├── .gitignore ├── 01-introduction ├── 01-introduction.Rnw ├── 01-introduction.pdf ├── 01-introduction.tex └── images │ ├── blacksmith.png │ ├── jaume_nit.jpg │ ├── spider_web.jpg │ └── wikipedia_table.png ├── 02-reading-files ├── 02-reading-files.Rnw ├── 02-reading-files.pdf ├── 02-reading-files.tex └── images │ ├── R_data_import_manual.png │ ├── alpha_data.png │ ├── blacksmith.png │ ├── cars2004_data.png │ ├── dsets_data.png │ ├── iris_data.png │ ├── mineria_webpage.png │ ├── moby_dick.jpg │ ├── moby_dick.png │ ├── moby_dick_535.png │ ├── moby_dick_book.png │ ├── moby_dick_gutenberg.png │ ├── rbook_files.png │ ├── read_functions.pdf │ ├── skulls_data.png │ ├── spider_web.jpg │ ├── taxon_data.png │ ├── travelbooks_data.png │ ├── web2r.pdf │ └── wikipedia_table.png ├── 03-xml-basics ├── 03-xml-basics.Rnw ├── 03-xml-basics.pdf ├── 03-xml-basics.tex └── images │ ├── blacksmith.png │ ├── goodwillhunting.jpg │ ├── parsing_xml.jpg │ ├── spider_web.jpg │ ├── xml_movie_tree1.pdf │ ├── xml_movie_tree2.pdf │ ├── xml_plants_catalog.png │ └── xmlcover.png ├── 04-parsing-xml ├── 04-parsing-xml.Rnw ├── 04-parsing-xml.pdf ├── 04-parsing-xml.tex └── images │ ├── mailing_lists.png │ ├── mailing_sig.png │ ├── mailing_sig_source.png │ ├── xml_package.png │ ├── xml_tree_navigate.pdf │ ├── xmlparsing_cover.png │ ├── xpath_director.pdf │ ├── xpath_firstname.pdf │ ├── xpath_lastname.pdf │ ├── xpath_movie.pdf │ ├── xpath_title.pdf │ ├── xpath_tree.pdf │ └── xpath_ytmt.pdf ├── 05-json-data ├── 05-json-data.Rnw ├── 05-json-data.pdf ├── 05-json-data.tex └── images │ ├── json_cover.png │ └── miserables_js.png ├── 06-http-basics-rcurl ├── 06-http-basics-rcurl.Rnw ├── 06-http-basics-rcurl.pdf ├── 06-http-basics-rcurl.tex └── images │ ├── Rproject.png │ ├── client_request_server_response.pdf │ ├── clients_servers.pdf │ ├── curl_request.png │ ├── hazards_form.png │ ├── http_browser.png │ ├── http_cover.png │ ├── http_request_response.pdf │ ├── rcurl_website.png │ ├── web_request.pdf │ └── web_surfing.pdf ├── 07-web-forms ├── 07-web-forms.Rnw ├── 07-web-forms.pdf ├── 07-web-forms.tex └── images │ ├── backpack_form.pdf │ ├── html_form_coffee.pdf │ ├── html_form_controls.pdf │ ├── html_form_get_post.pdf │ ├── html_form_gmail.pdf │ ├── html_form_google.pdf │ ├── html_form_twitter_facebook.pdf │ ├── html_form_works.pdf │ ├── national_parks_site.png │ ├── product_select.pdf │ └── webforms_cover.jpg ├── 08-web-apis ├── 08-web-apis.Rnw ├── 08-web-apis.pdf ├── 08-web-apis.tex └── images │ ├── bitly_api.png │ ├── eutilities_webpage.png │ ├── google_apis.png │ ├── ncbi_databases.png │ ├── ncbi_webpage.png │ ├── pubmed_search.png │ ├── pubmed_webpage.png │ ├── redwood.jpg │ └── us_census_api.png ├── Makefile ├── README.md ├── data ├── alpha.csv ├── alpha.xls ├── cars2004.csv ├── esearch_retmax103.xml ├── esearch_retmax20.xml ├── esummary.xml ├── harry_potter.html ├── harry_potter.txt ├── iris_data.txt ├── mailing_lists.html ├── miserables.txt ├── moby_dick.txt ├── npca.html ├── plant_catalog.xml ├── rproject_homepage.html ├── skulls_data.html ├── star_wars_json.R ├── swimming1500.html ├── taxon.txt ├── travelbooks.R ├── usingR.RData └── xml_movies_cover.r └── header.tex /.gitignore: -------------------------------------------------------------------------------- 1 | # Mac specific 2 | .DS_Store 3 | 4 | # R stuff 5 | .Rhistory 6 | 7 | # latex specific 8 | 0*/.DS_Store 9 | -------------------------------------------------------------------------------- /01-introduction/01-introduction.Rnw: -------------------------------------------------------------------------------- 1 | \documentclass{beamer} 2 | 3 | % load packages 4 | \usepackage{tikz} 5 | \usepackage{graphicx} 6 | \usepackage{upquote} 7 | \usepackage{listings} 8 | \usepackage{hyperref} 9 | \usepackage{color} 10 | \usepackage{lmodern} 11 | 12 | \input{../header.tex} 13 | 14 | \title[Getting data from the web with R]{\LARGE Getting Data from the Web with R} 15 | \subtitle[Web Data in R]{\large Part 1: Introduction} 16 | \author[gastonsanchez.com]{ 17 | \textcolor{gray}{\textbf{G}aston \textbf{S}anchez} 18 | } 19 | \institute[]{\scriptsize \textcolor{lightgray}{April-May 2014}} 20 | \date[CC BY-SA-NC 4.0]{ 21 | \textcolor{lightgrey}{\tiny{Content licensed under 22 | \href{http://creativecommons.org/licenses/by-nc-sa/4.0/}{CC BY-NC-SA 4.0}}} 23 | } 24 | 25 | 26 | \begin{document} 27 | 28 | <>= 29 | # smaller font size for chunks 30 | opts_chunk$set(size = 'tiny') 31 | thm <- knit_theme$get("bclear") 32 | knit_theme$set(thm) 33 | options(width=78) 34 | @ 35 | 36 | 37 | %--- the titlepage frame -------------------------% 38 | 39 | \begin{frame}[plain] 40 | \titlepage 41 | \end{frame} 42 | 43 | %------------------------------------------------ 44 | 45 | { % all template changes are local to this group. 46 | \setbeamertemplate{navigation symbols}{} 47 | \begin{frame}[plain] 48 | \begin{tikzpicture}[remember picture,overlay] 49 | \node[at=(current page.center)] { 50 | \includegraphics[height=\paperheight]{images/jaume_nit.jpg} 51 | }; 52 | \node[fill=black, opacity=0, text opacity=1] at (5.5,-3.8) {\large{ \color{white} Getting Data from the Web with R}}; 53 | \end{tikzpicture} 54 | \end{frame} 55 | } 56 | 57 | %------------------------------------------------ 58 | 59 | \begin{frame}[fragile] 60 | \frametitle{Readme} 61 | 62 | \begin{block}{\scriptsize License:} 63 | \tiny 64 | \begin{itemize} 65 | \item[] Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License \\ 66 | \url{http://creativecommons.org/licenses/by-nc-sa/4.0/}{} 67 | \end{itemize} 68 | \end{block} 69 | 70 | \begin{block}{\scriptsize You are free to:} 71 | \tiny 72 | \begin{itemize} 73 | \item[] \textcolor{darkgray}{\textbf{Share}} --- \textcolor{gray}{copy and redistribute the material} 74 | \item[] \textcolor{darkgray}{\textbf{Adapt}} --- \textcolor{gray}{rebuild and transform the material} 75 | \end{itemize} 76 | \end{block} 77 | 78 | \vspace{2mm} 79 | \begin{block}{\scriptsize Under the following conditions:} 80 | \tiny 81 | \begin{itemize} 82 | \item[] \textcolor{darkgray}{\textbf{Attribution}} --- \textcolor{gray}{You must give appropriate credit, provide a link to the license, and indicate if changes were made.} 83 | \item[] \textcolor{darkgray}{\textbf{NonCommercial}} --- \textcolor{gray}{You may not use this work for commercial purposes.} 84 | \item[] \textcolor{darkgray}{\textbf{Share Alike}} --- \textcolor{gray}{If you remix, transform, or build upon this 85 | work, you must distribute your contributions under the same license to this one.} 86 | \end{itemize} 87 | \end{block} 88 | 89 | \end{frame} 90 | 91 | %------------------------------------------------ 92 | 93 | \begin{frame} 94 | \frametitle{Lectures Menu} 95 | 96 | \begin{columns}[t] 97 | \begin{column}{0.1\textwidth} 98 | %--- empty space ---% 99 | \end{column} 100 | \begin{column}{0.8\textwidth} 101 | \begin{block}{Slide Decks} 102 | \begin{enumerate} 103 | \item \textbf{Introduction} 104 | \item \textcolor{lightgray}{Reading files from the Web} 105 | \item \textcolor{lightgray}{Basics of XML and HTML} 106 | \item \textcolor{lightgray}{Parsing XML / HTML content} 107 | \item \textcolor{lightgray}{Handling JSON data} 108 | \item \textcolor{lightgray}{HTTP Basics and the RCurl Package} 109 | \item \textcolor{lightgray}{Getting data via Web Forms} 110 | \item \textcolor{lightgray}{Getting data via Web APIs} 111 | \end{enumerate} 112 | \end{block} 113 | \end{column} 114 | \begin{column}{0.1\textwidth} 115 | %--- empty space ---% 116 | \end{column} 117 | \end{columns} 118 | 119 | \end{frame} 120 | 121 | %------------------------------------------------ 122 | 123 | \begin{frame} 124 | \frametitle{About these lectures} 125 | 126 | \begin{columns}[t] 127 | \begin{column}{0.1\textwidth} 128 | %--- empty space ---% 129 | \end{column} 130 | \begin{column}{0.8\textwidth} 131 | \begin{block}{Goal} 132 | My goal is \textbf{to give you an introduction} to some of the tools in R for getting data from the Web. 133 | 134 | \bigskip 135 | I don't pretend to cover everything nor going very deep. I just want to show you an overview of various Web Data scenarios you can handle with R. 136 | \end{block} 137 | \end{column} 138 | \begin{column}{0.1\textwidth} 139 | %--- empty space ---% 140 | \end{column} 141 | \end{columns} 142 | 143 | \end{frame} 144 | 145 | %------------------------------------------------ 146 | 147 | \begin{frame} 148 | \begin{center} 149 | \Huge{\textcolor{mandarina}{Preliminaries}} 150 | \end{center} 151 | \end{frame} 152 | 153 | %------------------------------------------------ 154 | 155 | \begin{frame} 156 | \frametitle{Requirements} 157 | 158 | \begin{block}{Must have:} 159 | \begin{itemize} 160 | \item Some experience working with R 161 | \item Some knowledge of HTML 162 | \item An insatiable curiosity for learning new things 163 | \end{itemize} 164 | \end{block} 165 | 166 | \begin{block}{Nice to have:} 167 | \begin{itemize} 168 | \item Knowledge about data storage formats 169 | \item Some programming experience 170 | \item Knowledge on how the Web works 171 | \end{itemize} 172 | \end{block} 173 | 174 | \end{frame} 175 | 176 | %------------------------------------------------ 177 | 178 | \begin{frame} 179 | \frametitle{Software} 180 | 181 | \begin{block}{You'll need:} 182 | \begin{itemize} 183 | \item R \textcolor{lightgray}{(preferably the last version)} \\ \url{http://cran.r-project.org/} 184 | \item RStudio \textcolor{lightgray}{(highly recommended)} \\ \url{https://www.rstudio.com/} 185 | \item Text Editor \\ \textcolor{lightgray}{(eg vim, emacs, TextWrangler, notepad, sublime text)} 186 | \item Web Browser \\ \textcolor{lightgray}{(eg Chrome, Safari, Firefox, Internet Explorer, Opera)} 187 | \item and a good internet connection! 188 | \end{itemize} 189 | \end{block} 190 | 191 | \end{frame} 192 | 193 | %------------------------------------------------ 194 | 195 | \begin{frame} 196 | \frametitle{In my case ...} 197 | 198 | \begin{block}{Software I used for these slides:} 199 | \begin{itemize} 200 | \item R version 3.1.0 (2014-04-10) -- "Spring Dance" 201 | \item Platform: x86\_64-apple-darwin10.8.0 (64-bit) 202 | \item IDE: RStudio Version 0.98.501 203 | \item Text Editor: TextWrangler 204 | \item Web Browser: Google Chrome Version 34.0.1847.131 205 | \item Operating System: OS-X Version 10.8.5 206 | \end{itemize} 207 | \end{block} 208 | 209 | \end{frame} 210 | 211 | %------------------------------------------------ 212 | 213 | \begin{frame} 214 | \frametitle{Resources} 215 | 216 | \begin{block}{Some R Books} 217 | \begin{itemize} 218 | \item XML and Web Technologies for Data Sciences with R \\ 219 | \low{by Deb Nolan and Duncan Temple Lang} 220 | \item Introduction to Data Technologies \\ 221 | \low{by Duncan Murdoch} 222 | \item Data Manipulation with R \\ 223 | \low{by Phil Spector} 224 | \item more references in each slide deck 225 | \end{itemize} 226 | \end{block} 227 | 228 | \end{frame} 229 | 230 | %------------------------------------------------ 231 | 232 | \begin{frame} 233 | \frametitle{Resources} 234 | 235 | \begin{block}{Web Scraping with R} 236 | \begin{itemize} 237 | \item Web scraping for the humanities and social sciences \\ 238 | \low{(by Rolf Fredheim and Aiora Zabala)} \\ 239 | {\tiny \url{http://quantifyingmemory.blogspot.co.uk/2014/02/web-scraping-basics.html}} 240 | \item Web Scraping with R \low{(by Xian Nan)} \\ 241 | {\tiny \url{http://cos.name/wp-content/uploads/2013/05/Web-Scraping-with-R-XiaoNan.pdf}} 242 | \item R-bloggers posts on \textit{Web Scraping} \\ 243 | {\tiny \url{http://www.r-bloggers.com/?s=web+scraping}} 244 | \end{itemize} 245 | \end{block} 246 | 247 | \end{frame} 248 | 249 | %------------------------------------------------ 250 | 251 | \begin{frame} 252 | \frametitle{Some R Packages} 253 | 254 | \begin{center} 255 | \begin{tabular}{l l} 256 | \hline 257 | Package & Description \\ 258 | \hline 259 | \highcode{RCurl} & R interface to the \code{libcurl} library \\ 260 | & for making general HTTP requests \\ 261 | \highcode{RHTMLForms} & Tools to process Web/HTML forms \\ 262 | \highcode{XML} & Tools for parsing XML and HTML documents \\ 263 | & and working with structured data from the Web \\ 264 | \highcode{RJSONIO} & Functions for handling JSON data \\ 265 | \highcode{jsonlite} & Functions for handling JSON data \\ 266 | \highcode{rjson} & Functions for handling JSON data \\ 267 | \highcode{ROAuth} & Interface for authentication via OAuth 1.0 \\ 268 | \highcode{SSOAP} & Use SOAP protocol to retrieve data \\ 269 | \hline 270 | \end{tabular} 271 | \end{center} 272 | 273 | CRAN Task View: \textit{Web Technologies and Services} \\ 274 | {\scriptsize \url{http://cran.r-project.org/web/views/WebTechnologies.html}} 275 | 276 | \end{frame} 277 | 278 | %------------------------------------------------ 279 | 280 | { % all template changes are local to this group. 281 | \setbeamertemplate{navigation symbols}{} 282 | \begin{frame}[plain] 283 | \begin{tikzpicture}[remember picture,overlay] 284 | \node[at=(current page.center)] { 285 | \includegraphics[width=\paperwidth]{images/spider_web.jpg} 286 | }; 287 | \node[fill=black, opacity=0, text opacity=1] at (7.5,-2.8) {\Huge{ \color{white} The Web}}; 288 | \end{tikzpicture} 289 | \end{frame} 290 | } 291 | 292 | %------------------------------------------------ 293 | 294 | \begin{frame} 295 | \frametitle{VIP Questions} 296 | 297 | \begin{columns}[t] 298 | \begin{column}{0.1\textwidth} 299 | %--- empty space ---% 300 | \end{column} 301 | \begin{column}{0.8\textwidth} 302 | \begin{block}{Very Important Preliminary Questions} 303 | The Data that you want: 304 | \begin{enumerate} 305 | \item Where is it located? 306 | \item How accessible is it? 307 | \item What is its structure / format? 308 | \end{enumerate} 309 | \end{block} 310 | \end{column} 311 | \begin{column}{0.1\textwidth} 312 | %--- empty space ---% 313 | \end{column} 314 | \end{columns} 315 | 316 | \end{frame} 317 | 318 | %------------------------------------------------ 319 | 320 | \begin{frame} 321 | \frametitle{VIP Questions} 322 | 323 | \begin{block}{Location of Data} 324 | \begin{itemize} 325 | \item Do you know the location (URL) beforehand? 326 | \item[] Or do you have to figure it out? \\ 327 | \item Is it in one single specific place? \\ 328 | \low{(eg one HTML table, one file in the Web)} 329 | \item Is it in one website but spread across several pages? \\ 330 | \low{(eg several HTML tables at different pages)} 331 | \item Is it spread across several websites? \\ 332 | \low{(eg multiple pieces of information in various sites)} 333 | \item Is it in one or several databases? 334 | \end{itemize} 335 | \end{block} 336 | 337 | \end{frame} 338 | 339 | %------------------------------------------------ 340 | 341 | \begin{frame} 342 | \frametitle{VIP Questions} 343 | 344 | \begin{block}{Accessibility of Data} 345 | \begin{itemize} 346 | \item Do you have free direct immediate access to data? 347 | \item Do you need to fill a Web Form? 348 | \item Do you need to use a Web API? 349 | \item Do you require username, password, authentication? 350 | \item Do you need to use a specifc transfer protocol? 351 | \item Do you need to use a specifc type/method of request? 352 | \end{itemize} 353 | \end{block} 354 | 355 | \end{frame} 356 | 357 | 358 | %------------------------------------------------ 359 | 360 | \begin{frame} 361 | \frametitle{VIP Questions} 362 | 363 | \begin{block}{Format / Structure of Data} 364 | \begin{itemize} 365 | \item Is it plain text? \\ 366 | \item Is it in tabular \low{(spreadsheet-like)} form? \\ 367 | \item Is it in HTML? \\ 368 | \item Is it in some XML-dialect? 369 | \item Is it in JSON format? 370 | \item Other formats: binary, images, maps, etc? 371 | \end{itemize} 372 | \end{block} 373 | 374 | \end{frame} 375 | 376 | %------------------------------------------------ 377 | 378 | \begin{frame} 379 | \frametitle{Glossary} 380 | 381 | \begin{block}{Some Acronyms} 382 | \begin{itemize} 383 | \item \textbf{WWW} World Wide Web 384 | \item \textbf{W3C} World Wide Web Consortium 385 | \item \textbf{URL} Uniform Resource Locator 386 | \item \textbf{HTTP} HyperText Transfer Protocol 387 | \item \textbf{XML} Extensible Markup Language 388 | \item \textbf{HTML} HyperText Markup Language 389 | \item \textbf{JSON} JavaScript Object Notation 390 | \end{itemize} 391 | \end{block} 392 | 393 | \end{frame} 394 | 395 | %------------------------------------------------ 396 | 397 | \end{document} -------------------------------------------------------------------------------- /01-introduction/01-introduction.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/01-introduction/01-introduction.pdf -------------------------------------------------------------------------------- /01-introduction/01-introduction.tex: -------------------------------------------------------------------------------- 1 | \documentclass{beamer}\usepackage[]{graphicx}\usepackage[]{color} 2 | %% maxwidth is the original width if it is less than linewidth 3 | %% otherwise use linewidth (to make sure the graphics do not exceed the margin) 4 | \makeatletter 5 | \def\maxwidth{ % 6 | \ifdim\Gin@nat@width>\linewidth 7 | \linewidth 8 | \else 9 | \Gin@nat@width 10 | \fi 11 | } 12 | \makeatother 13 | 14 | \definecolor{fgcolor}{rgb}{0.196, 0.196, 0.196} 15 | \newcommand{\hlnum}[1]{\textcolor[rgb]{0.063,0.58,0.627}{#1}}% 16 | \newcommand{\hlstr}[1]{\textcolor[rgb]{0.063,0.58,0.627}{#1}}% 17 | \newcommand{\hlcom}[1]{\textcolor[rgb]{0.588,0.588,0.588}{#1}}% 18 | \newcommand{\hlopt}[1]{\textcolor[rgb]{0.196,0.196,0.196}{#1}}% 19 | \newcommand{\hlstd}[1]{\textcolor[rgb]{0.196,0.196,0.196}{#1}}% 20 | \newcommand{\hlkwa}[1]{\textcolor[rgb]{0.231,0.416,0.784}{#1}}% 21 | \newcommand{\hlkwb}[1]{\textcolor[rgb]{0.627,0,0.314}{#1}}% 22 | \newcommand{\hlkwc}[1]{\textcolor[rgb]{0,0.631,0.314}{#1}}% 23 | \newcommand{\hlkwd}[1]{\textcolor[rgb]{0.78,0.227,0.412}{#1}}% 24 | \let\hlipl\hlkwb 25 | 26 | \usepackage{framed} 27 | \makeatletter 28 | \newenvironment{kframe}{% 29 | \def\at@end@of@kframe{}% 30 | \ifinner\ifhmode% 31 | \def\at@end@of@kframe{\end{minipage}}% 32 | \begin{minipage}{\columnwidth}% 33 | \fi\fi% 34 | \def\FrameCommand##1{\hskip\@totalleftmargin \hskip-\fboxsep 35 | \colorbox{shadecolor}{##1}\hskip-\fboxsep 36 | % There is no \\@totalrightmargin, so: 37 | \hskip-\linewidth \hskip-\@totalleftmargin \hskip\columnwidth}% 38 | \MakeFramed {\advance\hsize-\width 39 | \@totalleftmargin\z@ \linewidth\hsize 40 | \@setminipage}}% 41 | {\par\unskip\endMakeFramed% 42 | \at@end@of@kframe} 43 | \makeatother 44 | 45 | \definecolor{shadecolor}{rgb}{.97, .97, .97} 46 | \definecolor{messagecolor}{rgb}{0, 0, 0} 47 | \definecolor{warningcolor}{rgb}{1, 0, 1} 48 | \definecolor{errorcolor}{rgb}{1, 0, 0} 49 | \newenvironment{knitrout}{}{} % an empty environment to be redefined in TeX 50 | 51 | \usepackage{alltt} 52 | 53 | % load packages 54 | \usepackage{tikz} 55 | \usepackage{graphicx} 56 | \usepackage{upquote} 57 | \usepackage{listings} 58 | \usepackage{hyperref} 59 | \usepackage{color} 60 | \usepackage{lmodern} 61 | 62 | \input{../header.tex} 63 | 64 | \title[Getting data from the web with R]{\LARGE Getting Data from the Web with R} 65 | \subtitle[Web Data in R]{\large Part 1: Introduction} 66 | \author[gastonsanchez.com]{ 67 | \textcolor{gray}{\textbf{G}aston \textbf{S}anchez} 68 | } 69 | \institute[]{\scriptsize \textcolor{lightgray}{April-May 2014}} 70 | \date[CC BY-SA-NC 4.0]{ 71 | \textcolor{lightgrey}{\tiny{Content licensed under 72 | \href{http://creativecommons.org/licenses/by-nc-sa/4.0/}{CC BY-NC-SA 4.0}}} 73 | } 74 | \IfFileExists{upquote.sty}{\usepackage{upquote}}{} 75 | \begin{document} 76 | 77 | 78 | 79 | 80 | %--- the titlepage frame -------------------------% 81 | 82 | \begin{frame}[plain] 83 | \titlepage 84 | \end{frame} 85 | 86 | %------------------------------------------------ 87 | 88 | { % all template changes are local to this group. 