galaaz 0.4.9 → 0.4.10
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +798 -285
- data/blogs/galaaz_ggplot/galaaz_ggplot.Rmd +3 -12
- data/blogs/galaaz_ggplot/galaaz_ggplot.aux +5 -7
- data/blogs/galaaz_ggplot/galaaz_ggplot.html +69 -29
- data/blogs/galaaz_ggplot/galaaz_ggplot.pdf +0 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot_files/figure-html/midwest_rb.png +0 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot_files/figure-html/scatter_plot_rb.png +0 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot_files/figure-latex/midwest_rb.pdf +0 -0
- data/blogs/galaaz_ggplot/galaaz_ggplot_files/figure-latex/scatter_plot_rb.pdf +0 -0
- data/blogs/galaaz_ggplot/midwest.Rmd +1 -9
- data/blogs/gknit/gknit.Rmd +37 -40
- data/blogs/gknit/gknit.html +32 -30
- data/blogs/gknit/gknit.md +36 -37
- data/blogs/gknit/gknit.pdf +0 -0
- data/blogs/gknit/gknit.tex +35 -37
- data/blogs/manual/manual.Rmd +548 -125
- data/blogs/manual/manual.html +509 -286
- data/blogs/manual/manual.md +798 -285
- data/blogs/manual/manual.pdf +0 -0
- data/blogs/manual/manual.tex +2816 -0
- data/blogs/manual/manual_files/figure-latex/diverging_bar.pdf +0 -0
- data/blogs/nse_dplyr/nse_dplyr.Rmd +240 -74
- data/blogs/nse_dplyr/nse_dplyr.html +191 -87
- data/blogs/nse_dplyr/nse_dplyr.md +361 -107
- data/blogs/nse_dplyr/nse_dplyr.pdf +0 -0
- data/blogs/nse_dplyr/nse_dplyr.tex +1373 -0
- data/blogs/ruby_plot/ruby_plot.Rmd +61 -81
- data/blogs/ruby_plot/ruby_plot.html +54 -57
- data/blogs/ruby_plot/ruby_plot.md +48 -67
- data/blogs/ruby_plot/ruby_plot.pdf +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/dose_len.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facet_by_delivery.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facet_by_dose.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_by_delivery_color.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_by_delivery_color2.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_with_jitter.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_with_points.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/final_box_plot.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/final_violin_plot.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/violin_with_jitter.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/dose_len.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/facet_by_delivery.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/facet_by_dose.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/facets_by_delivery_color.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/facets_by_delivery_color2.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/facets_with_decorations.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/facets_with_jitter.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/facets_with_points.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/final_box_plot.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/final_violin_plot.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-latex/violin_with_jitter.png +0 -0
- data/lib/R_interface/rdata_frame.rb +0 -12
- data/lib/R_interface/robject.rb +14 -14
- data/lib/R_interface/ruby_extensions.rb +3 -31
- data/lib/R_interface/rvector.rb +0 -12
- data/lib/gknit/knitr_engine.rb +5 -3
- data/lib/util/exec_ruby.rb +22 -61
- data/specs/tmp.rb +26 -12
- data/version.rb +1 -1
- metadata +22 -17
- data/bin/gknit_old_r +0 -236
- data/blogs/dev/dev.Rmd +0 -23
- data/blogs/dev/dev.md +0 -58
- data/blogs/dev/dev2.Rmd +0 -65
- data/blogs/dev/model.rb +0 -41
- data/blogs/dplyr/dplyr.Rmd +0 -29
- data/blogs/dplyr/dplyr.html +0 -433
- data/blogs/dplyr/dplyr.md +0 -58
- data/blogs/dplyr/dplyr.rb +0 -63
- data/blogs/galaaz_ggplot/galaaz_ggplot.log +0 -640
- data/blogs/galaaz_ggplot/galaaz_ggplot.md +0 -431
- data/blogs/galaaz_ggplot/galaaz_ggplot.tex +0 -481
- data/blogs/galaaz_ggplot/midwest.png +0 -0
- data/blogs/galaaz_ggplot/scatter_plot.png +0 -0
- data/blogs/ruby_plot/ruby_plot.tex +0 -1077
Binary file
|
@@ -0,0 +1,2816 @@
|
|
1
|
+
\documentclass[11pt,]{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={Galaaz Manual},
|
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{\AlertTok}[1]{\textcolor[rgb]{0.94,0.16,0.16}{#1}}
|
42
|
+
\newcommand{\AnnotationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
43
|
+
\newcommand{\AttributeTok}[1]{\textcolor[rgb]{0.77,0.63,0.00}{#1}}
|
44
|
+
\newcommand{\BaseNTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
|
45
|
+
\newcommand{\BuiltInTok}[1]{#1}
|
46
|
+
\newcommand{\CharTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
|
47
|
+
\newcommand{\CommentTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textit{#1}}}
|
48
|
+
\newcommand{\CommentVarTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
49
|
+
\newcommand{\ConstantTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
|
50
|
+
\newcommand{\ControlFlowTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{\textbf{#1}}}
|
51
|
+
\newcommand{\DataTypeTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{#1}}
|
52
|
+
\newcommand{\DecValTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
|
53
|
+
\newcommand{\DocumentationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
54
|
+
\newcommand{\ErrorTok}[1]{\textcolor[rgb]{0.64,0.00,0.00}{\textbf{#1}}}
|
55
|
+
\newcommand{\ExtensionTok}[1]{#1}
|
56
|
+
\newcommand{\FloatTok}[1]{\textcolor[rgb]{0.00,0.00,0.81}{#1}}
|
57
|
+
\newcommand{\FunctionTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
|
58
|
+
\newcommand{\ImportTok}[1]{#1}
|
59
|
+
\newcommand{\InformationTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
60
|
+
\newcommand{\KeywordTok}[1]{\textcolor[rgb]{0.13,0.29,0.53}{\textbf{#1}}}
|
61
|
+
\newcommand{\NormalTok}[1]{#1}
|
62
|
+
\newcommand{\OperatorTok}[1]{\textcolor[rgb]{0.81,0.36,0.00}{\textbf{#1}}}
|
63
|
+
\newcommand{\OtherTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{#1}}
|
64
|
+
\newcommand{\PreprocessorTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textit{#1}}}
|
65
|
+
\newcommand{\RegionMarkerTok}[1]{#1}
|
66
|
+
\newcommand{\SpecialCharTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
|
67
|
+
\newcommand{\SpecialStringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
|
68
|
+
\newcommand{\StringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
|
69
|
+
\newcommand{\VariableTok}[1]{\textcolor[rgb]{0.00,0.00,0.00}{#1}}
|
70
|
+
\newcommand{\VerbatimStringTok}[1]{\textcolor[rgb]{0.31,0.60,0.02}{#1}}
|
71
|
+
\newcommand{\WarningTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{\textbf{\textit{#1}}}}
|
72
|
+
\usepackage{longtable,booktabs}
|
73
|
+
\usepackage{graphicx,grffile}
|
74
|
+
\makeatletter
|
75
|
+
\def\maxwidth{\ifdim\Gin@nat@width>\linewidth\linewidth\else\Gin@nat@width\fi}
|
76
|
+
\def\maxheight{\ifdim\Gin@nat@height>\textheight\textheight\else\Gin@nat@height\fi}
|
77
|
+
\makeatother
|
78
|
+
% Scale images if necessary, so that they will not overflow the page
|
79
|
+
% margins by default, and it is still possible to overwrite the defaults
|
80
|
+
% using explicit options in \includegraphics[width, height, ...]{}
|
81
|
+
\setkeys{Gin}{width=\maxwidth,height=\maxheight,keepaspectratio}
|
82
|
+
\IfFileExists{parskip.sty}{%
|
83
|
+
\usepackage{parskip}
|
84
|
+
}{% else
|
85
|
+
\setlength{\parindent}{0pt}
|
86
|
+
\setlength{\parskip}{6pt plus 2pt minus 1pt}
|
87
|
+
}
|
88
|
+
\setlength{\emergencystretch}{3em} % prevent overfull lines
|
89
|
+
\providecommand{\tightlist}{%
|
90
|
+
\setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}}
|
91
|
+
\setcounter{secnumdepth}{5}
|
92
|
+
% Redefines (sub)paragraphs to behave more like sections
|
93
|
+
\ifx\paragraph\undefined\else
|
94
|
+
\let\oldparagraph\paragraph
|
95
|
+
\renewcommand{\paragraph}[1]{\oldparagraph{#1}\mbox{}}
|
96
|
+
\fi
|
97
|
+
\ifx\subparagraph\undefined\else
|
98
|
+
\let\oldsubparagraph\subparagraph
|
99
|
+
\renewcommand{\subparagraph}[1]{\oldsubparagraph{#1}\mbox{}}
|
100
|
+
\fi
|
101
|
+
|
102
|
+
%%% Use protect on footnotes to avoid problems with footnotes in titles
|
103
|
+
\let\rmarkdownfootnote\footnote%
|
104
|
+
\def\footnote{\protect\rmarkdownfootnote}
|
105
|
+
|
106
|
+
%%% Change title format to be more compact
|
107
|
+
\usepackage{titling}
|
108
|
+
|
109
|
+
% Create subtitle command for use in maketitle
|
110
|
+
\newcommand{\subtitle}[1]{
|
111
|
+
\posttitle{
|
112
|
+
\begin{center}\large#1\end{center}
|
113
|
+
}
|
114
|
+
}
|
115
|
+
|
116
|
+
\setlength{\droptitle}{-2em}
|
117
|
+
|
118
|
+
\title{Galaaz Manual}
|
119
|
+
\pretitle{\vspace{\droptitle}\centering\huge}
|
120
|
+
\posttitle{\par}
|
121
|
+
\subtitle{How to tightly couple Ruby and R in GraalVM}
|
122
|
+
\author{Rodrigo Botafogo}
|
123
|
+
\preauthor{\centering\large\emph}
|
124
|
+
\postauthor{\par}
|
125
|
+
\predate{\centering\large\emph}
|
126
|
+
\postdate{\par}
|
127
|
+
\date{2019}
|
128
|
+
|
129
|
+
% usar portugues do Brasil
|
130
|
+
% \usepackage[brazilian]{babel}
|
131
|
+
\usepackage[utf8]{inputenc}
|
132
|
+
|
133
|
+
\usepackage{geometry}
|
134
|
+
\geometry{a4paper, top=1in}
|
135
|
+
|
136
|
+
% needed for kableExtra
|
137
|
+
\usepackage{longtable}
|
138
|
+
\usepackage{multirow}
|
139
|
+
\usepackage[table]{xcolor}
|
140
|
+
\usepackage{wrapfig}
|
141
|
+
\usepackage{float}
|
142
|
+
\usepackage{colortbl}
|
143
|
+
\usepackage{pdflscape}
|
144
|
+
\usepackage{tabu}
|
145
|
+
\usepackage{threeparttable}
|
146
|
+
\usepackage[normalem]{ulem}
|
147
|
+
|
148
|
+
\usepackage{bbm}
|
149
|
+
\usepackage{booktabs}
|
150
|
+
\usepackage{expex}
|
151
|
+
|
152
|
+
\usepackage{graphicx}
|
153
|
+
|
154
|
+
\usepackage{fancyhdr}
|
155
|
+
% set the header and foot style
|
156
|
+
% style 'fancy' adds the section name on the header
|
157
|
+
% and the page number on the footer
|
158
|
+
\pagestyle{fancy}
|
159
|
+
|
160
|
+
% style 'fancyhf' leaves header and footer empty
|
161
|
+
%\fancyhf{}
|
162
|
+
|
163
|
+
% sets the left head element to \rightmark, which contains the
|
164
|
+
% current section (\leftmark is the current chapter)
|
165
|
+
%\fancyhead[L]{\rightmark} .
|
166
|
+
|
167
|
+
% sets the right head element to the page number.
|
168
|
+
% \fancyhead[R]{\thepage}
|
169
|
+
|
170
|
+
% lets the head rule disappear.
|
171
|
+
% \renewcommand{\headrulewidth}{0pt}
|
172
|
+
% Possible selectors for the optional argument of \fancyhead/\fancyfoot
|
173
|
+
% are L (left), C (center) or R (right) for the position of the element
|
174
|
+
% and E (even) or O (odd) to distinguish even and odd pages. If you omit
|
175
|
+
% E/O the element is set for all pages.
|
176
|
+
|
177
|
+
% \usepackage{lipsum}
|
178
|
+
|
179
|
+
% make available command lastpage
|
180
|
+
\usepackage{lastpage}
|
181
|
+
|
182
|
+
% default fontsize 11pt better to add
|
183
|
+
% fontsize on the yaml header
|
184
|
+
% \usepackage[fontsize=11pt]{scrextend}
|
185
|
+
|
186
|
+
% comandos para formatar uma tabela
|
187
|
+
\usepackage{array}
|
188
|
+
\newcolumntype{L}[1]{>{\raggedright\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
189
|
+
\newcolumntype{C}[1]{>{\centering\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
190
|
+
\newcolumntype{R}[1]{>{\raggedleft\let\newline\\\arraybackslash\hspace{0pt}}m{#1}}
|
191
|
+
|
192
|
+
% necessário if we need to import other latex documents
|
193
|
+
\usepackage{import}
|
194
|
+
|
195
|
+
% Command to import an R variable to latex
|
196
|
+
\newcommand{\RtoLatex}[2]{\newcommand{#1}{#2}}
|
197
|
+
|
198
|
+
%
|
199
|
+
%\newcommand{\atraso}[1]{\color{red} \textbf {Tempo desde a Assinatura do Contrato: #1 dias}}
|
200
|
+
\usepackage{booktabs}
|
201
|
+
\usepackage{longtable}
|
202
|
+
\usepackage{array}
|
203
|
+
\usepackage{multirow}
|
204
|
+
\usepackage{wrapfig}
|
205
|
+
\usepackage{float}
|
206
|
+
\usepackage{colortbl}
|
207
|
+
\usepackage{pdflscape}
|
208
|
+
\usepackage{tabu}
|
209
|
+
\usepackage{threeparttable}
|
210
|
+
\usepackage{threeparttablex}
|
211
|
+
\usepackage[normalem]{ulem}
|
212
|
+
\usepackage{makecell}
|
213
|
+
\usepackage{xcolor}
|
214
|
+
|
215
|
+
\begin{document}
|
216
|
+
\maketitle
|
217
|
+
|
218
|
+
{
|
219
|
+
\setcounter{tocdepth}{2}
|
220
|
+
\tableofcontents
|
221
|
+
}
|
222
|
+
\hypertarget{introduction}{%
|
223
|
+
\section{Introduction}\label{introduction}}
|
224
|
+
|
225
|
+
Galaaz is a system for tightly coupling Ruby and R. Ruby is a powerful
|
226
|
+
language, with a large community, a very large set of libraries and
|
227
|
+
great for web development. However, it lacks libraries for data science,
|
228
|
+
statistics, scientific plotting and machine learning. On the other hand,
|
229
|
+
R is considered one of the most powerful languages for solving all of
|
230
|
+
the above problems. Maybe the strongest competitor to R is Python with
|
231
|
+
libraries such as NumPy, Panda, SciPy, SciKit-Learn and a couple more.
|
232
|
+
|
233
|
+
\hypertarget{system-compatibility}{%
|
234
|
+
\section{System Compatibility}\label{system-compatibility}}
|
235
|
+
|
236
|
+
\begin{itemize}
|
237
|
+
\tightlist
|
238
|
+
\item
|
239
|
+
Oracle Linux 7
|
240
|
+
\item
|
241
|
+
Ubuntu 18.04 LTS
|
242
|
+
\item
|
243
|
+
Ubuntu 16.04 LTS
|
244
|
+
\item
|
245
|
+
Fedora 28
|
246
|
+
\item
|
247
|
+
macOS 10.14 (Mojave)
|
248
|
+
\item
|
249
|
+
macOS 10.13 (High Sierra)
|
250
|
+
\end{itemize}
|
251
|
+
|
252
|
+
\hypertarget{dependencies}{%
|
253
|
+
\section{Dependencies}\label{dependencies}}
|
254
|
+
|
255
|
+
\begin{itemize}
|
256
|
+
\tightlist
|
257
|
+
\item
|
258
|
+
TruffleRuby
|
259
|
+
\item
|
260
|
+
FastR
|
261
|
+
\end{itemize}
|
262
|
+
|
263
|
+
\hypertarget{installation}{%
|
264
|
+
\section{Installation}\label{installation}}
|
265
|
+
|
266
|
+
\begin{itemize}
|
267
|
+
\tightlist
|
268
|
+
\item
|
269
|
+
Install GrallVM (\url{http://www.graalvm.org/})
|
270
|
+
\item
|
271
|
+
Install Ruby (gu install Ruby)
|
272
|
+
\item
|
273
|
+
Install FastR (gu install R)
|
274
|
+
\item
|
275
|
+
Install rake if you want to run the specs and examples (gem install
|
276
|
+
rake)
|
277
|
+
\end{itemize}
|
278
|
+
|
279
|
+
\hypertarget{usage}{%
|
280
|
+
\section{Usage}\label{usage}}
|
281
|
+
|
282
|
+
\begin{itemize}
|
283
|
+
\item
|
284
|
+
Interactive shell: use `gstudio' on the command line
|
285
|
+
|
286
|
+
\begin{quote}
|
287
|
+
gstudio
|
288
|
+
\end{quote}
|
289
|
+
\end{itemize}
|
290
|
+
|
291
|
+
\begin{Shaded}
|
292
|
+
\begin{Highlighting}[]
|
293
|
+
\NormalTok{ vec = R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{, }\DecValTok{4}\NormalTok{)}
|
294
|
+
\NormalTok{ puts vec}
|
295
|
+
\end{Highlighting}
|
296
|
+
\end{Shaded}
|
297
|
+
|
298
|
+
\begin{verbatim}
|
299
|
+
## [1] 1 2 3 4
|
300
|
+
\end{verbatim}
|
301
|
+
|
302
|
+
\begin{itemize}
|
303
|
+
\item
|
304
|
+
Run all specs
|
305
|
+
|
306
|
+
\begin{quote}
|
307
|
+
galaaz specs:all
|
308
|
+
\end{quote}
|
309
|
+
\item
|
310
|
+
Run graphics slideshow (80+ graphics)
|
311
|
+
|
312
|
+
\begin{quote}
|
313
|
+
galaaz sthda:all
|
314
|
+
\end{quote}
|
315
|
+
\item
|
316
|
+
Run labs from Introduction to Statistical Learning with R
|
317
|
+
|
318
|
+
\begin{quote}
|
319
|
+
galaaz islr:all
|
320
|
+
\end{quote}
|
321
|
+
\item
|
322
|
+
See all available examples
|
323
|
+
|
324
|
+
\begin{quote}
|
325
|
+
galaaz -T
|
326
|
+
\end{quote}
|
327
|
+
|
328
|
+
Shows a list with all available executalbe tasks. To execute a task,
|
329
|
+
substitute the `rake' word in the list with `galaaz'. For instance,
|
330
|
+
the following line shows up after `galaaz -T'
|
331
|
+
|
332
|
+
rake master\_list:scatter\_plot \# scatter\_plot from:\ldots{}.
|
333
|
+
|
334
|
+
execute
|
335
|
+
|
336
|
+
\begin{quote}
|
337
|
+
galaaz master\_list:scatter\_plot
|
338
|
+
\end{quote}
|
339
|
+
\end{itemize}
|
340
|
+
|
341
|
+
\hypertarget{gknitting-a-document}{%
|
342
|
+
\section{gKnitting a Document}\label{gknitting-a-document}}
|
343
|
+
|
344
|
+
This manual has been formatted usign gKnit. gKnit uses Knitr and R
|
345
|
+
markdown to knit a document in Ruby or R and output it in any of the
|
346
|
+
available formats for R markdown. gKnit runs atop of GraalVM, and
|
347
|
+
Galaaz. In gKnit, Ruby variables are persisted between chunks, making it
|
348
|
+
an ideal solution for literate programming. Also, since it is based on
|
349
|
+
Galaaz, Ruby chunks can have access to R variables and Polyglot
|
350
|
+
Programming with Ruby and R is quite natural.
|
351
|
+
|
352
|
+
\href{https://towardsdatascience.com/how-to-do-reproducible-research-in-ruby-with-gknit-c26d2684d64e}{gknit
|
353
|
+
is described in more details here}
|
354
|
+
|
355
|
+
\hypertarget{vector}{%
|
356
|
+
\section{Vector}\label{vector}}
|
357
|
+
|
358
|
+
Vectors can be thought of as contiguous cells containing data. Cells are
|
359
|
+
accessed through indexing operations such as x{[}5{]}. Galaaz has six
|
360
|
+
basic (`atomic') vector types: logical, integer, real, complex, string
|
361
|
+
(or character) and raw. The modes and storage modes for the different
|
362
|
+
vector types are listed in the following table.
|
363
|
+
|
364
|
+
\begin{longtable}[]{@{}lcr@{}}
|
365
|
+
\toprule
|
366
|
+
typeof & mode & storage.mode\tabularnewline
|
367
|
+
\midrule
|
368
|
+
\endhead
|
369
|
+
logical & logical & logical\tabularnewline
|
370
|
+
integer & numeric & integer\tabularnewline
|
371
|
+
double & numeric & double\tabularnewline
|
372
|
+
complex & complex & comples\tabularnewline
|
373
|
+
character & character & character\tabularnewline
|
374
|
+
raw & raw & raw\tabularnewline
|
375
|
+
\bottomrule
|
376
|
+
\end{longtable}
|
377
|
+
|
378
|
+
Single numbers, such as 4.2, and strings, such as ``four point two'' are
|
379
|
+
still vectors, of length 1; there are no more basic types. Vectors with
|
380
|
+
length zero are possible (and useful). String vectors have mode and
|
381
|
+
storage mode ``character''. A single element of a character vector is
|
382
|
+
often referred to as a character string.
