
|
518
|
+
\OtherTok{@confidence}\NormalTok{ = confidence}
|
519
|
+
\KeywordTok{end}
|
520
|
+
|
521
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
522
|
+
\CommentTok{# Creates the graph title, properly formated for this theme}
|
523
|
+
\CommentTok{# @param title [String] The title to add to the graph}
|
524
|
+
\CommentTok{# @return textGrob that can be included in a graph}
|
525
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
526
|
+
|
527
|
+
\KeywordTok{def}\NormalTok{ graph_params(}\StringTok{title: ""}\NormalTok{, }\StringTok{subtitle: ""}\NormalTok{, }\StringTok{caption: ""}\NormalTok{, }\StringTok{x_label: ""}\NormalTok{, }\StringTok{y_label: ""}\NormalTok{)}
|
528
|
+
\NormalTok{ R.labs(}
|
529
|
+
\StringTok{title: }\NormalTok{title, }
|
530
|
+
\StringTok{subtitle: }\NormalTok{subtitle, }
|
531
|
+
\StringTok{caption: }\NormalTok{caption,}
|
532
|
+
\StringTok{y_label: }\NormalTok{y_label, }
|
533
|
+
\StringTok{x_label: }\NormalTok{x_label, }
|
534
|
+
\NormalTok{ )}
|
535
|
+
\KeywordTok{end}
|
536
|
+
|
537
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
538
|
+
\CommentTok{# Prepare the plot's points}
|
539
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
540
|
+
|
541
|
+
\KeywordTok{def}\NormalTok{ points}
|
542
|
+
\NormalTok{ params = \{\}}
|
543
|
+
\NormalTok{ params[}\StringTok{:col}\NormalTok{] = }\OtherTok{@color_by} \KeywordTok{if} \OtherTok{@color_by}
|
544
|
+
\NormalTok{ params[}\StringTok{:size}\NormalTok{] = }\OtherTok{@size_by} \KeywordTok{if} \OtherTok{@size_by}
|
545
|
+
\NormalTok{ R.geom_point(E.aes(params))}
|
546
|
+
\KeywordTok{end}
|
547
|
+
|
548
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
549
|
+
\CommentTok{# Plots the scatterplot}
|
550
|
+
\CommentTok{#---------------------------------------------------------------------------------}
|
551
|
+
|
552
|
+
\KeywordTok{def}\NormalTok{ plot(device = }\StringTok{'awt'}\NormalTok{)}
|
553
|
+
\NormalTok{ device == }\StringTok{'awt'}\NormalTok{ ? R.awt : R.svg}
|
554
|
+
|
555
|
+
\NormalTok{ gg = }\OtherTok{@data}\NormalTok{.ggplot(E.aes(}\StringTok{x: }\OtherTok{@x}\NormalTok{, }\StringTok{y: }\OtherTok{@y}\NormalTok{)) +}
|
556
|
+
\NormalTok{ points + }
|
557
|
+
\NormalTok{ R.geom_smooth(}\StringTok{method: }\OtherTok{@method}\NormalTok{, }\StringTok{se: }\OtherTok{@confidence}\NormalTok{) +}
|
558
|
+
\NormalTok{ R.xlim(R.c(}\DecValTok{0}\NormalTok{, }\FloatTok{0.1}\NormalTok{)) +}
|
559
|
+
\NormalTok{ R.ylim(R.c(}\DecValTok{0}\NormalTok{, }\DecValTok{500000}\NormalTok{)) + }
|
560
|
+
\NormalTok{ graph_params(}\StringTok{title: }\OtherTok{@title}\NormalTok{,}
|
561
|
+
\StringTok{subtitle: }\OtherTok{@subtitle}\NormalTok{, }
|
562
|
+
\StringTok{y_label: }\OtherTok{@y_label}\NormalTok{, }
|
563
|
+
\StringTok{x_label: }\OtherTok{@x_label}\NormalTok{, }
|
564
|
+
\StringTok{caption: }\OtherTok{@caption}\NormalTok{) +}
|
565
|
+
\DataTypeTok{CorpTheme}\NormalTok{.global_theme}
|
566
|
+
|
567
|
+
\NormalTok{ R.png(}\StringTok{'scatter_plot.png'}\NormalTok{) }\KeywordTok{if}\NormalTok{ !(device == }\StringTok{'awt'}\NormalTok{)}
|
568
|
+
\NormalTok{ puts gg}
|
569