89 | \setbeamertemplate{navigation symbols}{} 90 | \begin{frame}[plain] 91 | \begin{tikzpicture}[remember picture,overlay] 92 | \node[at=(current page.center)] { 93 | \includegraphics[height=\paperheight]{images/jaume_nit.jpg} 94 | }; 95 | \node[fill=black, opacity=0, text opacity=1] at (5.5,-3.8) {\large{ \color{white} Getting Data from the Web with R}}; 96 | \end{tikzpicture} 97 | \end{frame} 98 | } 99 | 100 | %------------------------------------------------ 101 | 102 | \begin{frame}[fragile] 103 | \frametitle{Readme} 104 | 105 | \begin{block}{\scriptsize License:} 106 | \tiny 107 | \begin{itemize} 108 | \item[] Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License \\ 109 | \url{http://creativecommons.org/licenses/by-nc-sa/4.0/}{} 110 | \end{itemize} 111 | \end{block} 112 | 113 | \begin{block}{\scriptsize You are free to:} 114 | \tiny 115 | \begin{itemize} 116 | \item[] \textcolor{darkgray}{\textbf{Share}} --- \textcolor{gray}{copy and redistribute the material} 117 | \item[] \textcolor{darkgray}{\textbf{Adapt}} --- \textcolor{gray}{rebuild and transform the material} 118 | \end{itemize} 119 | \end{block} 120 | 121 | \vspace{2mm} 122 | \begin{block}{\scriptsize Under the following conditions:} 123 | \tiny 124 | \begin{itemize} 125 | \item[] \textcolor{darkgray}{\textbf{Attribution}} --- \textcolor{gray}{You must give appropriate credit, provide a link to the license, and indicate if changes were made.} 126 | \item[] \textcolor{darkgray}{\textbf{NonCommercial}} --- \textcolor{gray}{You may not use this work for commercial purposes.} 127 | \item[] \textcolor{darkgray}{\textbf{Share Alike}} --- \textcolor{gray}{If you remix, transform, or build upon this 128 | work, you must distribute your contributions under the same license to this one.} 129 | \end{itemize} 130 | \end{block} 131 | 132 | \end{frame} 133 | 134 | %------------------------------------------------ 135 | 136 | \begin{frame} 137 | \frametitle{Lectures Menu} 138 | 139 | \begin{columns}[t] 140 | \begin{column}{0.1\textwidth} 141 | %--- empty space ---% 142 | \end{column} 143 | \begin{column}{0.8\textwidth} 144 | \begin{block}{Slide Decks} 145 | \begin{enumerate} 146 | \item \textbf{Introduction} 147 | \item \textcolor{lightgray}{Reading files from the Web} 148 | \item \textcolor{lightgray}{Basics of XML and HTML} 149 | \item \textcolor{lightgray}{Parsing XML / HTML content} 150 | \item \textcolor{lightgray}{Handling JSON data} 151 | \item \textcolor{lightgray}{HTTP Basics and the RCurl Package} 152 | \item \textcolor{lightgray}{Getting data via Web Forms} 153 | \item \textcolor{lightgray}{Getting data via Web APIs} 154 | \end{enumerate} 155 | \end{block} 156 | \end{column} 157 | \begin{column}{0.1\textwidth} 158 | %--- empty space ---% 159 | \end{column} 160 | \end{columns} 161 | 162 | \end{frame} 163 | 164 | %------------------------------------------------ 165 | 166 | \begin{frame} 167 | \frametitle{About these lectures} 168 | 169 | \begin{columns}[t] 170 | \begin{column}{0.1\textwidth} 171 | %--- empty space ---% 172 | \end{column} 173 | \begin{column}{0.8\textwidth} 174 | \begin{block}{Goal} 175 | My goal is \textbf{to give you an introduction} to some of the tools in R for getting data from the Web. 176 | 177 | \bigskip 178 | I don't pretend to cover everything nor going very deep. I just want to show you an overview of various Web Data scenarios you can handle with R. 179 | \end{block} 180 | \end{column} 181 | \begin{column}{0.1\textwidth} 182 | %--- empty space ---% 183 | \end{column} 184 | \end{columns} 185 | 186 | \end{frame} 187 | 188 | %------------------------------------------------ 189 | 190 | \begin{frame} 191 | \begin{center} 192 | \Huge{\textcolor{mandarina}{Preliminaries}} 193 | \end{center} 194 | \end{frame} 195 | 196 | %------------------------------------------------ 197 | 198 | \begin{frame} 199 | \frametitle{Requirements} 200 | 201 | \begin{block}{Must have:} 202 | \begin{itemize} 203 | \item Some experience working with R 204 | \item Some knowledge of HTML 205 | \item An insatiable curiosity for learning new things 206 | \end{itemize} 207 | \end{block} 208 | 209 | \begin{block}{Nice to have:} 210 | \begin{itemize} 211 | \item Knowledge about data storage formats 212 | \item Some programming experience 213 | \item Knowledge on how the Web works 214 | \end{itemize} 215 | \end{block} 216 | 217 | \end{frame} 218 | 219 | %------------------------------------------------ 220 | 221 | \begin{frame} 222 | \frametitle{Software} 223 | 224 | \begin{block}{You'll need:} 225 | \begin{itemize} 226 | \item R \textcolor{lightgray}{(preferably the last version)} \\ \url{http://cran.r-project.org/} 227 | \item RStudio \textcolor{lightgray}{(highly recommended)} \\ \url{https://www.rstudio.com/} 228 | \item Text Editor \\ \textcolor{lightgray}{(eg vim, emacs, TextWrangler, notepad, sublime text)} 229 | \item Web Browser \\ \textcolor{lightgray}{(eg Chrome, Safari, Firefox, Internet Explorer, Opera)} 230 | \item and a good internet connection! 231 | \end{itemize} 232 | \end{block} 233 | 234 | \end{frame} 235 | 236 | %------------------------------------------------ 237 | 238 | \begin{frame} 239 | \frametitle{In my case ...} 240 | 241 | \begin{block}{Software I used for these slides:} 242 | \begin{itemize} 243 | \item R version 3.1.0 (2014-04-10) -- "Spring Dance" 244 | \item Platform: x86\_64-apple-darwin10.8.0 (64-bit) 245 | \item IDE: RStudio Version 0.98.501 246 | \item Text Editor: TextWrangler 247 | \item Web Browser: Google Chrome Version 34.0.1847.131 248 | \item Operating System: OS-X Version 10.8.5 249 | \end{itemize} 250 | \end{block} 251 | 252 | \end{frame} 253 | 254 | %------------------------------------------------ 255 | 256 | \begin{frame} 257 | \frametitle{Resources} 258 | 259 | \begin{block}{Some R Books} 260 | \begin{itemize} 261 | \item XML and Web Technologies for Data Sciences with R \\ 262 | \low{by Deb Nolan and Duncan Temple Lang} 263 | \item Introduction to Data Technologies \\ 264 | \low{by Duncan Murdoch} 265 | \item Data Manipulation with R \\ 266 | \low{by Phil Spector} 267 | \item more references in each slide deck 268 | \end{itemize} 269 | \end{block} 270 | 271 | \end{frame} 272 | 273 | %------------------------------------------------ 274 | 275 | \begin{frame} 276 | \frametitle{Resources} 277 | 278 | \begin{block}{Web Scraping with R} 279 | \begin{itemize} 280 | \item Web scraping for the humanities and social sciences \\ 281 | \low{(by Rolf Fredheim and Aiora Zabala)} \\ 282 | {\tiny \url{http://quantifyingmemory.blogspot.co.uk/2014/02/web-scraping-basics.html}} 283 | \item Web Scraping with R \low{(by Xian Nan)} \\ 284 | {\tiny \url{http://cos.name/wp-content/uploads/2013/05/Web-Scraping-with-R-XiaoNan.pdf}} 285 | \item R-bloggers posts on \textit{Web Scraping} \\ 286 | {\tiny \url{http://www.r-bloggers.com/?s=web+scraping}} 287 | \end{itemize} 288 | \end{block} 289 | 290 | \end{frame} 291 | 292 | %------------------------------------------------ 293 | 294 | \begin{frame} 295 | \frametitle{Some R Packages} 296 | 297 | \begin{center} 298 | \begin{tabular}{l l} 299 | \hline 300 | Package & Description \\ 301 | \hline 302 | \highcode{RCurl} & R interface to the \code{libcurl} library \\ 303 | & for making general HTTP requests \\ 304 | \highcode{RHTMLForms} & Tools to process Web/HTML forms \\ 305 | \highcode{XML} & Tools for parsing XML and HTML documents \\ 306 | & and working with structured data from the Web \\ 307 | \highcode{RJSONIO} & Functions for handling JSON data \\ 308 | \highcode{jsonlite} & Functions for handling JSON data \\ 309 | \highcode{rjson} & Functions for handling JSON data \\ 310 | \highcode{ROAuth} & Interface for authentication via OAuth 1.0 \\ 311 | \highcode{SSOAP} & Use SOAP protocol to retrieve data \\ 312 | \hline 313 | \end{tabular} 314 | \end{center} 315 | 316 | CRAN Task View: \textit{Web Technologies and Services} \\ 317 | {\scriptsize \url{http://cran.r-project.org/web/views/WebTechnologies.html}} 318 | 319 | \end{frame} 320 | 321 | %------------------------------------------------ 322 | 323 | { % all template changes are local to this group. 324 | \setbeamertemplate{navigation symbols}{} 325 | \begin{frame}[plain] 326 | \begin{tikzpicture}[remember picture,overlay] 327 | \node[at=(current page.center)] { 328 | \includegraphics[width=\paperwidth]{images/spider_web.jpg} 329 | }; 330 | \node[fill=black, opacity=0, text opacity=1] at (7.5,-2.8) {\Huge{ \color{white} The Web}}; 331 | \end{tikzpicture} 332 | \end{frame} 333 | } 334 | 335 | %------------------------------------------------ 336 | 337 | \begin{frame} 338 | \frametitle{VIP Questions} 339 | 340 | \begin{columns}[t] 341 | \begin{column}{0.1\textwidth} 342 | %--- empty space ---% 343 | \end{column} 344 | \begin{column}{0.8\textwidth} 345 | \begin{block}{Very Important Preliminary Questions} 346 | The Data that you want: 347 | \begin{enumerate} 348 | \item Where is it located? 349 | \item How accessible is it? 350 | \item What is its structure / format? 351 | \end{enumerate} 352 | \end{block} 353 | \end{column} 354 | \begin{column}{0.1\textwidth} 355 | %--- empty space ---% 356 | \end{column} 357 | \end{columns} 358 | 359 | \end{frame} 360 | 361 | %------------------------------------------------ 362 | 363 | \begin{frame} 364 | \frametitle{VIP Questions} 365 | 366 | \begin{block}{Location of Data} 367 | \begin{itemize} 368 | \item Do you know the location (URL) beforehand? 369 | \item[] Or do you have to figure it out? \\ 370 | \item Is it in one single specific place? \\ 371 | \low{(eg one HTML table, one file in the Web)} 372 | \item Is it in one website but spread across several pages? \\ 373 | \low{(eg several HTML tables at different pages)} 374 | \item Is it spread across several websites? \\ 375 | \low{(eg multiple pieces of information in various sites)} 376 | \item Is it in one or several databases? 377 | \end{itemize} 378 | \end{block} 379 | 380 | \end{frame} 381 | 382 | %------------------------------------------------ 383 | 384 | \begin{frame} 385 | \frametitle{VIP Questions} 386 | 387 | \begin{block}{Accessibility of Data} 388 | \begin{itemize} 389 | \item Do you have free direct immediate access to data? 390 | \item Do you need to fill a Web Form? 391 | \item Do you need to use a Web API? 392 | \item Do you require username, password, authentication? 393 | \item Do you need to use a specifc transfer protocol? 394 | \item Do you need to use a specifc type/method of request? 395 | \end{itemize} 396 | \end{block} 397 | 398 | \end{frame} 399 | 400 | 401 | %------------------------------------------------ 402 | 403 | \begin{frame} 404 | \frametitle{VIP Questions} 405 | 406 | \begin{block}{Format / Structure of Data} 407 | \begin{itemize} 408 | \item Is it plain text? \\ 409 | \item Is it in tabular \low{(spreadsheet-like)} form? \\ 410 | \item Is it in HTML? \\ 411 | \item Is it in some XML-dialect? 412 | \item Is it in JSON format? 413 | \item Other formats: binary, images, maps, etc? 414 | \end{itemize} 415 | \end{block} 416 | 417 | \end{frame} 418 | 419 | %------------------------------------------------ 420 | 421 | \begin{frame} 422 | \frametitle{Glossary} 423 | 424 | \begin{block}{Some Acronyms} 425 | \begin{itemize} 426 | \item \textbf{WWW} World Wide Web 427 | \item \textbf{W3C} World Wide Web Consortium 428 | \item \textbf{URL} Uniform Resource Locator 429 | \item \textbf{HTTP} HyperText Transfer Protocol 430 | \item \textbf{XML} Extensible Markup Language 431 | \item \textbf{HTML} HyperText Markup Language 432 | \item \textbf{JSON} JavaScript Object Notation 433 | \end{itemize} 434 | \end{block} 435 | 436 | \end{frame} 437 | 438 | %------------------------------------------------ 439 | 440 | \end{document} 441 | -------------------------------------------------------------------------------- /01-introduction/images/blacksmith.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/01-introduction/images/blacksmith.png -------------------------------------------------------------------------------- /01-introduction/images/jaume_nit.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/01-introduction/images/jaume_nit.jpg -------------------------------------------------------------------------------- /01-introduction/images/spider_web.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/01-introduction/images/spider_web.jpg -------------------------------------------------------------------------------- /01-introduction/images/wikipedia_table.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/01-introduction/images/wikipedia_table.png -------------------------------------------------------------------------------- /02-reading-files/02-reading-files.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/02-reading-files.pdf -------------------------------------------------------------------------------- /02-reading-files/images/R_data_import_manual.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/R_data_import_manual.png -------------------------------------------------------------------------------- /02-reading-files/images/alpha_data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/alpha_data.png -------------------------------------------------------------------------------- /02-reading-files/images/blacksmith.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/blacksmith.png -------------------------------------------------------------------------------- /02-reading-files/images/cars2004_data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/cars2004_data.png -------------------------------------------------------------------------------- /02-reading-files/images/dsets_data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/dsets_data.png -------------------------------------------------------------------------------- /02-reading-files/images/iris_data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/iris_data.png -------------------------------------------------------------------------------- /02-reading-files/images/mineria_webpage.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/mineria_webpage.png -------------------------------------------------------------------------------- /02-reading-files/images/moby_dick.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/moby_dick.jpg -------------------------------------------------------------------------------- /02-reading-files/images/moby_dick.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/moby_dick.png -------------------------------------------------------------------------------- /02-reading-files/images/moby_dick_535.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/moby_dick_535.png -------------------------------------------------------------------------------- /02-reading-files/images/moby_dick_book.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/moby_dick_book.png -------------------------------------------------------------------------------- /02-reading-files/images/moby_dick_gutenberg.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/moby_dick_gutenberg.png -------------------------------------------------------------------------------- /02-reading-files/images/rbook_files.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/rbook_files.png -------------------------------------------------------------------------------- /02-reading-files/images/read_functions.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/read_functions.pdf -------------------------------------------------------------------------------- /02-reading-files/images/skulls_data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/skulls_data.png -------------------------------------------------------------------------------- /02-reading-files/images/spider_web.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/spider_web.jpg -------------------------------------------------------------------------------- /02-reading-files/images/taxon_data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/taxon_data.png -------------------------------------------------------------------------------- /02-reading-files/images/travelbooks_data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/travelbooks_data.png -------------------------------------------------------------------------------- /02-reading-files/images/web2r.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/web2r.pdf -------------------------------------------------------------------------------- /02-reading-files/images/wikipedia_table.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/02-reading-files/images/wikipedia_table.png -------------------------------------------------------------------------------- /03-xml-basics/03-xml-basics.Rnw: -------------------------------------------------------------------------------- 1 | \documentclass{beamer} 2 | 3 | % load packages 4 | \usepackage{tikz} 5 | \usepackage{graphicx} 6 | \usepackage{upquote} 7 | \usepackage{listings} 8 | \usepackage{hyperref} 9 | \usepackage{color} 10 | \usepackage{lmodern} 11 | 12 | \input{../header.tex} 13 | 14 | \title[Getting data from the web with R]{\LARGE Getting Data from the Web with R} 15 | \subtitle[Web Data in R]{\large Part 3: Basics of XML} 16 | \author[gastonsanchez.com]{ 17 | \textcolor{gray}{\textbf{G}aston \textbf{S}anchez} 18 | } 19 | \institute[]{\scriptsize \textcolor{lightgray}{April-May 2014}} 20 | \date[CC BY-SA-NC 4.0]{ 21 | \textcolor{lightgray}{\tiny{Content licensed under 22 | \href{http://creativecommons.org/licenses/by-nc-sa/4.0/}{CC BY-NC-SA 4.0}}} 23 | } 24 | 25 | 26 | \begin{document} 27 | 28 | <>= 29 | # smaller font size for chunks 30 | opts_chunk$set(size = 'tiny') 31 | thm <- knit_theme$get("bclear") 32 | knit_theme$set(thm) 33 | options(width=78) 34 | @ 35 | 36 | 37 | %--- the titlepage frame -------------------------% 38 | 39 | \begin{frame}[plain] 40 | \titlepage 41 | \end{frame} 42 | 43 | %------------------------------------------------ 44 | 45 | { % all template changes are local to this group. 46 | \setbeamertemplate{navigation symbols}{} 47 | \begin{frame}[plain] 48 | \begin{tikzpicture}[remember picture,overlay] 49 | \node[at=(current page.center)] { 50 | \includegraphics[width=\paperwidth]{images/xmlcover.png} 51 | }; 52 | \end{tikzpicture} 53 | \end{frame} 54 | } 55 | 56 | %------------------------------------------------ 57 | 58 | \begin{frame}[fragile] 59 | \frametitle{Readme} 60 | 61 | \begin{block}{\scriptsize License:} 62 | \tiny 63 | \begin{itemize} 64 | \item[] Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License \\ 65 | \url{http://creativecommons.org/licenses/by-nc-sa/4.0/}{} 66 | \end{itemize} 67 | \end{block} 68 | 69 | \begin{block}{\scriptsize You are free to:} 70 | \tiny 71 | \begin{itemize} 72 | \item[] \textcolor{darkgray}{\textbf{Share}} --- \textcolor{gray}{copy and redistribute the material} 73 | \item[] \textcolor{darkgray}{\textbf{Adapt}} --- \textcolor{gray}{rebuild and transform the material} 74 | \end{itemize} 75 | \end{block} 76 | 77 | \vspace{2mm} 78 | \begin{block}{\scriptsize Under the following conditions:} 79 | \tiny 80 | \begin{itemize} 81 | \item[] \textcolor{darkgray}{\textbf{Attribution}} --- \textcolor{gray}{You must give appropriate credit, provide a link to the license, and indicate if changes were made.} 82 | \item[] \textcolor{darkgray}{\textbf{NonCommercial}} --- \textcolor{gray}{You may not use this work for commercial purposes.} 83 | \item[] \textcolor{darkgray}{\textbf{Share Alike}} --- \textcolor{gray}{If you remix, transform, or build upon this 84 | work, you must distribute your contributions under the same license to this one.