|
383
|
+
|
384
|
+
To create a vector the `c' (concatenate) method from the `R' module
|
385
|
+
should be used:
|
386
|
+
|
387
|
+
\begin{Shaded}
|
388
|
+
\begin{Highlighting}[]
|
389
|
+
\NormalTok{vec = R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{)}
|
390
|
+
\NormalTok{puts vec}
|
391
|
+
\end{Highlighting}
|
392
|
+
\end{Shaded}
|
393
|
+
|
394
|
+
\begin{verbatim}
|
395
|
+
## [1] 1 2 3
|
396
|
+
\end{verbatim}
|
397
|
+
|
398
|
+
Lets take a look at the type, mode and storage.mode of our vector vec.
|
399
|
+
In order to print this out, we are creating a data frame `df' and
|
400
|
+
printing it out. A data frame, for those not familiar with it, is
|
401
|
+
basically a table. Here we create the data frame and add the column name
|
402
|
+
by passing named parameters for each column, such as `typeof:', `mode:'
|
403
|
+
and 'storage\_\_mode?`. You should also note here that the double
|
404
|
+
underscore is converted to a'.'. So, when printed `storage\_\_mode' will
|
405
|
+
actually print as `storage.mode'.
|
406
|
+
|
407
|
+
Data frames will later be more carefully described. In R, the method
|
408
|
+
used to create a data frame is `data.frame', in Galaaz we use
|
409
|
+
`data\_\_frame'.
|
410
|
+
|
411
|
+
\begin{Shaded}
|
412
|
+
\begin{Highlighting}[]
|
413
|
+
\NormalTok{df = R.data__frame(}\StringTok{typeof: }\NormalTok{vec.typeof, }\StringTok{mode: }\NormalTok{vec.mode, }\StringTok{storage__mode: }\NormalTok{vec.storage__mode)}
|
414
|
+
\NormalTok{puts df}
|
415
|
+
\end{Highlighting}
|
416
|
+
\end{Shaded}
|
417
|
+
|
418
|
+
\begin{verbatim}
|
419
|
+
## typeof mode storage.mode
|
420
|
+
## 1 integer numeric integer
|
421
|
+
\end{verbatim}
|
422
|
+
|
423
|
+
If you want to create a vector with floating point numbers, then we need
|
424
|
+
at least one of the vector's element to be a float, such as 1.0. R users
|
425
|
+
should be careful, since in R a number like `1' is converted to float
|
426
|
+
and to have an integer the R developer will use `1L'. Galaaz follows
|
427
|
+
normal Ruby rules and the number 1 is an integer and 1.0 is a float.
|
428
|
+
|
429
|
+
\begin{Shaded}
|
430
|
+
\begin{Highlighting}[]
|
431
|
+
\NormalTok{vec = R.c(}\FloatTok{1.0}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{)}
|
432
|
+
\NormalTok{puts vec}
|
433
|
+
\end{Highlighting}
|
434
|
+
\end{Shaded}
|
435
|
+
|
436
|
+
\begin{verbatim}
|
437
|
+
## [1] 1 2 3
|
438
|
+
\end{verbatim}
|
439
|
+
|
440
|
+
\begin{Shaded}
|
441
|
+
\begin{Highlighting}[]
|
442
|
+
\NormalTok{df = R.data__frame(}\StringTok{typeof: }\NormalTok{vec.typeof, }\StringTok{mode: }\NormalTok{vec.mode, }\StringTok{storage__mode: }\NormalTok{vec.storage__mode)}
|
443
|
+
\NormalTok{outputs df.kable.kable_styling}
|
444
|
+
\end{Highlighting}
|
445
|
+
\end{Shaded}
|
446
|
+
|
447
|
+
\begin{table}[H]
|
448
|
+
\centering
|
449
|
+
\begin{tabular}{l|l|l}
|
450
|
+
\hline
|
451
|
+
typeof & mode & storage.mode\\
|
452
|
+
\hline
|
453
|
+
double & numeric & double\\
|
454
|
+
\hline
|
455
|
+
\end{tabular}
|
456
|
+
\end{table}
|
457
|
+
|
458
|
+
In this next example we try to create a vector with a variable `hello'
|
459
|
+
that has not yet being defined. This will raise an exception that is
|
460
|
+
printed out. We get two return blocks, the first with a message
|
461
|
+
explaining what went wrong and the second with the full backtrace of the
|
462
|
+
error.
|
463
|
+
|
464
|
+
\begin{Shaded}
|
465
|
+
\begin{Highlighting}[]
|
466
|
+
\NormalTok{vec = R.c(}\DecValTok{1}\NormalTok{, hello, }\DecValTok{5}\NormalTok{)}
|
467
|
+
\end{Highlighting}
|
468
|
+
\end{Shaded}
|
469
|
+
|
470
|
+
\begin{verbatim}
|
471
|
+
## Message:
|
472
|
+
## undefined local variable or method `hello' for #<RC:0x2e0 @out_list=nil>:RC
|
473
|
+
\end{verbatim}
|
474
|
+
|
475
|
+
\begin{verbatim}
|
476
|
+
## Message:
|
477
|
+
## /home/rbotafogo/desenv/galaaz/lib/util/exec_ruby.rb:103:in `get_binding'
|
478
|
+
## /home/rbotafogo/desenv/galaaz/lib/util/exec_ruby.rb:102:in `eval'
|
479
|
+
## /home/rbotafogo/desenv/galaaz/lib/util/exec_ruby.rb:102:in `exec_ruby'
|
480
|
+
## /home/rbotafogo/desenv/galaaz/lib/gknit/knitr_engine.rb:650:in `block in initialize'
|
481
|
+
## /home/rbotafogo/desenv/galaaz/lib/R_interface/ruby_callback.rb:77:in `call'
|
482
|
+
## /home/rbotafogo/desenv/galaaz/lib/R_interface/ruby_callback.rb:77:in `callback'
|
483
|
+
## (eval):3:in `function(...) {\n rb_method(...)'
|
484
|
+
## unknown.r:1:in `in_dir'
|
485
|
+
## unknown.r:1:in `block_exec:BLOCK0'
|
486
|
+
## /home/rbotafogo/lib/graalvm-ce-1.0.0-rc16/jre/languages/R/library/knitr/R/block.R:102:in `block_exec'
|
487
|
+
## /home/rbotafogo/lib/graalvm-ce-1.0.0-rc16/jre/languages/R/library/knitr/R/block.R:92:in `call_block'
|
488
|
+
## /home/rbotafogo/lib/graalvm-ce-1.0.0-rc16/jre/languages/R/library/knitr/R/block.R:6:in `process_group.block'
|
489
|
+
## /home/rbotafogo/lib/graalvm-ce-1.0.0-rc16/jre/languages/R/library/knitr/R/block.R:3:in `<no source>'
|
490
|
+
## unknown.r:1:in `withCallingHandlers'
|
491
|
+
## unknown.r:1:in `process_file'
|
492
|
+
## unknown.r:1:in `<no source>:BLOCK1'
|
493
|
+
## /home/rbotafogo/lib/graalvm-ce-1.0.0-rc16/jre/languages/R/library/knitr/R/output.R:129:in `<no source>'
|
494
|
+
## unknown.r:1:in `<no source>:BLOCK1'
|
495
|
+
## /home/rbotafogo/lib/graalvm-ce-1.0.0-rc16/jre/languages/R/library/rmarkdown/R/render.R:162:in `<no source>'
|
496
|
+
## <REPL>:5:in `<repl wrapper>'
|
497
|
+
## <REPL>:1
|
498
|
+
\end{verbatim}
|
499
|
+
|
500
|
+
Here is a vector with logical values
|
501
|
+
|
502
|
+
\begin{Shaded}
|
503
|
+
\begin{Highlighting}[]
|
504
|
+
\NormalTok{vec = R.c(}\DecValTok{true}\NormalTok{, }\DecValTok{true}\NormalTok{, }\DecValTok{false}\NormalTok{, }\DecValTok{false}\NormalTok{, }\DecValTok{true}\NormalTok{)}
|
505
|
+
\NormalTok{puts vec}
|
506
|
+
\end{Highlighting}
|
507
|
+
\end{Shaded}
|
508
|
+
|
509
|
+
\begin{verbatim}
|
510
|
+
## [1] TRUE TRUE FALSE FALSE TRUE
|
511
|
+
\end{verbatim}
|
512
|
+
|
513
|
+
\hypertarget{combining-vectors}{%
|
514
|
+
\subsection{Combining Vectors}\label{combining-vectors}}
|
515
|
+
|
516
|
+
The `c' functions used to create vectors can also be used to combine two
|
517
|
+
vectors:
|
518
|
+
|
519
|
+
\begin{Shaded}
|
520
|
+
\begin{Highlighting}[]
|
521
|
+
\NormalTok{vec1 = R.c(}\FloatTok{10.0}\NormalTok{, }\FloatTok{20.0}\NormalTok{, }\FloatTok{30.0}\NormalTok{)}
|
522
|
+
\NormalTok{vec2 = R.c(}\FloatTok{4.0}\NormalTok{, }\FloatTok{5.0}\NormalTok{, }\FloatTok{6.0}\NormalTok{)}
|
523
|
+
\NormalTok{vec = R.c(vec1, vec2)}
|
524
|
+
\NormalTok{puts vec}
|
525
|
+
\end{Highlighting}
|
526
|
+
\end{Shaded}
|
527
|
+
|
528
|
+
\begin{verbatim}
|
529
|
+
## [1] 10 20 30 4 5 6
|
530
|
+
\end{verbatim}
|
531
|
+
|
532
|
+
In galaaz, methods can be chainned (somewhat like the pipe operator in R
|
533
|
+
\%\textgreater{}\%, but more generic). In this next example, method `c'
|
534
|
+
is chainned after `vec1'. This also looks like `c' is a method of the
|
535
|
+
vector, but in reallity, this is actually closer to the pipe operator.
|
536
|
+
When Galaaz identifies that `c' is not a method of `vec' it actually
|
537
|
+
tries to call `R.c' with `vec1' as the first argument concatenated with
|
538
|
+
all the other available arguments. The code bellow is automatically
|
539
|
+
converted to the code above.
|
540
|
+
|
541
|
+
\begin{Shaded}
|
542
|
+
\begin{Highlighting}[]
|
543
|
+
\NormalTok{vec = vec1.c(vec2)}
|
544
|
+
\NormalTok{puts vec}
|
545
|
+
\end{Highlighting}
|
546
|
+
\end{Shaded}
|
547
|
+
|
548
|
+
\begin{verbatim}
|
549
|
+
## [1] 10 20 30 4 5 6
|
550
|
+
\end{verbatim}
|
551
|
+
|
552
|
+
\hypertarget{vector-arithmetic}{%
|
553
|
+
\subsection{Vector Arithmetic}\label{vector-arithmetic}}
|
554
|
+
|
555
|
+
Arithmetic operations on vectors are performed element by element:
|
556
|
+
|
557
|
+
\begin{Shaded}
|
558
|
+
\begin{Highlighting}[]
|
559
|
+
\NormalTok{puts vec1 + vec2}
|
560
|
+
\end{Highlighting}
|
561
|
+
\end{Shaded}
|
562
|
+
|
563
|
+
\begin{verbatim}
|
564
|
+
## [1] 14 25 36
|
565
|
+
\end{verbatim}
|
566
|
+
|
567
|
+
\begin{Shaded}
|
568
|
+
\begin{Highlighting}[]
|
569
|
+
\NormalTok{puts vec1 * }\DecValTok{5}
|
570
|
+
\end{Highlighting}
|
571
|
+
\end{Shaded}
|
572
|
+
|
573
|
+
\begin{verbatim}
|
574
|
+
## [1] 50 100 150
|
575
|
+
\end{verbatim}
|
576
|
+
|
577
|
+
When vectors have different length, a recycling rule is applied to the
|
578
|
+
shorter vector:
|
579
|
+
|
580
|
+
\begin{Shaded}
|
581
|
+
\begin{Highlighting}[]
|
582
|
+
\NormalTok{vec3 = R.c(}\FloatTok{1.0}\NormalTok{, }\FloatTok{2.0}\NormalTok{, }\FloatTok{3.0}\NormalTok{, }\FloatTok{4.0}\NormalTok{, }\FloatTok{5.0}\NormalTok{, }\FloatTok{6.0}\NormalTok{, }\FloatTok{7.0}\NormalTok{, }\FloatTok{8.0}\NormalTok{, }\FloatTok{9.0}\NormalTok{)}
|
583
|
+
\NormalTok{puts vec4 = vec1 + vec3}
|
584
|
+
\end{Highlighting}
|
585
|
+
\end{Shaded}
|
586
|
+
|
587
|
+
\begin{verbatim}
|
588
|
+
## [1] 11 22 33 14 25 36 17 28 39
|
589
|
+
\end{verbatim}
|
590
|
+
|
591
|
+
\hypertarget{vector-indexing}{%
|
592
|
+
\subsection{Vector Indexing}\label{vector-indexing}}
|
593
|
+
|
594
|
+
Vectors can be indexed by using the `{[}{]}' operator:
|
595
|
+
|
596
|
+
\begin{Shaded}
|
597
|
+
\begin{Highlighting}[]
|
598
|
+
\NormalTok{puts vec4[}\DecValTok{3}\NormalTok{]}
|
599
|
+
\end{Highlighting}
|
600
|
+
\end{Shaded}
|
601
|
+
|
602
|
+
\begin{verbatim}
|
603
|
+
## [1] 33
|
604
|
+
\end{verbatim}
|
605
|
+
|
606
|
+
We can also index a vector with another vector. For example, in the code
|
607
|
+
bellow, we take elements 1, 3, 5, and 7 from vec3:
|
608
|
+
|
609
|
+
\begin{Shaded}
|
610
|
+
\begin{Highlighting}[]
|
611
|
+
\NormalTok{puts vec4[R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{3}\NormalTok{, }\DecValTok{5}\NormalTok{, }\DecValTok{7}\NormalTok{)]}
|
612
|
+
\end{Highlighting}
|
613
|
+
\end{Shaded}
|
614
|
+
|
615
|
+
\begin{verbatim}
|
616
|
+
## [1] 11 33 25 17
|
617
|
+
\end{verbatim}
|
618
|
+
|
619
|
+
Repeating an index and having indices out of order is valid code:
|
620
|
+
|
621
|
+
\begin{Shaded}
|
622
|
+
\begin{Highlighting}[]
|
623
|
+
\NormalTok{puts vec4[R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{3}\NormalTok{, }\DecValTok{3}\NormalTok{, }\DecValTok{1}\NormalTok{)]}
|
624
|
+
\end{Highlighting}
|
625
|
+
\end{Shaded}
|
626
|
+
|
627
|
+
\begin{verbatim}
|
628
|
+
## [1] 11 33 33 11
|
629
|
+
\end{verbatim}
|
630
|
+
|
631
|
+
It is also possible to index a vector with a negative number or negative
|
632
|
+
vector. In these cases the indexed values are not returned:
|
633
|
+
|
634
|
+
\begin{Shaded}
|
635
|
+
\begin{Highlighting}[]
|
636
|
+
\NormalTok{puts vec4[-}\DecValTok{3}\NormalTok{]}
|
637
|
+
\NormalTok{puts vec4[-R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{3}\NormalTok{, }\DecValTok{5}\NormalTok{, }\DecValTok{7}\NormalTok{)]}
|
638
|
+
\end{Highlighting}
|
639
|
+
\end{Shaded}
|
640
|
+
|
641
|
+
\begin{verbatim}
|
642
|
+
## [1] 11 22 14 25 36 17 28 39
|
643
|
+
## [1] 22 14 36 28 39
|
644
|
+
\end{verbatim}
|
645
|
+
|
646
|
+
If an index is out of range, a missing value (NA) will be reported.
|
647
|
+
|
648
|
+
\begin{Shaded}
|
649
|
+
\begin{Highlighting}[]
|
650
|
+
\NormalTok{puts vec4[}\DecValTok{30}\NormalTok{]}
|
651
|
+
\end{Highlighting}
|
652
|
+
\end{Shaded}
|
653
|
+
|
654
|
+
\begin{verbatim}
|
655
|
+
## [1] NA
|
656
|
+
\end{verbatim}
|
657
|
+
|
658
|
+
It is also possible to index a vector by range:
|
659
|
+
|
660
|
+
\begin{Shaded}
|
661
|
+
\begin{Highlighting}[]
|
662
|
+
\NormalTok{puts vec4[(}\DecValTok{2}\NormalTok{..}\DecValTok{5}\NormalTok{)]}
|
663
|
+
\end{Highlighting}
|
664
|
+
\end{Shaded}
|
665
|
+
|
666
|
+
\begin{verbatim}
|
667
|
+
## [1] 22 33 14 25
|
668
|
+
\end{verbatim}
|
669
|
+
|
670
|
+
Elements in a vector can be named using the `names' attribute of a
|
671
|
+
vector:
|
672
|
+
|
673
|
+
\begin{Shaded}
|
674
|
+
\begin{Highlighting}[]
|
675
|
+
\NormalTok{full_name = R.c(}\StringTok{"Rodrigo"}\NormalTok{, }\StringTok{"A"}\NormalTok{, }\StringTok{"Botafogo"}\NormalTok{)}
|
676
|
+
\NormalTok{full_name.names = R.c(}\StringTok{"First"}\NormalTok{, }\StringTok{"Middle"}\NormalTok{, }\StringTok{"Last"}\NormalTok{)}
|
677
|
+
\NormalTok{puts full_name}
|
678
|
+
\end{Highlighting}
|
679
|
+
\end{Shaded}
|
680
|
+
|
681
|
+
\begin{verbatim}
|
682
|
+
## First Middle Last
|
683
|
+
## "Rodrigo" "A" "Botafogo"
|
684
|
+
\end{verbatim}
|
685
|
+
|
686
|
+
Or it can also be named by using the `c' function with named
|
687
|
+
paramenters:
|
688
|
+
|
689
|
+
\begin{Shaded}
|
690
|
+
\begin{Highlighting}[]
|
691
|
+
\NormalTok{full_name = R.c(}\DataTypeTok{First}\NormalTok{: }\StringTok{"Rodrigo"}\NormalTok{, }\DataTypeTok{Middle}\NormalTok{: }\StringTok{"A"}\NormalTok{, }\DataTypeTok{Last}\NormalTok{: }\StringTok{"Botafogo"}\NormalTok{)}
|
692
|
+
\NormalTok{puts full_name}
|
693
|
+
\end{Highlighting}
|
694
|
+
\end{Shaded}
|
695
|
+
|
696
|
+
\begin{verbatim}
|
697
|
+
## First Middle Last
|
698
|
+
## "Rodrigo" "A" "Botafogo"
|
699
|
+
\end{verbatim}
|
700
|
+
|
701
|
+
\hypertarget{extracting-native-ruby-types-from-a-vector}{%
|
702
|
+
\subsection{Extracting Native Ruby Types from a
|
703
|
+
Vector}\label{extracting-native-ruby-types-from-a-vector}}
|
704
|
+
|
705
|
+
Vectors created with `R.c' are of class R::Vector. You might have
|
706
|
+
noticed that when indexing a vector, a new vector is returned, even if
|
707
|
+
this vector has one single element. In order to use R::Vector with other
|
708
|
+
ruby classes it might be necessary to extract the actual Ruby native
|
709
|
+
type from the vector. In order to do this extraction the
|
710
|
+
`\textgreater{}\textgreater{}' operator is used.
|
711
|
+
|
712
|
+
\begin{Shaded}
|
713
|
+
\begin{Highlighting}[]
|
714
|
+
\NormalTok{puts vec4}
|
715
|
+
\NormalTok{puts vec4 >> }\DecValTok{0}
|
716
|
+
\NormalTok{puts vec4 >> }\DecValTok{4}
|
717
|
+
\end{Highlighting}
|
718
|
+
\end{Shaded}
|
719
|
+
|
720
|
+
\begin{verbatim}
|
721
|
+
## [1] 11 22 33 14 25 36 17 28 39
|
722
|
+
## 11.0
|
723
|
+
## 25.0
|
724
|
+
\end{verbatim}
|
725
|
+
|
726
|
+
Note that indexing with `\textgreater{}\textgreater{}' starts at 0 and
|
727
|
+
not at 1, also, we cannot do negative indexing.
|
728
|
+
|
729
|
+
\hypertarget{accessing-r-variables}{%
|
730
|
+
\section{Accessing R variables}\label{accessing-r-variables}}
|
731
|
+
|
732
|
+
Galaaz allows Ruby to access variables created in R. For example, the
|
733
|
+
`mtcars' data set is available in R and can be accessed from Ruby by
|
734
|
+
using the `tilda' operator followed by the symbol for the variable, in
|
735
|
+
this case `:mtcar'. In the code bellow method `outputs' is used to
|
736
|
+
output the `mtcars' data set nicely formatted in HTML by use of the
|
737
|
+
`kable' and `kable\_styling' functions. Method `outputs' is only
|
738
|
+
available when used with `gknit'.