|
+
\NormalTok{ R.dev__off}
|
570
|
+
|
571
|
+
\KeywordTok{end}
|
572
|
+
|
573
|
+
\KeywordTok{end}
|
574
|
+
\end{Highlighting}
|
575
|
+
\end{Shaded}
|
576
|
+
|
577
|
+
And this is the final code for making the scatter plot with the midwest
|
578
|
+
data
|
579
|
+
|
580
|
+
\begin{Shaded}
|
581
|
+
\begin{Highlighting}[]
|
582
|
+
\NormalTok{require }\StringTok{'galaaz'}
|
583
|
+
\NormalTok{require }\StringTok{'ggplot'}
|
584
|
+
|
585
|
+
\NormalTok{sp = }\DataTypeTok{ScatterPlot}\NormalTok{.new(~}\StringTok{:midwest}\NormalTok{, }\StringTok{x: :area}\NormalTok{, }\StringTok{y: :poptotal}\NormalTok{)}
|
586
|
+
\NormalTok{sp.title = }\StringTok{"Midwest Dataset - Scatterplot"}
|
587
|
+
\NormalTok{sp.subtitle = }\StringTok{"Area Vs Population"}
|
588
|
+
\NormalTok{sp.caption = }\StringTok{"Source: midwest"}
|
589
|
+
\NormalTok{sp.x_label = }\StringTok{"Area"}
|
590
|
+
\NormalTok{sp.y_label = }\StringTok{"Population"}
|
591
|
+
\NormalTok{sp.group_by(}\StringTok{color: :state}\NormalTok{, }\StringTok{size: :popdensity}\NormalTok{) }\CommentTok{# try sp.group_by(color: :state)}
|
592
|
+
\CommentTok{# available methods: "lm", "glm", "loess", "gam"}
|
593
|
+
\NormalTok{sp.add_smoothing_line(}\StringTok{method: "glm"}\NormalTok{) }
|
594
|
+
\NormalTok{sp.plot(}\StringTok{'svg'}\NormalTok{)}
|
595
|
+
|
596
|
+
\CommentTok{# require input from the user so that the script does not end removing the plot from}
|
597
|
+
\CommentTok{# the screen}
|
598
|
+
\end{Highlighting}
|
599
|
+
\end{Shaded}
|
600
|
+
|
601
|
+
\begin{figure}
|
602
|
+
\centering
|
603
|
+
\includegraphics[width=0.70000\textwidth]{scatter_plot.png}
|
604
|
+
\caption{Midwest Plot with `glm' function and modified theme}
|
605
|
+
\end{figure}
|
606
|
+
|
607
|
+
\section{Conclusion}\label{conclusion}
|
608
|
+
|
609
|
+
R is a very powerful language for statistical analysis, data analytics,
|
610
|
+
machine learning, plotting and many other scientific applications with a
|
611
|
+
very large package ecosystem. However R is often considered hard to
|
612
|
+
learn and lacking modern computer languages constructs such as object
|
613
|
+
oriented classes, modules, lambdas, etc. For this reason, many
|
614
|
+
developers have started or switched from R to Python.
|
615
|
+
|
616
|
+
With Galaaz, R programmers can almost transparently migrate from R to
|
617
|
+
Ruby, since syntax is almost identical and they have fastR as the R
|
618
|
+
engine. FastR, by most benchmarks, can be orders of magnitude faster
|
619
|
+
than Gnu R. Further, by using Galaaz the R developer can start (slowly
|
620
|
+
if needed) using all of Ruby's constructs and libraries that nicely
|
621
|
+
complement R packages.
|
622
|
+
|
623
|
+
For the Ruby developer, Galaaz allows the immediate use of R functions
|
624
|
+
completely transparently. As shown in the second example above, class
|
625
|
+
ScatterPlot completely hides all the details an R calls from the Ruby
|
626
|
+
developer, furthermore Galaaz is powered by TruffleRuby that can also be
|
627
|
+
orders of magnitude faster than MRI Ruby.
|
628
|
+
|
629
|
+
|
630
|
+
\end{document}
|