} 85 | \end{itemize} 86 | \end{block} 87 | 88 | \end{frame} 89 | 90 | %------------------------------------------------ 91 | 92 | \begin{frame} 93 | \frametitle{Lectures Menu} 94 | 95 | \begin{columns}[t] 96 | \begin{column}{0.1\textwidth} 97 | %--- empty space ---% 98 | \end{column} 99 | \begin{column}{0.8\textwidth} 100 | \begin{block}{Slide Decks} 101 | \begin{enumerate} 102 | \item \textcolor{lightgray}{Introduction} 103 | \item \textcolor{lightgray}{Reading files from the Web} 104 | \item \textbf{Basics of XML and HTML} 105 | \item \textcolor{lightgray}{Parsing XML / HTML documents} 106 | \item \textcolor{lightgray}{Handling JSON data} 107 | \item \textcolor{lightgray}{HTTP Basics and the RCurl package} 108 | \item \textcolor{lightgray}{Getting data via Web Forms} 109 | \item \textcolor{lightgray}{Getting data via Web APIs} 110 | \end{enumerate} 111 | \end{block} 112 | \end{column} 113 | \begin{column}{0.1\textwidth} 114 | %--- empty space ---% 115 | \end{column} 116 | \end{columns} 117 | 118 | \end{frame} 119 | 120 | %------------------------------------------------ 121 | 122 | \begin{frame} 123 | \begin{center} 124 | \Huge{\textcolor{mandarina}{Basics of XML \\ and HTML}} 125 | \end{center} 126 | \end{frame} 127 | 128 | %------------------------------------------------ 129 | 130 | \begin{frame} 131 | \frametitle{Goal} 132 | 133 | \begin{columns}[t] 134 | \begin{column}{0.1\textwidth} 135 | %--- empty space ---% 136 | \end{column} 137 | \begin{column}{0.8\textwidth} 138 | 139 | \begin{block}{XML \& HTML} 140 | The goal of these slides is to give you a \textbf{crash introduction to XML and HTML} so you can get a good grasp of those formats for the rest of the lectures 141 | \end{block} 142 | 143 | \end{column} 144 | \begin{column}{0.1\textwidth} 145 | %--- empty space ---% 146 | \end{column} 147 | \end{columns} 148 | 149 | \end{frame} 150 | 151 | %------------------------------------------------ 152 | 153 | \begin{frame} 154 | \frametitle{Synopsis} 155 | 156 | \begin{columns}[t] 157 | \begin{column}{0.1\textwidth} 158 | %--- empty space ---% 159 | \end{column} 160 | \begin{column}{0.8\textwidth} 161 | 162 | \begin{block}{In a nutshell} 163 | We'll cover a the following concepts: 164 | \begin{itemize} 165 | \item Importance of XML and HTML 166 | \item Hierarchical Structure 167 | \item Document Object Model (DOM) 168 | \end{itemize} 169 | \end{block} 170 | 171 | \end{column} 172 | \begin{column}{0.1\textwidth} 173 | %--- empty space ---% 174 | \end{column} 175 | \end{columns} 176 | 177 | \end{frame} 178 | 179 | %------------------------------------------------ 180 | 181 | \begin{frame} 182 | \frametitle{Some References} 183 | 184 | \begin{itemize} 185 | \item XML Files website {\scriptsize (\url{http://www.xmlfiles.com})} \\ 186 | \low{by Jan Egil Refsnes} 187 | \item XML in a Nutshell \\ 188 | \low{by Elliotte Rusty Harold; W. Scott Means} 189 | \item XML Tutorial {\scriptsize (\url{http://www.w3schools.com/xml/default.asp})} \\ 190 | \low{by w3schools} 191 | \item Introduction to Data Technologies \\ 192 | \low{by Paul Murrell} 193 | \item XML and Web Technologies for Data Sciences with R \\ 194 | \low{by Deb Nolan and Duncan Temple Lang} 195 | \end{itemize} 196 | 197 | \end{frame} 198 | 199 | %------------------------------------------------ 200 | 201 | \begin{frame} 202 | \frametitle{XML and HTML} 203 | 204 | \begin{block}{Why you should care about XML and HTML?} 205 | \begin{itemize} 206 | \item Large amounts of data and information are stored, shared and distributed using HTML and XML-dialects 207 | \item They are widely adopted and used in many applications 208 | \item Working with data from the Web means dealing with HTML 209 | \end{itemize} 210 | \end{block} 211 | 212 | \end{frame} 213 | 214 | 215 | %------------------------------------------------ 216 | 217 | \begin{frame} 218 | \begin{center} 219 | {\Huge \textcolor{mandarina}{XML}} \\ 220 | \bigskip 221 | {\Large \textcolor{mandarina}{eXtensible Markup Language}} 222 | \end{center} 223 | \end{frame} 224 | 225 | %------------------------------------------------ 226 | 227 | { % all template changes are local to this group. 228 | \setbeamertemplate{navigation symbols}{} 229 | \begin{frame}[plain] 230 | \begin{tikzpicture}[remember picture,overlay] 231 | \node[at=(current page.center)] { 232 | \includegraphics[width=\paperwidth]{images/xml_plants_catalog.png} 233 | }; 234 | \end{tikzpicture} 235 | \end{frame} 236 | } 237 | 238 | %------------------------------------------------ 239 | 240 | \begin{frame} 241 | \frametitle{Some Definitions} 242 | 243 | \begin{quotation} 244 | ``XML is a markup language that defines a set of rules for encoding documents in a format that is both human-readable and machine-readable'' 245 | \end{quotation} 246 | 247 | {\footnotesize 248 | \hspace{8mm} \url{http://en.wikipedia.org/wiki/XML} 249 | } 250 | 251 | \bigskip 252 | \begin{quotation} 253 | ``XML is a data description language used for describing data'' 254 | \end{quotation} 255 | 256 | {\footnotesize 257 | \hspace{8mm} \high{Paul Murrell} \\ 258 | \hspace{8mm} \low{Introduction to Data Technologies} 259 | } 260 | 261 | \end{frame} 262 | 263 | %------------------------------------------------ 264 | 265 | \begin{frame} 266 | \frametitle{Some Definitions} 267 | 268 | \begin{quotation} 269 | ``XML is a very general structure with which we can define any number of new formats to represent arbitrary data'' 270 | \end{quotation} 271 | 272 | \begin{quotation} 273 | ``XML is a standard for the semantic, hierarchical representation of data'' 274 | \end{quotation} 275 | 276 | {\footnotesize 277 | \hspace{8mm} \high{Deb Nolan \& Duncan Temple Lang} \\ 278 | \hspace{8mm} \low{XML and Web Technologies for Data Sciences with R} 279 | } 280 | 281 | \end{frame} 282 | 283 | %------------------------------------------------ 284 | 285 | \begin{frame} 286 | \frametitle{About XML} 287 | 288 | \begin{columns}[t] 289 | \begin{column}{0.1\textwidth} 290 | %--- empty space ---% 291 | \end{column} 292 | \begin{column}{0.8\textwidth} 293 | 294 | \begin{block}{XML} 295 | XML stands for \textbf{eXtensible Markup Language} 296 | \end{block} 297 | 298 | \begin{block}{Broadly speaking ...} 299 | XML provides a flexible framework to create formats for describing and representing data 300 | \end{block} 301 | 302 | \end{column} 303 | \begin{column}{0.1\textwidth} 304 | %--- empty space ---% 305 | \end{column} 306 | \end{columns} 307 | 308 | \end{frame} 309 | 310 | %------------------------------------------------ 311 | 312 | \begin{frame} 313 | \frametitle{Markups} 314 | 315 | \begin{block}{Markup} 316 | A \textbf{markup} is a sequence of characters or other symbols inserted at certain places in a document to indicate either: 317 | \begin{itemize} 318 | \item how the content should be displayed when printed or in screen 319 | \item describe the document's structure 320 | \end{itemize} 321 | \end{block} 322 | 323 | \begin{block}{Markup Language} 324 | A markup language is a system for \textbf{annotating} (i.e. \textit{marking}) a document in a way that the content is distinguished from its representation \low{(eg LaTeX, PostScript, HTML, SVG)} 325 | \end{block} 326 | 327 | \end{frame} 328 | 329 | %------------------------------------------------ 330 | 331 | \begin{frame}[fragile] 332 | \frametitle{Markups} 333 | 334 | \begin{block}{XML Markups} 335 | In XML (as well as in HTML) the marks (aka \textit{tags}) are defined using angle brackets: {\Huge \highcode{<>}} 336 | \end{block} 337 | 338 | \bigskip 339 | 340 | \code{ \high{}Text marked with special tag\high{} } 341 | 342 | \end{frame} 343 | 344 | %------------------------------------------------ 345 | 346 | \begin{frame}[fragile] 347 | \frametitle{Extensible} 348 | 349 | \begin{block}{Extensible?} 350 | The concept of \textit{extensibility} means that we can define our own marks, the order in which they occur, and how they should be processed. For example: 351 | \begin{itemize} 352 | \item \highcode{} 353 | \item \highcode{} 354 | \item \highcode{} 355 | \item \highcode{} 356 | \end{itemize} 357 | \end{block} 358 | 359 | \end{frame} 360 | 361 | %------------------------------------------------ 362 | 363 | \begin{frame} 364 | \frametitle{About XML} 365 | 366 | \begin{block}{XML is NOT} 367 | \begin{itemize} 368 | \item a programming language 369 | \item a network transfer protocol 370 | \item a database 371 | \end{itemize} 372 | \end{block} 373 | 374 | \begin{block}{XML is} 375 | \begin{itemize} 376 | \item more than a markup language 377 | \item a generic language that provides structure and syntax for representing any type of information 378 | \item a meta-language: it allows us to create or define other languages 379 | \end{itemize} 380 | \end{block} 381 | 382 | \end{frame} 383 | 384 | %------------------------------------------------ 385 | 386 | \begin{frame} 387 | \frametitle{XML Applications} 388 | 389 | \begin{block}{Some XML dialects} 390 | \begin{itemize} 391 | \item \textbf{KML} (\textit{Keyhole Markup Language}) for describing geo-spatial information used in Google Earth, Google Maps, Google Sky 392 | \item \textbf{SVG} (\textit{Scalable Vector Graphics}) for visual graphical displays of two-dimensional graphics with support for interactivity and animation 393 | \item \textbf{PMML} (\textit{Predictive Model Markup Language}) for describing and exchanging models produced by data mining and machine learning algorithms 394 | \end{itemize} 395 | \end{block} 396 | 397 | \end{frame} 398 | 399 | 400 | %------------------------------------------------ 401 | 402 | \begin{frame} 403 | \frametitle{XML Applications (con't)} 404 | 405 | \begin{block}{Some XML dialects} 406 | \begin{itemize} 407 | \item \textbf{RSS} (\textit{Rich Site Summary}) feeds for publishing blog entries 408 | \item \textbf{SDMX} (\textit{Statistical Data and Metadata Exchange}) for organizing and exchanging statistical information 409 | \item \textbf{GML} (\textit{Geography Markup Language}) for representing geographical features 410 | \item \textbf{SBML} (\textit{Systems Biology Markup Language}) for describing biological systems 411 | \end{itemize} 412 | \end{block} 413 | 414 | \end{frame} 415 | 416 | %------------------------------------------------ 417 | 418 | \begin{frame} 419 | \begin{center} 420 | \Huge{\textcolor{mandarina}{Minimalist Example}} 421 | \end{center} 422 | \end{frame} 423 | 424 | %------------------------------------------------ 425 | 426 | { % all template changes are local to this group. 427 | \setbeamertemplate{navigation symbols}{} 428 | \begin{frame}[plain] 429 | \begin{tikzpicture}[remember picture,overlay] 430 | \node[at=(current page.center)] { 431 | \includegraphics[width=\paperwidth]{images/goodwillhunting.jpg} 432 | }; 433 | \end{tikzpicture} 434 | \end{frame} 435 | } 436 | 437 | %------------------------------------------------ 438 | 439 | \begin{frame}[fragile] 440 | \frametitle{XML Example} 441 | 442 | \begin{block}{Ultra Simple XML} 443 | \begin{verbatim} 444 | 445 | Good Will Hunting 446 | 447 | \end{verbatim} 448 | \end{block} 449 | 450 | \bigskip 451 | 452 | \begin{itemize} 453 | \item one single element {\textit{movie}} 454 | \item start-tag: \highcode{} 455 | \item end-tag: \highcode{} 456 | \item content: \highcode{Good Will Hunting} 457 | \end{itemize} 458 | 459 | \end{frame} 460 | 461 | %------------------------------------------------ 462 | 463 | \begin{frame}[fragile] 464 | \frametitle{XML Example} 465 | 466 | \begin{block}{Ultra Simple XML} 467 | \begin{verbatim} 468 | 469 | Good Will Hunting 470 | 471 | \end{verbatim} 472 | \end{block} 473 | 474 | \bigskip 475 | 476 | \begin{itemize} 477 | \item xml elements can have \textbf{attributes} 478 | \item attributes: \highcode{mins} \low{(minutes)} and \highcode{lang} \low{(language)} 479 | \item attributes are \textit{attached} to the element's start tag 480 | \item attribute values \textbf{must be quoted!} 481 | \end{itemize} 482 | 483 | \end{frame} 484 | 485 | %------------------------------------------------ 486 | 487 | \begin{frame}[fragile] 488 | \frametitle{XML Example} 489 | 490 | \begin{block}{Minimalist XML} 491 | \begin{verbatim} 492 | 493 | Good Will Hunting 494 | Gus Van Sant 495 | 1998 496 | drama 497 | 498 | \end{verbatim} 499 | \end{block} 500 | 501 | \bigskip 502 | 503 | \begin{itemize} 504 | \item an xml element may contain other elements 505 | \item \textit{movie} contains several elements: \textit{title, director, year, genre} 506 | \end{itemize} 507 | 508 | \end{frame} 509 | 510 | %------------------------------------------------ 511 | 512 | \begin{frame}[fragile] 513 | \frametitle{XML Example} 514 | 515 | \begin{block}{Simple XML} 516 | \begin{verbatim} 517 | 518 | Good Will Hunting 519 | 520 | Gus 521 | Van Sant 522 | 523 | 1998 524 | drama 525 | 526 | \end{verbatim} 527 | \end{block} 528 | 529 | \bigskip 530 | 531 | \begin{itemize} 532 | \item Now \textit{director} has two child elements: \textit{first\_name} and \textit{last\_name} 533 | \end{itemize} 534 | 535 | \end{frame} 536 | 537 | %------------------------------------------------ 538 | 539 | \begin{frame}[fragile] 540 | \frametitle{XML Hierarchy Structure} 541 | 542 | \begin{block}{Conceptual XML} 543 | \begin{verbatim} 544 | 545 | ... 546 | ... 547 | ... 548 | ... 549 | 550 | \end{verbatim} 551 | \end{block} 552 | 553 | \bigskip 554 | 555 | \begin{itemize} 556 | \item An XML document can be represented with a \textbf{tree structure} 557 | \item An XML document must have \textbf{one single Root} element 558 | \item The \code{Root} may contain \code{child} elements 559 | \item A \code{child} element may contain \code{subchild} elements 560 | \end{itemize} 561 | 562 | \end{frame} 563 | 564 | %------------------------------------------------ 565 | 566 | \begin{frame} 567 | \frametitle{XML Tree Structure} 568 | 569 | \begin{center} 570 | \includegraphics[width=9cm]{images/xml_movie_tree1.pdf} 571 | \end{center} 572 | 573 | \end{frame} 574 | 575 | %------------------------------------------------ 576 | 577 | \begin{frame} 578 | \frametitle{XML Tree Structure (con't)} 579 | 580 | \begin{center} 581 | \includegraphics[width=9cm]{images/xml_movie_tree2.pdf} 582 | \end{center} 583 | 584 | \end{frame} 585 | 586 | %------------------------------------------------ 587 | 588 | \begin{frame} 589 | \frametitle{Well-Formedness} 590 | 591 | \begin{block}{Well-formed XML} 592 | We say that an XML document is \textbf{well-formed} when it obeys the basic syntax rules of XML. Some of those rules are: 593 | \begin{itemize} 594 | \item one root element containing the rest of elements 595 | \item properly nested elements 596 | \item self-closing tags 597 | \item attributes appear in start-tags of elements 598 | \item attribute values must be quoted 599 | \item element names and attribute names are case sensitive 600 | \end{itemize} 601 | \end{block} 602 | 603 | \end{frame} 604 | 605 | %------------------------------------------------ 606 | 607 | \begin{frame} 608 | \frametitle{Well-Formedness} 609 | 610 | \begin{block}{Importance of Well-formed XML} 611 | Not well-formed XML documents produce potentially fatal errors or warnings when parsed. 612 | 613 | \bigskip 614 | Documents may be well-formed but not valid. Well-formed just guarantees that the document meets the basic XML structure, not that the content is valid. 615 | \end{block} 616 | 617 | \end{frame} 618 | 619 | %------------------------------------------------ 620 | 621 | \begin{frame} 622 | \begin{center} 623 | \Huge{\textcolor{mandarina}{Additional XML Elements}} 624 | \end{center} 625 | \end{frame} 626 | 627 | %------------------------------------------------ 628 | 629 | \begin{frame}[fragile] 630 | \frametitle{Some Additional Elements} 631 | 632 | \begin{block}{Example with extra elemets} 633 | { \small 634 | \begin{verbatim} 635 | 636 | 5 & b < 10 ]]> 637 | 638 | 639 | 640 | 641 | Good Will Hunting 642 | 643 | Gus 644 | Van Sant 645 | 646 | 1998 647 | drama 648 | 649 | \end{verbatim} 650 | } 651 | \end{block} 652 | 653 | \end{frame} 654 | 655 | %------------------------------------------------ 656 | 657 | \begin{frame} 658 | \frametitle{Additional Elements} 659 | 660 | \begin{center} 661 | \textcolor{turquoise}{Additional (optional) XML elements} 662 | 663 | \bigskip 664 | \begin{tabular}{l l} 665 | \hline 666 | Markup & Description \\ 667 | \hline 668 | \code{} & XML Declaration \\ 669 | & \low{identifies content as an XML document} \\ 670 | \code{} & Processing Instruction \\ 671 | & \low{processing instructions passed to application \code{PI}} \\ 672 | \code{} & Document-type Declaration \\ 673 | & \low{defines the structure of an XML document} \\ 674 | \code{} & CDATA Character Data \\ 675 | & \low{anything inside a CDATA is ignored by the parser} \\ 676 | \code{} & Comment \\ 677 | & \low{for writing comments} \\ 678 | \hline 679 | \end{tabular} 680 | \end{center} 681 | 682 | \end{frame} 683 | 684 | %------------------------------------------------ 685 | 686 | \begin{frame} 687 | \frametitle{DTD} 688 | 689 | \begin{block}{Document-Type Declaration} 690 | The Document-type Declaration identifies the \textbf{type} of the document. The \textit{type} indicates the structure of a \textbf{valid} document: 691 | 692 | \begin{itemize} 693 | \item what elements are allowed to be present 694 | \item how elements can be combined 695 | \item how elements must be ordered 696 | \end{itemize} 697 | \end{block} 698 | 699 | Basically, the DTD specifies what the format allows to do. 700 | \end{frame} 701 | 702 | %------------------------------------------------ 703 | 704 | \begin{frame} 705 | \begin{center} 706 | \Huge{\textcolor{mandarina}{Wrapping Up}} 707 | \end{center} 708 | \end{frame} 709 | 710 | %------------------------------------------------ 711 | 712 | \begin{frame} 713 | \frametitle{About XML} 714 | 715 | \begin{block}{About XML} 716 | \begin{itemize} 717 | \item designed to store and transfer data 718 | \item designed to be self-descriptive 719 | \item tags are not predefined and can be extended 720 | \end{itemize} 721 | \end{block} 722 | 723 | \end{frame} 724 | 725 | %------------------------------------------------ 726 | 727 | \begin{frame} 728 | \frametitle{Characteristics of XML} 729 | 730 | \begin{block}{XML is} 731 | \begin{itemize} 732 | \item a generic language that provides structure and syntax for many markup dialects 733 | \item is a syntax or format for defining markup languages 734 | \item a standard for the semantic, hierarchical representation of data 735 | \item provides a general approach for representing all types of information dialects 736 | \end{itemize} 737 | \end{block} 738 | 739 | \end{frame} 740 | 741 | %------------------------------------------------ 742 | 743 | \begin{frame}[fragile] 744 | \frametitle{XML document example} 745 | 746 | \begin{block}{Simple XML} 747 | \begin{verbatim} 748 | 749 | 750 | 751 | 752 | Good Will Hunting 753 | 754 | Gus 755 | Van Sant 756 | 757 | 1998 758 | drama 759 | 760 | \end{verbatim} 761 | \end{block} 762 | 763 | \end{frame} 764 | 765 | %------------------------------------------------ 766 | 767 | \begin{frame} 768 | \frametitle{XML Tree Structure} 769 | 770 | \begin{block}{Each Node can have:} 771 | \begin{itemize} 772 | \item a Name 773 | \item any number of attributes 774 | \item optional content 775 | \item other nested elements 776 | \end{itemize} 777 | \end{block} 778 | 779 | \begin{block}{Traversing the tree} 780 | There's a \textbf{unique} path from the root node to any given node 781 | \end{block} 782 | 783 | \end{frame} 784 | 785 | %------------------------------------------------ 786 | 787 | \end{document} -------------------------------------------------------------------------------- /03-xml-basics/03-xml-basics.