|
739
|
+
|
740
|
+
\begin{Shaded}
|
741
|
+
\begin{Highlighting}[]
|
742
|
+
\NormalTok{outputs (~}\StringTok{:mtcars}\NormalTok{).kable.kable_styling}
|
743
|
+
\end{Highlighting}
|
744
|
+
\end{Shaded}
|
745
|
+
|
746
|
+
\begin{table}[H]
|
747
|
+
\centering
|
748
|
+
\begin{tabular}{l|r|r|r|r|r|r|r|r|r|r|r}
|
749
|
+
\hline
|
750
|
+
& mpg & cyl & disp & hp & drat & wt & qsec & vs & am & gear & carb\\
|
751
|
+
\hline
|
752
|
+
Mazda RX4 & 21.0 & 6 & 160.0 & 110 & 3.90 & 2.620 & 16.46 & 0 & 1 & 4 & 4\\
|
753
|
+
\hline
|
754
|
+
Mazda RX4 Wag & 21.0 & 6 & 160.0 & 110 & 3.90 & 2.875 & 17.02 & 0 & 1 & 4 & 4\\
|
755
|
+
\hline
|
756
|
+
Datsun 710 & 22.8 & 4 & 108.0 & 93 & 3.85 & 2.320 & 18.61 & 1 & 1 & 4 & 1\\
|
757
|
+
\hline
|
758
|
+
Hornet 4 Drive & 21.4 & 6 & 258.0 & 110 & 3.08 & 3.215 & 19.44 & 1 & 0 & 3 & 1\\
|
759
|
+
\hline
|
760
|
+
Hornet Sportabout & 18.7 & 8 & 360.0 & 175 & 3.15 & 3.440 & 17.02 & 0 & 0 & 3 & 2\\
|
761
|
+
\hline
|
762
|
+
Valiant & 18.1 & 6 & 225.0 & 105 & 2.76 & 3.460 & 20.22 & 1 & 0 & 3 & 1\\
|
763
|
+
\hline
|
764
|
+
Duster 360 & 14.3 & 8 & 360.0 & 245 & 3.21 & 3.570 & 15.84 & 0 & 0 & 3 & 4\\
|
765
|
+
\hline
|
766
|
+
Merc 240D & 24.4 & 4 & 146.7 & 62 & 3.69 & 3.190 & 20.00 & 1 & 0 & 4 & 2\\
|
767
|
+
\hline
|
768
|
+
Merc 230 & 22.8 & 4 & 140.8 & 95 & 3.92 & 3.150 & 22.90 & 1 & 0 & 4 & 2\\
|
769
|
+
\hline
|
770
|
+
Merc 280 & 19.2 & 6 & 167.6 & 123 & 3.92 & 3.440 & 18.30 & 1 & 0 & 4 & 4\\
|
771
|
+
\hline
|
772
|
+
Merc 280C & 17.8 & 6 & 167.6 & 123 & 3.92 & 3.440 & 18.90 & 1 & 0 & 4 & 4\\
|
773
|
+
\hline
|
774
|
+
Merc 450SE & 16.4 & 8 & 275.8 & 180 & 3.07 & 4.070 & 17.40 & 0 & 0 & 3 & 3\\
|
775
|
+
\hline
|
776
|
+
Merc 450SL & 17.3 & 8 & 275.8 & 180 & 3.07 & 3.730 & 17.60 & 0 & 0 & 3 & 3\\
|
777
|
+
\hline
|
778
|
+
Merc 450SLC & 15.2 & 8 & 275.8 & 180 & 3.07 & 3.780 & 18.00 & 0 & 0 & 3 & 3\\
|
779
|
+
\hline
|
780
|
+
Cadillac Fleetwood & 10.4 & 8 & 472.0 & 205 & 2.93 & 5.250 & 17.98 & 0 & 0 & 3 & 4\\
|
781
|
+
\hline
|
782
|
+
Lincoln Continental & 10.4 & 8 & 460.0 & 215 & 3.00 & 5.424 & 17.82 & 0 & 0 & 3 & 4\\
|
783
|
+
\hline
|
784
|
+
Chrysler Imperial & 14.7 & 8 & 440.0 & 230 & 3.23 & 5.345 & 17.42 & 0 & 0 & 3 & 4\\
|
785
|
+
\hline
|
786
|
+
Fiat 128 & 32.4 & 4 & 78.7 & 66 & 4.08 & 2.200 & 19.47 & 1 & 1 & 4 & 1\\
|
787
|
+
\hline
|
788
|
+
Honda Civic & 30.4 & 4 & 75.7 & 52 & 4.93 & 1.615 & 18.52 & 1 & 1 & 4 & 2\\
|
789
|
+
\hline
|
790
|
+
Toyota Corolla & 33.9 & 4 & 71.1 & 65 & 4.22 & 1.835 & 19.90 & 1 & 1 & 4 & 1\\
|
791
|
+
\hline
|
792
|
+
Toyota Corona & 21.5 & 4 & 120.1 & 97 & 3.70 & 2.465 & 20.01 & 1 & 0 & 3 & 1\\
|
793
|
+
\hline
|
794
|
+
Dodge Challenger & 15.5 & 8 & 318.0 & 150 & 2.76 & 3.520 & 16.87 & 0 & 0 & 3 & 2\\
|
795
|
+
\hline
|
796
|
+
AMC Javelin & 15.2 & 8 & 304.0 & 150 & 3.15 & 3.435 & 17.30 & 0 & 0 & 3 & 2\\
|
797
|
+
\hline
|
798
|
+
Camaro Z28 & 13.3 & 8 & 350.0 & 245 & 3.73 & 3.840 & 15.41 & 0 & 0 & 3 & 4\\
|
799
|
+
\hline
|
800
|
+
Pontiac Firebird & 19.2 & 8 & 400.0 & 175 & 3.08 & 3.845 & 17.05 & 0 & 0 & 3 & 2\\
|
801
|
+
\hline
|
802
|
+
Fiat X1-9 & 27.3 & 4 & 79.0 & 66 & 4.08 & 1.935 & 18.90 & 1 & 1 & 4 & 1\\
|
803
|
+
\hline
|
804
|
+
Porsche 914-2 & 26.0 & 4 & 120.3 & 91 & 4.43 & 2.140 & 16.70 & 0 & 1 & 5 & 2\\
|
805
|
+
\hline
|
806
|
+
Lotus Europa & 30.4 & 4 & 95.1 & 113 & 3.77 & 1.513 & 16.90 & 1 & 1 & 5 & 2\\
|
807
|
+
\hline
|
808
|
+
Ford Pantera L & 15.8 & 8 & 351.0 & 264 & 4.22 & 3.170 & 14.50 & 0 & 1 & 5 & 4\\
|
809
|
+
\hline
|
810
|
+
Ferrari Dino & 19.7 & 6 & 145.0 & 175 & 3.62 & 2.770 & 15.50 & 0 & 1 & 5 & 6\\
|
811
|
+
\hline
|
812
|
+
Maserati Bora & 15.0 & 8 & 301.0 & 335 & 3.54 & 3.570 & 14.60 & 0 & 1 & 5 & 8\\
|
813
|
+
\hline
|
814
|
+
Volvo 142E & 21.4 & 4 & 121.0 & 109 & 4.11 & 2.780 & 18.60 & 1 & 1 & 4 & 2\\
|
815
|
+
\hline
|
816
|
+
\end{tabular}
|
817
|
+
\end{table}
|
818
|
+
|
819
|
+
\hypertarget{matrix}{%
|
820
|
+
\section{Matrix}\label{matrix}}
|
821
|
+
|
822
|
+
A matrix is a collection of elements organized as a two dimensional
|
823
|
+
table. A matrix can be created by the `matrix' function:
|
824
|
+
|
825
|
+
\begin{Shaded}
|
826
|
+
\begin{Highlighting}[]
|
827
|
+
\NormalTok{mat = R.matrix(R.c(}\FloatTok{1.0}\NormalTok{, }\FloatTok{2.0}\NormalTok{, }\FloatTok{3.0}\NormalTok{, }\FloatTok{4.0}\NormalTok{, }\FloatTok{5.0}\NormalTok{, }\FloatTok{6.0}\NormalTok{, }\FloatTok{7.0}\NormalTok{, }\FloatTok{8.0}\NormalTok{, }\FloatTok{9.0}\NormalTok{),}
|
828
|
+
\StringTok{nrow: }\DecValTok{3}\NormalTok{,}
|
829
|
+
\StringTok{ncol: }\DecValTok{3}\NormalTok{)}
|
830
|
+
|
831
|
+
\NormalTok{puts mat}
|
832
|
+
\end{Highlighting}
|
833
|
+
\end{Shaded}
|
834
|
+
|
835
|
+
\begin{verbatim}
|
836
|
+
## [,1] [,2] [,3]
|
837
|
+
## [1,] 1 4 7
|
838
|
+
## [2,] 2 5 8
|
839
|
+
## [3,] 3 6 9
|
840
|
+
\end{verbatim}
|
841
|
+
|
842
|
+
Note that matrices data is organized by column first. It is possible to
|
843
|
+
organize the matrix memory by row first passing an extra argument to the
|
844
|
+
`matrix' function:
|
845
|
+
|
846
|
+
\begin{Shaded}
|
847
|
+
\begin{Highlighting}[]
|
848
|
+
\NormalTok{mat_row = R.matrix(R.c(}\FloatTok{1.0}\NormalTok{, }\FloatTok{2.0}\NormalTok{, }\FloatTok{3.0}\NormalTok{, }\FloatTok{4.0}\NormalTok{, }\FloatTok{5.0}\NormalTok{, }\FloatTok{6.0}\NormalTok{, }\FloatTok{7.0}\NormalTok{, }\FloatTok{8.0}\NormalTok{, }\FloatTok{9.0}\NormalTok{),}
|
849
|
+
\StringTok{nrow: }\DecValTok{3}\NormalTok{,}
|
850
|
+
\StringTok{ncol: }\DecValTok{3}\NormalTok{,}
|
851
|
+
\StringTok{byrow: }\DecValTok{true}\NormalTok{)}
|
852
|
+
|
853
|
+
\NormalTok{puts mat_row}
|
854
|
+
\end{Highlighting}
|
855
|
+
\end{Shaded}
|
856
|
+
|
857
|
+
\begin{verbatim}
|
858
|
+
## [,1] [,2] [,3]
|
859
|
+
## [1,] 1 2 3
|
860
|
+
## [2,] 4 5 6
|
861
|
+
## [3,] 7 8 9
|
862
|
+
\end{verbatim}
|
863
|
+
|
864
|
+
\hypertarget{indexing-a-matrix}{%
|
865
|
+
\subsection{Indexing a Matrix}\label{indexing-a-matrix}}
|
866
|
+
|
867
|
+
A matrix can be indexed by {[}row, column{]}:
|
868
|
+
|
869
|
+
\begin{Shaded}
|
870
|
+
\begin{Highlighting}[]
|
871
|
+
\NormalTok{puts mat_row[}\DecValTok{1}\NormalTok{, }\DecValTok{1}\NormalTok{]}
|
872
|
+
\NormalTok{puts mat_row[}\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{]}
|
873
|
+
\end{Highlighting}
|
874
|
+
\end{Shaded}
|
875
|
+
|
876
|
+
\begin{verbatim}
|
877
|
+
## [1] 1
|
878
|
+
## [1] 6
|
879
|
+
\end{verbatim}
|
880
|
+
|
881
|
+
It is possible to index an entire row or column with the `:all' keyword
|
882
|
+
|
883
|
+
\begin{Shaded}
|
884
|
+
\begin{Highlighting}[]
|
885
|
+
\NormalTok{puts mat_row[}\DecValTok{1}\NormalTok{, }\StringTok{:all}\NormalTok{]}
|
886
|
+
\NormalTok{puts mat_row[}\StringTok{:all}\NormalTok{, }\DecValTok{2}\NormalTok{]}
|
887
|
+
\end{Highlighting}
|
888
|
+
\end{Shaded}
|
889
|
+
|
890
|
+
\begin{verbatim}
|
891
|
+
## [1] 1 2 3
|
892
|
+
## [1] 2 5 8
|
893
|
+
\end{verbatim}
|
894
|
+
|
895
|
+
Indexing with a vector is also possible for matrices. In the following
|
896
|
+
example we want rows 1 and 3 and columns 2 and 3 building a 2 x 2
|
897
|
+
matrix.
|
898
|
+
|
899
|
+
\begin{Shaded}
|
900
|
+
\begin{Highlighting}[]
|
901
|
+
\NormalTok{puts mat_row[R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{3}\NormalTok{), R.c(}\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{)]}
|
902
|
+
\end{Highlighting}
|
903
|
+
\end{Shaded}
|
904
|
+
|
905
|
+
\begin{verbatim}
|
906
|
+
## [,1] [,2]
|
907
|
+
## [1,] 2 3
|
908
|
+
## [2,] 8 9
|
909
|
+
\end{verbatim}
|
910
|
+
|
911
|
+
Matrices can be combined with functions `rbind':
|
912
|
+
|
913
|
+
\begin{Shaded}
|
914
|
+
\begin{Highlighting}[]
|
915
|
+
\NormalTok{puts mat_row.rbind(mat)}
|
916
|
+
\end{Highlighting}
|
917
|
+
\end{Shaded}
|
918
|
+
|
919
|
+
\begin{verbatim}
|
920
|
+
## [,1] [,2] [,3]
|
921
|
+
## [1,] 1 2 3
|
922
|
+
## [2,] 4 5 6
|
923
|
+
## [3,] 7 8 9
|
924
|
+
## [4,] 1 4 7
|
925
|
+
## [5,] 2 5 8
|
926
|
+
## [6,] 3 6 9
|
927
|
+
\end{verbatim}
|
928
|
+
|
929
|
+
and `cbind':
|
930
|
+
|
931
|
+
\begin{Shaded}
|
932
|
+
\begin{Highlighting}[]
|
933
|
+
\NormalTok{puts mat_row.cbind(mat)}
|
934
|
+
\end{Highlighting}
|
935
|
+
\end{Shaded}
|
936
|
+
|
937
|
+
\begin{verbatim}
|
938
|
+
## [,1] [,2] [,3] [,4] [,5] [,6]
|
939
|
+
## [1,] 1 2 3 1 4 7
|
940
|
+
## [2,] 4 5 6 2 5 8
|
941
|
+
## [3,] 7 8 9 3 6 9
|
942
|
+
\end{verbatim}
|
943
|
+
|
944
|
+
\hypertarget{list}{%
|
945
|
+
\section{List}\label{list}}
|
946
|
+
|
947
|
+
A list is a data structure that can contain sublists of different types,
|
948
|
+
while vector and matrix can only hold one type of element.
|
949
|
+
|
950
|
+
\begin{Shaded}
|
951
|
+
\begin{Highlighting}[]
|
952
|
+
\NormalTok{nums = R.c(}\FloatTok{1.0}\NormalTok{, }\FloatTok{2.0}\NormalTok{, }\FloatTok{3.0}\NormalTok{)}
|
953
|
+
\NormalTok{strs = R.c(}\StringTok{"a"}\NormalTok{, }\StringTok{"b"}\NormalTok{, }\StringTok{"c"}\NormalTok{, }\StringTok{"d"}\NormalTok{)}
|
954
|
+
\NormalTok{bool = R.c(}\DecValTok{true}\NormalTok{, }\DecValTok{true}\NormalTok{, }\DecValTok{false}\NormalTok{)}
|
955
|
+
\NormalTok{lst = R.list(}\StringTok{nums: }\NormalTok{nums, }\StringTok{strs: }\NormalTok{strs, }\StringTok{bool: }\NormalTok{bool)}
|
956
|
+
\NormalTok{puts lst}
|
957
|
+
\end{Highlighting}
|
958
|
+
\end{Shaded}
|
959
|
+
|
960
|
+
\begin{verbatim}
|
961
|
+
## $nums
|
962
|
+
## [1] 1 2 3
|
963
|
+
##
|
964
|
+
## $strs
|
965
|
+
## [1] "a" "b" "c" "d"
|
966
|
+
##
|
967
|
+
## $bool
|
968
|
+
## [1] TRUE TRUE FALSE
|
969
|
+
\end{verbatim}
|
970
|
+
|
971
|
+
Note that `lst' elements are named elements.
|
972
|
+
|
973
|
+
\hypertarget{list-indexing}{%
|
974
|
+
\subsection{List Indexing}\label{list-indexing}}
|
975
|
+
|
976
|
+
List indexing, also called slicing, is done using the `{[}{]}' operator
|
977
|
+
and the `{[}{[}{]}{]}' operator. Let's first start with the `{[}{]}'
|
978
|
+
operator. The list above has three sublist indexing with `{[}{]}' will
|
979
|
+
return one of the sublists.
|
980
|
+
|
981
|
+
\begin{Shaded}
|
982
|
+
\begin{Highlighting}[]
|
983
|
+
\NormalTok{puts lst[}\DecValTok{1}\NormalTok{]}
|
984
|
+
\end{Highlighting}
|
985
|
+
\end{Shaded}
|
986
|
+
|
987
|
+
\begin{verbatim}
|
988
|
+
## $nums
|
989
|
+
## [1] 1 2 3
|
990
|
+
\end{verbatim}
|
991
|
+
|
992
|
+
Note that when using `{[}{]}' a new list is returned. When using the
|
993
|
+
double square bracket operator the value returned is the actual element
|
994
|
+
of the list in the given position and not a slice of the original list
|
995
|
+
|
996
|
+
\begin{Shaded}
|
997
|
+
\begin{Highlighting}[]
|
998
|
+
\NormalTok{puts lst[[}\DecValTok{1}\NormalTok{]]}
|
999
|
+
\end{Highlighting}
|
1000
|
+
\end{Shaded}
|
1001
|
+
|
1002
|
+
\begin{verbatim}
|
1003
|
+
## [1] 1 2 3
|
1004
|
+
\end{verbatim}
|
1005
|
+
|
1006
|
+
When elements are named, as dones with lst, indexing can be done by
|
1007
|
+
name:
|
1008
|
+
|
1009
|
+
\begin{Shaded}
|
1010
|
+
\begin{Highlighting}[]
|
1011
|
+
\NormalTok{puts lst[[}\StringTok{'bool'}\NormalTok{]][[}\DecValTok{1}\NormalTok{]] >> }\DecValTok{0}
|
1012
|
+
\end{Highlighting}
|
1013
|
+
\end{Shaded}
|
1014
|
+
|
1015
|
+
\begin{verbatim}
|
1016
|
+
## true
|
1017
|
+
\end{verbatim}
|
1018
|
+
|
1019
|
+
In this example, first the `bool' element of the list was extracted, not
|
1020
|
+
as a list, but as a vector, then the first element of the vector was
|
1021
|
+
extracted (note that vectors also accept the `{[}{[}{]}{]}' operator)
|
1022
|
+
and then the vector was indexed by its first element, extracting the
|
1023
|
+
native Ruby type.
|
1024
|
+
|
1025
|
+
\hypertarget{data-frame}{%
|
1026
|
+
\section{Data Frame}\label{data-frame}}
|
1027
|
+
|
1028
|
+
A data frame is a table like structure in which each column has the same
|
1029
|
+
number of rows. Data frames are the basic structure for storing data for
|
1030
|
+
data analysis. We have already seen a data frame previously when we
|
1031
|
+
accessed variable `\textasciitilde{}:mtcars'. In order to create a data
|
1032
|
+
frame, function 'data\_\_frame' is used:
|
1033
|
+
|
1034
|
+
\begin{Shaded}
|
1035
|
+
\begin{Highlighting}[]
|
1036
|
+
\NormalTok{df = R.data__frame(}
|
1037
|
+
\StringTok{year: }\NormalTok{R.c(}\DecValTok{2010}\NormalTok{, }\DecValTok{2011}\NormalTok{, }\DecValTok{2012}\NormalTok{),}
|
1038
|
+
\StringTok{income: }\NormalTok{R.c(}\FloatTok{1000.0}\NormalTok{, }\FloatTok{1500.0}\NormalTok{, }\FloatTok{2000.0}\NormalTok{))}
|
1039
|
+
|
1040
|
+
\NormalTok{puts df}
|
1041
|
+
\end{Highlighting}
|
1042
|
+
\end{Shaded}
|
1043
|
+
|
1044
|
+
\begin{verbatim}
|
1045
|
+
## year income
|
1046
|
+
## 1 2010 1000
|
1047
|
+
## 2 2011 1500
|
1048
|
+
## 3 2012 2000
|
1049
|
+
\end{verbatim}
|
1050
|
+
|
1051
|
+
\hypertarget{data-frame-indexing}{%
|
1052
|
+
\subsection{Data Frame Indexing}\label{data-frame-indexing}}
|
1053
|
+
|
1054
|
+
A data frame can be indexed the same way as a matrix, by using `{[}row,
|
1055
|
+
column{]}', where row and column can either be a numeric or the name of
|
1056
|
+
the row or column
|
1057
|
+
|
1058
|
+
\begin{Shaded}
|
1059
|
+
\begin{Highlighting}[]
|
1060
|
+
\NormalTok{puts (~}\StringTok{:mtcars}\NormalTok{).head}
|
1061
|
+
\NormalTok{puts (~}\StringTok{:mtcars}\NormalTok{)[}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{]}
|
1062
|
+
\NormalTok{puts (~}\StringTok{:mtcars}\NormalTok{)[}\StringTok{'Datsun 710'}\NormalTok{, }\StringTok{'mpg'}\NormalTok{]}
|
1063
|
+
\end{Highlighting}
|
1064
|
+
\end{Shaded}
|
1065
|
+
|
1066
|
+
\begin{verbatim}
|
1067
|
+
## mpg cyl disp hp drat wt qsec vs am gear carb
|
1068
|
+
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
|
1069
|
+
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
|
1070
|
+
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
|
1071
|
+
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
|
1072
|
+
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
|
1073
|
+
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
|
1074
|
+
## [1] 6
|
1075
|
+
## [1] 22.8
|
1076
|
+
\end{verbatim}
|
1077
|
+
|
1078
|
+
Extracting a column from a data frame as a vector can be done by using
|
1079
|
+
the double square bracket operator:
|
1080
|
+
|
1081
|
+
\begin{Shaded}
|
1082
|
+
\begin{Highlighting}[]
|
1083
|
+
\NormalTok{puts (~}\StringTok{:mtcars}\NormalTok{)[[}\StringTok{'mpg'}\NormalTok{]]}
|
1084
|
+
\end{Highlighting}
|
1085
|
+
\end{Shaded}
|
1086
|
+
|
1087
|
+
\begin{verbatim}
|
1088
|
+
## [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2
|
1089
|
+
## [15] 10.4 10.4 14.7 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4
|
1090
|
+
## [29] 15.8 19.7 15.0 21.4
|
1091
|
+
\end{verbatim}
|
1092
|
+
|
1093
|
+
A data frame column can also be accessed as if it were an instance
|
1094
|
+
variable of the data frame:
|
1095
|
+
|
1096
|
+
\begin{Shaded}
|
1097
|
+
\begin{Highlighting}[]
|
1098
|
+
\NormalTok{puts (~}\StringTok{:mtcars}\NormalTok{).mpg}
|
1099
|
+
\end{Highlighting}
|
1100
|
+
\end{Shaded}
|
1101
|
+
|
1102
|
+
\begin{verbatim}
|
1103
|
+
## [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2
|
1104
|
+
## [15] 10.4 10.4 14.7 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4
|
1105
|
+
## [29] 15.8 19.7 15.0 21.4
|
1106
|
+
\end{verbatim}
|
1107
|
+
|
1108
|
+
Slicing a data frame can be done by indexing it with a vector (we use
|
1109
|
+
`head' to reduce the output):
|
1110
|
+
|
1111
|
+
\begin{Shaded}
|
1112
|
+
\begin{Highlighting}[]
|
1113
|
+
\NormalTok{puts (~}\StringTok{:mtcars}\NormalTok{)[R.c(}\StringTok{'mpg'}\NormalTok{, }\StringTok{'hp'}\NormalTok{)].head}
|
1114
|
+
\end{Highlighting}
|
1115
|
+
\end{Shaded}
|
1116
|
+
|
1117
|
+
\begin{verbatim}
|
1118
|
+
## mpg hp
|
1119
|
+
## Mazda RX4 21.0 110
|
1120
|
+
## Mazda RX4 Wag 21.0 110
|
1121
|
+
## Datsun 710 22.8 93
|
1122
|
+
## Hornet 4 Drive 21.4 110
|
1123
|
+
## Hornet Sportabout 18.7 175
|
1124
|
+
## Valiant 18.1 105
|
1125
|
+
\end{verbatim}
|
1126
|
+
|
1127
|
+
A row slice can be obtained by indexing by row and using the `:all'
|
1128
|
+
keyword for the column:
|
1129
|
+
|
1130
|
+
\begin{Shaded}
|
1131
|
+
\begin{Highlighting}[]
|
1132
|
+
\NormalTok{puts (~}\StringTok{:mtcars}\NormalTok{)[R.c(}\StringTok{'Datsun 710'}\NormalTok{, }\StringTok{'Camaro Z28'}\NormalTok{), }\StringTok{:all}\NormalTok{]}
|
1133
|
+
\end{Highlighting}
|
1134
|
+
\end{Shaded}
|
1135
|
+
|
1136
|
+
\begin{verbatim}
|
1137
|
+
## mpg cyl disp hp drat wt qsec vs am gear carb
|
1138
|
+
## Datsun 710 22.8 4 108 93 3.85 2.32 18.61 1 1 4 1
|
1139
|
+
## Camaro Z28 13.3 8 350 245 3.73 3.84 15.41 0 0 3 4
|
1140
|
+
\end{verbatim}
|
1141
|
+
|
1142
|
+
Finally, a data frame can also be indexed with a logical vector. In this
|
1143
|
+
next example, the `am' column of :mtcars is compared with 0 (with method
|
1144
|
+
`eq'). When `am' is equal to 0 the car is automatic. So, by doing
|
1145
|
+
`(\textasciitilde{}:mtcars).am.eq 0' a logical vector is created with
|
1146
|
+
`true' whenever `am' is 0 and `false' otherwise.
|
1147
|
+
|
1148
|
+
\begin{Shaded}
|
1149
|
+
\begin{Highlighting}[]
|
1150
|
+
\CommentTok{# obtain a vector with 'true' for cars with automatic transmission}
|
1151
|
+
\NormalTok{automatic = (~}\StringTok{:mtcars}\NormalTok{).am.eq }\DecValTok{0}
|
1152
|
+
\NormalTok{puts automatic}
|
1153
|
+
\end{Highlighting}
|
1154
|
+
\end{Shaded}
|
1155
|
+
|
1156
|
+
\begin{verbatim}
|
1157
|
+
## [1] FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
|
1158
|
+
## [12] TRUE TRUE TRUE TRUE TRUE TRUE FALSE FALSE FALSE TRUE TRUE
|
1159
|
+
## [23] TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
|
1160
|
+
\end{verbatim}
|
1161
|
+
|
1162
|
+
Using this logical vector, the data frame is indexed, returning a new
|
1163
|
+
data frame in which all cars have automatic transmission.
|
1164
|
+
|
1165
|
+
\begin{Shaded}
|
1166
|
+
\begin{Highlighting}[]
|
1167
|
+
\CommentTok{# slice the data frame by using this vector}
|
1168
|
+
\NormalTok{puts (~}\StringTok{:mtcars}\NormalTok{)[automatic, }\StringTok{:all}\NormalTok{]}
|
1169
|
+
\end{Highlighting}
|
1170
|
+
\end{Shaded}
|
1171
|
+
|
1172
|
+
\begin{verbatim}
|
1173
|
+
## mpg cyl disp hp drat wt qsec vs am gear carb
|
1174
|
+
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
|
1175
|
+
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
|
1176
|
+
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
|
1177
|
+
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
|
1178
|
+
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
|
1179
|
+
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
|
1180
|
+
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
|
1181
|
+
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
|
1182
|
+
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
|
1183
|
+
## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
|
1184
|
+
## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
|
1185
|
+
## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
|
1186
|
+
## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
|
1187
|
+
## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
|
1188
|
+
## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
|
1189
|
+
## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
|
1190
|
+
## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
|
1191
|
+
## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
|
1192
|
+
## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
|
1193
|
+
\end{verbatim}
|
1194
|
+
|
1195
|
+
\hypertarget{writing-expressions-in-galaaz}{%
|
1196
|
+
\section{Writing Expressions in
|
1197
|
+
Galaaz}\label{writing-expressions-in-galaaz}}
|
1198
|
+
|
1199
|
+
Galaaz extends Ruby to work with complex expressions, similar to R's
|
1200
|
+
expressions build with `quote' (base R) or `quo' (tidyverse). Let's take
|
1201
|
+
a look at some of those expressions.
|
1202
|
+
|
1203
|
+
\hypertarget{expressions-from-operators}{%
|
1204
|
+
\subsection{Expressions from
|
1205
|
+
operators}\label{expressions-from-operators}}
|
1206
|
+
|
1207
|
+
The code bellow creates an expression summing two symbols
|
1208
|
+
|
1209
|
+
\begin{Shaded}
|
1210
|
+
\begin{Highlighting}[]
|
1211
|
+
\NormalTok{exp1 = }\StringTok{:a}\NormalTok{ + }\StringTok{:b}
|
1212
|
+
\NormalTok{puts exp1}
|
1213
|
+
\end{Highlighting}
|
1214
|
+
\end{Shaded}
|
1215
|
+
|
1216
|
+
\begin{verbatim}
|
1217
|
+
## a + b
|
1218
|
+
\end{verbatim}
|
1219
|
+
|
1220
|
+
We can build any complex mathematical expression
|
1221
|
+
|
1222
|
+
\begin{Shaded}
|
1223
|
+
\begin{Highlighting}[]
|
1224
|
+
\NormalTok{exp2 = (}\StringTok{:a}\NormalTok{ + }\StringTok{:b}\NormalTok{) * }\FloatTok{2.0}\NormalTok{ + }\StringTok{:c}\NormalTok{ ** }\DecValTok{2}\NormalTok{ / }\StringTok{:z}
|
1225
|
+
\NormalTok{puts exp2}
|
1226
|
+
\end{Highlighting}
|
1227
|
+
\end{Shaded}
|
1228
|
+
|
1229
|
+
\begin{verbatim}
|
1230
|
+
## (a + b) * 2 + c^2L/z
|
1231
|
+
\end{verbatim}
|
1232
|
+
|
1233
|
+
It is also possible to use inequality operators in building expressions
|
1234
|
+
|
1235
|
+
\begin{Shaded}
|
1236
|
+
\begin{Highlighting}[]
|
1237
|
+
\NormalTok{exp3 = (}\StringTok{:a}\NormalTok{ + }\StringTok{:b}\NormalTok{) >= }\StringTok{:z}
|
1238
|
+
\NormalTok{puts exp3}
|
1239
|
+
\end{Highlighting}
|
1240
|
+
\end{Shaded}
|
1241
|
+
|
1242
|
+
\begin{verbatim}
|
1243
|
+
## a + b >= z
|
1244
|
+
\end{verbatim}
|
1245
|
+
|
1246
|
+
Galaaz provides both symbolic representations for operators, such as
|
1247
|
+
(\textgreater{}, \textless{}, !=) as functional notation for those
|
1248
|
+
operators such as (.gt, .ge, etc.). So the same expression written above
|
1249
|
+
can also be written as
|
1250
|
+
|
1251
|
+
\begin{Shaded}
|
1252
|
+
\begin{Highlighting}[]
|
1253
|
+
\NormalTok{exp4 = (}\StringTok{:a}\NormalTok{ + }\StringTok{:b}\NormalTok{).ge }\StringTok{:z}
|
1254
|
+
\NormalTok{puts exp4}
|
1255
|
+
\end{Highlighting}
|
1256
|
+
\end{Shaded}
|
1257
|
+
|
1258
|
+
\begin{verbatim}
|
1259
|
+
## a + b >= z
|
1260
|
+
\end{verbatim}
|
1261
|
+
|
1262
|
+
Two type of expression can only be created with the functional
|
1263
|
+
representation of the operators, those are expressions involving `==',
|
1264
|
+
and `='. In order to write an expression involving `==' we need to use
|
1265
|
+
the method `.eq' and for `=' we need the function `.assign'
|
1266
|
+
|
1267
|
+
\begin{Shaded}
|
1268
|
+
\begin{Highlighting}[]
|
1269
|
+
\NormalTok{exp5 = (}\StringTok{:a}\NormalTok{ + }\StringTok{:b}\NormalTok{).eq }\StringTok{:z}
|
1270
|
+
\NormalTok{puts exp5}
|
1271
|
+
\end{Highlighting}
|
1272
|
+
\end{Shaded}
|
1273
|
+
|
1274
|
+
\begin{verbatim}
|
1275
|
+
## a + b == z
|
1276
|
+
\end{verbatim}
|
1277
|
+
|
1278
|
+
\begin{Shaded}
|
1279
|
+
\begin{Highlighting}[]
|
1280
|
+
\NormalTok{exp6 = }\StringTok{:y}\NormalTok{.assign }\StringTok{:a}\NormalTok{ + }\StringTok{:b}
|
1281
|
+
\NormalTok{puts exp6}
|
1282
|
+
\end{Highlighting}
|
1283
|
+
\end{Shaded}
|
1284
|
+
|
1285
|
+
\begin{verbatim}
|
1286
|
+
## y <- a + b
|
1287
|
+
\end{verbatim}
|
1288
|
+
|
1289
|
+
In general we think that using the functional notation is preferable to
|
1290
|
+
using the symbolic notation as otherwise, we end up writing invalid
|
1291
|
+
expressions such as
|
1292
|
+
|
1293
|
+
\begin{Shaded}
|
1294
|
+
\begin{Highlighting}[]
|
1295
|
+
\NormalTok{exp_wrong = (}\StringTok{:a}\NormalTok{ + }\StringTok{:b}\NormalTok{) == }\StringTok{:z}
|
1296
|
+
\NormalTok{puts exp_wrong}
|
1297
|
+
\end{Highlighting}
|
1298
|
+
\end{Shaded}
|
1299
|
+
|
1300
|
+
\begin{verbatim}
|
1301
|
+
## Message:
|
1302
|
+
## Error in function (x, y, num.eq = TRUE, single.NA = TRUE, attrib.as.set = TRUE, :
|
1303
|
+
## object 'a' not found (RError)
|
1304
|
+
## Translated to internal error
|
1305
|
+
\end{verbatim}
|
1306
|
+
|
1307
|
+
and it might be difficult to understand what is going on here. The
|
1308
|
+
problem lies with the fact that when using `==' we are comparing
|
1309
|
+
expression (:a + :b) to expression :z with `=='. When the comparison is
|
1310
|
+
executed, the system tries to evaluate :a, :b and :z, and those symbols
|
1311
|
+
at this time are not bound to anything and we get a ``object `a' not
|
1312
|
+
found'' message. If we only use functional notation, this type of error
|
1313
|
+
will not occur.
|
1314
|
+
|
1315
|
+
\hypertarget{expressions-with-r-methods}{%
|
1316
|
+
\subsection{Expressions with R
|
1317
|
+
methods}\label{expressions-with-r-methods}}
|
1318
|
+
|
1319
|
+
It is often necessary to create an expression that uses a method or
|
1320
|
+
function. For instance, in mathematics, it's quite natural to write an
|
1321
|
+
expressin such as \(y = sin(x)\). In this case, the `sin' function is
|
1322
|
+
part of the expression and should not immediately executed. Now, let's
|
1323
|
+
say that `x' is an angle of 45\(^\circ\) and we acttually want our
|
1324
|
+
expression to be \(y = 0.850...\). When we want the function to be part
|
1325
|
+
of the expression, we call the function preceeding it by the letter E,
|
1326
|
+
such as `E.sin(x)'
|
1327
|
+
|
1328
|
+
\begin{Shaded}
|
1329
|
+
\begin{Highlighting}[]
|
1330
|
+
\NormalTok{exp7 = }\StringTok{:y}\NormalTok{.assign E.sin(}\StringTok{:x}\NormalTok{)}
|
1331
|
+
\NormalTok{puts exp7}
|
1332
|
+
\end{Highlighting}
|
1333
|
+
\end{Shaded}
|
1334
|
+
|
1335
|
+
\begin{verbatim}
|
1336
|
+
## y <- sin(x)
|
1337
|
+
\end{verbatim}
|
1338
|
+
|
1339
|
+
Expressions can also be written using `.' notation:
|
1340
|
+
|
1341
|
+
\begin{Shaded}
|
1342
|
+
\begin{Highlighting}[]
|
1343
|
+
\NormalTok{exp8 = }\StringTok{:y}\NormalTok{.assign }\StringTok{:x}\NormalTok{.sin}
|
1344
|
+
\NormalTok{puts exp8}
|
1345
|
+
\end{Highlighting}
|
1346
|
+
\end{Shaded}
|
1347
|
+
|
1348
|
+
\begin{verbatim}
|
1349
|
+
## y <- sin(x)
|
1350
|
+
\end{verbatim}
|
1351
|
+
|
1352
|
+
When a function has multiple arguments, the first one can be used before
|
1353
|
+
the `.':
|
1354
|
+
|
1355
|
+
\begin{Shaded}
|
1356
|
+
\begin{Highlighting}[]
|
1357
|
+
\NormalTok{exp9 = }\StringTok{:x}\NormalTok{.c(}\StringTok{:y}\NormalTok{)}
|
1358
|
+
\NormalTok{puts exp9}
|
1359
|
+
\end{Highlighting}
|
1360
|
+
\end{Shaded}
|
1361
|
+
|
1362
|
+
\begin{verbatim}
|
1363
|
+
## c(x, y)
|
1364
|
+
\end{verbatim}
|
1365
|
+
|
1366
|
+
\hypertarget{evaluating-an-expression}{%
|
1367
|
+
\subsection{Evaluating an Expression}\label{evaluating-an-expression}}
|
1368
|
+
|
1369
|
+
Expressions can be evaluated by calling function `eval' with a binding.
|
1370
|
+
A binding can be provided with a list:
|
1371
|
+
|
1372
|
+
\begin{Shaded}
|
1373
|
+
\begin{Highlighting}[]
|
1374
|
+
\NormalTok{exp = (}\StringTok{:a}\NormalTok{ + }\StringTok{:b}\NormalTok{) * }\FloatTok{2.0}\NormalTok{ + }\StringTok{:c}\NormalTok{ ** }\DecValTok{2}\NormalTok{ / }\StringTok{:z}
|
1375
|
+
\NormalTok{puts exp.eval(R.list(}\StringTok{a: }\DecValTok{10}\NormalTok{, }\StringTok{b: }\DecValTok{20}\NormalTok{, }\StringTok{c: }\DecValTok{30}\NormalTok{, }\StringTok{z: }\DecValTok{40}\NormalTok{))}
|
1376
|
+
\end{Highlighting}
|
1377
|
+
\end{Shaded}
|
1378
|
+
|
1379
|
+
\begin{verbatim}
|
1380
|
+
## [1] 82.5
|
1381
|
+
\end{verbatim}
|
1382
|
+
|
1383
|
+
\ldots{} with a data frame:
|
1384
|
+
|
1385
|
+
\begin{Shaded}
|
1386
|
+
\begin{Highlighting}[]
|
1387
|
+
\NormalTok{df = R.data__frame(}
|
1388
|
+
\StringTok{a: }\NormalTok{R.c(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{3}\NormalTok{),}
|
1389
|
+
\StringTok{b: }\NormalTok{R.c(}\DecValTok{10}\NormalTok{, }\DecValTok{20}\NormalTok{, }\DecValTok{30}\NormalTok{),}
|
1390
|
+
\StringTok{c: }\NormalTok{R.c(}\DecValTok{100}\NormalTok{, }\DecValTok{200}\NormalTok{, }\DecValTok{300}\NormalTok{),}
|
1391
|
+
\StringTok{z: }\NormalTok{R.c(}\DecValTok{1000}\NormalTok{, }\DecValTok{2000}\NormalTok{, }\DecValTok{3000}\NormalTok{))}
|
1392
|
+
|
1393
|
+
\NormalTok{puts exp.eval(df)}
|
1394
|
+
\end{Highlighting}
|
1395
|
+
\end{Shaded}
|
1396
|
+
|
1397
|
+
\begin{verbatim}
|
1398
|
+
## [1] 32 64 96
|
1399
|
+
\end{verbatim}
|
1400
|
+
|
1401
|
+
\hypertarget{manipulating-data}{%
|
1402
|
+
\section{Manipulating Data}\label{manipulating-data}}
|
1403
|
+
|
1404
|
+
One of the major benefits of Galaaz is to bring strong data manipulation
|
1405
|
+
to Ruby. The following examples were extracted from Hardley's ``R for
|
1406
|
+
Data Science'' (\url{https://r4ds.had.co.nz/}). This is a highly
|
1407
|
+
recommended book for those not already familiar with the `tidyverse'
|
1408
|
+
style of programming in R. In the sections to follow, we will limit
|
1409
|
+
ourselves to convert the R code to Galaaz.
|
1410
|
+
|
1411
|
+
For these examples, we will investigate the nycflights13 data set
|
1412
|
+
available on the package by the same name. We use function
|
1413
|
+
`R.install\_and\_loads' that checks if the library is available locally,
|
1414
|
+
and if not, installs it. This data frame contains all 336,776 flights
|
1415
|
+
that departed from New York City in 2013. The data comes from the US
|
1416
|
+
Bureau of Transportation Statistics.