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/03-xml-basics.pdf -------------------------------------------------------------------------------- /03-xml-basics/03-xml-basics.tex: -------------------------------------------------------------------------------- 1 | \documentclass{beamer}\usepackage[]{graphicx}\usepackage[]{color} 2 | %% maxwidth is the original width if it is less than linewidth 3 | %% otherwise use linewidth (to make sure the graphics do not exceed the margin) 4 | \makeatletter 5 | \def\maxwidth{ % 6 | \ifdim\Gin@nat@width>\linewidth 7 | \linewidth 8 | \else 9 | \Gin@nat@width 10 | \fi 11 | } 12 | \makeatother 13 | 14 | \definecolor{fgcolor}{rgb}{0.196, 0.196, 0.196} 15 | \newcommand{\hlnum}[1]{\textcolor[rgb]{0.063,0.58,0.627}{#1}}% 16 | \newcommand{\hlstr}[1]{\textcolor[rgb]{0.063,0.58,0.627}{#1}}% 17 | \newcommand{\hlcom}[1]{\textcolor[rgb]{0.588,0.588,0.588}{#1}}% 18 | \newcommand{\hlopt}[1]{\textcolor[rgb]{0.196,0.196,0.196}{#1}}% 19 | \newcommand{\hlstd}[1]{\textcolor[rgb]{0.196,0.196,0.196}{#1}}% 20 | \newcommand{\hlkwa}[1]{\textcolor[rgb]{0.231,0.416,0.784}{#1}}% 21 | \newcommand{\hlkwb}[1]{\textcolor[rgb]{0.627,0,0.314}{#1}}% 22 | \newcommand{\hlkwc}[1]{\textcolor[rgb]{0,0.631,0.314}{#1}}% 23 | \newcommand{\hlkwd}[1]{\textcolor[rgb]{0.78,0.227,0.412}{#1}}% 24 | \let\hlipl\hlkwb 25 | 26 | \usepackage{framed} 27 | \makeatletter 28 | \newenvironment{kframe}{% 29 | \def\at@end@of@kframe{}% 30 | \ifinner\ifhmode% 31 | \def\at@end@of@kframe{\end{minipage}}% 32 | \begin{minipage}{\columnwidth}% 33 | \fi\fi% 34 | \def\FrameCommand##1{\hskip\@totalleftmargin \hskip-\fboxsep 35 | \colorbox{shadecolor}{##1}\hskip-\fboxsep 36 | % There is no \\@totalrightmargin, so: 37 | \hskip-\linewidth \hskip-\@totalleftmargin \hskip\columnwidth}% 38 | \MakeFramed {\advance\hsize-\width 39 | \@totalleftmargin\z@ \linewidth\hsize 40 | \@setminipage}}% 41 | {\par\unskip\endMakeFramed% 42 | \at@end@of@kframe} 43 | \makeatother 44 | 45 | \definecolor{shadecolor}{rgb}{.97, .97, .97} 46 | \definecolor{messagecolor}{rgb}{0, 0, 0} 47 | \definecolor{warningcolor}{rgb}{1, 0, 1} 48 | \definecolor{errorcolor}{rgb}{1, 0, 0} 49 | \newenvironment{knitrout}{}{} % an empty environment to be redefined in TeX 50 | 51 | \usepackage{alltt} 52 | 53 | % load packages 54 | \usepackage{tikz} 55 | \usepackage{graphicx} 56 | \usepackage{upquote} 57 | \usepackage{listings} 58 | \usepackage{hyperref} 59 | \usepackage{color} 60 | \usepackage{lmodern} 61 | 62 | \input{../header.tex} 63 | 64 | \title[Getting data from the web with R]{\LARGE Getting Data from the Web with R} 65 | \subtitle[Web Data in R]{\large Part 3: Basics of XML} 66 | \author[gastonsanchez.com]{ 67 | \textcolor{gray}{\textbf{G}aston \textbf{S}anchez} 68 | } 69 | \institute[]{\scriptsize \textcolor{lightgray}{April-May 2014}} 70 | \date[CC BY-SA-NC 4.0]{ 71 | \textcolor{lightgray}{\tiny{Content licensed under 72 | \href{http://creativecommons.org/licenses/by-nc-sa/4.0/}{CC BY-NC-SA 4.0}}} 73 | } 74 | \IfFileExists{upquote.sty}{\usepackage{upquote}}{} 75 | \begin{document} 76 | 77 | 78 | 79 | 80 | %--- the titlepage frame -------------------------% 81 | 82 | \begin{frame}[plain] 83 | \titlepage 84 | \end{frame} 85 | 86 | %------------------------------------------------ 87 | 88 | { % all template changes are local to this group. 89 | \setbeamertemplate{navigation symbols}{} 90 | \begin{frame}[plain] 91 | \begin{tikzpicture}[remember picture,overlay] 92 | \node[at=(current page.center)] { 93 | \includegraphics[width=\paperwidth]{images/xmlcover.png} 94 | }; 95 | \end{tikzpicture} 96 | \end{frame} 97 | } 98 | 99 | %------------------------------------------------ 100 | 101 | \begin{frame}[fragile] 102 | \frametitle{Readme} 103 | 104 | \begin{block}{\scriptsize License:} 105 | \tiny 106 | \begin{itemize} 107 | \item[] Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License \\ 108 | \url{http://creativecommons.org/licenses/by-nc-sa/4.0/}{} 109 | \end{itemize} 110 | \end{block} 111 | 112 | \begin{block}{\scriptsize You are free to:} 113 | \tiny 114 | \begin{itemize} 115 | \item[] \textcolor{darkgray}{\textbf{Share}} --- \textcolor{gray}{copy and redistribute the material} 116 | \item[] \textcolor{darkgray}{\textbf{Adapt}} --- \textcolor{gray}{rebuild and transform the material} 117 | \end{itemize} 118 | \end{block} 119 | 120 | \vspace{2mm} 121 | \begin{block}{\scriptsize Under the following conditions:} 122 | \tiny 123 | \begin{itemize} 124 | \item[] \textcolor{darkgray}{\textbf{Attribution}} --- \textcolor{gray}{You must give appropriate credit, provide a link to the license, and indicate if changes were made.} 125 | \item[] \textcolor{darkgray}{\textbf{NonCommercial}} --- \textcolor{gray}{You may not use this work for commercial purposes.} 126 | \item[] \textcolor{darkgray}{\textbf{Share Alike}} --- \textcolor{gray}{If you remix, transform, or build upon this 127 | work, you must distribute your contributions under the same license to this one.} 128 | \end{itemize} 129 | \end{block} 130 | 131 | \end{frame} 132 | 133 | %------------------------------------------------ 134 | 135 | \begin{frame} 136 | \frametitle{Lectures Menu} 137 | 138 | \begin{columns}[t] 139 | \begin{column}{0.1\textwidth} 140 | %--- empty space ---% 141 | \end{column} 142 | \begin{column}{0.8\textwidth} 143 | \begin{block}{Slide Decks} 144 | \begin{enumerate} 145 | \item \textcolor{lightgray}{Introduction} 146 | \item \textcolor{lightgray}{Reading files from the Web} 147 | \item \textbf{Basics of XML and HTML} 148 | \item \textcolor{lightgray}{Parsing XML / HTML documents} 149 | \item \textcolor{lightgray}{Handling JSON data} 150 | \item \textcolor{lightgray}{HTTP Basics and the RCurl package} 151 | \item \textcolor{lightgray}{Getting data via Web Forms} 152 | \item \textcolor{lightgray}{Getting data via Web APIs} 153 | \end{enumerate} 154 | \end{block} 155 | \end{column} 156 | \begin{column}{0.1\textwidth} 157 | %--- empty space ---% 158 | \end{column} 159 | \end{columns} 160 | 161 | \end{frame} 162 | 163 | %------------------------------------------------ 164 | 165 | \begin{frame} 166 | \begin{center} 167 | \Huge{\textcolor{mandarina}{Basics of XML \\ and HTML}} 168 | \end{center} 169 | \end{frame} 170 | 171 | %------------------------------------------------ 172 | 173 | \begin{frame} 174 | \frametitle{Goal} 175 | 176 | \begin{columns}[t] 177 | \begin{column}{0.1\textwidth} 178 | %--- empty space ---% 179 | \end{column} 180 | \begin{column}{0.8\textwidth} 181 | 182 | \begin{block}{XML \& HTML} 183 | The goal of these slides is to give you a \textbf{crash introduction to XML and HTML} so you can get a good grasp of those formats for the rest of the lectures 184 | \end{block} 185 | 186 | \end{column} 187 | \begin{column}{0.1\textwidth} 188 | %--- empty space ---% 189 | \end{column} 190 | \end{columns} 191 | 192 | \end{frame} 193 | 194 | %------------------------------------------------ 195 | 196 | \begin{frame} 197 | \frametitle{Synopsis} 198 | 199 | \begin{columns}[t] 200 | \begin{column}{0.1\textwidth} 201 | %--- empty space ---% 202 | \end{column} 203 | \begin{column}{0.8\textwidth} 204 | 205 | \begin{block}{In a nutshell} 206 | We'll cover a the following concepts: 207 | \begin{itemize} 208 | \item Importance of XML and HTML 209 | \item Hierarchical Structure 210 | \item Document Object Model (DOM) 211 | \end{itemize} 212 | \end{block} 213 | 214 | \end{column} 215 | \begin{column}{0.1\textwidth} 216 | %--- empty space ---% 217 | \end{column} 218 | \end{columns} 219 | 220 | \end{frame} 221 | 222 | %------------------------------------------------ 223 | 224 | \begin{frame} 225 | \frametitle{Some References} 226 | 227 | \begin{itemize} 228 | \item XML Files website {\scriptsize (\url{http://www.xmlfiles.com})} \\ 229 | \low{by Jan Egil Refsnes} 230 | \item XML in a Nutshell \\ 231 | \low{by Elliotte Rusty Harold; W. Scott Means} 232 | \item XML Tutorial {\scriptsize (\url{http://www.w3schools.com/xml/default.asp})} \\ 233 | \low{by w3schools} 234 | \item Introduction to Data Technologies \\ 235 | \low{by Paul Murrell} 236 | \item XML and Web Technologies for Data Sciences with R \\ 237 | \low{by Deb Nolan and Duncan Temple Lang} 238 | \end{itemize} 239 | 240 | \end{frame} 241 | 242 | %------------------------------------------------ 243 | 244 | \begin{frame} 245 | \frametitle{XML and HTML} 246 | 247 | \begin{block}{Why you should care about XML and HTML?} 248 | \begin{itemize} 249 | \item Large amounts of data and information are stored, shared and distributed using HTML and XML-dialects 250 | \item They are widely adopted and used in many applications 251 | \item Working with data from the Web means dealing with HTML 252 | \end{itemize} 253 | \end{block} 254 | 255 | \end{frame} 256 | 257 | 258 | %------------------------------------------------ 259 | 260 | \begin{frame} 261 | \begin{center} 262 | {\Huge \textcolor{mandarina}{XML}} \\ 263 | \bigskip 264 | {\Large \textcolor{mandarina}{eXtensible Markup Language}} 265 | \end{center} 266 | \end{frame} 267 | 268 | %------------------------------------------------ 269 | 270 | { % all template changes are local to this group. 271 | \setbeamertemplate{navigation symbols}{} 272 | \begin{frame}[plain] 273 | \begin{tikzpicture}[remember picture,overlay] 274 | \node[at=(current page.center)] { 275 | \includegraphics[width=\paperwidth]{images/xml_plants_catalog.png} 276 | }; 277 | \end{tikzpicture} 278 | \end{frame} 279 | } 280 | 281 | %------------------------------------------------ 282 | 283 | \begin{frame} 284 | \frametitle{Some Definitions} 285 | 286 | \begin{quotation} 287 | ``XML is a markup language that defines a set of rules for encoding documents in a format that is both human-readable and machine-readable'' 288 | \end{quotation} 289 | 290 | {\footnotesize 291 | \hspace{8mm} \url{http://en.wikipedia.org/wiki/XML} 292 | } 293 | 294 | \bigskip 295 | \begin{quotation} 296 | ``XML is a data description language used for describing data'' 297 | \end{quotation} 298 | 299 | {\footnotesize 300 | \hspace{8mm} \high{Paul Murrell} \\ 301 | \hspace{8mm} \low{Introduction to Data Technologies} 302 | } 303 | 304 | \end{frame} 305 | 306 | %------------------------------------------------ 307 | 308 | \begin{frame} 309 | \frametitle{Some Definitions} 310 | 311 | \begin{quotation} 312 | ``XML is a very general structure with which we can define any number of new formats to represent arbitrary data'' 313 | \end{quotation} 314 | 315 | \begin{quotation} 316 | ``XML is a standard for the semantic, hierarchical representation of data'' 317 | \end{quotation} 318 | 319 | {\footnotesize 320 | \hspace{8mm} \high{Deb Nolan \& Duncan Temple Lang} \\ 321 | \hspace{8mm} \low{XML and Web Technologies for Data Sciences with R} 322 | } 323 | 324 | \end{frame} 325 | 326 | %------------------------------------------------ 327 | 328 | \begin{frame} 329 | \frametitle{About XML} 330 | 331 | \begin{columns}[t] 332 | \begin{column}{0.1\textwidth} 333 | %--- empty space ---% 334 | \end{column} 335 | \begin{column}{0.8\textwidth} 336 | 337 | \begin{block}{XML} 338 | XML stands for \textbf{eXtensible Markup Language} 339 | \end{block} 340 | 341 | \begin{block}{Broadly speaking ...} 342 | XML provides a flexible framework to create formats for describing and representing data 343 | \end{block} 344 | 345 | \end{column} 346 | \begin{column}{0.1\textwidth} 347 | %--- empty space ---% 348 | \end{column} 349 | \end{columns} 350 | 351 | \end{frame} 352 | 353 | %------------------------------------------------ 354 | 355 | \begin{frame} 356 | \frametitle{Markups} 357 | 358 | \begin{block}{Markup} 359 | A \textbf{markup} is a sequence of characters or other symbols inserted at certain places in a document to indicate either: 360 | \begin{itemize} 361 | \item how the content should be displayed when printed or in screen 362 | \item describe the document's structure 363 | \end{itemize} 364 | \end{block} 365 | 366 | \begin{block}{Markup Language} 367 | A markup language is a system for \textbf{annotating} (i.e. \textit{marking}) a document in a way that the content is distinguished from its representation \low{(eg LaTeX, PostScript, HTML, SVG)} 368 | \end{block} 369 | 370 | \end{frame} 371 | 372 | %------------------------------------------------ 373 | 374 | \begin{frame}[fragile] 375 | \frametitle{Markups} 376 | 377 | \begin{block}{XML Markups} 378 | In XML (as well as in HTML) the marks (aka \textit{tags}) are defined using angle brackets: {\Huge \highcode{<>}} 379 | \end{block} 380 | 381 | \bigskip 382 | 383 | \code{ \high{}Text marked with special tag\high{} } 384 | 385 | \end{frame} 386 | 387 | %------------------------------------------------ 388 | 389 | \begin{frame}[fragile] 390 | \frametitle{Extensible} 391 | 392 | \begin{block}{Extensible?} 393 | The concept of \textit{extensibility} means that we can define our own marks, the order in which they occur, and how they should be processed. For example: 394 | \begin{itemize} 395 | \item \highcode{} 396 | \item \highcode{} 397 | \item \highcode{} 398 | \item \highcode{} 399 | \end{itemize} 400 | \end{block} 401 | 402 | \end{frame} 403 | 404 | %------------------------------------------------ 405 | 406 | \begin{frame} 407 | \frametitle{About XML} 408 | 409 | \begin{block}{XML is NOT} 410 | \begin{itemize} 411 | \item a programming language 412 | \item a network transfer protocol 413 | \item a database 414 | \end{itemize} 415 | \end{block} 416 | 417 | \begin{block}{XML is} 418 | \begin{itemize} 419 | \item more than a markup language 420 | \item a generic language that provides structure and syntax for representing any type of information 421 | \item a meta-language: it allows us to create or define other languages 422 | \end{itemize} 423 | \end{block} 424 | 425 | \end{frame} 426 | 427 | %------------------------------------------------ 428 | 429 | \begin{frame} 430 | \frametitle{XML Applications} 431 | 432 | \begin{block}{Some XML dialects} 433 | \begin{itemize} 434 | \item \textbf{KML} (\textit{Keyhole Markup Language}) for describing geo-spatial information used in Google Earth, Google Maps, Google Sky 435 | \item \textbf{SVG} (\textit{Scalable Vector Graphics}) for visual graphical displays of two-dimensional graphics with support for interactivity and animation 436 | \item \textbf{PMML} (\textit{Predictive Model Markup Language}) for describing and exchanging models produced by data mining and machine learning algorithms 437 | \end{itemize} 438 | \end{block} 439 | 440 | \end{frame} 441 | 442 | 443 | %------------------------------------------------ 444 | 445 | \begin{frame} 446 | \frametitle{XML Applications (con't)} 447 | 448 | \begin{block}{Some XML dialects} 449 | \begin{itemize} 450 | \item \textbf{RSS} (\textit{Rich Site Summary}) feeds for publishing blog entries 451 | \item \textbf{SDMX} (\textit{Statistical Data and Metadata Exchange}) for organizing and exchanging statistical information 452 | \item \textbf{GML} (\textit{Geography Markup Language}) for representing geographical features 453 | \item \textbf{SBML} (\textit{Systems Biology Markup Language}) for describing biological systems 454 | \end{itemize} 455 | \end{block} 456 | 457 | \end{frame} 458 | 459 | %------------------------------------------------ 460 | 461 | \begin{frame} 462 | \begin{center} 463 | \Huge{\textcolor{mandarina}{Minimalist Example}} 464 | \end{center} 465 | \end{frame} 466 | 467 | %------------------------------------------------ 468 | 469 | { % all template changes are local to this group. 470 | \setbeamertemplate{navigation symbols}{} 471 | \begin{frame}[plain] 472 | \begin{tikzpicture}[remember picture,overlay] 473 | \node[at=(current page.center)] { 474 | \includegraphics[width=\paperwidth]{images/goodwillhunting.jpg} 475 | }; 476 | \end{tikzpicture} 477 | \end{frame} 478 | } 479 | 480 | %------------------------------------------------ 481 | 482 | \begin{frame}[fragile] 483 | \frametitle{XML Example} 484 | 485 | \begin{block}{Ultra Simple XML} 486 | \begin{verbatim} 487 | 488 | Good Will Hunting 489 | 490 | \end{verbatim} 491 | \end{block} 492 | 493 | \bigskip 494 | 495 | \begin{itemize} 496 | \item one single element {\textit{movie}} 497 | \item start-tag: \highcode{} 498 | \item end-tag: \highcode{} 499 | \item content: \highcode{Good Will Hunting} 500 | \end{itemize} 501 | 502 | \end{frame} 503 | 504 | %------------------------------------------------ 505 | 506 | \begin{frame}[fragile] 507 | \frametitle{XML Example} 508 | 509 | \begin{block}{Ultra Simple XML} 510 | \begin{verbatim} 511 | 512 | Good Will Hunting 513 | 514 | \end{verbatim} 515 | \end{block} 516 | 517 | \bigskip 518 | 519 | \begin{itemize} 520 | \item xml elements can have \textbf{attributes} 521 | \item attributes: \highcode{mins} \low{(minutes)} and \highcode{lang} \low{(language)} 522 | \item attributes are \textit{attached} to the element's start tag 523 | \item attribute values \textbf{must be quoted!} 524 | \end{itemize} 525 | 526 | \end{frame} 527 | 528 | %------------------------------------------------ 529 | 530 | \begin{frame}[fragile] 531 | \frametitle{XML Example} 532 | 533 | \begin{block}{Minimalist XML} 534 | \begin{verbatim} 535 | 536 | Good Will Hunting 537 | Gus Van Sant 538 | 1998 539 | drama 540 | 541 | \end{verbatim} 542 | \end{block} 543 | 544 | \bigskip 545 | 546 | \begin{itemize} 547 | \item an xml element may contain other elements 548 | \item \textit{movie} contains several elements: \textit{title, director, year, genre} 549 | \end{itemize} 550 | 551 | \end{frame} 552 | 553 | %------------------------------------------------ 554 | 555 | \begin{frame}[fragile] 556 | \frametitle{XML Example} 557 | 558 | \begin{block}{Simple XML} 559 | \begin{verbatim} 560 | 561 | Good Will Hunting 562 | 563 | Gus 564 | Van Sant 565 | 566 | 1998 567 | drama 568 | 569 | \end{verbatim} 570 | \end{block} 571 | 572 | \bigskip 573 | 574 | \begin{itemize} 575 | \item Now \textit{director} has two child elements: \textit{first\_name} and \textit{last\_name} 576 | \end{itemize} 577 | 578 | \end{frame} 579 | 580 | %------------------------------------------------ 581 | 582 | \begin{frame}[fragile] 583 | \frametitle{XML Hierarchy Structure} 584 | 585 | \begin{block}{Conceptual XML} 586 | \begin{verbatim} 587 | 588 | ... 589 | ... 590 | ... 591 | ... 592 | 593 | \end{verbatim} 594 | \end{block} 595 | 596 | \bigskip 597 | 598 | \begin{itemize} 599 | \item An XML document can be represented with a \textbf{tree structure} 600 | \item An XML document must have \textbf{one single Root} element 601 | \item The \code{Root} may contain \code{child} elements 602 | \item A \code{child} element may contain \code{subchild} elements 603 | \end{itemize} 604 | 605 | \end{frame} 606 | 607 | %------------------------------------------------ 608 | 609 | \begin{frame} 610 | \frametitle{XML Tree Structure} 611 | 612 | \begin{center} 613 | \includegraphics[width=9cm]{images/xml_movie_tree1.pdf} 614 | \end{center} 615 | 616 | \end{frame} 617 | 618 | %------------------------------------------------ 619 | 620 | \begin{frame} 621 | \frametitle{XML Tree Structure (con't)} 622 | 623 | \begin{center} 624 | \includegraphics[width=9cm]{images/xml_movie_tree2.pdf} 625 | \end{center} 626 | 627 | \end{frame} 628 | 629 | %------------------------------------------------ 630 | 631 | \begin{frame} 632 | \frametitle{Well-Formedness} 633 | 634 | \begin{block}{Well-formed XML} 635 | We say that an XML document is \textbf{well-formed} when it obeys the basic syntax rules of XML. Some of those rules are: 636 | \begin{itemize} 637 | \item one root element containing the rest of elements 638 | \item properly nested elements 639 | \item self-closing tags 640 | \item attributes appear in start-tags of elements 641 | \item attribute values must be quoted 642 | \item element names and attribute names are case sensitive 643 | \end{itemize} 644 | \end{block} 645 | 646 | \end{frame} 647 | 648 | %------------------------------------------------ 649 | 650 | \begin{frame} 651 | \frametitle{Well-Formedness} 652 | 653 | \begin{block}{Importance of Well-formed XML} 654 | Not well-formed XML documents produce potentially fatal errors or warnings when parsed. 655 | 656 | \bigskip 657 | Documents may be well-formed but not valid. Well-formed just guarantees that the document meets the basic XML structure, not that the content is valid. 