|
1417
|
+
|
1418
|
+
\begin{Shaded}
|
1419
|
+
\begin{Highlighting}[]
|
1420
|
+
\NormalTok{R.install_and_loads(}\StringTok{'nycflights13'}\NormalTok{)}
|
1421
|
+
\NormalTok{R.library(}\StringTok{'dplyr'}\NormalTok{)}
|
1422
|
+
\end{Highlighting}
|
1423
|
+
\end{Shaded}
|
1424
|
+
|
1425
|
+
\begin{Shaded}
|
1426
|
+
\begin{Highlighting}[]
|
1427
|
+
\NormalTok{flights = ~}\StringTok{:flights}
|
1428
|
+
\NormalTok{puts flights.head.as__data__frame}
|
1429
|
+
\end{Highlighting}
|
1430
|
+
\end{Shaded}
|
1431
|
+
|
1432
|
+
\begin{verbatim}
|
1433
|
+
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
|
1434
|
+
## 1 2013 1 1 517 515 2 830 819
|
1435
|
+
## 2 2013 1 1 533 529 4 850 830
|
1436
|
+
## 3 2013 1 1 542 540 2 923 850
|
1437
|
+
## 4 2013 1 1 544 545 -1 1004 1022
|
1438
|
+
## 5 2013 1 1 554 600 -6 812 837
|
1439
|
+
## 6 2013 1 1 554 558 -4 740 728
|
1440
|
+
## arr_delay carrier flight tailnum origin dest air_time distance hour
|
1441
|
+
## 1 11 UA 1545 N14228 EWR IAH 227 1400 5
|
1442
|
+
## 2 20 UA 1714 N24211 LGA IAH 227 1416 5
|
1443
|
+
## 3 33 AA 1141 N619AA JFK MIA 160 1089 5
|
1444
|
+
## 4 -18 B6 725 N804JB JFK BQN 183 1576 5
|
1445
|
+
## 5 -25 DL 461 N668DN LGA ATL 116 762 6
|
1446
|
+
## 6 12 UA 1696 N39463 EWR ORD 150 719 5
|
1447
|
+
## minute time_hour
|
1448
|
+
## 1 15 2013-01-01 05:00:00
|
1449
|
+
## 2 29 2013-01-01 05:00:00
|
1450
|
+
## 3 40 2013-01-01 05:00:00
|
1451
|
+
## 4 45 2013-01-01 05:00:00
|
1452
|
+
## 5 0 2013-01-01 06:00:00
|
1453
|
+
## 6 58 2013-01-01 05:00:00
|
1454
|
+
\end{verbatim}
|
1455
|
+
|
1456
|
+
\hypertarget{filtering-rows-with-filter}{%
|
1457
|
+
\subsection{Filtering rows with
|
1458
|
+
Filter}\label{filtering-rows-with-filter}}
|
1459
|
+
|
1460
|
+
In this example we filter the flights data set by giving to the filter
|
1461
|
+
function two expressions: the first :month.eq 1
|
1462
|
+
|
1463
|
+
\begin{Shaded}
|
1464
|
+
\begin{Highlighting}[]
|
1465
|
+
\NormalTok{puts flights.filter((}\StringTok{:month}\NormalTok{.eq }\DecValTok{1}\NormalTok{), (}\StringTok{:day}\NormalTok{.eq }\DecValTok{1}\NormalTok{)).head.as__data__frame}
|
1466
|
+
\end{Highlighting}
|
1467
|
+
\end{Shaded}
|
1468
|
+
|
1469
|
+
\begin{verbatim}
|
1470
|
+
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
|
1471
|
+
## 1 2013 1 1 517 515 2 830 819
|
1472
|
+
## 2 2013 1 1 533 529 4 850 830
|
1473
|
+
## 3 2013 1 1 542 540 2 923 850
|
1474
|
+
## 4 2013 1 1 544 545 -1 1004 1022
|
1475
|
+
## 5 2013 1 1 554 600 -6 812 837
|
1476
|
+
## 6 2013 1 1 554 558 -4 740 728
|
1477
|
+
## arr_delay carrier flight tailnum origin dest air_time distance hour
|
1478
|
+
## 1 11 UA 1545 N14228 EWR IAH 227 1400 5
|
1479
|
+
## 2 20 UA 1714 N24211 LGA IAH 227 1416 5
|
1480
|
+
## 3 33 AA 1141 N619AA JFK MIA 160 1089 5
|
1481
|
+
## 4 -18 B6 725 N804JB JFK BQN 183 1576 5
|
1482
|
+
## 5 -25 DL 461 N668DN LGA ATL 116 762 6
|
1483
|
+
## 6 12 UA 1696 N39463 EWR ORD 150 719 5
|
1484
|
+
## minute time_hour
|
1485
|
+
## 1 15 2013-01-01 05:00:00
|
1486
|
+
## 2 29 2013-01-01 05:00:00
|
1487
|
+
## 3 40 2013-01-01 05:00:00
|
1488
|
+
## 4 45 2013-01-01 05:00:00
|
1489
|
+
## 5 0 2013-01-01 06:00:00
|
1490
|
+
## 6 58 2013-01-01 05:00:00
|
1491
|
+
\end{verbatim}
|
1492
|
+
|
1493
|
+
\hypertarget{logical-operators}{%
|
1494
|
+
\subsection{Logical Operators}\label{logical-operators}}
|
1495
|
+
|
1496
|
+
All flights that departed in November of December
|
1497
|
+
|
1498
|
+
\begin{Shaded}
|
1499
|
+
\begin{Highlighting}[]
|
1500
|
+
\NormalTok{puts flights.filter((}\StringTok{:month}\NormalTok{.eq }\DecValTok{11}\NormalTok{) | (}\StringTok{:month}\NormalTok{.eq }\DecValTok{12}\NormalTok{)).head.as__data__frame}
|
1501
|
+
\end{Highlighting}
|
1502
|
+
\end{Shaded}
|
1503
|
+
|
1504
|
+
\begin{verbatim}
|
1505
|
+
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
|
1506
|
+
## 1 2013 11 1 5 2359 6 352 345
|
1507
|
+
## 2 2013 11 1 35 2250 105 123 2356
|
1508
|
+
## 3 2013 11 1 455 500 -5 641 651
|
1509
|
+
## 4 2013 11 1 539 545 -6 856 827
|
1510
|
+
## 5 2013 11 1 542 545 -3 831 855
|
1511
|
+
## 6 2013 11 1 549 600 -11 912 923
|
1512
|
+
## arr_delay carrier flight tailnum origin dest air_time distance hour
|
1513
|
+
## 1 7 B6 745 N568JB JFK PSE 205 1617 23
|
1514
|
+
## 2 87 B6 1816 N353JB JFK SYR 36 209 22
|
1515
|
+
## 3 -10 US 1895 N192UW EWR CLT 88 529 5
|
1516
|
+
## 4 29 UA 1714 N38727 LGA IAH 229 1416 5
|
1517
|
+
## 5 -24 AA 2243 N5CLAA JFK MIA 147 1089 5
|
1518
|
+
## 6 -11 UA 303 N595UA JFK SFO 359 2586 6
|
1519
|
+
## minute time_hour
|
1520
|
+
## 1 59 2013-11-01 23:00:00
|
1521
|
+
## 2 50 2013-11-01 22:00:00
|
1522
|
+
## 3 0 2013-11-01 05:00:00
|
1523
|
+
## 4 45 2013-11-01 05:00:00
|
1524
|
+
## 5 45 2013-11-01 05:00:00
|
1525
|
+
## 6 0 2013-11-01 06:00:00
|
1526
|
+
\end{verbatim}
|
1527
|
+
|
1528
|
+
The same as above, but using the `in' operator. In R, it is possible to
|
1529
|
+
define many operators by doing \%\%. The \%in\% operator checks if a
|
1530
|
+
value is in a vector. In order to use those operators from Galaaz the
|
1531
|
+
`.\_' method is used, where the first argument is the operator's symbol,
|
1532
|
+
in this case `:in' and the second argument is the vector:
|
1533
|
+
|
1534
|
+
\begin{Shaded}
|
1535
|
+
\begin{Highlighting}[]
|
1536
|
+
\NormalTok{puts flights.filter(}\StringTok{:month}\NormalTok{._ }\StringTok{:in}\NormalTok{, R.c(}\DecValTok{11}\NormalTok{, }\DecValTok{12}\NormalTok{)).head.as__data__frame}
|
1537
|
+
\end{Highlighting}
|
1538
|
+
\end{Shaded}
|
1539
|
+
|
1540
|
+
\begin{verbatim}
|
1541
|
+
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
|
1542
|
+
## 1 2013 11 1 5 2359 6 352 345
|
1543
|
+
## 2 2013 11 1 35 2250 105 123 2356
|
1544
|
+
## 3 2013 11 1 455 500 -5 641 651
|
1545
|
+
## 4 2013 11 1 539 545 -6 856 827
|
1546
|
+
## 5 2013 11 1 542 545 -3 831 855
|
1547
|
+
## 6 2013 11 1 549 600 -11 912 923
|
1548
|
+
## arr_delay carrier flight tailnum origin dest air_time distance hour
|
1549
|
+
## 1 7 B6 745 N568JB JFK PSE 205 1617 23
|
1550
|
+
## 2 87 B6 1816 N353JB JFK SYR 36 209 22
|
1551
|
+
## 3 -10 US 1895 N192UW EWR CLT 88 529 5
|
1552
|
+
## 4 29 UA 1714 N38727 LGA IAH 229 1416 5
|
1553
|
+
## 5 -24 AA 2243 N5CLAA JFK MIA 147 1089 5
|
1554
|
+
## 6 -11 UA 303 N595UA JFK SFO 359 2586 6
|
1555
|
+
## minute time_hour
|
1556
|
+
## 1 59 2013-11-01 23:00:00
|
1557
|
+
## 2 50 2013-11-01 22:00:00
|
1558
|
+
## 3 0 2013-11-01 05:00:00
|
1559
|
+
## 4 45 2013-11-01 05:00:00
|
1560
|
+
## 5 45 2013-11-01 05:00:00
|
1561
|
+
## 6 0 2013-11-01 06:00:00
|
1562
|
+
\end{verbatim}
|
1563
|
+
|
1564
|
+
\hypertarget{filtering-with-na-not-available}{%
|
1565
|
+
\subsection{Filtering with NA (Not
|
1566
|
+
Available)}\label{filtering-with-na-not-available}}
|
1567
|
+
|
1568
|
+
Let's first create a `tibble' with a Not Available value (R::NA).
|
1569
|
+
Tibbles are a modern version of a data frame and operate very similarly
|
1570
|
+
to one. It differs in how it outputs the values and the result of some
|
1571
|
+
subsetting operations that are more consistent than what is obtained
|
1572
|
+
from data frame.
|
1573
|
+
|
1574
|
+
\begin{Shaded}
|
1575
|
+
\begin{Highlighting}[]
|
1576
|
+
\NormalTok{df = R.tibble(}\StringTok{x: }\NormalTok{R.c(}\DecValTok{1}\NormalTok{, R::}\DataTypeTok{NA}\NormalTok{, }\DecValTok{3}\NormalTok{))}
|
1577
|
+
\NormalTok{puts df.as__data__frame}
|
1578
|
+
\end{Highlighting}
|
1579
|
+
\end{Shaded}
|
1580
|
+
|
1581
|
+
\begin{verbatim}
|
1582
|
+
## x
|
1583
|
+
## 1 1
|
1584
|
+
## 2 NA
|
1585
|
+
## 3 3
|
1586
|
+
\end{verbatim}
|
1587
|
+
|
1588
|
+
Now filtering by :x \textgreater{} 1 shows all lines that satisfy this
|
1589
|
+
condition, where the row with R:NA does not.
|
1590
|
+
|
1591
|
+
\begin{Shaded}
|
1592
|
+
\begin{Highlighting}[]
|
1593
|
+
\NormalTok{puts df.filter(}\StringTok{:x}\NormalTok{ > }\DecValTok{1}\NormalTok{).as__data__frame}
|
1594
|
+
\end{Highlighting}
|
1595
|
+
\end{Shaded}
|
1596
|
+
|
1597
|
+
\begin{verbatim}
|
1598
|
+
## x
|
1599
|
+
## 1 3
|
1600
|
+
\end{verbatim}
|
1601
|
+
|
1602
|
+
To match an NA use method 'is\_\_na'
|
1603
|
+
|
1604
|
+
\begin{Shaded}
|
1605
|
+
\begin{Highlighting}[]
|
1606
|
+
\NormalTok{puts df.filter((}\StringTok{:x}\NormalTok{.is__na) | (}\StringTok{:x}\NormalTok{ > }\DecValTok{1}\NormalTok{)).as__data__frame}
|
1607
|
+
\end{Highlighting}
|
1608
|
+
\end{Shaded}
|
1609
|
+
|
1610
|
+
\begin{verbatim}
|
1611
|
+
## x
|
1612
|
+
## 1 NA
|
1613
|
+
## 2 3
|
1614
|
+
\end{verbatim}
|
1615
|
+
|
1616
|
+
\hypertarget{arrange-rows-with-arrange}{%
|
1617
|
+
\subsection{Arrange Rows with arrange}\label{arrange-rows-with-arrange}}
|
1618
|
+
|
1619
|
+
Arrange reorders the rows of a data frame by the given arguments.
|
1620
|
+
|
1621
|
+
\begin{Shaded}
|
1622
|
+
\begin{Highlighting}[]
|
1623
|
+
\NormalTok{puts flights.arrange(}\StringTok{:year}\NormalTok{, }\StringTok{:month}\NormalTok{, }\StringTok{:day}\NormalTok{).head.as__data__frame}
|
1624
|
+
\end{Highlighting}
|
1625
|
+
\end{Shaded}
|
1626
|
+
|
1627
|
+
\begin{verbatim}
|
1628
|
+
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
|
1629
|
+
## 1 2013 1 1 517 515 2 830 819
|
1630
|
+
## 2 2013 1 1 533 529 4 850 830
|
1631
|
+
## 3 2013 1 1 542 540 2 923 850
|
1632
|
+
## 4 2013 1 1 544 545 -1 1004 1022
|
1633
|
+
## 5 2013 1 1 554 600 -6 812 837
|
1634
|
+
## 6 2013 1 1 554 558 -4 740 728
|
1635
|
+
## arr_delay carrier flight tailnum origin dest air_time distance hour
|
1636
|
+
## 1 11 UA 1545 N14228 EWR IAH 227 1400 5
|
1637
|
+
## 2 20 UA 1714 N24211 LGA IAH 227 1416 5
|
1638
|
+
## 3 33 AA 1141 N619AA JFK MIA 160 1089 5
|
1639
|
+
## 4 -18 B6 725 N804JB JFK BQN 183 1576 5
|
1640
|
+
## 5 -25 DL 461 N668DN LGA ATL 116 762 6
|
1641
|
+
## 6 12 UA 1696 N39463 EWR ORD 150 719 5
|
1642
|
+
## minute time_hour
|
1643
|
+
## 1 15 2013-01-01 05:00:00
|
1644
|
+
## 2 29 2013-01-01 05:00:00
|
1645
|
+
## 3 40 2013-01-01 05:00:00
|
1646
|
+
## 4 45 2013-01-01 05:00:00
|
1647
|
+
## 5 0 2013-01-01 06:00:00
|
1648
|
+
## 6 58 2013-01-01 05:00:00
|
1649
|
+
\end{verbatim}
|
1650
|
+
|
1651
|
+
To arrange in descending order, use function `desc'
|
1652
|
+
|
1653
|
+
\begin{Shaded}
|
1654
|
+
\begin{Highlighting}[]
|
1655
|
+
\NormalTok{puts flights.arrange(}\StringTok{:dep_delay}\NormalTok{.desc).head.as__data__frame}
|
1656
|
+
\end{Highlighting}
|
1657
|
+
\end{Shaded}
|
1658
|
+
|
1659
|
+
\begin{verbatim}
|
1660
|
+
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
|
1661
|
+
## 1 2013 1 9 641 900 1301 1242 1530
|
1662
|
+
## 2 2013 6 15 1432 1935 1137 1607 2120
|
1663
|
+
## 3 2013 1 10 1121 1635 1126 1239 1810
|
1664
|
+
## 4 2013 9 20 1139 1845 1014 1457 2210
|
1665
|
+
## 5 2013 7 22 845 1600 1005 1044 1815
|
1666
|
+
## 6 2013 4 10 1100 1900 960 1342 2211
|
1667
|
+
## arr_delay carrier flight tailnum origin dest air_time distance hour
|
1668
|
+
## 1 1272 HA 51 N384HA JFK HNL 640 4983 9
|
1669
|
+
## 2 1127 MQ 3535 N504MQ JFK CMH 74 483 19
|
1670
|
+
## 3 1109 MQ 3695 N517MQ EWR ORD 111 719 16
|
1671
|
+
## 4 1007 AA 177 N338AA JFK SFO 354 2586 18
|
1672
|
+
## 5 989 MQ 3075 N665MQ JFK CVG 96 589 16
|
1673
|
+
## 6 931 DL 2391 N959DL JFK TPA 139 1005 19
|
1674
|
+
## minute time_hour
|
1675
|
+
## 1 0 2013-01-09 09:00:00
|
1676
|
+
## 2 35 2013-06-15 19:00:00
|
1677
|
+
## 3 35 2013-01-10 16:00:00
|
1678
|
+
## 4 45 2013-09-20 18:00:00
|
1679
|
+
## 5 0 2013-07-22 16:00:00
|
1680
|
+
## 6 0 2013-04-10 19:00:00
|
1681
|
+
\end{verbatim}
|
1682
|
+
|
1683
|
+
\hypertarget{selecting-columns}{%
|
1684
|
+
\subsection{Selecting columns}\label{selecting-columns}}
|
1685
|
+
|
1686
|
+
To select specific columns from a dataset we use function `select':
|
1687
|
+
|
1688
|
+
\begin{Shaded}
|
1689
|
+
\begin{Highlighting}[]
|
1690
|
+
\NormalTok{puts flights.select(}\StringTok{:year}\NormalTok{, }\StringTok{:month}\NormalTok{, }\StringTok{:day}\NormalTok{).head.as__data__frame}
|
1691
|
+
\end{Highlighting}
|
1692
|
+
\end{Shaded}
|
1693
|
+
|
1694
|
+
\begin{verbatim}
|
1695
|
+
## year month day
|
1696
|
+
## 1 2013 1 1
|
1697
|
+
## 2 2013 1 1
|
1698
|
+
## 3 2013 1 1
|
1699
|
+
## 4 2013 1 1
|
1700
|
+
## 5 2013 1 1
|
1701
|
+
## 6 2013 1 1
|
1702
|
+
\end{verbatim}
|
1703
|
+
|
1704
|
+
It is also possible to select column in a given range
|
1705
|
+
|
1706
|
+
\begin{Shaded}
|
1707
|
+
\begin{Highlighting}[]
|
1708
|
+
\NormalTok{puts flights.select(}\StringTok{:year}\NormalTok{.up_to }\StringTok{:day}\NormalTok{).head.as__data__frame}
|
1709
|
+
\end{Highlighting}
|
1710
|
+
\end{Shaded}
|
1711
|
+
|
1712
|
+
\begin{verbatim}
|
1713
|
+
## year month day
|
1714
|
+
## 1 2013 1 1
|
1715
|
+
## 2 2013 1 1
|
1716
|
+
## 3 2013 1 1
|
1717
|
+
## 4 2013 1 1
|
1718
|
+
## 5 2013 1 1
|
1719
|
+
## 6 2013 1 1
|
1720
|
+
\end{verbatim}
|
1721
|
+
|
1722
|
+
Select all columns that start with a given name sequence
|
1723
|
+
|
1724
|
+
\begin{Shaded}
|
1725
|
+
\begin{Highlighting}[]
|
1726
|
+
\NormalTok{puts flights.select(E.starts_with(}\StringTok{'arr'}\NormalTok{)).head.as__data__frame}
|
1727
|
+
\end{Highlighting}
|
1728
|
+
\end{Shaded}
|
1729
|
+
|
1730
|
+
\begin{verbatim}
|
1731
|
+
## arr_time arr_delay
|
1732
|
+
## 1 830 11
|
1733
|
+
## 2 850 20
|
1734
|
+
## 3 923 33
|
1735
|
+
## 4 1004 -18
|
1736
|
+
## 5 812 -25
|
1737
|
+
## 6 740 12
|
1738
|
+
\end{verbatim}
|
1739
|
+
|
1740
|
+
Other functions that can be used:
|
1741
|
+
|
1742
|
+
\begin{itemize}
|
1743
|
+
\item
|
1744
|
+
ends\_with(``xyz''): matches names that end with ``xyz''.
|
1745
|
+
\item
|
1746
|
+
contains(``ijk''): matches names that contain ``ijk''.
|
1747
|
+
\item
|
1748
|
+
matches(``(.)\textbackslash{}1''): selects variables that match a
|
1749
|
+
regular expression. This one matches any variables that contain
|
1750
|
+
repeated characters.
|
1751
|
+
\item
|
1752
|
+
num\_range(``x'', (1..3)): matches x1, x2 and x3
|
1753
|
+
\end{itemize}
|
1754
|
+
|
1755
|
+
A helper function that comes in handy when we just want to rearrange
|
1756
|
+
column order is `Everything':
|
1757
|
+
|
1758
|
+
\begin{Shaded}
|
1759
|
+
\begin{Highlighting}[]
|
1760
|
+
\NormalTok{puts flights.select(}\StringTok{:year}\NormalTok{, }\StringTok{:month}\NormalTok{, }\StringTok{:day}\NormalTok{, E.everything).head.as__data__frame}
|
1761
|
+
\end{Highlighting}
|
1762
|
+
\end{Shaded}
|
1763
|
+
|
1764
|
+
\begin{verbatim}
|
1765
|
+
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
|
1766
|
+
## 1 2013 1 1 517 515 2 830 819
|
1767
|
+
## 2 2013 1 1 533 529 4 850 830
|
1768
|
+
## 3 2013 1 1 542 540 2 923 850
|
1769
|
+
## 4 2013 1 1 544 545 -1 1004 1022
|
1770
|
+
## 5 2013 1 1 554 600 -6 812 837
|
1771
|
+
## 6 2013 1 1 554 558 -4 740 728
|
1772
|
+
## arr_delay carrier flight tailnum origin dest air_time distance hour
|
1773
|
+
## 1 11 UA 1545 N14228 EWR IAH 227 1400 5
|
1774
|
+
## 2 20 UA 1714 N24211 LGA IAH 227 1416 5
|
1775
|
+
## 3 33 AA 1141 N619AA JFK MIA 160 1089 5
|
1776
|
+
## 4 -18 B6 725 N804JB JFK BQN 183 1576 5
|
1777
|
+
## 5 -25 DL 461 N668DN LGA ATL 116 762 6
|
1778
|
+
## 6 12 UA 1696 N39463 EWR ORD 150 719 5
|
1779
|
+
## minute time_hour
|
1780
|
+
## 1 15 2013-01-01 05:00:00
|
1781
|
+
## 2 29 2013-01-01 05:00:00
|
1782
|
+
## 3 40 2013-01-01 05:00:00
|
1783
|
+
## 4 45 2013-01-01 05:00:00
|
1784
|
+
## 5 0 2013-01-01 06:00:00
|
1785
|
+
## 6 58 2013-01-01 05:00:00
|
1786
|
+
\end{verbatim}
|
1787
|
+
|
1788
|
+
\hypertarget{add-variables-to-a-dataframe-with-mutate}{%
|
1789
|
+
\subsection{Add variables to a dataframe with
|
1790
|
+
`mutate'}\label{add-variables-to-a-dataframe-with-mutate}}
|
1791
|
+
|
1792
|
+
\begin{Shaded}
|
1793
|
+
\begin{Highlighting}[]
|
1794
|
+
\NormalTok{flights_sm = flights.}
|
1795
|
+
\NormalTok{ select((}\StringTok{:year}\NormalTok{.up_to }\StringTok{:day}\NormalTok{),}
|
1796
|
+
\NormalTok{ E.ends_with(}\StringTok{'delay'}\NormalTok{),}
|
1797
|
+
\StringTok{:distance}\NormalTok{,}
|
1798
|
+
\StringTok{:air_time}\NormalTok{)}
|
1799
|
+
|
1800
|
+
\NormalTok{puts flights_sm.head.as__data__frame}
|
1801
|
+
\end{Highlighting}
|
1802
|
+
\end{Shaded}
|
1803
|
+
|
1804
|
+
\begin{verbatim}
|
1805
|
+
## year month day dep_delay arr_delay distance air_time
|
1806
|
+
## 1 2013 1 1 2 11 1400 227
|
1807
|
+
## 2 2013 1 1 4 20 1416 227
|
1808
|
+
## 3 2013 1 1 2 33 1089 160
|
1809
|
+
## 4 2013 1 1 -1 -18 1576 183
|
1810
|
+
## 5 2013 1 1 -6 -25 762 116
|
1811
|
+
## 6 2013 1 1 -4 12 719 150
|
1812
|
+
\end{verbatim}
|
1813
|
+
|
1814
|
+
\begin{Shaded}
|
1815
|
+
\begin{Highlighting}[]
|
1816
|
+
\NormalTok{flights_sm = flights_sm.}
|
1817
|
+
\NormalTok{ mutate(}\StringTok{gain: :dep_delay}\NormalTok{ - }\StringTok{:arr_delay}\NormalTok{,}
|
1818
|
+
\StringTok{speed: :distance}\NormalTok{ / }\StringTok{:air_time}\NormalTok{ * }\DecValTok{60}\NormalTok{)}
|
1819
|
+
\NormalTok{puts flights_sm.head.as__data__frame}
|
1820
|
+
\end{Highlighting}
|
1821
|
+
\end{Shaded}
|
1822
|
+
|
1823
|
+
\begin{verbatim}
|
1824
|
+
## year month day dep_delay arr_delay distance air_time gain speed
|
1825
|
+
## 1 2013 1 1 2 11 1400 227 -9 370.0441
|
1826
|
+
## 2 2013 1 1 4 20 1416 227 -16 374.2731
|
1827
|
+
## 3 2013 1 1 2 33 1089 160 -31 408.3750
|
1828
|
+
## 4 2013 1 1 -1 -18 1576 183 17 516.7213
|
1829
|
+
## 5 2013 1 1 -6 -25 762 116 19 394.1379
|
1830
|
+
## 6 2013 1 1 -4 12 719 150 -16 287.6000
|
1831
|
+
\end{verbatim}
|
1832
|
+
|
1833
|
+
\hypertarget{summarising-data}{%
|
1834
|
+
\subsection{Summarising data}\label{summarising-data}}
|
1835
|
+
|
1836
|
+
Function `summarise' calculates summaries for the data frame. When no
|
1837
|
+
`group\_by' is used a single value is obtained from the data frame:
|
1838
|
+
|
1839
|
+
\begin{Shaded}
|
1840
|
+
\begin{Highlighting}[]
|
1841
|
+
\NormalTok{puts flights.summarise(}\StringTok{delay: }\NormalTok{E.mean(}\StringTok{:dep_delay}\NormalTok{, }\StringTok{na__rm: }\DecValTok{true}\NormalTok{)).as__data__frame}
|
1842
|
+
\end{Highlighting}
|
1843
|
+
\end{Shaded}
|
1844
|
+
|
1845
|
+
\begin{verbatim}
|
1846
|
+
## delay
|
1847
|
+
## 1 12.63907
|
1848
|
+
\end{verbatim}
|
1849
|
+
|
1850
|
+
When a data frame is groupe with `group\_by' summaries apply to the
|
1851
|
+
given group:
|
1852
|
+
|
1853
|
+
\begin{Shaded}
|
1854
|
+
\begin{Highlighting}[]
|
1855
|
+
\NormalTok{by_day = flights.group_by(}\StringTok{:year}\NormalTok{, }\StringTok{:month}\NormalTok{, }\StringTok{:day}\NormalTok{)}
|
1856
|
+
\NormalTok{puts by_day.summarise(}\StringTok{delay: :dep_delay}\NormalTok{.mean(}\StringTok{na__rm: }\DecValTok{true}\NormalTok{)).head.as__data__frame}
|
1857
|
+
\end{Highlighting}
|
1858
|
+
\end{Shaded}
|
1859
|
+
|
1860
|
+
\begin{verbatim}
|
1861
|
+
## year month day delay
|
1862
|
+
## 1 2013 1 1 11.548926
|
1863
|
+
## 2 2013 1 2 13.858824
|
1864
|
+
## 3 2013 1 3 10.987832
|
1865
|
+
## 4 2013 1 4 8.951595
|
1866
|
+
## 5 2013 1 5 5.732218
|
1867
|
+
## 6 2013 1 6 7.148014
|
1868
|
+
\end{verbatim}
|
1869
|
+
|
1870
|
+
Next we put many operations together by pipping them one after the
|
1871
|
+
other:
|
1872
|
+
|
1873
|
+
\begin{Shaded}
|
1874
|
+
\begin{Highlighting}[]
|
1875
|
+
\NormalTok{delays = flights.}
|
1876
|
+
\NormalTok{ group_by(}\StringTok{:dest}\NormalTok{).}
|
1877
|
+
\NormalTok{ summarise(}
|
1878
|
+
\StringTok{count: }\NormalTok{E.n,}
|
1879
|
+
\StringTok{dist: :distance}\NormalTok{.mean(}\StringTok{na__rm: }\DecValTok{true}\NormalTok{),}
|
1880
|
+
\StringTok{delay: :arr_delay}\NormalTok{.mean(}\StringTok{na__rm: }\DecValTok{true}\NormalTok{)).}
|
1881
|
+
\NormalTok{ filter(}\StringTok{:count}\NormalTok{ > }\DecValTok{20}\NormalTok{, }\StringTok{:dest}\NormalTok{ != }\StringTok{"NHL"}\NormalTok{)}
|
1882
|
+
|
1883
|
+
\NormalTok{puts delays.as__data__frame.head}
|
1884
|
+
\end{Highlighting}
|
1885
|
+
\end{Shaded}
|
1886
|
+
|
1887
|
+
\begin{verbatim}
|
1888
|
+
## dest count dist delay
|
1889
|
+
## 1 ABQ 254 1826.0000 4.381890
|
1890
|
+
## 2 ACK 265 199.0000 4.852273
|
1891
|
+
## 3 ALB 439 143.0000 14.397129
|
1892
|
+
## 4 ATL 17215 757.1082 11.300113
|
1893
|
+
## 5 AUS 2439 1514.2530 6.019909
|
1894
|
+
## 6 AVL 275 583.5818 8.003831
|
1895
|
+
\end{verbatim}
|
1896
|
+
|
1897
|
+
\hypertarget{using-data-table}{%
|
1898
|
+
\section{Using Data Table}\label{using-data-table}}
|
1899
|
+
|
1900
|
+
\begin{Shaded}
|
1901
|
+
\begin{Highlighting}[]
|
1902
|
+
\NormalTok{R.library(}\StringTok{'data.table'}\NormalTok{)}
|
1903
|
+
\NormalTok{R.install_and_loads(}\StringTok{'curl'}\NormalTok{)}
|
1904
|
+
|
1905
|
+
\NormalTok{input = }\StringTok{"https://raw.githubusercontent.com/Rdatatable/data.table/master/vignettes/flights14.csv"}
|
1906
|
+
\NormalTok{flights = R.fread(input)}
|
1907
|
+
\NormalTok{puts flights}
|
1908
|
+
\NormalTok{puts flights.dim}
|
1909
|
+
\end{Highlighting}
|
1910
|
+
\end{Shaded}
|
1911
|
+
|
1912
|
+
\begin{verbatim}
|
1913
|
+
## year month day dep_delay arr_delay carrier origin dest air_time
|
1914
|
+
## 1: 2014 1 1 14 13 AA JFK LAX 359
|
1915
|
+
## 2: 2014 1 1 -3 13 AA JFK LAX 363
|
1916
|
+
## 3: 2014 1 1 2 9 AA JFK LAX 351
|
1917
|
+
## 4: 2014 1 1 -8 -26 AA LGA PBI 157
|
1918
|
+
## 5: 2014 1 1 2 1 AA JFK LAX 350
|
1919
|
+
## ---
|
1920
|
+
## 253312: 2014 10 31 1 -30 UA LGA IAH 201
|
1921
|
+
## 253313: 2014 10 31 -5 -14 UA EWR IAH 189
|
1922
|
+
## 253314: 2014 10 31 -8 16 MQ LGA RDU 83
|
1923
|
+
## 253315: 2014 10 31 -4 15 MQ LGA DTW 75
|
1924
|
+
## 253316: 2014 10 31 -5 1 MQ LGA SDF 110
|
1925
|
+
## distance hour
|
1926
|
+
## 1: 2475 9
|
1927
|
+
## 2: 2475 11
|
1928
|
+
## 3: 2475 19
|
1929
|
+
## 4: 1035 7
|
1930
|
+
## 5: 2475 13
|
1931
|
+
## ---
|
1932
|
+
## 253312: 1416 14
|
1933
|
+
## 253313: 1400 8
|
1934
|
+
## 253314: 431 11
|
1935
|
+
## 253315: 502 11
|
1936
|
+
## 253316: 659 8
|
1937
|
+
## [1] 253316 11
|
1938
|
+
\end{verbatim}
|
1939
|
+
|
1940
|
+
\begin{Shaded}
|
1941
|
+
\begin{Highlighting}[]
|
1942
|
+
|
1943
|
+
\NormalTok{data_table = R.data__table(}
|
1944
|
+
\DataTypeTok{ID}\NormalTok{: R.c(}\StringTok{"b"}\NormalTok{,}\StringTok{"b"}\NormalTok{,}\StringTok{"b"}\NormalTok{,}\StringTok{"a"}\NormalTok{,}\StringTok{"a"}\NormalTok{,}\StringTok{"c"}\NormalTok{),}
|
1945
|
+
\StringTok{a: }\NormalTok{(}\DecValTok{1}\NormalTok{..}\DecValTok{6}\NormalTok{),}
|
1946
|
+
\StringTok{b: }\NormalTok{(}\DecValTok{7}\NormalTok{..}\DecValTok{12}\NormalTok{),}
|
1947
|
+
\StringTok{c: }\NormalTok{(}\DecValTok{13}\NormalTok{..}\DecValTok{18}\NormalTok{)}
|
1948
|
+
\NormalTok{)}
|
1949
|
+
|
1950
|
+
\NormalTok{puts data_table}
|
1951
|
+
\NormalTok{puts data_table.}\DataTypeTok{ID}
|
1952
|
+
\end{Highlighting}
|
1953
|
+
\end{Shaded}
|
1954
|
+
|
1955
|
+
\begin{verbatim}
|
1956
|
+
## ID a b c
|
1957
|
+
## 1: b 1 7 13
|
1958
|
+
## 2: b 2 8 14
|
1959
|
+
## 3: b 3 9 15
|
1960
|
+
## 4: a 4 10 16
|
1961
|
+
## 5: a 5 11 17
|
1962
|
+
## 6: c 6 12 18
|
1963
|
+
## [1] "b" "b" "b" "a" "a" "c"
|
1964
|
+
\end{verbatim}
|
1965
|
+
|
1966
|
+
\begin{Shaded}
|
1967
|
+
\begin{Highlighting}[]
|
1968
|
+
\CommentTok{# subset rows in i}
|
1969
|
+
\NormalTok{ans = flights[(}\StringTok{:origin}\NormalTok{.eq }\StringTok{"JFK"}\NormalTok{) & (}\StringTok{:month}\NormalTok{.eq }\DecValTok{6}\NormalTok{)]}
|
1970
|
+
\NormalTok{puts ans.head}
|
1971
|
+
|
1972
|
+
\CommentTok{# Get the first two rows from flights.}
|
1973
|
+
|
1974
|
+
\NormalTok{ans = flights[(}\DecValTok{1}\NormalTok{..}\DecValTok{2}\NormalTok{)]}
|
1975
|
+
\NormalTok{puts ans}
|
1976
|
+
|
1977
|
+
\CommentTok{# Sort flights first by column origin in ascending order, and then by dest in descending order:}
|
1978
|
+
|
1979
|
+
\CommentTok{# ans = flights[E.order(:origin, -(:dest))]}
|
1980
|
+
\CommentTok{# puts ans.head}
|
1981
|
+
\end{Highlighting}
|
1982
|
+
\end{Shaded}
|
1983
|
+
|
1984
|
+
\begin{verbatim}
|
1985
|
+
## year month day dep_delay arr_delay carrier origin dest air_time
|
1986
|
+
## 1: 2014 6 1 -9 -5 AA JFK LAX 324
|
1987
|
+
## 2: 2014 6 1 -10 -13 AA JFK LAX 329
|
1988
|
+
## 3: 2014 6 1 18 -1 AA JFK LAX 326
|
1989
|
+
## 4: 2014 6 1 -6 -16 AA JFK LAX 320
|
1990
|
+
## 5: 2014 6 1 -4 -45 AA JFK LAX 326
|
1991
|
+
## 6: 2014 6 1 -6 -23 AA JFK LAX 329
|
1992
|
+
## distance hour
|
1993
|
+
## 1: 2475 8
|
1994
|
+
## 2: 2475 12
|
1995
|
+
## 3: 2475 7
|
1996
|
+
## 4: 2475 10
|
1997
|
+
## 5: 2475 18
|
1998
|
+
## 6: 2475 14
|
1999
|
+
## year month day dep_delay arr_delay carrier origin dest air_time
|
2000
|
+
## 1: 2014 1 1 14 13 AA JFK LAX 359
|
2001
|
+
## 2: 2014 1 1 -3 13 AA JFK LAX 363
|
2002
|
+
## distance hour
|
2003
|
+
## 1: 2475 9
|
2004
|
+
## 2: 2475 11
|
2005
|
+
\end{verbatim}
|
2006
|
+
|
2007
|
+
\begin{Shaded}
|
2008
|
+
\begin{Highlighting}[]
|
2009
|
+
\CommentTok{# Select column(s) in j}
|
2010
|
+
\CommentTok{# select arr_delay column, but return it as a vector.}
|
2011
|
+
|
2012
|
+
\NormalTok{ans = flights[}\StringTok{:all}\NormalTok{, }\StringTok{:arr_delay}\NormalTok{]}
|
2013
|
+
\NormalTok{puts ans.head}
|
2014
|
+
|
2015
|
+
\CommentTok{# Select arr_delay column, but return as a data.table instead.}
|
2016
|
+
|
2017
|
+
\NormalTok{ans = flights[}\StringTok{:all}\NormalTok{, }\StringTok{:arr_delay}\NormalTok{.list]}
|
2018
|
+
\NormalTok{puts ans.head}
|
2019
|
+
|
2020
|
+
\NormalTok{ans = flights[}\StringTok{:all}\NormalTok{, E.list(}\StringTok{:arr_delay}\NormalTok{, }\StringTok{:dep_delay}\NormalTok{)]}
|
2021
|
+
\end{Highlighting}
|
2022
|
+
\end{Shaded}
|
2023
|
+
|
2024
|
+
\begin{verbatim}
|
2025
|
+
## [1] 13 13 9 -26 1 0
|
2026
|
+
## arr_delay
|
2027
|
+
## 1: 13
|
2028
|
+
## 2: 13
|
2029
|
+
## 3: 9
|
2030
|
+
## 4: -26
|
2031
|
+
## 5: 1
|
2032
|
+
## 6: 0
|
2033
|
+
\end{verbatim}
|
2034
|
+
|
2035
|
+
\hypertarget{graphics-in-galaaz}{%
|
2036
|
+
\section{Graphics in Galaaz}\label{graphics-in-galaaz}}
|
2037
|
+
|
2038
|
+
Creating graphics in Galaaz is quite easy, as it can use all the power
|
2039
|
+
of ggplot2. There are many resources in the web that teaches ggplot, so
|
2040
|
+
here we give a quick example of ggplot integration with Ruby. We
|
2041
|
+
continue to use the :mtcars dataset and we will plot a diverging bar
|
2042
|
+
plot, showing cars that have `above' or `below' gas consuption. Let's
|
2043
|
+
first prepare the data frame with the necessary data:
|
2044
|
+
|
2045
|
+
\begin{Shaded}
|
2046
|
+
\begin{Highlighting}[]
|
2047
|
+
\CommentTok{# copy the R variable :mtcars to the Ruby mtcars variable}
|
2048
|
+
\NormalTok{mtcars = ~}\StringTok{:mtcars}
|
2049
|
+
|
2050
|
+
\CommentTok{# create a new column 'car_name' to store the car names so that it can be}
|
2051
|
+
\CommentTok{# used for plotting. The 'rownames' of the data frame cannot be used as}
|
2052
|
+
\CommentTok{# data for plotting}
|
2053
|
+
\NormalTok{mtcars.car_name = R.rownames(}\StringTok{:mtcars}\NormalTok{)}
|
2054
|
+
|
2055
|
+
\CommentTok{# compute normalized mpg and add it to a new column called mpg_z}
|
2056
|
+
\CommentTok{# Note that the mean value for mpg can be obtained by calling the 'mean'}
|
2057
|
+
\CommentTok{# function on the vector 'mtcars.mpg'. The same with the standard}
|
2058
|
+
\CommentTok{# deviation 'sd'. The vector is then rounded to two digits with 'round 2'}
|
2059
|
+
\NormalTok{mtcars.mpg_z = ((mtcars.mpg - mtcars.mpg.mean)/mtcars.mpg.sd).round }\DecValTok{2}
|
2060
|
+
|
2061
|
+
\CommentTok{# create a new column 'mpg_type'. Function 'ifelse' is a vectorized function}
|
2062
|
+
\CommentTok{# that looks at every element of the mpg_z vector and if the value is below}
|
2063
|
+
\CommentTok{# 0, returns 'below', otherwise returns 'above'}
|
2064
|
+
\NormalTok{mtcars.mpg_type = (mtcars.mpg_z < }\DecValTok{0}\NormalTok{).ifelse(}\StringTok{"below"}\NormalTok{, }\StringTok{"above"}\NormalTok{)}
|
2065
|
+
|
2066
|
+
\CommentTok{# order the mtcar data set by the mpg_z vector from smaler to larger values}
|
2067
|
+
\NormalTok{mtcars = mtcars[mtcars.mpg_z.order, }\StringTok{:all}\NormalTok{]}
|
2068
|
+
|
2069
|
+
\CommentTok{# convert the car_name column to a factor to retain sorted order in plot}
|
2070
|
+
\NormalTok{mtcars.car_name = mtcars.car_name.factor }\StringTok{levels: }\NormalTok{mtcars.car_name}
|
2071
|
+
|
2072
|
+
\CommentTok{# let's look at the final data frame}
|
2073
|
+
\NormalTok{puts mtcars.head}
|
2074
|
+
\end{Highlighting}
|
2075
|
+
\end{Shaded}
|
2076
|
+
|
2077
|
+
\begin{verbatim}
|
2078
|
+
## mpg cyl disp hp drat wt qsec vs am gear carb
|
2079
|
+
## Cadillac Fleetwood 10.4 8 472 205 2.93 5.250 17.98 0 0 3 4
|
2080
|
+
## Lincoln Continental 10.4 8 460 215 3.00 5.424 17.82 0 0 3 4
|
2081
|
+
## Camaro Z28 13.3 8 350 245 3.73 3.840 15.41 0 0 3 4
|
2082
|
+
## Duster 360 14.3 8 360 245 3.21 3.570 15.84 0 0 3 4
|
2083
|
+
## Chrysler Imperial 14.7 8 440 230 3.23 5.345 17.42 0 0 3 4
|
2084
|
+
## Maserati Bora 15.0 8 301 335 3.54 3.570 14.60 0 1 5 8
|
2085
|
+
## car_name mpg_z mpg_type
|
2086
|
+
## Cadillac Fleetwood Cadillac Fleetwood -1.61 below
|
2087
|
+
## Lincoln Continental Lincoln Continental -1.61 below
|
2088
|
+
## Camaro Z28 Camaro Z28 -1.13 below
|
2089
|
+
## Duster 360 Duster 360 -0.96 below
|
2090
|
+
## Chrysler Imperial Chrysler Imperial -0.89 below
|
2091
|
+
## Maserati Bora Maserati Bora -0.84 below
|
2092
|
+
\end{verbatim}
|
2093
|
+
|
2094
|
+
Now, lets plot the diverging bar plot. When using gKnit, there is no
|
2095
|
+
need to call `R.awt' to create a plotting device, since gKnit does take
|
2096
|
+
care of it. Galaaz provides integration with ggplot. The interested
|
2097
|
+
reader should check online for more information on ggplot, since it is
|
2098
|
+
outside the scope of this manual describing how ggplot works. We give
|
2099
|
+
here but a brief description on how this plot is generated.
|
2100
|
+
|
2101
|
+
ggplot implements the `grammar of graphics'. In this approach, plots are
|
2102
|
+
build by adding layers to the plot. On the first layer we describe what
|
2103
|
+
we want on the `x' and `y' axis of the plot. In this case, we have
|
2104
|
+
`car\_name' on the `x' axis and `mpg\_z' on the `y' axis. Then the type
|
2105
|
+
of graph is specified by adding `geom\_bar' (for a bar graph). We
|
2106
|
+
specify that our bars should be filled using `mpg\_type', which is
|
2107
|
+
either `above' or `bellow' giving then two colours for filling. On the
|
2108
|
+
next layer we specify the labels for the graph, then we add the title
|
2109
|
+
and subtitle. Finally, in a bar chart usually bars go on the vertical
|
2110
|
+
direction, but in this graph we want the bars to be horizontally layed
|
2111
|
+
so we add `coord\_flip'.