658 | \end{block} 659 | 660 | \end{frame} 661 | 662 | %------------------------------------------------ 663 | 664 | \begin{frame} 665 | \begin{center} 666 | \Huge{\textcolor{mandarina}{Additional XML Elements}} 667 | \end{center} 668 | \end{frame} 669 | 670 | %------------------------------------------------ 671 | 672 | \begin{frame}[fragile] 673 | \frametitle{Some Additional Elements} 674 | 675 | \begin{block}{Example with extra elemets} 676 | { \small 677 | \begin{verbatim} 678 | 679 | 5 & b < 10 ]]> 680 | 681 | 682 | 683 | 684 | Good Will Hunting 685 | 686 | Gus 687 | Van Sant 688 | 689 | 1998 690 | drama 691 | 692 | \end{verbatim} 693 | } 694 | \end{block} 695 | 696 | \end{frame} 697 | 698 | %------------------------------------------------ 699 | 700 | \begin{frame} 701 | \frametitle{Additional Elements} 702 | 703 | \begin{center} 704 | \textcolor{turquoise}{Additional (optional) XML elements} 705 | 706 | \bigskip 707 | \begin{tabular}{l l} 708 | \hline 709 | Markup & Description \\ 710 | \hline 711 | \code{} & XML Declaration \\ 712 | & \low{identifies content as an XML document} \\ 713 | \code{} & Processing Instruction \\ 714 | & \low{processing instructions passed to application \code{PI}} \\ 715 | \code{} & Document-type Declaration \\ 716 | & \low{defines the structure of an XML document} \\ 717 | \code{} & CDATA Character Data \\ 718 | & \low{anything inside a CDATA is ignored by the parser} \\ 719 | \code{} & Comment \\ 720 | & \low{for writing comments} \\ 721 | \hline 722 | \end{tabular} 723 | \end{center} 724 | 725 | \end{frame} 726 | 727 | %------------------------------------------------ 728 | 729 | \begin{frame} 730 | \frametitle{DTD} 731 | 732 | \begin{block}{Document-Type Declaration} 733 | The Document-type Declaration identifies the \textbf{type} of the document. The \textit{type} indicates the structure of a \textbf{valid} document: 734 | 735 | \begin{itemize} 736 | \item what elements are allowed to be present 737 | \item how elements can be combined 738 | \item how elements must be ordered 739 | \end{itemize} 740 | \end{block} 741 | 742 | Basically, the DTD specifies what the format allows to do. 743 | \end{frame} 744 | 745 | %------------------------------------------------ 746 | 747 | \begin{frame} 748 | \begin{center} 749 | \Huge{\textcolor{mandarina}{Wrapping Up}} 750 | \end{center} 751 | \end{frame} 752 | 753 | %------------------------------------------------ 754 | 755 | \begin{frame} 756 | \frametitle{About XML} 757 | 758 | \begin{block}{About XML} 759 | \begin{itemize} 760 | \item designed to store and transfer data 761 | \item designed to be self-descriptive 762 | \item tags are not predefined and can be extended 763 | \end{itemize} 764 | \end{block} 765 | 766 | \end{frame} 767 | 768 | %------------------------------------------------ 769 | 770 | \begin{frame} 771 | \frametitle{Characteristics of XML} 772 | 773 | \begin{block}{XML is} 774 | \begin{itemize} 775 | \item a generic language that provides structure and syntax for many markup dialects 776 | \item is a syntax or format for defining markup languages 777 | \item a standard for the semantic, hierarchical representation of data 778 | \item provides a general approach for representing all types of information dialects 779 | \end{itemize} 780 | \end{block} 781 | 782 | \end{frame} 783 | 784 | %------------------------------------------------ 785 | 786 | \begin{frame}[fragile] 787 | \frametitle{XML document example} 788 | 789 | \begin{block}{Simple XML} 790 | \begin{verbatim} 791 | 792 | 793 | 794 | 795 | Good Will Hunting 796 | 797 | Gus 798 | Van Sant 799 | 800 | 1998 801 | drama 802 | 803 | \end{verbatim} 804 | \end{block} 805 | 806 | \end{frame} 807 | 808 | %------------------------------------------------ 809 | 810 | \begin{frame} 811 | \frametitle{XML Tree Structure} 812 | 813 | \begin{block}{Each Node can have:} 814 | \begin{itemize} 815 | \item a Name 816 | \item any number of attributes 817 | \item optional content 818 | \item other nested elements 819 | \end{itemize} 820 | \end{block} 821 | 822 | \begin{block}{Traversing the tree} 823 | There's a \textbf{unique} path from the root node to any given node 824 | \end{block} 825 | 826 | \end{frame} 827 | 828 | %------------------------------------------------ 829 | 830 | \end{document} 831 | -------------------------------------------------------------------------------- /03-xml-basics/images/blacksmith.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/images/blacksmith.png -------------------------------------------------------------------------------- /03-xml-basics/images/goodwillhunting.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/images/goodwillhunting.jpg -------------------------------------------------------------------------------- /03-xml-basics/images/parsing_xml.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/images/parsing_xml.jpg -------------------------------------------------------------------------------- /03-xml-basics/images/spider_web.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/images/spider_web.jpg -------------------------------------------------------------------------------- /03-xml-basics/images/xml_movie_tree1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/images/xml_movie_tree1.pdf -------------------------------------------------------------------------------- /03-xml-basics/images/xml_movie_tree2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/images/xml_movie_tree2.pdf -------------------------------------------------------------------------------- /03-xml-basics/images/xml_plants_catalog.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/images/xml_plants_catalog.png -------------------------------------------------------------------------------- /03-xml-basics/images/xmlcover.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/03-xml-basics/images/xmlcover.png -------------------------------------------------------------------------------- /04-parsing-xml/04-parsing-xml.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/04-parsing-xml.pdf -------------------------------------------------------------------------------- /04-parsing-xml/images/mailing_lists.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/mailing_lists.png -------------------------------------------------------------------------------- /04-parsing-xml/images/mailing_sig.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/mailing_sig.png -------------------------------------------------------------------------------- /04-parsing-xml/images/mailing_sig_source.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/mailing_sig_source.png -------------------------------------------------------------------------------- /04-parsing-xml/images/xml_package.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xml_package.png -------------------------------------------------------------------------------- /04-parsing-xml/images/xml_tree_navigate.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xml_tree_navigate.pdf -------------------------------------------------------------------------------- /04-parsing-xml/images/xmlparsing_cover.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xmlparsing_cover.png -------------------------------------------------------------------------------- /04-parsing-xml/images/xpath_director.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xpath_director.pdf -------------------------------------------------------------------------------- /04-parsing-xml/images/xpath_firstname.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xpath_firstname.pdf -------------------------------------------------------------------------------- /04-parsing-xml/images/xpath_lastname.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xpath_lastname.pdf -------------------------------------------------------------------------------- /04-parsing-xml/images/xpath_movie.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xpath_movie.pdf -------------------------------------------------------------------------------- /04-parsing-xml/images/xpath_title.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xpath_title.pdf -------------------------------------------------------------------------------- /04-parsing-xml/images/xpath_tree.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xpath_tree.pdf -------------------------------------------------------------------------------- /04-parsing-xml/images/xpath_ytmt.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/04-parsing-xml/images/xpath_ytmt.pdf -------------------------------------------------------------------------------- /05-json-data/05-json-data.Rnw: -------------------------------------------------------------------------------- 1 | \documentclass{beamer} 2 | 3 | % load packages 4 | \usepackage{tikz} 5 | \usepackage{graphicx} 6 | \usepackage{upquote} 7 | \usepackage{listings} 8 | \usepackage{hyperref} 9 | \usepackage{color} 10 | \usepackage{lmodern} 11 | 12 | \input{../header.tex} 13 | 14 | \title[Getting data from the web with R]{\LARGE Getting Data from the Web with R} 15 | \subtitle[Web Data in R]{\large Part 5: Handling JSON data} 16 | \author[gastonsanchez.com]{ 17 | \textcolor{gray}{\textbf{G}aston \textbf{S}anchez} 18 | } 19 | \institute[]{\scriptsize \textcolor{lightgray}{April-May 2014}} 20 | \date[CC BY-SA-NC 4.0]{ 21 | \textcolor{lightgray}{\tiny{Content licensed under 22 | \href{http://creativecommons.org/licenses/by-nc-sa/4.0/}{CC BY-NC-SA 4.0}}} 23 | } 24 | 25 | 26 | \begin{document} 27 | <>= 28 | # smaller font size for chunks 29 | opts_chunk$set(size = 'tiny') 30 | thm <- knit_theme$get("bclear") 31 | knit_theme$set(thm) 32 | options(width=78) 33 | @ 34 | 35 | 36 | %--- the titlepage frame -------------------------% 37 | 38 | \begin{frame}[plain] 39 | \titlepage 40 | \end{frame} 41 | 42 | %------------------------------------------------ 43 | 44 | { % all template changes are local to this group. 45 | \setbeamertemplate{navigation symbols}{} 46 | \begin{frame}[plain] 47 | \begin{tikzpicture}[remember picture,overlay] 48 | \node[at=(current page.center)] { 49 | \includegraphics[width=\paperwidth]{images/json_cover.png} 50 | }; 51 | \end{tikzpicture} 52 | \end{frame} 53 | } 54 | 55 | %------------------------------------------------ 56 | 57 | \begin{frame}[fragile] 58 | \frametitle{Readme} 59 | 60 | \begin{block}{\scriptsize License:} 61 | \tiny 62 | \begin{itemize} 63 | \item[] Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License \\ 64 | \url{http://creativecommons.org/licenses/by-nc-sa/4.0/}{} 65 | \end{itemize} 66 | \end{block} 67 | 68 | \begin{block}{\scriptsize You are free to:} 69 | \tiny 70 | \begin{itemize} 71 | \item[] \textcolor{darkgray}{\textbf{Share}} --- \textcolor{gray}{copy and redistribute the material} 72 | \item[] \textcolor{darkgray}{\textbf{Adapt}} --- \textcolor{gray}{rebuild and transform the material} 73 | \end{itemize} 74 | \end{block} 75 | 76 | \vspace{2mm} 77 | \begin{block}{\scriptsize Under the following conditions:} 78 | \tiny 79 | \begin{itemize} 80 | \item[] \textcolor{darkgray}{\textbf{Attribution}} --- \textcolor{gray}{You must give appropriate credit, provide a link to the license, and indicate if changes were made.} 81 | \item[] \textcolor{darkgray}{\textbf{NonCommercial}} --- \textcolor{gray}{You may not use this work for commercial purposes.} 82 | \item[] \textcolor{darkgray}{\textbf{Share Alike}} --- \textcolor{gray}{If you remix, transform, or build upon this 83 | work, you must distribute your contributions under the same license to this one.} 84 | \end{itemize} 85 | \end{block} 86 | 87 | \end{frame} 88 | 89 | %------------------------------------------------ 90 | 91 | \begin{frame} 92 | \frametitle{Lectures Menu} 93 | 94 | \begin{columns}[t] 95 | \begin{column}{0.1\textwidth} 96 | %--- empty space ---% 97 | \end{column} 98 | \begin{column}{0.8\textwidth} 99 | \begin{block}{Slide Decks} 100 | \begin{enumerate} 101 | \item \textcolor{lightgray}{Introduction} 102 | \item \textcolor{lightgray}{Reading files from the Web} 103 | \item \textcolor{lightgray}{Basics of XML and HTML} 104 | \item \textcolor{lightgray}{Parsing XML / HTML content} 105 | \item \textbf{Handling JSON data} 106 | \item \textcolor{lightgray}{HTTP Basics and the RCurl Package} 107 | \item \textcolor{lightgray}{Getting data via Web Forms} 108 | \item \textcolor{lightgray}{Getting data via Web APIs} 109 | \end{enumerate} 110 | \end{block} 111 | \end{column} 112 | \begin{column}{0.1\textwidth} 113 | %--- empty space ---% 114 | \end{column} 115 | \end{columns} 116 | 117 | \end{frame} 118 | 119 | %------------------------------------------------ 120 | 121 | \begin{frame} 122 | \begin{center} 123 | \Huge{\textcolor{mandarina}{JSON Data}} 124 | \end{center} 125 | \end{frame} 126 | 127 | %------------------------------------------------ 128 | 129 | \begin{frame} 130 | \frametitle{Goal} 131 | 132 | \begin{columns}[t] 133 | \begin{column}{0.1\textwidth} 134 | %--- empty space ---% 135 | \end{column} 136 | \begin{column}{0.8\textwidth} 137 | 138 | \begin{block}{JSON} 139 | The goal of these slides is to provide an introduction for \textbf{handling JSON data in R} 140 | \end{block} 141 | 142 | \end{column} 143 | \begin{column}{0.1\textwidth} 144 | %--- empty space ---% 145 | \end{column} 146 | \end{columns} 147 | 148 | \end{frame} 149 | 150 | %------------------------------------------------ 151 | 152 | \begin{frame} 153 | \frametitle{Synopsis} 154 | 155 | \begin{columns}[t] 156 | \begin{column}{0.1\textwidth} 157 | %--- empty space ---% 158 | \end{column} 159 | \begin{column}{0.8\textwidth} 160 | 161 | \begin{block}{In a nutshell} 162 | We'll cover the following topics: 163 | \begin{itemize} 164 | \item JSON Basics 165 | \item R packages for JSON data 166 | \item Reading JSON data from the Web 167 | \end{itemize} 168 | \end{block} 169 | 170 | \end{column} 171 | \begin{column}{0.1\textwidth} 172 | %--- empty space ---% 173 | \end{column} 174 | \end{columns} 175 | 176 | \end{frame} 177 | 178 | %------------------------------------------------ 179 | 180 | \begin{frame} 181 | \frametitle{Some References} 182 | 183 | \begin{itemize} 184 | \item XML and Web Technlogies for Data Sciences with R \\ 185 | \low{by Deb Nolan and Duncan Temple Lang} 186 | \item Introducing JSON \\ 187 | {\scriptsize \url{http://www.json.org/}} 188 | \item R package RJSONIO \\ 189 | {\scriptsize \url{http://cran.r-project.org/web/packages/RJSONIO/index.html}} 190 | \item R package jsonlite \\ 191 | {\scriptsize \url{http://cran.r-project.org/web/packages/jsonlite/vignettes/json-mapping.pdf}} 192 | \item R package rjson \\ 193 | {\scriptsize \url{http://cran.r-project.org/web/packages/rjson/index.html}} 194 | \end{itemize} 195 | 196 | \end{frame} 197 | 198 | %------------------------------------------------ 199 | 200 | \begin{frame} 201 | \begin{center} 202 | \Huge{\textcolor{mandarina}{JSON Basics}} 203 | \end{center} 204 | \end{frame} 205 | 206 | %------------------------------------------------ 207 | 208 | \begin{frame} 209 | \frametitle{Basics First} 210 | 211 | \begin{columns}[t] 212 | \begin{column}{0.1\textwidth} 213 | %--- empty space ---% 214 | \end{column} 215 | \begin{column}{0.7\textwidth} 216 | 217 | \begin{block}{Fundamentals} 218 | JSON stands for \textbf{JavaScript Object Notation} \\ 219 | and it is a format for representing data 220 | \begin{itemize} 221 | \item general purpose format 222 | \item lightweight format 223 | \item widely popular 224 | \item fairly simple 225 | \end{itemize} 226 | \end{block} 227 | 228 | \end{column} 229 | \begin{column}{0.1\textwidth} 230 | %--- empty space ---% 231 | \end{column} 232 | \end{columns} 233 | 234 | \end{frame} 235 | 236 | %------------------------------------------------ 237 | 238 | \begin{frame} 239 | \frametitle{Basics First} 240 | 241 | \begin{block}{Why should we care?} 242 | When working with data from the Web, we'll inevitably find some JSON data 243 | \begin{itemize} 244 | \item JSON can be used directly in JavaScript code for Web pages 245 | \item many Web APIs provide data in JSON format 246 | \item R has packages designed to handle JSON data 247 | \end{itemize} 248 | \end{block} 249 | 250 | \end{frame} 251 | 252 | %------------------------------------------------ 253 | 254 | \begin{frame} 255 | \begin{center} 256 | \Huge{\textcolor{mandarina}{Understanding JSON}} 257 | \end{center} 258 | \end{frame} 259 | 260 | %------------------------------------------------ 261 | 262 | \begin{frame} 263 | \frametitle{Understanding JSON} 264 | 265 | \begin{columns}[t] 266 | \begin{column}{0.3\textwidth} 267 | \begin{block}{JSON Data Types} 268 | \begin{itemize} 269 | \item[] \highcode{null} 270 | \item[] \highcode{true} 271 | \item[] \highcode{false} 272 | \item[] \highcode{number} 273 | \item[] \highcode{string} 274 | \end{itemize} 275 | \end{block} 276 | \end{column} 277 | 278 | \begin{column}{0.4\textwidth} 279 | \begin{block}{JSON Data Containers} 280 | \begin{itemize} 281 | \item[] square brackets \highcode{[ ]} 282 | \item[] curly brackets \highcode{\{ \}} 283 | \end{itemize} 284 | \end{block} 285 | \end{column} 286 | \end{columns} 287 | 288 | \end{frame} 289 | 290 | %------------------------------------------------ 291 | 292 | \begin{frame} 293 | \frametitle{JSON Arrays} 294 | 295 | \begin{block}{Unnamed Arrays} 296 | Square brackets \highcode{[ ]} are used for \textbf{ordered unnamed arrays} 297 | \begin{itemize} 298 | \item \code{ [ 1, 2, 3, ... ] } 299 | \item \code{ [ true, true, false, ... ] } 300 | \end{itemize} 301 | \end{block} 302 | 303 | \begin{block}{Named Arrays} 304 | Curly brackets \highcode{\{ \}} are used for \textbf{named arrays} 305 | \begin{itemize} 306 | \item \code{ \{ "dollars" : 5, "euros" : 20, ... \} } 307 | \item \code{ \{ "city" : "Berkeley", "state" : "CA", ... \} } 308 | \end{itemize} 309 | \end{block} 310 | 311 | \end{frame} 312 | 313 | %------------------------------------------------ 314 | 315 | \begin{frame}[fragile] 316 | \frametitle{JSON Arrays} 317 | 318 | Containers can be nested 319 | 320 | \begin{columns}[t] 321 | \begin{column}{0.5\textwidth} 322 | \begin{block}{Example A} 323 | {\footnotesize 324 | \begin{verbatim} 325 | { 326 | "name": ["X", "Y", "Z"], 327 | "grams": [300, 200, 500], 328 | "qty": [4, 5, null], 329 | "new": [true, false, true], 330 | } 331 | \end{verbatim} 332 | } 333 | \end{block} 334 | \end{column} 335 | 336 | \begin{column}{0.5\textwidth} 337 | \begin{block}{Example B} 338 | {\footnotesize 339 | \begin{verbatim} 340 | [ 341 | { "name": "X", 342 | "grams": 300, 343 | "qty": 4, 344 | "new": true }, 345 | { "name": "Y", 346 | "grams": 200, 347 | "qty": 5, 348 | "new": false }, 349 | { "name": "Z", 350 | "grams": 500, 351 | "qty": null, 352 | "new": true} 353 | ] 354 | \end{verbatim} 355 | } 356 | \end{block} 357 | \end{column} 358 | \end{columns} 359 | 360 | \end{frame} 361 | 362 | %------------------------------------------------ 363 | 364 | \begin{frame}[fragile] 365 | \frametitle{Data Table Toy Example} 366 | 367 | \begin{center} 368 | \textcolor{turquoise}{Imagine we have some data} 369 | 370 | \bigskip 371 | \begin{tabular}{l l l l l} 372 | \hline 373 | Name & Gender & Homeland & Born & Jedi \\ 374 | \hline 375 | Anakin & male & Tatooine & 41.9BBY & yes \\ 376 | Amidala & female & Naboo & 46BBY & no \\ 377 | Luke & male & Tatooine & 19BBY & yes \\ 378 | Leia & female & Alderaan & 19BBY & no \\ 379 | Obi-Wan & male & Stewjon & 57BBY & yes \\ 380 | Han & male & Corellia & 29BBY & no \\ 381 | Palpatine & male & Naboo & 82BBY & no \\ 382 | R2-D2 & unknown & Naboo & 33BBY & no \\ 383 | \hline 384 | \end{tabular} 385 | \end{center} 386 | 387 | There are several ways to represent this data in JSON format 388 | 389 | \end{frame} 390 | 391 | %------------------------------------------------ 392 | 393 | \begin{frame}[fragile] 394 | \frametitle{One way to represent data} 395 | 396 | {\footnotesize 397 | \begin{verbatim} 398 | [ 399 | { 400 | "Name": "Anakin", 401 | "Gender": "male", 402 | "Homeworld": "Tatooine", 403 | "Born": "41.9BBY", 404 | "Jedi": "yes" 405 | }, 406 | ... 