|
2112
|
+
|
2113
|
+
\begin{Shaded}
|
2114
|
+
\begin{Highlighting}[]
|
2115
|
+
\NormalTok{require }\StringTok{'ggplot'}
|
2116
|
+
|
2117
|
+
\NormalTok{puts mtcars.ggplot(E.aes(}\StringTok{x: :car_name}\NormalTok{, }\StringTok{y: :mpg_z}\NormalTok{, }\StringTok{label: :mpg_z}\NormalTok{)) +}
|
2118
|
+
\NormalTok{ R.geom_bar(E.aes(}\StringTok{fill: :mpg_type}\NormalTok{), }\StringTok{stat: 'identity'}\NormalTok{, }\StringTok{width: }\FloatTok{0.5}\NormalTok{) +}
|
2119
|
+
\NormalTok{ R.scale_fill_manual(}\StringTok{name: 'Mileage'}\NormalTok{,}
|
2120
|
+
\StringTok{labels: }\NormalTok{R.c(}\StringTok{'Above Average'}\NormalTok{, }\StringTok{'Below Average'}\NormalTok{),}
|
2121
|
+
\StringTok{values: }\NormalTok{R.c(}\StringTok{'above'}\NormalTok{: }\StringTok{'#00ba38'}\NormalTok{, }\StringTok{'below'}\NormalTok{: }\StringTok{'#f8766d'}\NormalTok{)) +}
|
2122
|
+
\NormalTok{ R.labs(}\StringTok{subtitle: "Normalised mileage from 'mtcars'"}\NormalTok{,}
|
2123
|
+
\StringTok{title: "Diverging Bars"}\NormalTok{) + }
|
2124
|
+
\NormalTok{ R.coord_flip}
|
2125
|
+
\end{Highlighting}
|
2126
|
+
\end{Shaded}
|
2127
|
+
|
2128
|
+
\includegraphics{/home/rbotafogo/desenv/galaaz/blogs/manual/manual_files/figure-latex/diverging_bar.pdf}
|
2129
|
+
|
2130
|
+
\hypertarget{coding-with-tidyverse}{%
|
2131
|
+
\section{Coding with Tidyverse}\label{coding-with-tidyverse}}
|
2132
|
+
|
2133
|
+
In R, and when coding with `tidyverse', arguments to a function are
|
2134
|
+
usually not \emph{referencially transparent}. That is, you can't replace
|
2135
|
+
a value with a seemingly equivalent object that you've defined
|
2136
|
+
elsewhere. To see the problem, let's first define a data frame:
|
2137
|
+
|
2138
|
+
\begin{Shaded}
|
2139
|
+
\begin{Highlighting}[]
|
2140
|
+
\NormalTok{df = R.data__frame(}\StringTok{x: }\NormalTok{(}\DecValTok{1}\NormalTok{..}\DecValTok{3}\NormalTok{), }\StringTok{y: }\NormalTok{(}\DecValTok{3}\NormalTok{..}\DecValTok{1}\NormalTok{))}
|
2141
|
+
\NormalTok{puts df}
|
2142
|
+
\end{Highlighting}
|
2143
|
+
\end{Shaded}
|
2144
|
+
|
2145
|
+
\begin{verbatim}
|
2146
|
+
## x y
|
2147
|
+
## 1 1 3
|
2148
|
+
## 2 2 2
|
2149
|
+
## 3 3 1
|
2150
|
+
\end{verbatim}
|
2151
|
+
|
2152
|
+
and now, let's look at this code:
|
2153
|
+
|
2154
|
+
\begin{Shaded}
|
2155
|
+
\begin{Highlighting}[]
|
2156
|
+
\NormalTok{my_var <-}\StringTok{ }\NormalTok{x}
|
2157
|
+
\KeywordTok{filter}\NormalTok{(df, my_var }\OperatorTok{==}\StringTok{ }\DecValTok{1}\NormalTok{)}
|
2158
|
+
\end{Highlighting}
|
2159
|
+
\end{Shaded}
|
2160
|
+
|
2161
|
+
It generates the following error: "object `x' not found.
|
2162
|
+
|
2163
|
+
However, in Galaaz, arguments are referencially transparent as can be
|
2164
|
+
seen by the code bellow. Note initally that `my\_var = :x' will not give
|
2165
|
+
the error ``object `x' not found'' since `:x' is treated as an
|
2166
|
+
expression and assigned to my\_var. Then when doing (my\_var.eq 1),
|
2167
|
+
my\_var is a variable that resolves to `:x' and it becomes equivalent to
|
2168
|
+
(:x.eq 1) which is what we want.
|
2169
|
+
|
2170
|
+
\begin{Shaded}
|
2171
|
+
\begin{Highlighting}[]
|
2172
|
+
\NormalTok{my_var = }\StringTok{:x}
|
2173
|
+
\NormalTok{puts df.filter(my_var.eq }\DecValTok{1}\NormalTok{)}
|
2174
|
+
\end{Highlighting}
|
2175
|
+
\end{Shaded}
|
2176
|
+
|
2177
|
+
\begin{verbatim}
|
2178
|
+
## x y
|
2179
|
+
## 1 1 3
|
2180
|
+
\end{verbatim}
|
2181
|
+
|
2182
|
+
As stated by Hardley
|
2183
|
+
|
2184
|
+
\begin{quote}
|
2185
|
+
dplyr code is ambiguous. Depending on what variables are defined where,
|
2186
|
+
filter(df, x == y) could be equivalent to any of:
|
2187
|
+
\end{quote}
|
2188
|
+
|
2189
|
+
\begin{verbatim}
|
2190
|
+
df[df$x == df$y, ]
|
2191
|
+
df[df$x == y, ]
|
2192
|
+
df[x == df$y, ]
|
2193
|
+
df[x == y, ]
|
2194
|
+
\end{verbatim}
|
2195
|
+
|
2196
|
+
In galaaz this ambiguity does not exist, filter(df, x.eq y) is not a
|
2197
|
+
valid expression as expressions are build with symbols. In doing
|
2198
|
+
filter(df, :x.eq y) we are looking for elements of the `x' column that
|
2199
|
+
are equal to a previously defined y variable. Finally in filter(df,
|
2200
|
+
:x.eq :y) we are looking for elements in which the `x' column value is
|
2201
|
+
equal to the `y' column value. This can be seen in the following two
|
2202
|
+
chunks of code:
|
2203
|
+
|
2204
|
+
\begin{Shaded}
|
2205
|
+
\begin{Highlighting}[]
|
2206
|
+
\NormalTok{y = }\DecValTok{1}
|
2207
|
+
\NormalTok{x = }\DecValTok{2}
|
2208
|
+
|
2209
|
+
\CommentTok{# looking for values where the 'x' column is equal to the 'y' column}
|
2210
|
+
\NormalTok{puts df.filter(}\StringTok{:x}\NormalTok{.eq }\StringTok{:y}\NormalTok{)}
|
2211
|
+
\end{Highlighting}
|
2212
|
+
\end{Shaded}
|
2213
|
+
|
2214
|
+
\begin{verbatim}
|
2215
|
+
## x y
|
2216
|
+
## 1 2 2
|
2217
|
+
\end{verbatim}
|
2218
|
+
|
2219
|
+
\begin{Shaded}
|
2220
|
+
\begin{Highlighting}[]
|
2221
|
+
\CommentTok{# looking for values where the 'x' column is equal to the 'y' variable}
|
2222
|
+
\CommentTok{# in this case, the number 1}
|
2223
|
+
\NormalTok{puts df.filter(}\StringTok{:x}\NormalTok{.eq y)}
|
2224
|
+
\end{Highlighting}
|
2225
|
+
\end{Shaded}
|
2226
|
+
|
2227
|
+
\begin{verbatim}
|
2228
|
+
## x y
|
2229
|
+
## 1 1 3
|
2230
|
+
\end{verbatim}
|
2231
|
+
|
2232
|
+
\hypertarget{writing-a-function-that-applies-to-different-data-sets}{%
|
2233
|
+
\subsection{Writing a function that applies to different data
|
2234
|
+
sets}\label{writing-a-function-that-applies-to-different-data-sets}}
|
2235
|
+
|
2236
|
+
Let's suppose that we want to write a function that receives as the
|
2237
|
+
first argument a data frame and as second argument an expression that
|
2238
|
+
adds a column to the data frame that is equal to the sum of elements in
|
2239
|
+
column `a' plus `x'.
|
2240
|
+
|
2241
|
+
Here is the intended behaviour using the `mutate' function of `dplyr':
|
2242
|
+
|
2243
|
+
\begin{verbatim}
|
2244
|
+
mutate(df1, y = a + x)
|
2245
|
+
mutate(df2, y = a + x)
|
2246
|
+
mutate(df3, y = a + x)
|
2247
|
+
mutate(df4, y = a + x)
|
2248
|
+
\end{verbatim}
|
2249
|
+
|
2250
|
+
The naive approach to writing an R function to solve this problem is:
|
2251
|
+
|
2252
|
+
\begin{verbatim}
|
2253
|
+
mutate_y <- function(df) {
|
2254
|
+
mutate(df, y = a + x)
|
2255
|
+
}
|
2256
|
+
\end{verbatim}
|
2257
|
+
|
2258
|
+
Unfortunately, in R, this function can fail silently if one of the
|
2259
|
+
variables isn't present in the data frame, but is present in the global
|
2260
|
+
environment. We will not go through here how to solve this problem in R.
|
2261
|
+
|
2262
|
+
In Galaaz the method mutate\_y bellow will work fine and will never fail
|
2263
|
+
silently.
|
2264
|
+
|
2265
|
+
\begin{Shaded}
|
2266
|
+
\begin{Highlighting}[]
|
2267
|
+
\KeywordTok{def}\NormalTok{ mutate_y(df)}
|
2268
|
+
\NormalTok{ df.mutate(}\StringTok{:y}\NormalTok{.assign }\StringTok{:a}\NormalTok{ + }\StringTok{:x}\NormalTok{)}
|
2269
|
+
\KeywordTok{end}
|
2270
|
+
\end{Highlighting}
|
2271
|
+
\end{Shaded}
|
2272
|
+
|
2273
|
+
Here we create a data frame that has only one column named `x':
|
2274
|
+
|
2275
|
+
\begin{Shaded}
|
2276
|
+
\begin{Highlighting}[]
|
2277
|
+
\NormalTok{df1 = R.data__frame(}\StringTok{x: }\NormalTok{(}\DecValTok{1}\NormalTok{..}\DecValTok{3}\NormalTok{))}
|
2278
|
+
\NormalTok{puts df1}
|
2279
|
+
\end{Highlighting}
|
2280
|
+
\end{Shaded}
|
2281
|
+
|
2282
|
+
\begin{verbatim}
|
2283
|
+
## x
|
2284
|
+
## 1 1
|
2285
|
+
## 2 2
|
2286
|
+
## 3 3
|
2287
|
+
\end{verbatim}
|
2288
|
+
|
2289
|
+
Note that method mutate\_y will fail independetly from the fact that
|
2290
|
+
variable `a' is defined and in the scope of the method. Variable `a' has
|
2291
|
+
no relationship with the symbol `:a' used in the definition of
|
2292
|
+
`mutate\_y' above:
|
2293
|
+
|
2294
|
+
\begin{Shaded}
|
2295
|
+
\begin{Highlighting}[]
|
2296
|
+
\NormalTok{a = }\DecValTok{10}
|
2297
|
+
\NormalTok{mutate_y(df1)}
|
2298
|
+
\end{Highlighting}
|
2299
|
+
\end{Shaded}
|
2300
|
+
|
2301
|
+
\begin{verbatim}
|
2302
|
+
## Message:
|
2303
|
+
## Error in mutate_impl(.data, dots) :
|
2304
|
+
## Evaluation error: object 'a' not found.
|
2305
|
+
## In addition: Warning message:
|
2306
|
+
## In mutate_impl(.data, dots) :
|
2307
|
+
## mismatched protect/unprotect (unprotect with empty protect stack) (RError)
|
2308
|
+
## Translated to internal error
|
2309
|
+
\end{verbatim}
|
2310
|
+
|
2311
|
+
\hypertarget{different-expressions}{%
|
2312
|
+
\subsection{Different expressions}\label{different-expressions}}
|
2313
|
+
|
2314
|
+
Let's move to the next problem as presented by Hardley where trying to
|
2315
|
+
write a function in R that will receive two argumens, the first a
|
2316
|
+
variable and the second an expression is not trivial. Bellow we create a
|
2317
|
+
data frame and we want to write a function that groups data by a
|
2318
|
+
variable and summarises it by an expression:
|
2319
|
+
|
2320
|
+
\begin{Shaded}
|
2321
|
+
\begin{Highlighting}[]
|
2322
|
+
\KeywordTok{set.seed}\NormalTok{(}\DecValTok{123}\NormalTok{)}
|
2323
|
+
|
2324
|
+
\NormalTok{df <-}\StringTok{ }\KeywordTok{data.frame}\NormalTok{(}
|
2325
|
+
\DataTypeTok{g1 =} \KeywordTok{c}\NormalTok{(}\DecValTok{1}\NormalTok{, }\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{2}\NormalTok{),}
|
2326
|
+
\DataTypeTok{g2 =} \KeywordTok{c}\NormalTok{(}\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{1}\NormalTok{, }\DecValTok{2}\NormalTok{, }\DecValTok{1}\NormalTok{),}
|
2327
|
+
\DataTypeTok{a =} \KeywordTok{sample}\NormalTok{(}\DecValTok{5}\NormalTok{),}
|
2328
|
+
\DataTypeTok{b =} \KeywordTok{sample}\NormalTok{(}\DecValTok{5}\NormalTok{)}
|
2329
|
+
\NormalTok{)}
|
2330
|
+
|
2331
|
+
\KeywordTok{as.data.frame}\NormalTok{(df) }
|
2332
|
+
\end{Highlighting}
|
2333
|
+
\end{Shaded}
|
2334
|
+
|
2335
|
+
\begin{verbatim}
|
2336
|
+
## g1 g2 a b
|
2337
|
+
## 1 1 1 2 1
|
2338
|
+
## 2 1 2 4 3
|
2339
|
+
## 3 2 1 5 4
|
2340
|
+
## 4 2 2 3 2
|
2341
|
+
## 5 2 1 1 5
|
2342
|
+
\end{verbatim}
|
2343
|
+
|
2344
|
+
\begin{Shaded}
|
2345
|
+
\begin{Highlighting}[]
|
2346
|
+
\NormalTok{d2 <-}\StringTok{ }\NormalTok{df }\OperatorTok{%>%}
|
2347
|
+
\StringTok{ }\KeywordTok{group_by}\NormalTok{(g1) }\OperatorTok{%>%}
|
2348
|
+
\StringTok{ }\KeywordTok{summarise}\NormalTok{(}\DataTypeTok{a =} \KeywordTok{mean}\NormalTok{(a))}
|
2349
|
+
|
2350
|
+
\KeywordTok{as.data.frame}\NormalTok{(d2) }
|
2351
|
+
\end{Highlighting}
|
2352
|
+
\end{Shaded}
|
2353
|
+
|
2354
|
+
\begin{verbatim}
|
2355
|
+
## g1 a
|
2356
|
+
## 1 1 3
|
2357
|
+
## 2 2 3
|
2358
|
+
\end{verbatim}
|
2359
|
+
|
2360
|
+
\begin{Shaded}
|
2361
|
+
\begin{Highlighting}[]
|
2362
|
+
\NormalTok{d2 <-}\StringTok{ }\NormalTok{df }\OperatorTok{%>%}
|
2363
|
+
\StringTok{ }\KeywordTok{group_by}\NormalTok{(g2) }\OperatorTok{%>%}
|
2364
|
+
\StringTok{ }\KeywordTok{summarise}\NormalTok{(}\DataTypeTok{a =} \KeywordTok{mean}\NormalTok{(a))}
|
2365
|
+
|
2366
|
+
\KeywordTok{as.data.frame}\NormalTok{(d2) }
|
2367
|
+
\end{Highlighting}
|
2368
|
+
\end{Shaded}
|
2369
|
+
|
2370
|
+
\begin{verbatim}
|
2371
|
+
## g2 a
|
2372
|
+
## 1 1 2.666667
|
2373
|
+
## 2 2 3.500000
|
2374
|
+
\end{verbatim}
|
2375
|
+
|
2376
|
+
As shown by Hardley, one might expect this function to do the trick:
|
2377
|
+
|
2378
|
+
\begin{Shaded}
|
2379
|
+
\begin{Highlighting}[]
|
2380
|
+
\NormalTok{my_summarise <-}\StringTok{ }\ControlFlowTok{function}\NormalTok{(df, group_var) \{}
|
2381
|
+
\NormalTok{ df }\OperatorTok{%>%}
|
2382
|
+
\StringTok{ }\KeywordTok{group_by}\NormalTok{(group_var) }\OperatorTok{%>%}
|
2383
|
+
\StringTok{ }\KeywordTok{summarise}\NormalTok{(}\DataTypeTok{a =} \KeywordTok{mean}\NormalTok{(a))}
|
2384
|
+
\NormalTok{\}}
|
2385
|
+
|
2386
|
+
\CommentTok{# my_summarise(df, g1)}
|
2387
|
+
\CommentTok{#> Error: Column `group_var` is unknown}
|
2388
|
+
\end{Highlighting}
|
2389
|
+
\end{Shaded}
|
2390
|
+
|
2391
|
+
In order to solve this problem, coding with dplyr requires the
|
2392
|
+
introduction of many new concepts and functions such as `quo', `quos',
|
2393
|
+
`enquo', `enquos', `!!' (bang bang), `!!!' (triple bang). Again, we'll
|
2394
|
+
leave to Hardley the explanation on how to use all those functions.
|
2395
|
+
|
2396
|
+
Now, let's try to implement the same function in galaaz. The next code
|
2397
|
+
block first prints the `df' data frame defined previously in R (to
|
2398
|
+
access an R variable from Galaaz, we use the tilda operator
|
2399
|
+
`\textasciitilde{}' applied to the R variable name as symbol, i.e.,
|
2400
|
+
`:df'.
|
2401
|
+
|
2402
|
+
\begin{Shaded}
|
2403
|
+
\begin{Highlighting}[]
|
2404
|
+
\NormalTok{puts ~}\StringTok{:df}
|
2405
|
+
\end{Highlighting}
|
2406
|
+
\end{Shaded}
|
2407
|
+
|
2408
|
+
\begin{verbatim}
|
2409
|
+
## g1 g2 a b
|
2410
|
+
## 1 1 1 2 1
|
2411
|
+
## 2 1 2 4 3
|
2412
|
+
## 3 2 1 5 4
|
2413
|
+
## 4 2 2 3 2
|
2414
|
+
## 5 2 1 1 5
|
2415
|
+
\end{verbatim}
|
2416
|
+
|
2417
|
+
We then create the `my\_summarize' method and call it passing the R data
|
2418
|
+
frame and the group by variable `:g1':
|
2419
|
+
|
2420
|
+
\begin{Shaded}
|
2421
|
+
\begin{Highlighting}[]
|
2422
|
+
\KeywordTok{def}\NormalTok{ my_summarize(df, group_var)}
|
2423
|
+
\NormalTok{ df.group_by(group_var).}
|
2424
|
+
\NormalTok{ summarize(}\StringTok{a: :a}\NormalTok{.mean)}
|
2425
|
+
\KeywordTok{end}
|
2426
|
+
|
2427
|
+
\NormalTok{puts my_summarize(}\StringTok{:df}\NormalTok{, }\StringTok{:g1}\NormalTok{).as__data__frame}
|
2428
|
+
\end{Highlighting}
|
2429
|
+
\end{Shaded}
|
2430
|
+
|
2431
|
+
\begin{verbatim}
|
2432
|
+
## g1 a
|
2433
|
+
## 1 1 3
|
2434
|
+
## 2 2 3
|
2435
|
+
\end{verbatim}
|
2436
|
+
|
2437
|
+
It works!!! Well, let's make sure this was not just some coincidence
|
2438
|
+
|
2439
|
+
\begin{Shaded}
|
2440
|
+
\begin{Highlighting}[]
|
2441
|
+
\NormalTok{puts my_summarize(}\StringTok{:df}\NormalTok{, }\StringTok{:g2}\NormalTok{).as__data__frame}
|
2442
|
+
\end{Highlighting}
|
2443
|
+
\end{Shaded}
|
2444
|
+
|
2445
|
+
\begin{verbatim}
|
2446
|
+
## g2 a
|
2447
|
+
## 1 1 2.666667
|
2448
|
+
## 2 2 3.500000
|
2449
|
+
\end{verbatim}
|
2450
|
+
|
2451
|
+
Great, everything is fine! No magic, no new functions, no complexities,
|
2452
|
+
just normal, standard Ruby code. If you've ever done NSE in R, this
|
2453
|
+
certainly feels much safer and easy to implement.
|
2454
|
+
|
2455
|
+
\hypertarget{different-input-variables}{%
|
2456
|
+
\subsection{Different input variables}\label{different-input-variables}}
|
2457
|
+
|
2458
|
+
In the previous section we've managed to get rid of all NSE formulation
|
2459
|
+
for a simple example, but does this remain true for more complex
|
2460
|
+
examples, or will the Galaaz way prove inpractical for more complex
|
2461
|
+
code?
|
2462
|
+
|
2463
|
+
In the next example Hardley proposes us to write a function that given
|
2464
|
+
an expression such as `a' or `a * b', calculates three summaries. What
|
2465
|
+
we want a function that does the same as these R statements:
|
2466
|
+
|
2467
|
+
\begin{verbatim}
|
2468
|
+
summarise(df, mean = mean(a), sum = sum(a), n = n())
|
2469
|
+
#> # A tibble: 1 x 3
|
2470
|
+
#> mean sum n
|
2471
|
+
#> <dbl> <int> <int>
|
2472
|
+
#> 1 3 15 5
|
2473
|
+
|
2474
|
+
summarise(df, mean = mean(a * b), sum = sum(a * b), n = n())
|
2475
|
+
#> # A tibble: 1 x 3
|
2476
|
+
#> mean sum n
|
2477
|
+
#> <dbl> <int> <int>
|
2478
|
+
#> 1 9 45 5
|
2479
|
+
\end{verbatim}
|
2480
|
+
|
2481
|
+
Let's try it in galaaz:
|
2482
|
+
|
2483
|
+
\begin{Shaded}
|
2484
|
+
\begin{Highlighting}[]
|
2485
|
+
\KeywordTok{def}\NormalTok{ my_summarise2(df, expr)}
|
2486
|
+
\NormalTok{ df.summarize(}
|
2487
|
+
\StringTok{mean: }\NormalTok{E.mean(expr),}
|
2488
|
+
\StringTok{sum: }\NormalTok{E.sum(expr),}
|
2489
|
+
\StringTok{n: }\NormalTok{E.n}
|
2490
|
+
\NormalTok{ )}
|
2491
|
+
\KeywordTok{end}
|
2492
|
+
|
2493
|
+
\NormalTok{puts my_summarise2((~}\StringTok{:df}\NormalTok{), }\StringTok{:a}\NormalTok{)}
|
2494
|
+
\NormalTok{puts }\StringTok{"\textbackslash{}n"}
|
2495
|
+
\NormalTok{puts my_summarise2((~}\StringTok{:df}\NormalTok{), }\StringTok{:a}\NormalTok{ * }\StringTok{:b}\NormalTok{)}
|
2496
|
+
\end{Highlighting}
|
2497
|
+
\end{Shaded}
|
2498
|
+
|
2499
|
+
\begin{verbatim}
|
2500
|
+
## mean sum n
|
2501
|
+
## 1 3 15 5
|
2502
|
+
##
|
2503
|
+
## mean sum n
|
2504
|
+
## 1 9 45 5
|
2505
|
+
\end{verbatim}
|
2506
|
+
|
2507
|
+
Once again, there is no need to use any special theory or functions. The
|
2508
|
+
only point to be careful about is the use of `E' to build expressions
|
2509
|
+
from functions `mean', `sum' and `n'.