407 | { 408 | "Name": "R2-D2", 409 | "Gender": "unknown", 410 | "Homeworld": "Naboo", 411 | "Born": "33BBY", 412 | "Jedi": "no" 413 | }, 414 | ] 415 | \end{verbatim} 416 | } 417 | \end{frame} 418 | 419 | %------------------------------------------------ 420 | 421 | \begin{frame}[fragile] 422 | \frametitle{Another way to represent data} 423 | 424 | {\footnotesize 425 | \begin{verbatim} 426 | { 427 | "Name": [ "Anakin", "Amidala", "Luke", ... , "R2-D2" ], 428 | "Gender": [ "male", "female", "male", ... , "unknown" ], 429 | "Homeworld": [ "Tatooine", "Naboo", "Tatooine", ... , "Naboo" ], 430 | "Born": [ "41.9BBY", "46BBY", "19BBY", ... , "33BBY" ], 431 | "Jedi": [ "yes", "no", "yes", ... , "no" ] 432 | } 433 | 434 | \end{verbatim} 435 | } 436 | \end{frame} 437 | 438 | %------------------------------------------------ 439 | 440 | \begin{frame} 441 | \begin{center} 442 | \Huge{\textcolor{mandarina}{JSON R packages}} 443 | \end{center} 444 | \end{frame} 445 | 446 | %------------------------------------------------ 447 | 448 | \begin{frame} 449 | \frametitle{R packages} 450 | 451 | \begin{block}{R packages for JSON} 452 | R has 3 packages for working with JSON data 453 | 454 | \begin{itemize} 455 | \item \highcode{"RJSONIO"} by Duncan Temple Lang 456 | \item \highcode{"rjson"} by Alex Couture-Beil 457 | \item \highcode{"jsonlite"} by Jeroen Ooms, Duncan Temple Lang, Jonathan Wallace 458 | \end{itemize} 459 | \end{block} 460 | 461 | All packages provide 2 main functions ---\highcode{toJSON()} and \highcode{fromJSON()}--- that allow conversion \textbf{to} and \textbf{from} data in JSON format, respectively. \\ 462 | \low{We'll focus on the functions from \code{"RJSONIO"}} 463 | 464 | \end{frame} 465 | 466 | %------------------------------------------------ 467 | 468 | \begin{frame}[fragile] 469 | \frametitle{R package RJSONIO} 470 | 471 | \begin{block}{R package \code{"RJSONIO"}} 472 | If you don't have \code{"RJSONIO"} you'll have to install it: 473 | <>= 474 | # install RJSONIO 475 | install.packages("RJSONIO", dependencies = TRUE) 476 | @ 477 | \end{block} 478 | 479 | \end{frame} 480 | 481 | %------------------------------------------------ 482 | 483 | \begin{frame}[fragile] 484 | \frametitle{R package RJSONIO} 485 | 486 | \begin{block}{Main functions} 487 | There are 2 primary functions in \code{"RJSONIO"} 488 | \begin{itemize} 489 | \item \highcode{toJSON()} converts an R object to a string in JSON 490 | \item \highcode{fromJSON()} converts JSON content to R objects 491 | \end{itemize} 492 | \end{block} 493 | 494 | \end{frame} 495 | 496 | %------------------------------------------------ 497 | 498 | \begin{frame}[fragile] 499 | \frametitle{\code{toJSON()}} 500 | 501 | \begin{block}{Function \code{toJSON()}} 502 | \begin{verbatim} 503 | toJSON(x, container = isContainer(x, asIs, .level), 504 | collapse = "\n", ...) 505 | \end{verbatim} 506 | 507 | \begin{itemize} 508 | \item \highcode{x} the R object to be converted to JSON format 509 | \item \highcode{container} whether to treat the object as a vector/container or a scalar 510 | \item \highcode{collapse} string used as separator when combining the individual lines of the generated JSON content 511 | \item \highcode{...} additional arguments controlling the JSON formatting 512 | \end{itemize} 513 | \end{block} 514 | 515 | \end{frame} 516 | 517 | %------------------------------------------------ 518 | 519 | \begin{frame}[fragile] 520 | \frametitle{\code{fromJSON()}} 521 | 522 | \begin{block}{Function \code{fromJSON()}} 523 | \begin{verbatim} 524 | fromJSON(content, handler = NULL, default.size = 100, 525 | depth = 150L, allowComments = TRUE, ...) 526 | \end{verbatim} 527 | 528 | \begin{itemize} 529 | \item \highcode{content} the JSON content: either a file name or a character string 530 | \item \highcode{handler} R object responsible for processing each individual token/element 531 | \item \highcode{deafult.size} size to use for arrays and objects in an effort to avoid reallocating each time we add a new element. 532 | \item \highcode{depth} maximum number of nested JSON levels 533 | \item \highcode{allowComments} whether to allow C-style comments within the JSON content 534 | \item \highcode{...} additional parameters 535 | \end{itemize} 536 | \end{block} 537 | 538 | \end{frame} 539 | 540 | %------------------------------------------------ 541 | 542 | \begin{frame}[fragile] 543 | \frametitle{Data Table Toy Example} 544 | 545 | \begin{center} 546 | \textcolor{turquoise}{Imagine we have some tabular data} 547 | \end{center} 548 | 549 | \begin{center} 550 | \begin{tabular}{l l l l l} 551 | \hline 552 | Name & Gender & Homeland & Born & Jedi \\ 553 | \hline 554 | Anakin & male & Tatooine & 41.9BBY & yes \\ 555 | Amidala & female & Naboo & 46BBY & no \\ 556 | Luke & male & Tatooine & 19BBY & yes \\ 557 | Leia & female & Alderaan & 19BBY & no \\ 558 | Obi-Wan & male & Stewjon & 57BBY & yes \\ 559 | Han & male & Corellia & 29BBY & no \\ 560 | Palpatine & male & Naboo & 82BBY & no \\ 561 | R2-D2 & unknown & Naboo & 33BBY & no \\ 562 | \hline 563 | \end{tabular} 564 | \end{center} 565 | 566 | \end{frame} 567 | 568 | %------------------------------------------------ 569 | 570 | \begin{frame}[fragile] 571 | \frametitle{R Data Frame} 572 | 573 | <>= 574 | # toy data 575 | sw_data = rbind( 576 | c("Anakin", "male", "Tatooine", "41.9BBY", "yes"), 577 | c("Amidala", "female", "Naboo", "46BBY", "no"), 578 | c("Luke", "male", "Tatooine", "19BBY", "yes"), 579 | c("Leia", "female", "Alderaan", "19BBY", "no"), 580 | c("Obi-Wan", "male", "Stewjon", "57BBY", "yes"), 581 | c("Han", "male", "Corellia", "29BBY", "no"), 582 | c("Palpatine", "male", "Naboo", "82BBY", "no"), 583 | c("R2-D2", "unknown", "Naboo", "33BBY", "no")) 584 | 585 | # convert to data.frame and add column names 586 | swdf = data.frame(sw_data) 587 | names(swdf) = c("Name", "Gender", "Homeworld", "Born", "Jedi") 588 | swdf 589 | @ 590 | 591 | \end{frame} 592 | 593 | %------------------------------------------------ 594 | 595 | \begin{frame}[fragile] 596 | \frametitle{From R to JSON} 597 | 598 | <>= 599 | # load RJSONIO 600 | library(RJSONIO) 601 | 602 | # convert R data.frame to JSON 603 | sw_json = toJSON(swdf) 604 | 605 | # what class? 606 | class(sw_json) 607 | 608 | # display JSON format 609 | cat(sw_json) 610 | @ 611 | 612 | \end{frame} 613 | 614 | %------------------------------------------------ 615 | 616 | \begin{frame}[fragile] 617 | \frametitle{From JSON to R} 618 | 619 | <>= 620 | # convert JSON string to R list 621 | sw_R = fromJSON(sw_json) 622 | 623 | # what class? 624 | class(sw_R) 625 | 626 | # display JSON format 627 | sw_R 628 | @ 629 | 630 | \end{frame} 631 | 632 | %------------------------------------------------ 633 | 634 | \begin{frame} 635 | \begin{center} 636 | \Huge{\textcolor{mandarina}{Reading JSON Data}} 637 | \end{center} 638 | \end{frame} 639 | 640 | %------------------------------------------------ 641 | 642 | \begin{frame} 643 | \frametitle{JSON Data from the Web} 644 | 645 | \begin{block}{How do we read JSON data from the Web?} 646 | We read JSON data in several ways. One way is to pass the url directly to \code{fromJSON()}. Another way is by passing \code{fromJSON()} the name of the file with the JSON content as a single string. 647 | \end{block} 648 | 649 | \end{frame} 650 | 651 | %------------------------------------------------ 652 | 653 | \begin{frame} 654 | \frametitle{File: miserables.js} 655 | 656 | We'll read the \textit{miserables} dataset from: \\ 657 | \url{http://mbostock.github.io/protovis/ex/miserables.js} 658 | 659 | \begin{center} 660 | \includegraphics[width=8cm]{images/miserables_js.png} 661 | \end{center} 662 | 663 | \end{frame} 664 | 665 | %------------------------------------------------ 666 | 667 | \begin{frame} 668 | \frametitle{Reading Issues} 669 | 670 | \begin{block}{Houston we have a problem ...} 671 | The data is in a file that contains several javascript comments and some other javascript notation. 672 | 673 | \bigskip 674 | Unfortunately, we cannot use any of the \code{fromJSON()} functions directly on this type of content. 675 | 676 | \bigskip 677 | Instead, we need to read the content as text, get rid of the comments, and change some characters before using \code{fromJSON()} 678 | \end{block} 679 | 680 | \end{frame} 681 | 682 | %------------------------------------------------ 683 | 684 | \begin{frame}[fragile] 685 | \frametitle{Reading \code{miserables.js}} 686 | 687 | <>= 688 | # load RJSONIO and jsonlite 689 | library(RJSONIO) 690 | library(jsonlite) 691 | 692 | # url with JSON content 693 | miser = "http://mbostock.github.io/protovis/ex/miserables.js" 694 | 695 | # import content as text (character vector) 696 | miserables = readLines(miser) 697 | 698 | # eliminate first 11 lines (containing comments) 699 | miserables = miserables[-c(1:11)] 700 | @ 701 | 702 | <>= 703 | library(RJSONIO) 704 | library(jsonlite) 705 | miser = "/Users/Gaston/Documents/Data_Technologies/data/miserables.txt" 706 | miserables = readLines(miser) 707 | miserables = miserables[-c(1:11)] 708 | @ 709 | 710 | Now check the first and the last lines: 711 | 712 | <>= 713 | # first line 714 | miserables[1] 715 | # last line 716 | miserables[length(miserables)] 717 | @ 718 | 719 | \end{frame} 720 | 721 | %------------------------------------------------ 722 | 723 | \begin{frame}[fragile] 724 | \frametitle{Preparing JSON content} 725 | 726 | We need to modify the first and last lines so they don't contain non-JSON javascript notation 727 | 728 | <>= 729 | # open curly bracket in first line 730 | miserables[1] = "{" 731 | 732 | # closing curly bracket in last line 733 | miserables[length(miserables)] = "}" 734 | @ 735 | 736 | Now we must concatenate all the content into a single string: 737 | 738 | <>= 739 | # JSON content in one single string 740 | miserables_str = paste(miserables, collapse = "") 741 | @ 742 | 743 | Once we have the JSON content in the proper shape, we can parse it with \highcode{fromJSON()}. 744 | 745 | \end{frame} 746 | 747 | %------------------------------------------------ 748 | 749 | \begin{frame}[fragile] 750 | \frametitle{Parsing JSON content} 751 | 752 | \highcode{fromJSON()} from package \code{"RJSONIO"}: 753 | 754 | \begin{columns}[t] 755 | \begin{column}{0.5\textwidth} 756 | <>= 757 | # fromJSON() in package RJSONIO 758 | mis1 = RJSONIO::fromJSON(miserables_str) 759 | 760 | # class 761 | class(mis1) 762 | # how many elements 763 | length(mis1) 764 | # names 765 | names(mis1) 766 | @ 767 | \end{column} 768 | 769 | \begin{column}{0.5\textwidth} 770 | <>= 771 | # class of each element 772 | lapply(mis1, class) 773 | # how many elements in each list component 774 | lapply(mis1, length) 775 | @ 776 | \end{column} 777 | \end{columns} 778 | 779 | \end{frame} 780 | 781 | %------------------------------------------------ 782 | 783 | \begin{frame}[fragile] 784 | \frametitle{Parsing JSON content} 785 | 786 | \begin{columns}[t] 787 | \begin{column}{0.5\textwidth} 788 | <>= 789 | # take a peek at nodes 790 | head(mis1[[1]], n = 3) 791 | @ 792 | \end{column} 793 | 794 | \begin{column}{0.5\textwidth} 795 | <>= 796 | # take a peek at links 797 | head(mis1[[2]], n = 3) 798 | @ 799 | \end{column} 800 | \end{columns} 801 | 802 | \end{frame} 803 | 804 | %------------------------------------------------ 805 | 806 | \begin{frame}[fragile] 807 | \frametitle{Parsing Differences} 808 | 809 | \begin{block}{\code{"RJSONIO"} -vs- \code{"jsonlite"}} 810 | The package \code{"jsonlite"} is a fork of \code{"RJSONIO"}. However, \code{"jsonlite"} implements a smarter mapping between JSON data and R classes. 811 | 812 | \bigskip 813 | From the previous example, we saw that \code{"jsonlite"} returns a list of data frames instead of the list of lists returned by \code{"RJSONIO"} 814 | \end{block} 815 | 816 | \end{frame} 817 | 818 | %------------------------------------------------ 819 | 820 | \end{document} -------------------------------------------------------------------------------- /05-json-data/05-json-data.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/05-json-data/05-json-data.pdf -------------------------------------------------------------------------------- /05-json-data/images/json_cover.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/05-json-data/images/json_cover.png -------------------------------------------------------------------------------- /05-json-data/images/miserables_js.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/05-json-data/images/miserables_js.png -------------------------------------------------------------------------------- /06-http-basics-rcurl/06-http-basics-rcurl.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/06-http-basics-rcurl.pdf -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/Rproject.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/Rproject.png -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/client_request_server_response.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/client_request_server_response.pdf -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/clients_servers.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/clients_servers.pdf -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/curl_request.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/curl_request.png -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/hazards_form.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/hazards_form.png -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/http_browser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/http_browser.png -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/http_cover.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/http_cover.png -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/http_request_response.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/http_request_response.pdf -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/rcurl_website.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/rcurl_website.png -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/web_request.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/web_request.pdf -------------------------------------------------------------------------------- /06-http-basics-rcurl/images/web_surfing.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/06-http-basics-rcurl/images/web_surfing.pdf -------------------------------------------------------------------------------- /07-web-forms/07-web-forms.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/07-web-forms.pdf -------------------------------------------------------------------------------- /07-web-forms/images/backpack_form.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/backpack_form.pdf -------------------------------------------------------------------------------- /07-web-forms/images/html_form_coffee.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/html_form_coffee.pdf -------------------------------------------------------------------------------- /07-web-forms/images/html_form_controls.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/html_form_controls.pdf -------------------------------------------------------------------------------- /07-web-forms/images/html_form_get_post.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/html_form_get_post.pdf -------------------------------------------------------------------------------- /07-web-forms/images/html_form_gmail.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/html_form_gmail.pdf -------------------------------------------------------------------------------- /07-web-forms/images/html_form_google.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/html_form_google.pdf -------------------------------------------------------------------------------- /07-web-forms/images/html_form_twitter_facebook.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/html_form_twitter_facebook.pdf -------------------------------------------------------------------------------- /07-web-forms/images/html_form_works.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/html_form_works.pdf -------------------------------------------------------------------------------- /07-web-forms/images/national_parks_site.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/national_parks_site.png -------------------------------------------------------------------------------- /07-web-forms/images/product_select.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/product_select.pdf -------------------------------------------------------------------------------- /07-web-forms/images/webforms_cover.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/07-web-forms/images/webforms_cover.jpg -------------------------------------------------------------------------------- /08-web-apis/08-web-apis.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/08-web-apis.pdf -------------------------------------------------------------------------------- /08-web-apis/images/bitly_api.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/bitly_api.png -------------------------------------------------------------------------------- /08-web-apis/images/eutilities_webpage.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/eutilities_webpage.png -------------------------------------------------------------------------------- /08-web-apis/images/google_apis.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/google_apis.png -------------------------------------------------------------------------------- /08-web-apis/images/ncbi_databases.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/ncbi_databases.png -------------------------------------------------------------------------------- /08-web-apis/images/ncbi_webpage.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/ncbi_webpage.png -------------------------------------------------------------------------------- /08-web-apis/images/pubmed_search.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/pubmed_search.png -------------------------------------------------------------------------------- /08-web-apis/images/pubmed_webpage.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/pubmed_webpage.png -------------------------------------------------------------------------------- /08-web-apis/images/redwood.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/redwood.jpg -------------------------------------------------------------------------------- /08-web-apis/images/us_census_api.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/08-web-apis/images/us_census_api.png -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- 1 | # Title: Makefile for tutorial-R-web-data 2 | # Author: Gaston Sanchez 3 | # 4 | # Note: 5 | # This makefile makes use of "Automatic-Variables" extensively. Specifically: 6 | # $(@D) the directory part of the file name of the target 7 | # $(Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. 