|
2510
|
+
|
2511
|
+
\hypertarget{different-input-and-output-variable}{%
|
2512
|
+
\subsection{Different input and output
|
2513
|
+
variable}\label{different-input-and-output-variable}}
|
2514
|
+
|
2515
|
+
Now the next challenge presented by Hardley is to vary the name of the
|
2516
|
+
output variables based on the received expression. So, if the input
|
2517
|
+
expression is `a', we want our data frame columns to be named `mean\_a'
|
2518
|
+
and `sum\_a'. Now, if the input expression is `b', columns should be
|
2519
|
+
named `mean\_b' and `sum\_b'.
|
2520
|
+
|
2521
|
+
\begin{verbatim}
|
2522
|
+
mutate(df, mean_a = mean(a), sum_a = sum(a))
|
2523
|
+
#> # A tibble: 5 x 6
|
2524
|
+
#> g1 g2 a b mean_a sum_a
|
2525
|
+
#> <dbl> <dbl> <int> <int> <dbl> <int>
|
2526
|
+
#> 1 1 1 1 3 3 15
|
2527
|
+
#> 2 1 2 4 2 3 15
|
2528
|
+
#> 3 2 1 2 1 3 15
|
2529
|
+
#> 4 2 2 5 4 3 15
|
2530
|
+
#> # … with 1 more row
|
2531
|
+
|
2532
|
+
mutate(df, mean_b = mean(b), sum_b = sum(b))
|
2533
|
+
#> # A tibble: 5 x 6
|
2534
|
+
#> g1 g2 a b mean_b sum_b
|
2535
|
+
#> <dbl> <dbl> <int> <int> <dbl> <int>
|
2536
|
+
#> 1 1 1 1 3 3 15
|
2537
|
+
#> 2 1 2 4 2 3 15
|
2538
|
+
#> 3 2 1 2 1 3 15
|
2539
|
+
#> 4 2 2 5 4 3 15
|
2540
|
+
#> # … with 1 more row
|
2541
|
+
\end{verbatim}
|
2542
|
+
|
2543
|
+
In order to solve this problem in R, Hardley needs to introduce some
|
2544
|
+
more new functions and notations: `quo\_name' and the `:=' operator from
|
2545
|
+
package `rlang'
|
2546
|
+
|
2547
|
+
Here is our Ruby code:
|
2548
|
+
|
2549
|
+
\begin{Shaded}
|
2550
|
+
\begin{Highlighting}[]
|
2551
|
+
\KeywordTok{def}\NormalTok{ my_mutate(df, expr)}
|
2552
|
+
\NormalTok{ mean_name = }\StringTok{"mean_}\OtherTok{#\{}\NormalTok{expr.to_s}\OtherTok{\}}\StringTok{"}
|
2553
|
+
\NormalTok{ sum_name = }\StringTok{"sum_}\OtherTok{#\{}\NormalTok{expr.to_s}\OtherTok{\}}\StringTok{"}
|
2554
|
+
|
2555
|
+
\NormalTok{ df.mutate(mean_name => E.mean(expr),}
|
2556
|
+
\NormalTok{ sum_name => E.sum(expr))}
|
2557
|
+
\KeywordTok{end}
|
2558
|
+
|
2559
|
+
\NormalTok{puts my_mutate((~}\StringTok{:df}\NormalTok{), }\StringTok{:a}\NormalTok{)}
|
2560
|
+
\NormalTok{puts }\StringTok{"\textbackslash{}n"}
|
2561
|
+
\NormalTok{puts my_mutate((~}\StringTok{:df}\NormalTok{), }\StringTok{:b}\NormalTok{)}
|
2562
|
+
\end{Highlighting}
|
2563
|
+
\end{Shaded}
|
2564
|
+
|
2565
|
+
\begin{verbatim}
|
2566
|
+
## g1 g2 a b mean_a sum_a
|
2567
|
+
## 1 1 1 2 1 3 15
|
2568
|
+
## 2 1 2 4 3 3 15
|
2569
|
+
## 3 2 1 5 4 3 15
|
2570
|
+
## 4 2 2 3 2 3 15
|
2571
|
+
## 5 2 1 1 5 3 15
|
2572
|
+
##
|
2573
|
+
## g1 g2 a b mean_b sum_b
|
2574
|
+
## 1 1 1 2 1 3 15
|
2575
|
+
## 2 1 2 4 3 3 15
|
2576
|
+
## 3 2 1 5 4 3 15
|
2577
|
+
## 4 2 2 3 2 3 15
|
2578
|
+
## 5 2 1 1 5 3 15
|
2579
|
+
\end{verbatim}
|
2580
|
+
|
2581
|
+
It really seems that ``Non Standard Evaluation'' is actually quite
|
2582
|
+
standard in Galaaz! But, you might have noticed a small change in the
|
2583
|
+
way the arguments to the mutate method were called. In a previous
|
2584
|
+
example we used df.summarise(mean: E.mean(:a), \ldots{}) where the
|
2585
|
+
column name was followed by a `:' colom. In this example, we have
|
2586
|
+
df.mutate(mean\_name =\textgreater{} E.mean(expr), \ldots{}) and
|
2587
|
+
variable mean\_name is not followed by `:' but by `=\textgreater{}'.
|
2588
|
+
This is standard Ruby notation.
|
2589
|
+
|
2590
|
+
{[}explain\ldots{}.{]}
|
2591
|
+
|
2592
|
+
\hypertarget{capturing-multiple-variables}{%
|
2593
|
+
\subsection{Capturing multiple
|
2594
|
+
variables}\label{capturing-multiple-variables}}
|
2595
|
+
|
2596
|
+
Moving on with new complexities, Hardley proposes us to solve the
|
2597
|
+
problem in which the summarise function will receive any number of
|
2598
|
+
grouping variables.
|
2599
|
+
|
2600
|
+
This again is quite standard Ruby. In order to receive an undefined
|
2601
|
+
number of paramenters the paramenter is preceded by '*':
|
2602
|
+
|
2603
|
+
\begin{Shaded}
|
2604
|
+
\begin{Highlighting}[]
|
2605
|
+
\KeywordTok{def}\NormalTok{ my_summarise3(df, *group_vars)}
|
2606
|
+
\NormalTok{ df.group_by(*group_vars).}
|
2607
|
+
\NormalTok{ summarise(}\StringTok{a: }\NormalTok{E.mean(}\StringTok{:a}\NormalTok{))}
|
2608
|
+
\KeywordTok{end}
|
2609
|
+
|
2610
|
+
\NormalTok{puts my_summarise3((~}\StringTok{:df}\NormalTok{), }\StringTok{:g1}\NormalTok{, }\StringTok{:g2}\NormalTok{).as__data__frame}
|
2611
|
+
\end{Highlighting}
|
2612
|
+
\end{Shaded}
|
2613
|
+
|
2614
|
+
\begin{verbatim}
|
2615
|
+
## g1 g2 a
|
2616
|
+
## 1 1 1 2
|
2617
|
+
## 2 1 2 4
|
2618
|
+
## 3 2 1 3
|
2619
|
+
## 4 2 2 3
|
2620
|
+
\end{verbatim}
|
2621
|
+
|
2622
|
+
\hypertarget{why-does-r-require-nse-and-galaaz-does-not}{%
|
2623
|
+
\subsection{Why does R require NSE and Galaaz does
|
2624
|
+
not?}\label{why-does-r-require-nse-and-galaaz-does-not}}
|
2625
|
+
|
2626
|
+
NSE introduces a number of new concepts, such as `quoting',
|
2627
|
+
`quasiquotation', `unquoting' and `unquote-splicing', while in Galaaz
|
2628
|
+
none of those concepts are needed. What gives?
|
2629
|
+
|
2630
|
+
R is an extremely flexible language and it has lazy evaluation of
|
2631
|
+
parameters. When in R a function is called as `summarise(df, a = b)',
|
2632
|
+
the summarise function receives the litteral `a = b' parameter and can
|
2633
|
+
work with this as if it were a string. In R, it is not clear what a and
|
2634
|
+
b are, they can be expressions or they can be variables, it is up to the
|
2635
|
+
function to decide what `a = b' means.
|
2636
|
+
|
2637
|
+
In Ruby, there is no lazy evaluation of parameters and `a' is always a
|
2638
|
+
variable and so is `b'. Variables assume their value as soon as they are
|
2639
|
+
used, so `x = a' is immediately evaluate and variable `x' will receive
|
2640
|
+
the value of variable `a' as soon as the Ruby statement is executed.
|
2641
|
+
Ruby also provides the notion of a symbol; `:a' is a symbol and does not
|
2642
|
+
evaluate to anything. Galaaz uses Ruby symbols to build expressions that
|
2643
|
+
are not bound to anything: `:a.eq :b' is clearly an expression and has
|
2644
|
+
no relationship whatsoever with the statment `a = b'. By using symbols,
|
2645
|
+
variables and expressions all the possible ambiguities that are found in
|
2646
|
+
R are eliminated in Galaaz.
|
2647
|
+
|
2648
|
+
The main problem that remains, is that in R, functions are not clearly
|
2649
|
+
documented as what type of input they are expecting, they might be
|
2650
|
+
expecting regular variables or they might be expecting expressions and
|
2651
|
+
the R function will know how to deal with an input of the form `a = b',
|
2652
|
+
now for the Ruby developer it might not be immediately clear if it
|
2653
|
+
should call the function passing the value `true' if variable `a' is
|
2654
|
+
equal to variable `b' or if it should call the function passing the
|
2655
|
+
expression `:a.eq :b'.
|
2656
|
+
|
2657
|
+
\hypertarget{advanced-dplyr-features}{%
|
2658
|
+
\subsection{Advanced dplyr features}\label{advanced-dplyr-features}}
|
2659
|
+
|
2660
|
+
In the blog: Programming with dplyr by using dplyr
|
2661
|
+
(\url{https://www.r-bloggers.com/programming-with-dplyr-by-using-dplyr/})
|
2662
|
+
Iñaki Úcar shows surprise that some R users are trying to code in dplyr
|
2663
|
+
avoiding the use of NSE. For instance he says:
|
2664
|
+
|
2665
|
+
\begin{quote}
|
2666
|
+
Take the example of seplyr. It stands for standard evaluation dplyr, and
|
2667
|
+
enables us to program over dplyr without having ``to bring in (or study)
|
2668
|
+
any deep-theory or heavy-weight tools such as rlang/tidyeval''.
|
2669
|
+
\end{quote}
|
2670
|
+
|
2671
|
+
For me, there isn't really any surprise that users are trying to avoid
|
2672
|
+
dplyr deep-theory. R users frequently are not programmers and learning
|
2673
|
+
to code is already hard business, on top of that, having to learn how to
|
2674
|
+
`quote' or `enquo' or `quos' or `enquos' is not necessarily a `piece of
|
2675
|
+
cake'. So much so, that `tidyeval' has some more advanced functions that
|
2676
|
+
instead of using quoted expressions, uses strings as arguments.
|
2677
|
+
|
2678
|
+
In the following examples, we show the use of functions `group\_by\_at',
|
2679
|
+
`summarise\_at' and `rename\_at' that receive strings as argument. The
|
2680
|
+
data frame used in `starwars' that describes features of characters in
|
2681
|
+
the Starwars movies:
|
2682
|
+
|
2683
|
+
\begin{Shaded}
|
2684
|
+
\begin{Highlighting}[]
|
2685
|
+
\NormalTok{puts (~}\StringTok{:starwars}\NormalTok{).head.as__data__frame}
|
2686
|
+
\end{Highlighting}
|
2687
|
+
\end{Shaded}
|
2688
|
+
|
2689
|
+
\begin{verbatim}
|
2690
|
+
## name height mass hair_color skin_color eye_color birth_year
|
2691
|
+
## 1 Luke Skywalker 172 77 blond fair blue 19.0
|
2692
|
+
## 2 C-3PO 167 75 <NA> gold yellow 112.0
|
2693
|
+
## 3 R2-D2 96 32 <NA> white, blue red 33.0
|
2694
|
+
## 4 Darth Vader 202 136 none white yellow 41.9
|
2695
|
+
## 5 Leia Organa 150 49 brown light brown 19.0
|
2696
|
+
## 6 Owen Lars 178 120 brown, grey light blue 52.0
|
2697
|
+
## gender homeworld species
|
2698
|
+
## 1 male Tatooine Human
|
2699
|
+
## 2 <NA> Tatooine Droid
|
2700
|
+
## 3 <NA> Naboo Droid
|
2701
|
+
## 4 male Tatooine Human
|
2702
|
+
## 5 female Alderaan Human
|
2703
|
+
## 6 male Tatooine Human
|
2704
|
+
## films
|
2705
|
+
## 1 Revenge of the Sith, Return of the Jedi, The Empire Strikes Back, A New Hope, The Force Awakens
|
2706
|
+
## 2 Attack of the Clones, The Phantom Menace, Revenge of the Sith, Return of the Jedi, The Empire Strikes Back, A New Hope
|
2707
|
+
## 3 Attack of the Clones, The Phantom Menace, Revenge of the Sith, Return of the Jedi, The Empire Strikes Back, A New Hope, The Force Awakens
|
2708
|
+
## 4 Revenge of the Sith, Return of the Jedi, The Empire Strikes Back, A New Hope
|
2709
|
+
## 5 Revenge of the Sith, Return of the Jedi, The Empire Strikes Back, A New Hope, The Force Awakens
|
2710
|
+
## 6 Attack of the Clones, Revenge of the Sith, A New Hope
|
2711
|
+
## vehicles starships
|
2712
|
+
## 1 Snowspeeder, Imperial Speeder Bike X-wing, Imperial shuttle
|
2713
|
+
## 2
|
2714
|
+
## 3
|
2715
|
+
## 4 TIE Advanced x1
|
2716
|
+
## 5 Imperial Speeder Bike
|
2717
|
+
## 6
|
2718
|
+
\end{verbatim}
|
2719
|
+
|
2720
|
+
The grouped\_mean function bellow will receive a grouping variable and
|
2721
|
+
calculate summaries for the value\_variables given:
|
2722
|
+
|
2723
|
+
\begin{Shaded}
|
2724
|
+
\begin{Highlighting}[]
|
2725
|
+
\NormalTok{grouped_mean <-}\StringTok{ }\ControlFlowTok{function}\NormalTok{(data, grouping_variables, value_variables) \{}
|
2726
|
+
\NormalTok{ data }\OperatorTok{%>%}
|
2727
|
+
\StringTok{ }\KeywordTok{group_by_at}\NormalTok{(grouping_variables) }\OperatorTok{%>%}
|
2728
|
+
\StringTok{ }\KeywordTok{mutate}\NormalTok{(}\DataTypeTok{count =} \KeywordTok{n}\NormalTok{()) }\OperatorTok{%>%}
|
2729
|
+
\StringTok{ }\KeywordTok{summarise_at}\NormalTok{(}\KeywordTok{c}\NormalTok{(value_variables, }\StringTok{"count"}\NormalTok{), mean, }\DataTypeTok{na.rm =} \OtherTok{TRUE}\NormalTok{) }\OperatorTok{%>%}
|
2730
|
+
\StringTok{ }\KeywordTok{rename_at}\NormalTok{(value_variables, }\KeywordTok{funs}\NormalTok{(}\KeywordTok{paste0}\NormalTok{(}\StringTok{"mean_"}\NormalTok{, .)))}
|
2731
|
+
\NormalTok{ \}}
|
2732
|
+
|
2733
|
+
\NormalTok{gm =}\StringTok{ }\NormalTok{starwars }\OperatorTok{%>%}\StringTok{ }
|
2734
|
+
\StringTok{ }\KeywordTok{grouped_mean}\NormalTok{(}\StringTok{"eye_color"}\NormalTok{, }\KeywordTok{c}\NormalTok{(}\StringTok{"mass"}\NormalTok{, }\StringTok{"birth_year"}\NormalTok{))}
|
2735
|
+
|
2736
|
+
\KeywordTok{as.data.frame}\NormalTok{(gm) }
|
2737
|
+
\end{Highlighting}
|
2738
|
+
\end{Shaded}
|
2739
|
+
|
2740
|
+
\begin{verbatim}
|
2741
|
+
## eye_color mean_mass mean_birth_year count
|
2742
|
+
## 1 black 76.28571 33.00000 10
|
2743
|
+
## 2 blue 86.51667 67.06923 19
|
2744
|
+
## 3 blue-gray 77.00000 57.00000 1
|
2745
|
+
## 4 brown 66.09231 108.96429 21
|
2746
|
+
## 5 dark NaN NaN 1
|
2747
|
+
## 6 gold NaN NaN 1
|
2748
|
+
## 7 green, yellow 159.00000 NaN 1
|
2749
|
+
## 8 hazel 66.00000 34.50000 3
|
2750
|
+
## 9 orange 282.33333 231.00000 8
|
2751
|
+
## 10 pink NaN NaN 1
|
2752
|
+
## 11 red 81.40000 33.66667 5
|
2753
|
+
## 12 red, blue NaN NaN 1
|
2754
|
+
## 13 unknown 31.50000 NaN 3
|
2755
|
+
## 14 white 48.00000 NaN 1
|
2756
|
+
## 15 yellow 81.11111 76.38000 11
|
2757
|
+
\end{verbatim}
|
2758
|
+
|
2759
|
+
The same code with Galaaz, becomes:
|
2760
|
+
|
2761
|
+
\begin{Shaded}
|
2762
|
+
\begin{Highlighting}[]
|
2763
|
+
\KeywordTok{def}\NormalTok{ grouped_mean(data, grouping_variables, value_variables)}
|
2764
|
+
\NormalTok{ data.}
|
2765
|
+
\NormalTok{ group_by_at(grouping_variables).}
|
2766
|
+
\NormalTok{ mutate(}\StringTok{count: }\NormalTok{E.n).}
|
2767
|
+
\NormalTok{ summarise_at(E.c(value_variables, }\StringTok{"count"}\NormalTok{), ~}\StringTok{:mean}\NormalTok{, }\StringTok{na__rm: }\DecValTok{true}\NormalTok{).}
|
2768
|
+
\NormalTok{ rename_at(value_variables, E.funs(E.paste0(}\StringTok{"mean_"}\NormalTok{, value_variables)))}
|
2769
|
+
\KeywordTok{end}
|
2770
|
+
|
2771
|
+
\NormalTok{puts grouped_mean((~}\StringTok{:starwars}\NormalTok{), }\StringTok{"eye_color"}\NormalTok{, E.c(}\StringTok{"mass"}\NormalTok{, }\StringTok{"birth_year"}\NormalTok{)).as__data__frame}
|
2772
|
+
\end{Highlighting}
|
2773
|
+
\end{Shaded}
|
2774
|
+
|
2775
|
+
\begin{verbatim}
|
2776
|
+
## eye_color mean_mass mean_birth_year count
|
2777
|
+
## 1 black 76.28571 33.00000 10
|
2778
|
+
## 2 blue 86.51667 67.06923 19
|
2779
|
+
## 3 blue-gray 77.00000 57.00000 1
|
2780
|
+
## 4 brown 66.09231 108.96429 21
|
2781
|
+
## 5 dark NaN NaN 1
|
2782
|
+
## 6 gold NaN NaN 1
|
2783
|
+
## 7 green, yellow 159.00000 NaN 1
|
2784
|
+
## 8 hazel 66.00000 34.50000 3
|
2785
|
+
## 9 orange 282.33333 231.00000 8
|
2786
|
+
## 10 pink NaN NaN 1
|
2787
|
+
## 11 red 81.40000 33.66667 5
|
2788
|
+
## 12 red, blue NaN NaN 1
|
2789
|
+
## 13 unknown 31.50000 NaN 3
|
2790
|
+
## 14 white 48.00000 NaN 1
|
2791
|
+
## 15 yellow 81.11111 76.38000 11
|
2792
|
+
\end{verbatim}
|
2793
|
+
|
2794
|
+
{[}TO BE CONTINUED\ldots{}{]}
|
2795
|
+
|
2796
|
+
\hypertarget{contributing}{%
|
2797
|
+
\section{Contributing}\label{contributing}}
|
2798
|
+
|
2799
|
+
\begin{itemize}
|
2800
|
+
\tightlist
|
2801
|
+
\item
|
2802
|
+
Fork it
|
2803
|
+
\item
|
2804
|
+
Create your feature branch (git checkout -b my-new-feature)
|
2805
|
+
\item
|
2806
|
+
Write Tests!
|
2807
|
+
\item
|
2808
|
+
Commit your changes (git commit -am `Add some feature')
|
2809
|
+
\item
|
2810
|
+
Push to the branch (git push origin my-new-feature)
|
2811
|
+
\item
|
2812
|
+
Create new Pull Request
|
2813
|
+
\end{itemize}
|
2814
|
+
|
2815
|
+
|
2816
|
+
\end{document}
|