27 | 28 | Author: [Gaston Sanchez](http://gastonsanchez.com) 29 | -------------------------------------------------------------------------------- /data/alpha.csv: -------------------------------------------------------------------------------- 1 | iden,beta1,gamma1,delta1,alfa1,altra1,estr1,beta2,gamma2,delta2,alfa2,edat,memb,estd,eciv,prof1,prof2,ingr 1,0,0,0,0,1,0,1,0,0,0,40,4,12,1,1,0,190 2,0,0,0,0,1,0,0,0,0,1,57,2,12,1,1,0,220 3,0,0,0,0,1,0,0,0,0,1,35,1,16,0,1,0,220 4,0,0,0,0,1,0,0,1,0,0,54,3,14,1,1,0,220 5,0,0,1,0,0,0,0,0,1,0,43,5,14,1,0,1,110 6,0,0,1,0,0,0,0,1,0,0,19,6,14,0,0,0,220 7,0,0,0,0,1,0,0,0,0,0,38,5,18,1,1,0,220 8,0,0,0,0,1,0,0,1,0,0,42,3,14,1,1,0,220 9,0,0,1,0,0,0,0,0,1,0,21,2,12,0,1,0,25 10,0,0,0,1,0,0,0,0,0,0,19,5,14,0,0,0,190 11,0,0,0,1,0,0,0,0,1,0,18,4,10,0,0,1,110 12,0,0,0,0,0,1,0,0,0,1,48,3,18,1,1,0,190 13,0,0,1,0,0,0,0,0,1,0,30,1,18,0,1,0,25 14,0,0,0,0,0,0,0,0,0,0,28,2,12,1,1,0,85 15,1,0,0,0,0,0,0,0,1,0,20,2,14,0,0,0,220 16,0,0,0,0,0,1,0,0,0,1,18,5,14,0,0,0,220 17,0,0,0,1,0,0,0,0,0,1,21,7,14,0,0,0,125 18,0,0,0,0,1,0,1,0,0,0,23,2,16,1,1,0,170 19,0,0,0,1,0,0,0,0,0,1,28,1,14,0,1,0,150 20,0,0,1,0,0,0,0,0,1,0,45,3,18,1,1,0,150 21,0,0,1,0,0,0,0,0,1,0,48,1,16,0,0,1,110 22,0,0,0,1,0,0,0,0,0,1,24,2,12,0,1,0,110 23,0,0,0,0,1,0,0,0,0,1,33,3,16,1,1,0,220 24,0,0,0,1,0,0,1,0,0,0,47,5,16,1,1,0,220 25,0,0,0,0,1,0,0,0,1,0,20,4,14,0,0,1,220 26,0,0,0,0,1,0,0,0,1,0,57,2,12,1,0,1,110 27,0,0,0,0,1,0,1,0,0,0,56,2,18,1,1,0,190 28,0,0,1,0,0,0,0,0,0,1,37,4,12,1,1,0,220 29,0,0,1,0,0,0,0,0,1,0,18,5,14,0,0,0,220 30,0,1,0,0,0,0,0,1,0,0,21,4,14,1,1,0,110 31,0,0,1,0,0,0,1,0,0,0,19,7,12,0,0,1,150 32,0,0,0,1,0,0,0,0,1,0,27,2,16,1,0,0,25 33,0,0,0,0,0,1,0,0,1,0,23,3,14,0,0,1,220 34,0,0,0,0,1,0,0,0,1,0,25,4,16,1,0,1,125 35,0,0,1,0,0,0,0,0,1,0,23,1,14,0,1,0,60 36,1,0,0,0,0,0,1,0,0,0,30,2,18,1,1,0,220 37,0,0,1,0,0,0,0,0,1,0,20,5,12,0,0,1,150 38,0,0,0,1,0,0,1,0,0,0,18,4,14,0,0,0,190 39,0,0,1,0,0,0,0,0,1,0,18,1,12,0,0,1,60 40,0,0,1,0,0,0,0,0,1,0,22,2,14,1,0,1,170 41,0,0,0,1,0,0,1,0,0,0,42,5,12,1,0,1,150 42,0,0,0,0,1,0,0,0,1,0,19,7,14,0,0,1,150 43,0,0,0,0,0,0,0,0,0,0,18,4,10,0,0,1,220 44,0,0,0,0,0,0,0,0,1,0,24,4,14,1,0,0,60 45,0,0,0,0,0,0,0,0,0,1,28,1,14,0,1,0,125 46,0,1,0,0,0,0,0,1,0,0,21,4,12,0,0,1,170 47,0,0,1,0,0,0,0,0,0,1,33,1,18,1,1,0,220 48,0,0,0,0,1,0,0,0,1,0,20,7,14,0,0,0,220 49,0,0,1,0,0,0,0,1,0,0,18,4,12,0,0,0,220 50,0,0,0,1,0,0,0,1,0,0,50,4,18,1,0,1,190 51,0,0,0,0,1,0,0,0,1,0,23,3,16,0,0,0,220 52,0,0,0,0,1,0,0,1,0,0,21,9,12,0,1,0,125 53,1,0,0,0,0,0,1,0,0,0,23,2,12,1,0,1,125 54,0,0,0,0,0,1,0,1,0,0,24,8,14,0,0,1,190 55,0,0,1,0,0,0,0,0,1,0,24,2,14,0,0,1,85 56,0,0,1,0,0,0,0,0,0,1,32,4,12,1,1,0,110 57,1,0,0,0,0,0,1,0,0,0,35,5,14,1,1,0,220 58,0,0,1,0,0,0,0,0,0,1,25,3,16,1,0,1,150 59,0,0,0,0,1,0,0,0,0,1,42,4,16,1,1,0,125 60,0,0,1,0,0,0,0,0,1,0,25,4,14,1,0,1,125 61,0,1,0,0,0,0,0,1,0,0,63,2,16,1,0,0,150 62,0,0,1,0,0,0,0,0,0,1,44,3,18,1,1,0,220 63,0,0,0,0,1,0,0,0,0,1,25,1,12,0,0,1,190 64,0,0,0,0,1,0,0,0,1,0,36,5,14,1,1,0,150 65,0,0,1,0,0,0,0,0,1,0,18,7,14,0,0,0,220 66,0,0,0,0,0,1,0,0,0,0,23,3,14,0,0,0,60 67,0,0,0,1,0,0,0,0,0,1,64,3,12,1,0,1,25 68,1,0,0,0,0,0,0,0,1,0,29,1,14,0,0,1,150 69,0,0,0,0,0,1,0,0,0,1,21,3,14,0,0,0,190 70,0,0,0,1,0,0,0,0,1,0,29,3,18,1,1,0,220 71,1,0,0,0,0,0,0,0,0,1,42,3,16,1,1,0,190 72,0,0,0,1,0,0,0,0,1,0,36,4,14,1,1,0,170 73,0,0,1,0,0,0,0,0,1,0,36,5,18,1,1,0,220 74,0,0,0,1,0,0,0,0,0,0,30,4,18,1,1,0,110 75,0,0,0,0,1,0,0,1,0,0,21,1,12,0,0,1,25 76,0,0,0,0,1,0,0,1,0,0,23,1,14,0,1,0,60 77,0,0,0,0,1,0,0,0,1,0,41,4,16,1,1,0,190 78,0,0,1,0,0,0,0,0,1,0,40,6,16,1,1,0,190 79,0,0,1,0,0,0,0,0,1,0,45,4,18,1,1,0,125 80,0,0,1,0,0,0,0,0,1,0,24,5,14,1,0,1,60 81,0,1,0,0,0,0,1,0,0,0,21,4,14,0,0,0,25 82,0,0,0,0,1,0,0,0,1,0,37,4,12,1,1,0,220 83,0,0,0,1,0,0,0,0,0,1,27,3,12,1,1,0,85 84,0,0,0,0,1,0,0,0,0,1,44,4,14,1,1,0,220 85,1,0,0,0,0,0,1,0,0,0,45,3,12,1,1,0,125 86,0,0,1,0,0,0,0,0,0,1,32,2,14,1,1,0,220 87,0,0,0,0,1,0,0,0,1,0,25,1,14,0,1,0,60 88,0,0,1,0,0,0,0,0,1,0,26,2,12,0,1,0,125 89,1,0,0,0,0,0,0,0,0,1,19,6,12,0,1,0,190 90,0,0,0,0,1,0,0,0,1,0,26,3,10,1,0,1,60 91,1,0,0,0,0,0,0,0,1,0,18,4,14,0,0,1,220 92,0,0,1,0,0,0,0,0,1,0,32,3,14,0,1,0,125 93,0,0,0,1,0,0,0,1,0,0,42,1,8,1,0,1,170 94,0,0,1,0,0,0,0,0,1,0,29,3,16,1,0,1,190 95,0,0,0,0,0,0,0,1,0,0,21,4,14,0,0,0,110 96,0,0,0,0,1,0,0,0,1,0,19,3,12,0,0,0,85 97,0,0,0,0,1,0,1,0,0,0,21,3,14,0,0,0,125 98,0,0,1,0,0,0,0,0,1,0,33,4,12,1,0,1,150 99,0,0,0,0,1,0,0,0,0,1,51,4,18,1,1,0,150 100,0,0,0,0,0,0,0,1,0,0,25,3,16,0,1,0,220 101,0,0,0,0,1,0,0,0,1,0,20,3,14,0,1,0,85 102,0,0,0,0,1,0,0,0,1,0,40,9,18,1,1,0,220 103,0,0,1,0,0,0,0,0,1,0,18,4,10,0,0,0,220 104,0,0,0,1,0,0,0,0,1,0,28,7,12,1,0,1,110 105,0,0,0,0,0,0,0,0,1,0,49,3,12,1,0,1,220 106,0,0,0,0,1,0,0,1,0,0,46,4,8,1,0,1,110 107,0,0,1,0,0,0,0,0,1,0,27,4,16,1,0,1,60 108,0,0,0,0,0,0,0,0,0,1,34,4,18,1,1,0,220 109,0,0,1,0,0,0,0,0,1,0,26,2,14,1,0,1,150 110,0,0,1,0,0,0,0,0,1,0,19,3,14,0,0,0,220 111,0,0,0,1,0,0,0,0,0,1,41,5,16,1,1,0,190 112,1,0,0,0,0,0,1,0,0,0,53,2,16,1,1,0,220 113,0,0,0,1,0,0,0,0,0,1,39,3,18,1,1,0,220 114,0,0,0,0,1,0,0,0,1,0,19,6,14,0,0,1,220 115,0,0,1,0,0,0,0,0,1,0,18,1,12,0,0,1,25 116,0,0,0,0,0,0,0,0,1,0,45,3,16,0,1,0,170 117,0,0,0,0,1,0,0,0,1,0,19,6,14,0,1,0,220 118,1,0,0,0,0,0,0,0,0,1,25,3,12,0,0,1,85 119,0,0,0,0,1,0,0,0,0,1,56,4,16,1,1,0,190 120,0,0,0,1,0,0,1,0,0,0,37,4,14,1,1,0,220 121,0,0,0,0,1,0,0,0,1,0,19,5,10,0,1,0,220 122,0,0,1,0,0,0,0,0,1,0,61,1,18,0,1,0,85 123,0,0,1,0,0,0,0,0,1,0,18,5,10,0,0,0,170 124,0,0,0,0,0,1,0,0,1,0,32,4,16,1,1,0,220 125,0,0,0,0,1,0,0,0,0,1,42,4,16,1,1,0,220 126,0,0,0,1,0,0,0,0,0,1,38,3,16,0,1,0,125 127,0,0,1,0,0,0,0,0,1,0,58,4,14,1,1,0,220 128,0,0,0,0,1,0,0,1,0,0,28,3,14,1,0,1,125 129,0,0,0,0,1,0,0,0,0,1,34,1,14,0,0,1,150 130,0,0,1,0,0,0,0,0,0,1,20,3,12,1,0,1,25 131,0,0,0,1,0,0,0,1,0,0,37,6,12,1,0,1,125 132,1,0,0,0,0,0,0,0,0,1,21,4,12,0,0,1,150 133,0,0,0,0,1,0,1,0,0,0,55,3,16,1,0,1,170 134,1,0,0,0,0,0,1,0,0,0,57,2,12,1,0,0,170 135,0,0,0,0,1,0,0,0,0,1,24,2,18,1,1,0,85 136,0,0,0,0,1,0,0,1,0,0,30,4,16,1,1,0,220 137,0,0,0,1,0,0,0,0,0,1,40,5,18,1,1,0,170 138,0,0,0,0,1,0,0,0,0,1,27,2,16,1,1,0,220 139,0,0,0,0,1,0,0,0,0,1,29,1,18,0,1,0,60 140,1,0,0,0,0,0,0,0,0,1,30,4,14,1,0,1,110 141,0,0,1,0,0,0,0,0,1,0,26,2,18,1,1,0,190 142,0,0,0,0,0,0,0,0,1,0,21,7,14,0,0,1,220 143,0,0,0,0,1,0,1,0,0,0,19,1,10,0,0,1,25 144,0,0,0,0,0,0,0,0,0,1,26,4,14,0,0,0,25 145,0,0,1,0,0,0,0,0,1,0,24,2,18,1,1,0,220 146,1,0,0,0,0,0,0,0,1,0,40,9,16,1,1,0,125 147,0,0,1,0,0,0,0,0,1,0,18,3,12,0,0,1,190 148,0,0,0,0,1,0,0,0,1,0,52,2,12,1,1,0,110 149,0,0,1,0,0,0,0,0,1,0,18,5,14,0,0,0,85 150,1,0,0,0,0,0,1,0,0,0,30,2,14,0,1,0,85 151,0,0,1,0,0,0,0,0,1,0,18,4,12,0,0,1,170 152,0,0,0,0,1,0,0,0,0,1,21,4,14,0,0,0,110 153,0,0,0,0,0,1,0,0,0,1,30,5,14,0,0,1,125 154,0,0,0,0,1,0,0,0,1,0,22,5,18,0,1,0,125 155,0,0,1,0,0,0,1,0,0,0,22,1,14,0,0,1,85 156,0,0,0,0,1,0,0,0,0,1,27,2,16,1,1,0,220 157,0,0,0,0,1,0,0,0,0,0,35,5,14,1,1,0,220 158,1,0,0,0,0,0,0,0,1,0,28,4,18,0,0,0,85 159,0,0,0,0,1,0,0,0,1,0,54,3,12,1,1,0,220 160,0,1,0,0,0,0,1,0,0,0,20,1,14,0,0,1,60 161,0,0,1,0,0,0,0,0,1,0,20,1,12,0,0,1,60 162,0,0,0,1,0,0,0,0,0,1,26,1,14,0,1,0,220 163,0,0,0,0,1,0,1,0,0,0,40,7,12,1,0,1,150 164,0,0,0,1,0,0,1,0,0,0,26,3,12,1,0,1,85 165,0,0,0,1,0,0,0,0,0,1,18,4,10,0,0,0,25 166,0,0,0,0,0,0,0,0,1,0,25,1,12,0,1,0,85 167,0,0,1,0,0,0,1,0,0,0,54,5,18,1,1,0,220 168,0,0,0,1,0,0,0,0,0,1,20,1,14,0,0,0,220 169,0,0,0,1,0,0,0,0,0,1,19,4,14,0,0,0,110 170,0,0,1,0,0,0,0,0,1,0,60,2,14,1,0,0,220 171,0,0,0,0,1,0,0,0,0,0,45,6,18,1,1,0,125 172,0,0,0,0,1,0,0,0,0,0,63,2,16,1,1,0,220 173,0,0,0,0,0,1,0,0,1,0,20,6,16,0,0,0,220 174,1,0,0,0,0,0,0,0,1,0,63,1,18,0,1,0,150 175,0,0,0,1,0,0,0,0,0,1,64,2,16,1,0,0,110 176,0,0,0,1,0,0,0,0,1,0,20,6,14,0,0,0,220 177,0,0,0,1,0,0,0,0,0,1,18,2,10,0,0,1,60 178,0,0,0,0,0,0,0,1,0,0,58,2,10,1,0,0,110 179,0,0,0,0,1,0,0,0,0,1,18,4,10,0,0,0,125 180,0,0,1,0,0,0,0,0,1,0,22,9,14,0,0,0,150 181,0,0,0,0,0,0,0,0,0,0,24,2,14,0,0,1,85 182,0,0,0,0,1,0,0,0,1,0,38,1,12,0,0,1,125 183,0,1,0,0,0,0,0,0,1,0,21,2,14,1,1,0,170 184,1,0,0,0,0,0,0,0,1,0,24,1,12,0,0,1,110 185,0,0,0,0,1,0,0,0,0,1,52,2,16,1,1,0,220 186,0,0,0,0,1,0,0,0,1,0,20,6,12,0,0,1,220 187,0,0,0,1,0,0,0,0,0,1,50,3,10,1,0,1,110 188,0,0,0,1,0,0,0,0,0,1,21,5,12,0,0,1,220 189,0,0,0,0,1,0,0,0,1,0,19,3,10,0,0,1,110 190,0,0,0,0,0,0,0,0,0,1,19,3,10,0,0,1,170 191,0,0,1,0,0,0,0,0,1,0,21,4,12,1,0,1,170 192,0,0,0,0,0,0,1,0,0,0,20,4,14,0,1,0,25 193,0,0,0,0,0,0,0,0,0,1,20,1,14,0,1,0,60 194,1,0,0,0,0,0,0,0,1,0,29,3,14,1,0,1,125 195,0,0,1,0,0,0,0,0,1,0,23,2,14,1,0,1,85 196,0,0,0,0,1,0,1,0,0,0,20,5,12,0,1,0,220 197,0,0,0,0,1,0,0,0,1,0,24,1,14,0,0,1,25 198,0,0,0,0,0,1,0,0,1,0,23,6,14,0,0,1,170 199,0,0,1,0,0,0,0,0,0,1,25,2,14,1,0,0,110 200,0,0,0,0,1,0,0,0,0,1,21,1,14,0,0,1,85 201,0,0,1,0,0,0,0,0,1,0,20,8,14,0,0,1,220 202,0,0,0,1,0,0,0,0,0,1,27,4,18,0,1,0,220 203,0,0,1,0,0,0,1,0,0,0,21,6,10,0,0,1,85 204,1,0,0,0,0,0,1,0,0,0,19,6,10,0,0,1,220 205,1,0,0,0,0,0,1,0,0,0,31,3,14,1,1,0,220 206,0,0,0,0,1,0,0,0,0,1,46,4,12,1,0,1,125 207,0,0,0,0,1,0,1,0,0,0,39,9,12,1,0,1,125 208,0,0,0,1,0,0,0,0,0,1,40,6,10,1,0,1,85 209,0,0,0,0,1,0,0,0,0,1,63,4,18,1,1,0,220 210,0,0,0,0,1,0,0,0,0,1,58,2,16,1,1,0,220 211,0,0,0,0,1,0,0,0,1,0,49,4,14,1,1,0,220 212,0,0,0,0,0,0,0,0,1,0,36,4,14,1,0,1,170 213,1,0,0,0,0,0,1,0,0,0,31,3,14,1,0,1,190 214,1,0,0,0,0,0,1,0,0,0,52,6,14,1,0,1,110 215,0,0,1,0,0,0,0,0,1,0,58,1,6,0,0,1,110 216,0,0,0,1,0,0,0,0,0,1,48,3,16,1,0,1,190 217,0,1,0,0,0,0,0,1,0,0,33,4,12,1,0,1,220 218,0,0,0,0,1,0,0,0,0,1,30,3,10,1,0,1,125 219,0,0,0,1,0,0,0,0,0,0,30,2,18,1,0,0,25 220,0,0,1,0,0,0,0,0,1,0,34,1,14,0,1,0,110 221,0,0,0,1,0,0,0,0,0,1,41,4,16,1,1,0,110 222,0,0,0,0,1,0,0,0,0,1,38,4,16,1,1,0,110 223,0,0,0,1,0,0,0,0,0,1,30,1,16,0,1,0,85 224,0,0,1,0,0,0,0,0,1,0,31,4,14,1,1,0,220 225,1,0,0,0,0,0,1,0,0,0,64,2,14,1,0,0,110 226,0,1,0,0,0,0,1,0,0,0,56,2,8,1,0,0,150 227,0,0,0,1,0,0,0,0,1,0,33,1,12,0,1,0,85 228,0,0,0,0,1,0,0,0,1,0,60,2,14,1,1,0,60 229,0,0,0,0,1,0,0,0,1,0,64,2,14,1,1,0,25 230,0,0,0,0,1,0,0,0,0,1,39,4,10,1,0,1,220 231,0,0,0,1,0,0,0,0,0,1,31,4,12,1,0,1,110 232,0,0,0,0,1,0,0,0,0,1,34,4,12,1,1,0,85 233,0,0,0,1,0,0,0,0,0,1,53,2,14,1,1,0,220 234,0,0,1,0,0,0,0,0,1,0,30,3,14,1,0,1,125 235,0,0,0,0,0,0,0,0,0,1,44,2,10,1,0,1,110 236,0,0,0,1,0,0,0,0,0,1,44,3,12,1,0,1,170 237,0,0,0,0,1,0,0,0,0,0,54,2,12,1,1,0,85 238,0,0,0,0,1,0,0,0,0,1,35,3,6,1,0,1,85 239,0,0,0,1,0,0,0,0,0,1,54,2,10,1,0,1,110 240,1,0,0,0,0,0,1,0,0,0,44,2,16,1,1,0,150 241,0,0,0,1,0,0,0,0,1,0,34,3,18,1,1,0,220 242,0,0,1,0,0,0,0,0,1,0,45,3,14,1,0,1,125 243,0,0,0,1,0,0,0,0,0,1,35,4,12,1,0,1,85 244,0,0,0,0,1,0,0,1,0,0,46,5,16,1,1,0,150 245,0,0,0,0,1,0,0,0,0,1,41,6,6,1,0,1,150 246,0,0,0,1,0,0,1,0,0,0,32,3,12,0,0,1,150 247,0,0,1,0,0,0,0,0,1,0,53,7,12,1,0,1,220 248,0,0,1,0,0,0,0,0,1,0,54,4,10,1,0,1,220 249,0,0,0,1,0,0,0,0,0,1,48,5,14,1,1,0,220 250,0,0,0,0,1,0,0,0,1,0,62,2,16,1,1,0,150 251,0,0,0,0,1,0,0,1,0,0,47,5,12,1,1,0,170 252,0,0,0,0,1,0,0,1,0,0,30,3,12,1,0,1,190 -------------------------------------------------------------------------------- /data/alpha.xls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/data/alpha.xls -------------------------------------------------------------------------------- /data/cars2004.csv: -------------------------------------------------------------------------------- 1 | Model,Cylinders,Horsepower,Speed,Weight,Width,Length 2 | Citroen C2 1.1 Base,1124,61,158,932,1659,3666 3 | Smart Fortwo Coupe,698,52,135,730,1515,2500 4 | Mini 1.6 170,1598,170,218,1215,1690,3625 5 | Nissan Micra 1.2 65,1240,65,154,965,1660,3715 6 | Renault Clio 3.0 V6,2946,255,245,1400,1810,3812 7 | Audi A3 1.9 TDI,1896,105,187,1295,1765,4203 8 | Peugeot 307 1.4 HDI 70,1398,70,160,1179,1746,4202 9 | Peugeot 407 3.0 V6 BVA,2946,211,229,1640,1811,4676 10 | Mercedes Classe C 270 CDI,2685,170,230,1600,1728,4528 11 | BMW 530d,2993,218,245,1595,1846,4841 12 | Jaguar S-Type 2.7 V6 Bi-Turbo,2720,207,230,1722,1818,4905 13 | BMW 745i,4398,333,250,1870,1902,5029 14 | Mercedes Classe S 400 CDI,3966,260,250,1915,2092,5038 15 | Citroen C3 Pluriel 1.6i,1587,110,185,1177,1700,3934 16 | BMW Z4 2.5i,2494,192,235,1260,1781,4091 17 | Audi TT 1.8T 180,1781,180,228,1280,1764,4041 18 | Aston Martin Vanquish,5935,460,306,1835,1923,4665 19 | Bentley Continental GT,5998,560,318,2385,1918,4804 20 | Ferrari Enzo,5998,660,350,1365,2650,4700 21 | Renault Scenic 1.9 dCi 120,1870,120,188,1430,1805,4259 22 | Volkswagen Touran 1.9 TDI 105,1896,105,180,1498,1794,4391 23 | Land Rover Defender Td5,2495,122,135,1695,1790,3883 24 | Land Rover Discovery Td5,2495,138,157,2175,2190,4705 25 | Nissan X-Trail 2.2 dCi,2184,136,180,1520,1765,4455 -------------------------------------------------------------------------------- /data/esearch_retmax103.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 10310301NCID_1_347770334_130.14.22.215_9001_1399490825_59805424 4 | 23959643 5 | 23730202 6 | 23520917 7 | 23281708 8 | 23281599 9 | 23266811 10 | 23261826 11 | 23260131 12 | 23251346 13 | 23235118 14 | 23230266 15 | 23166509 16 | 23153121 17 | 23151206 18 | 23148531 19 | 23141859 20 | 23115822 21 | 23112225 22 | 23102215 23 | 23086744 24 | 23066043 25 | 23065348 26 | 23064634 27 | 23056365 28 | 23049969 29 | 22983818 30 | 22965039 31 | 22955987 32 | 22955986 33 | 22955982 34 | 22955974 35 | 22955971 36 | 22955793 37 | 22955617 38 | 22955616 39 | 22952639 40 | 22926102 41 | 22908741 42 | 22906809 43 | 22850674 44 | 22849370 45 | 22829947 46 | 22808122 47 | 22792041 48 | 22779033 49 | 22736453 50 | 22734843 51 | 22714408 52 | 22701604 53 | 22700182 54 | 22683623 55 | 22665225 56 | 22648820 57 | 22642107 58 | 22624854 59 | 22615578 60 | 22608825 61 | 22606341 62 | 22593554 63 | 22586432 64 | 22567964 65 | 22550155 66 | 22548216 67 | 22539467 68 | 22523069 69 | 22495928 70 | 22495107 71 | 22492999 72 | 22465810 73 | 22456607 74 | 22451669 75 | 22445588 76 | 22434427 77 | 22383546 78 | 22372745 79 | 22365773 80 | 22364178 81 | 22344433 82 | 22326088 83 | 22313678 84 | 22309575 85 | 24511453 86 | 22300442 87 | 24478921 88 | 22253817 89 | 22248320 90 | 22231539 91 | 22228013 92 | 22213110 93 | 24705081 94 | 22183967 95 | 22175250 96 | 22170741 97 | 22138481 98 | 22102592 99 | 22093876 100 | 22075116 101 | 22057813 102 | 22057783 103 | 22050290 104 | 22031941 105 | 21945885 106 | 21559844 107 | human genome[title] title 2906 N 2012[pdat] pdat 1067564 N AND human genome[title] AND 2012[pdat] 108 | -------------------------------------------------------------------------------- /data/esearch_retmax20.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 1032001NCID_1_282865897_130.14.18.34_9001_1399488846_694838780 4 | 23959643 5 | 23730202 6 | 23520917 7 | 23281708 8 | 23281599 9 | 23266811 10 | 23261826 11 | 23260131 12 | 23251346 13 | 23235118 14 | 23230266 15 | 23166509 16 | 23153121 17 | 23151206 18 | 23148531 19 | 23141859 20 | 23115822 21 | 23112225 22 | 23102215 23 | 23086744 24 | human genome[title] title 2906 N 2012[pdat] pdat 1067564 N AND human genome[title] AND 2012[pdat] 25 | -------------------------------------------------------------------------------- /data/harry_potter.txt: -------------------------------------------------------------------------------- 1 | Harry Potter and the Sorcerer's Stone 2 | 3 | CHAPTER ONE 4 | 5 | THE BOY WHO LIVED 6 | 7 | Mr. and Mrs. Dursley, of number four, Privet Drive, were proud to say 8 | that they were perfectly normal, thank you very much. They were the last 9 | people you'd expect to be involved in anything strange or mysterious, 10 | because they just didn't hold with such nonsense. 11 | 12 | Mr. Dursley was the director of a firm called Grunnings, which made 13 | drills. He was a big, beefy man with hardly any neck, although he did 14 | have a very large mustache. Mrs. Dursley was thin and blonde and had 15 | nearly twice the usual amount of neck, which came in very useful as she 16 | spent so much of her time craning over garden fences, spying on the 17 | neighbors. The Dursley s had a small son called Dudley and in their 18 | opinion there was no finer boy anywhere. 19 | 20 | The Dursleys had everything they wanted, but they also had a secret, and 21 | their greatest fear was that somebody would discover it. They didn't 22 | think they could bear it if anyone found out about the Potters. Mrs. 23 | Potter was Mrs. Dursley's sister, but they hadn't met for several years; 24 | in fact, Mrs. Dursley pretended she didn't have a sister, because her 25 | sister and her good-for-nothing husband were as unDursleyish as it was 26 | possible to be. The Dursleys shuddered to think what the neighbors would 27 | say if the Potters arrived in the street. The Dursleys knew that the 28 | Potters had a small son, too, but they had never even seen him. This boy 29 | was another good reason for keeping the Potters away; they didn't want 30 | Dudley mixing with a child like that. 31 | -------------------------------------------------------------------------------- /data/iris_data.txt: -------------------------------------------------------------------------------- 1 | 5.1,3.5,1.4,0.2,Iris-setosa 2 | 4.9,3.0,1.4,0.2,Iris-setosa 3 | 4.7,3.2,1.3,0.2,Iris-setosa 4 | 4.6,3.1,1.5,0.2,Iris-setosa 5 | 5.0,3.6,1.4,0.2,Iris-setosa 6 | 5.4,3.9,1.7,0.4,Iris-setosa 7 | 4.6,3.4,1.4,0.3,Iris-setosa 8 | 5.0,3.4,1.5,0.2,Iris-setosa 9 | 4.4,2.9,1.4,0.2,Iris-setosa 10 | 4.9,3.1,1.5,0.1,Iris-setosa 11 | 5.4,3.7,1.5,0.2,Iris-setosa 12 | 4.8,3.4,1.6,0.2,Iris-setosa 13 | 4.8,3.0,1.4,0.1,Iris-setosa 14 | 4.3,3.0,1.1,0.1,Iris-setosa 15 | 5.8,4.0,1.2,0.2,Iris-setosa 16 | 5.7,4.4,1.5,0.4,Iris-setosa 17 | 5.4,3.9,1.3,0.4,Iris-setosa 18 | 5.1,3.5,1.4,0.3,Iris-setosa 19 | 5.7,3.8,1.7,0.3,Iris-setosa 20 | 5.1,3.8,1.5,0.3,Iris-setosa 21 | 5.4,3.4,1.7,0.2,Iris-setosa 22 | 5.1,3.7,1.5,0.4,Iris-setosa 23 | 4.6,3.6,1.0,0.2,Iris-setosa 24 | 5.1,3.3,1.7,0.5,Iris-setosa 25 | 4.8,3.4,1.9,0.2,Iris-setosa 26 | 5.0,3.0,1.6,0.2,Iris-setosa 27 | 5.0,3.4,1.6,0.4,Iris-setosa 28 | 5.2,3.5,1.5,0.2,Iris-setosa 29 | 5.2,3.4,1.4,0.2,Iris-setosa 30 | 4.7,3.2,1.6,0.2,Iris-setosa 31 | 4.8,3.1,1.6,0.2,Iris-setosa 32 | 5.4,3.4,1.5,0.4,Iris-setosa 33 | 5.2,4.1,1.5,0.1,Iris-setosa 34 | 5.5,4.2,1.4,0.2,Iris-setosa 35 | 4.9,3.1,1.5,0.1,Iris-setosa 36 | 5.0,3.2,1.2,0.2,Iris-setosa 37 | 5.5,3.5,1.3,0.2,Iris-setosa 38 | 4.9,3.1,1.5,0.1,Iris-setosa 39 | 4.4,3.0,1.3,0.2,Iris-setosa 40 | 5.1,3.4,1.5,0.2,Iris-setosa 41 | 5.0,3.5,1.3,0.3,Iris-setosa 42 | 4.5,2.3,1.3,0.3,Iris-setosa 43 | 4.4,3.2,1.3,0.2,Iris-setosa 44 | 5.0,3.5,1.6,0.6,Iris-setosa 45 | 5.1,3.8,1.9,0.4,Iris-setosa 46 | 4.8,3.0,1.4,0.3,Iris-setosa 47 | 5.1,3.8,1.6,0.2,Iris-setosa 48 | 4.6,3.2,1.4,0.2,Iris-setosa 49 | 5.3,3.7,1.5,0.2,Iris-setosa 50 | 5.0,3.3,1.4,0.2,Iris-setosa 51 | 7.0,3.2,4.7,1.4,Iris-versicolor 52 | 6.4,3.2,4.5,1.5,Iris-versicolor 53 | 6.9,3.1,4.9,1.5,Iris-versicolor 54 | 5.5,2.3,4.0,1.3,Iris-versicolor 55 | 6.5,2.8,4.6,1.5,Iris-versicolor 56 | 5.7,2.8,4.5,1.3,Iris-versicolor 57 | 6.3,3.3,4.7,1.6,Iris-versicolor 58 | 4.9,2.4,3.3,1.0,Iris-versicolor 59 | 6.6,2.9,4.6,1.3,Iris-versicolor 60 | 5.2,2.7,3.9,1.4,Iris-versicolor 61 | 5.0,2.0,3.5,1.0,Iris-versicolor 62 | 5.9,3.0,4.2,1.5,Iris-versicolor 63 | 6.0,2.2,4.0,1.0,Iris-versicolor 64 | 6.1,2.9,4.7,1.4,Iris-versicolor 65 | 5.6,2.9,3.6,1.3,Iris-versicolor 66 | 6.7,3.1,4.4,1.4,Iris-versicolor 67 | 5.6,3.0,4.5,1.5,Iris-versicolor 68 | 5.8,2.7,4.1,1.0,Iris-versicolor 69 | 6.2,2.2,4.5,1.5,Iris-versicolor 70 | 5.6,2.5,3.9,1.1,Iris-versicolor 71 | 5.9,3.2,4.8,1.8,Iris-versicolor 72 | 6.1,2.8,4.0,1.3,Iris-versicolor 73 | 6.3,2.5,4.9,1.5,Iris-versicolor 74 | 6.1,2.8,4.7,1.2,Iris-versicolor 75 | 6.4,2.9,4.3,1.3,Iris-versicolor 76 | 6.6,3.0,4.4,1.4,Iris-versicolor 77 | 6.8,2.8,4.8,1.4,Iris-versicolor 78 | 6.7,3.0,5.0,1.7,Iris-versicolor 79 | 6.0,2.9,4.5,1.5,Iris-versicolor 80 | 5.7,2.6,3.5,1.0,Iris-versicolor 81 | 5.5,2.4,3.8,1.1,Iris-versicolor 82 | 5.5,2.4,3.7,1.0,Iris-versicolor 83 | 5.8,2.7,3.9,1.2,Iris-versicolor 84 | 6.0,2.7,5.1,1.6,Iris-versicolor 85 | 5.4,3.0,4.5,1.5,Iris-versicolor 86 | 6.0,3.4,4.5,1.6,Iris-versicolor 87 | 6.7,3.1,4.7,1.5,Iris-versicolor 88 | 6.3,2.3,4.4,1.3,Iris-versicolor 89 | 5.6,3.0,4.1,1.3,Iris-versicolor 90 | 5.5,2.5,4.0,1.3,Iris-versicolor 91 | 5.5,2.6,4.4,1.2,Iris-versicolor 92 | 6.1,3.0,4.6,1.4,Iris-versicolor 93 | 5.8,2.6,4.0,1.2,Iris-versicolor 94 | 5.0,2.3,3.3,1.0,Iris-versicolor 95 | 5.6,2.7,4.2,1.3,Iris-versicolor 96 | 5.7,3.0,4.2,1.2,Iris-versicolor 97 | 5.7,2.9,4.2,1.3,Iris-versicolor 98 | 6.2,2.9,4.3,1.3,Iris-versicolor 99 | 5.1,2.5,3.0,1.1,Iris-versicolor 100 | 5.7,2.8,4.1,1.3,Iris-versicolor 101 | 6.3,3.3,6.0,2.5,Iris-virginica 102 | 5.8,2.7,5.1,1.9,Iris-virginica 103 | 7.1,3.0,5.9,2.1,Iris-virginica 104 | 6.3,2.9,5.6,1.8,Iris-virginica 105 | 6.5,3.0,5.8,2.2,Iris-virginica 106 | 7.6,3.0,6.6,2.1,Iris-virginica 107 | 4.9,2.5,4.5,1.7,Iris-virginica 108 | 7.3,2.9,6.3,1.8,Iris-virginica 109 | 6.7,2.5,5.8,1.8,Iris-virginica 110 | 7.2,3.6,6.1,2.5,Iris-virginica 111 | 6.5,3.2,5.1,2.0,Iris-virginica 112 | 6.4,2.7,5.3,1.9,Iris-virginica 113 | 6.8,3.0,5.5,2.1,Iris-virginica 114 | 5.7,2.5,5.0,2.0,Iris-virginica 115 | 5.8,2.8,5.1,2.4,Iris-virginica 116 | 6.4,3.2,5.3,2.3,Iris-virginica 117 | 6.5,3.0,5.5,1.8,Iris-virginica 118 | 7.7,3.8,6.7,2.2,Iris-virginica 119 | 7.7,2.6,6.9,2.3,Iris-virginica 120 | 6.0,2.2,5.0,1.5,Iris-virginica 121 | 6.9,3.2,5.7,2.3,Iris-virginica 122 | 5.6,2.8,4.9,2.0,Iris-virginica 123 | 7.7,2.8,6.7,2.0,Iris-virginica 124 | 6.3,2.7,4.9,1.8,Iris-virginica 125 | 6.7,3.3,5.7,2.1,Iris-virginica 126 | 7.2,3.2,6.0,1.8,Iris-virginica 127 | 6.2,2.8,4.8,1.8,Iris-virginica 128 | 6.1,3.0,4.9,1.8,Iris-virginica 129 | 6.4,2.8,5.6,2.1,Iris-virginica 130 | 7.2,3.0,5.8,1.6,Iris-virginica 131 | 7.4,2.8,6.1,1.9,Iris-virginica 132 | 7.9,3.8,6.4,2.0,Iris-virginica 133 | 6.4,2.8,5.6,2.2,Iris-virginica 134 | 6.3,2.8,5.1,1.5,Iris-virginica 135 | 6.1,2.6,5.6,1.4,Iris-virginica 136 | 7.7,3.0,6.1,2.3,Iris-virginica 137 | 6.3,3.4,5.6,2.4,Iris-virginica 138 | 6.4,3.1,5.5,1.8,Iris-virginica 139 | 6.0,3.0,4.8,1.8,Iris-virginica 140 | 6.9,3.1,5.4,2.1,Iris-virginica 141 | 6.7,3.1,5.6,2.4,Iris-virginica 142 | 6.9,3.1,5.1,2.3,Iris-virginica 143 | 5.8,2.7,5.1,1.9,Iris-virginica 144 | 6.8,3.2,5.9,2.3,Iris-virginica 145 | 6.7,3.3,5.7,2.5,Iris-virginica 146 | 6.7,3.0,5.2,2.3,Iris-virginica 147 | 6.3,2.5,5.0,1.9,Iris-virginica 148 | 6.5,3.0,5.2,2.0,Iris-virginica 149 | 6.2,3.4,5.4,2.3,Iris-virginica 150 | 5.9,3.0,5.1,1.8,Iris-virginica 151 | -------------------------------------------------------------------------------- /data/mailing_lists.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | R: Mailing Lists 6 | 7 | 8 | 9 | 10 |

Mailing Lists

11 | 12 |

Please read the instructions 13 | below and the posting guide 14 | before sending anything to any mailing list! 15 |

16 | 17 |

Thanks to Martin Maechler (and ETH Zurich), 18 | there are four general mailing lists devoted to R:

19 | 20 |
21 |
R-announce
22 |

This list is for major announcements about the 23 | development of R and the availability of new code.
24 | It has a low volume (typically only a few messages a 25 | month) and everyone mildly interested should consider subscribing, 26 | but note that R-help gets everything from R-announce as well, so 27 | you don't need to subscribe to both of them.

28 | 29 |

30 | Note that the list is moderated to be used for 31 | announcements mainly by the R Core Development Team. 32 |
33 | Use the 35 | web interface for information, subscription, archives, etc. 36 |

37 |
38 | 39 |
R-packages
40 |

41 | This list is for announcements as well, usually on 42 | the availability of new or enhanced contributed packages (on CRAN, typically). 44 |

45 | 46 |

47 | Note that the list is moderated. However, CRAN package 48 | authors (and others, similarly qualified) can freely post. 49 |
50 | As with R-announce, all messages to R-packages are 51 | automatically forwarded to the main R-help mailing list; 52 | we still recommend to subscribe to R-packages if you read R-help 53 | only in digest form. 54 |
55 | Use the 57 | web interface for information, subscription, archives, etc. 58 |

59 |
60 | 61 |
 
62 |
R-help
63 |

64 | The ‘main’ R mailing list, for discussion 65 | about problems and solutions using R, announcements (not 66 | covered by ‘R-announce’ or ‘R-packages’, 67 | see above), about the availability of new functionality for 68 | R and documentation of R, comparison and 69 | compatibility with S-plus, and for the posting of nice 70 | examples and benchmarks. 71 | Do read the posting guide 72 | before sending anything! 73 |

74 |

75 | This has become quite an active list with dozens of 76 | messages per day. An alternative is to subscribe and choose daily 77 | digests (in plain or MIME format). 78 |
79 | Use the 80 | web interface for information, subscription, archives, etc. 81 |

82 |
83 | 84 |
 
85 |
R-devel
86 |
This list is intended for questions and discussion about code 87 | development in R. Questions likely to prompt discussion 88 | unintelligible to non-programmers or topics that are too technical 89 | for R-help's audience should go to R-devel, see the posting guide section. 91 | The list is also for proposals of new functionality for R, 92 | and pre-testing of new versions. It is meant particularly for 93 | those who maintain an active position in the development of 94 | R. Therefore, it also receives all (filtered, 95 | i.e. non-spam!) bug reports from R-bugs. 97 |

98 | If you don't want to receive more than a daily message, you 99 | can subscribe and choose digests (in plain or MIME format). 100 |
101 | Use the 102 | web interface for information, subscription, archives, etc. 103 |

104 |
105 | 106 | Additionally, there are several specific Special Interest 107 | Group (=: SIG) mailing lists; 108 | however do post to only one list at time ('SIG' or general one), 109 | cross-posting is considered to be impolite. 110 |
111 | 112 | 113 | 114 | 115 | 116 | 117 | 118 | 119 | 120 | 121 | 122 | 123 | 124 | 125 | 126 | 127 | 128 | 129 | 130 | 131 | 132 | 133 | 134 | 135 | 136 | 137 | 138 | 139 | 140 | 141 | 142 | 143 | 144 | 145 | 146 | 147 | 148 | 149 | 150 | 151 | 152 | 153 | 154 | 155 | 156 | 157 | 158 | 159 | 160 | 161 | 162 | 163 | 164 | 165 | 166 | 167 | 168 | 169 | 170 | 171 | 172 | 173 | 174 | 175 | 176 | 177 | 178 | 179 | 180 | 181 | 182 | 183 | 184 | 185 | 186 | 187 | 188 | 189 | 190 | 191 | 192 | 193 | 194 | 195 | 196 | 197 | 198 | 199 | 200 | 201 |
R-SIG-MacR Special Interest Group on Mac ports of R
R-sig-DBR SIG on Database Interfaces
R-SIG-DebianR Special Interest Group for Debian ports of R
R-sig-dynamic-models Special Interest Group for Dynamic Simulation Models in R
R-sig-EpiR for epidemiological data analysis
R-sig-ecologyUsing R in ecological data analysis
R-SIG-FedoraR Special Interest Group for Fedora and Redhat ports of R
R-SIG-FinanceSpecial Interest Group for 'R in Finance'
R-sig-GeoR Special Interest Group on using Geographical data and Mapping
R-sig-gRR SIG on gRaphical models
R-SIG-GUIR Special Interest Group on GUI Development
R-SIG-HPCR SIG on High-Performance Computing
R-sig-JobsR SIG List for Announcements of Jobs where R is used
R-sig-mixed-modelsR SIG on Mixed Effect Models, notably lmer() related
R-sig-mediawikiR SIG on the R Extension for Mediawiki
R-sig-networksR SIG for users and developers of network- or graph-related software within R
R-sig-phyloR SIG on phylogenetic and comparative methods and analyses
R-sig-QAR SIG on Quality Assurance & Validation
R-sig-RobustR SIG on Robust Statistics
R-sig-teachingSIG on Teaching Statistics (and more) using R
R-sig-WikiSIG on the Development of an "R Wiki"
202 |
203 | 204 | To satisfy geographic or regional (or subject) needs, some R users have 205 | formed "R User Groups" for which there are mailing 206 | lists. Information about (some of) these groups and their lists can be 207 | found at the 208 | RUG web page, 209 | maintained by John C. Nash. 210 | 211 | 212 |

Archives and Search Facilities

213 | 214 | 215 | 228 | 229 |

General Instructions

230 | 231 | 232 |

233 | Note that you should configure your e-mail software in such a way as to 234 | send only plain text, i.e., no HTML. 235 | ‘html-ified’ messages are usually considerably longer (in bytes!) and 236 | harder to filter for spam or viruses. 237 | Many of these (e.g. ‘html-only’ ones) are currently 238 | spam-filtered or otherwise intercepted completely and without notice to 239 | the sender. 240 | 241 | For more details and instructions on turning off HTML for your e-mail 242 | software, see here. 243 |
244 | Furthermore, most binary e-mail attachments are not accepted, 245 | i.e., they are removed from the posting completely. As an 246 | exception, we allow application/pdf, application/postscript, and 247 | image/png (and x-tar and gzip on R-devel). You can use text/plain as well, 248 | or simply paste text into your message instead. 249 |

250 | 251 |

Information about the list can be obtained by sending an email 252 | with ‘info’ as its contents to r-help-request@R-project.org. 254 |
255 | Note that you can can subscribe and unsubscribe by E-mail 256 | (instead of the web interface), however to unsubscribe you currently need the 257 | mailing list password which you get when subscribing and in a monthly reminder. 258 |

259 | 260 |

To send a message to everyone on the r-help mailing list, send 261 | email to 262 | r-help@R-project.org. 263 |
264 | Do please create a new email message when posting to the list rather than 265 | replying to a previous message and simply changing the subject line! 266 | This allows sensible threading in the mailing list archives (and 267 | many users e-mail readers). 268 | 269 | Subscription and posting to the other lists is done 270 | analogously, with ‘r-help’ replaced by ‘r-announce’ and 271 | ‘r-devel’, respectively. Note that the r-announce list is 272 | gatewayed into r-help, so you don't need to subscribe to both of 273 | them.

274 | 275 |

It is recommended that you send mail to r-help (or r-devel if 276 | appropriate) rather than only to the R developers (who are also 277 | subscribed to the list, of course). This may save them precious time they 278 | can use for constantly improving R, and will typically also 279 | result in much quicker feedback for yourself.

280 | 281 |

Of course, in the case of bug reports it would be very helpful 282 | to have code which reliably reproduces the problem, see the 283 | 284 | entry in the R FAQ. 285 |

286 | 287 |

288 |

289 |
Author: R-core
290 | Problems with the mailing lists: Use the links above and their e-mail 291 | adresses. 292 |
293 |

294 | Last modified: Aug 25, 2008 by Martyn Plummer 295 | 296 | 297 | -------------------------------------------------------------------------------- /data/miserables.txt: -------------------------------------------------------------------------------- 1 | // This file contains the weighted network of coappearances of characters in 2 | // Victor Hugo's novel "Les Miserables". Nodes represent characters as indicated 3 | // by the labels, and edges connect any pair of characters that appear in the 4 | // same chapter of the book. The values on the edges are the number of such 5 | // coappearances. The data on coappearances were taken from D. E. Knuth, The 6 | // Stanford GraphBase: A Platform for Combinatorial Computing, Addison-Wesley, 7 | // Reading, MA (1993). 8 | // 9 | // The group labels were transcribed from "Finding and evaluating community 10 | // structure in networks" by M. E. J. Newman and M. Girvan. 11 | 12 | var miserables = { 13 | nodes:[ 14 | {nodeName:"Myriel", group:1}, 15 | {nodeName:"Napoleon", group:1}, 16 | {nodeName:"Mlle. Baptistine", group:1}, 17 | {nodeName:"Mme. Magloire", group:1}, 18 | {nodeName:"Countess de Lo", group:1}, 19 | {nodeName:"Geborand", group:1}, 20 | {nodeName:"Champtercier", group:1}, 21 | {nodeName:"Cravatte", group:1}, 22 | {nodeName:"Count", group:1}, 23 | {nodeName:"Old Man", group:1}, 24 | {nodeName:"Labarre", group:2}, 25 | {nodeName:"Valjean", group:2}, 26 | {nodeName:"Marguerite", group:3}, 27 | {nodeName:"Mme. de R", group:2}, 28 | {nodeName:"Isabeau", group:2}, 29 | {nodeName:"Gervais", group:2}, 30 | {nodeName:"Tholomyes", group:3}, 31 | {nodeName:"Listolier", group:3}, 32 | {nodeName:"Fameuil", group:3}, 33 | {nodeName:"Blacheville", group:3}, 34 | {nodeName:"Favourite", group:3}, 35 | {nodeName:"Dahlia", group:3}, 36 | {nodeName:"Zephine", group:3}, 37 | {nodeName:"Fantine", group:3}, 38 | {nodeName:"Mme. Thenardier", group:4}, 39 | {nodeName:"Thenardier", group:4}, 40 | {nodeName:"Cosette", group:5}, 41 | {nodeName:"Javert", group:4}, 42 | {nodeName:"Fauchelevent", group:0}, 43 | {nodeName:"Bamatabois", group:2}, 44 | {nodeName:"Perpetue", group:3}, 45 | {nodeName:"Simplice", group:2}, 46 | {nodeName:"Scaufflaire", group:2}, 47 | {nodeName:"Woman 1", group:2}, 48 | {nodeName:"Judge", group:2}, 49 | {nodeName:"Champmathieu", group:2}, 50 | {nodeName:"Brevet", group:2}, 51 | {nodeName:"Chenildieu", group:2}, 52 | {nodeName:"Cochepaille", group:2}, 53 | {nodeName:"Pontmercy", group:4}, 54 | {nodeName:"Boulatruelle", group:6}, 55 | {nodeName:"Eponine", group:4}, 56 | {nodeName:"Anzelma", group:4}, 57 | {nodeName:"Woman 2", group:5}, 58 | {nodeName:"Mother Innocent", group:0}, 59 | {nodeName:"Gribier", group:0}, 60 | {nodeName:"Jondrette", group:7}, 61 | {nodeName:"Mme. Burgon", group:7}, 62 | {nodeName:"Gavroche", group:8}, 63 | {nodeName:"Gillenormand", group:5}, 64 | {nodeName:"Magnon", group:5}, 65 | {nodeName:"Mlle. Gillenormand", group:5}, 66 | {nodeName:"Mme. Pontmercy", group:5}, 67 | {nodeName:"Mlle. Vaubois", group:5}, 68 | {nodeName:"Lt. Gillenormand", group:5}, 69 | {nodeName:"Marius", group:8}, 70 | {nodeName:"Baroness T", group:5}, 71 | {nodeName:"Mabeuf", group:8}, 72 | {nodeName:"Enjolras", group:8}, 73 | {nodeName:"Combeferre", group:8}, 74 | {nodeName:"Prouvaire", group:8}, 75 | {nodeName:"Feuilly", group:8}, 76 | {nodeName:"Courfeyrac", group:8}, 77 | {nodeName:"Bahorel", group:8}, 78 | {nodeName:"Bossuet", group:8}, 79 | {nodeName:"Joly", group:8}, 80 | {nodeName:"Grantaire", group:8}, 81 | {nodeName:"Mother Plutarch", group:9}, 82 | {nodeName:"Gueulemer", group:4}, 83 | {nodeName:"Babet", group:4}, 84 | {nodeName:"Claquesous", group:4}, 85 | {nodeName:"Montparnasse", group:4}, 86 | {nodeName:"Toussaint", group:5}, 87 | {nodeName:"Child 1", group:10}, 88 | {nodeName:"Child 2", group:10}, 89 | {nodeName:"Brujon", group:4}, 90 | {nodeName:"Mme. Hucheloup", group:8} 91 | ], 92 | links:[ 93 | {source:1, target:0, value:1}, 94 | {source:2, target:0, value:8}, 95 | {source:3, target:0, value:10}, 96 | {source:3, target:2, value:6}, 97 | {source:4, target:0, value:1}, 98 | {source:5, target:0, value:1}, 99 | {source:6, target:0, value:1}, 100 | {source:7, target:0, value:1}, 101 | {source:8, target:0, value:2}, 102 | {source:9, target:0, value:1}, 103 | {source:11, target:10, value:1}, 104 | {source:11, target:3, value:3}, 105 | {source:11, target:2, value:3}, 106 | {source:11, target:0, value:5}, 107 | {source:12, target:11, value:1}, 108 | {source:13, target:11, value:1}, 109 | {source:14, target:11, value:1}, 110 | {source:15, target:11, value:1}, 111 | {source:17, target:16, value:4}, 112 | {source:18, target:16, value:4}, 113 | {source:18, target:17, value:4}, 114 | {source:19, target:16, value:4}, 115 | {source:19, target:17, value:4}, 116 | {source:19, target:18, value:4}, 117 | {source:20, target:16, value:3}, 118 | {source:20, target:17, value:3}, 119 | {source:20, target:18, value:3}, 120 | {source:20, target:19, value:4}, 121 | {source:21, target:16, value:3}, 122 | {source:21, target:17, value:3}, 123 | {source:21, target:18, value:3}, 124 | {source:21, target:19, value:3}, 125 | {source:21, target:20, value:5}, 126 | {source:22, target:16, value:3}, 127 | {source:22, target:17, value:3}, 128 | {source:22, target:18, value:3}, 129 | {source:22, target:19, value:3}, 130 | {source:22, target:20, value:4}, 131 | {source:22, target:21, value:4}, 132 | {source:23, target:16, value:3}, 133 | {source:23, target:17, value:3}, 134 | {source:23, target:18, value:3}, 135 | {source:23, target:19, value:3}, 136 | {source:23, target:20, value:4}, 137 | {source:23, target:21, value:4}, 138 | {source:23, target:22, value:4}, 139 | {source:23, target:12, value:2}, 140 | {source:23, target:11, value:9}, 141 | {source:24, target:23, value:2}, 142 | {source:24, target:11, value:7}, 143 | {source:25, target:24, value:13}, 144 | {source:25, target:23, value:1}, 145 | {source:25, target:11, value:12}, 146 | {source:26, target:24, value:4}, 147 | {source:26, target:11, value:31}, 148 | {source:26, target:16, value:1}, 149 | {source:26, target:25, value:1}, 150 | {source:27, target:11, value:17}, 151 | {source:27, target:23, value:5}, 152 | {source:27, target:25, value:5}, 153 | {source:27, target:24, value:1}, 154 | {source:27, target:26, value:1}, 155 | {source:28, target:11, value:8}, 156 | {source:28, target:27, value:1}, 157 | {source:29, target:23, value:1}, 158 | {source:29, target:27, value:1}, 159 | {source:29, target:11, value:2}, 160 | {source:30, target:23, value:1}, 161 | {source:31, target:30, value:2}, 162 | {source:31, target:11, value:3}, 163 | {source:31, target:23, value:2}, 164 | {source:31, target:27, value:1}, 165 | {source:32, target:11, value:1}, 166 | {source:33, target:11, value:2}, 167 | {source:33, target:27, value:1}, 168 | {source:34, target:11, value:3}, 169 | {source:34, target:29, value:2}, 170 | {source:35, target:11, value:3}, 171 | {source:35, target:34, value:3}, 172 | {source:35, target:29, value:2}, 173 | {source:36, target:34, value:2}, 174 | {source:36, target:35, value:2}, 175 | {source:36, target:11, value:2}, 176 | {source:36, target:29, value:1}, 177 | {source:37, target:34, value:2}, 178 | {source:37, target:35, value:2}, 179 | {source:37, target:36, value:2}, 180 | {source:37, target:11, value:2}, 181 | {source:37, target:29, value:1}, 182 | {source:38, target:34, value:2}, 183 | {source:38, target:35, value:2}, 184 | {source:38, target:36, value:2}, 185 | {source:38, target:37, value:2}, 186 | {source:38, target:11, value:2}, 187 | {source:38, target:29, value:1}, 188 | {source:39, target:25, value:1}, 189 | {source:40, target:25, value:1}, 190 | {source:41, target:24, value:2}, 191 | {source:41, target:25, value:3}, 192 | {source:42, target:41, value:2}, 193 | {source:42, target:25, value:2}, 194 | {source:42, target:24, value:1}, 195 | {source:43, target:11, value:3}, 196 | {source:43, target:26, value:1}, 197 | {source:43, target:27, value:1}, 198 | {source:44, target:28, value:3}, 199 | {source:44, target:11, value:1}, 200 | {source:45, target:28, value:2}, 201 | {source:47, target:46, value:1}, 202 | {source:48, target:47, value:2}, 203 | {source:48, target:25, value:1}, 204 | {source:48, target:27, value:1}, 205 | {source:48, target:11, value:1}, 206 | {source:49, target:26, value:3}, 207 | {source:49, target:11, value:2}, 208 | {source:50, target:49, value:1}, 209 | {source:50, target:24, value:1}, 210 | {source:51, target:49, value:9}, 211 | {source:51, target:26, value:2}, 212 | {source:51, target:11, value:2}, 213 | {source:52, target:51, value:1}, 214 | {source:52, target:39, value:1}, 215 | {source:53, target:51, value:1}, 216 | {source:54, target:51, value:2}, 217 | {source:54, target:49, value:1}, 218 | {source:54, target:26, value:1}, 219 | {source:55, target:51, value:6}, 220 | {source:55, target:49, value:12}, 221 | {source:55, target:39, value:1}, 222 | {source:55, target:54, value:1}, 223 | {source:55, target:26, value:21}, 224 | {source:55, target:11, value:19}, 225 | {source:55, target:16, value:1}, 226 | {source:55, target:25, value:2}, 227 | {source:55, target:41, value:5}, 228 | {source:55, target:48, value:4}, 229 | {source:56, target:49, value:1}, 230 | {source:56, target:55, value:1}, 231 | {source:57, target:55, value:1}, 232 | {source:57, target:41, value:1}, 233 | {source:57, target:48, value:1}, 234 | {source:58, target:55, value:7}, 235 | {source:58, target:48, value:7}, 236 | {source:58, target:27, value:6}, 237 | {source:58, target:57, value:1}, 238 | {source:58, target:11, value:4}, 239 | {source:59, target:58, value:15}, 240 | {source:59, target:55, value:5}, 241 | {source:59, target:48, value:6}, 242 | {source:59, target:57, value:2}, 243 | {source:60, target:48, value:1}, 244 | {source:60, target:58, value:4}, 245 | {source:60, target:59, value:2}, 246 | {source:61, target:48, value:2}, 247 | {source:61, target:58, value:6}, 248 | {source:61, target:60, value:2}, 249 | {source:61, target:59, value:5}, 250 | {source:61, target:57, value:1}, 251 | {source:61, target:55, value:1}, 252 | {source:62, target:55, value:9}, 253 | {source:62, target:58, value:17}, 254 | {source:62, target:59, value:13}, 255 | {source:62, target:48, value:7}, 256 | {source:62, target:57, value:2}, 257 | {source:62, target:41, value:1}, 258 | {source:62, target:61, value:6}, 259 | {source:62, target:60, value:3}, 260 | {source:63, target:59, value:5}, 261 | {source:63, target:48, value:5}, 262 | {source:63, target:62, value:6}, 263 | {source:63, target:57, value:2}, 264 | {source:63, target:58, value:4}, 265 | {source:63, target:61, value:3}, 266 | {source:63, target:60, value:2}, 267 | {source:63, target:55, value:1}, 268 | {source:64, target:55, value:5}, 269 | {source:64, target:62, value:12}, 270 | {source:64, target:48, value:5}, 271 | {source:64, target:63, value:4}, 272 | {source:64, target:58, value:10}, 273 | {source:64, target:61, value:6}, 274 | {source:64, target:60, value:2}, 275 | {source:64, target:59, value:9}, 276 | {source:64, target:57, value:1}, 277 | {source:64, target:11, value:1}, 278 | {source:65, target:63, value:5}, 279 | {source:65, target:64, value:7}, 280 | {source:65, target:48, value:3}, 281 | {source:65, target:62, value:5}, 282 | {source:65, target:58, value:5}, 283 | {source:65, target:61, value:5}, 284 | {source:65, target:60, value:2}, 285 | {source:65, target:59, value:5}, 286 | {source:65, target:57, value:1}, 287 | {source:65, target:55, value:2}, 288 | {source:66, target:64, value:3}, 289 | {source:66, target:58, value:3}, 290 | {source:66, target:59, value:1}, 291 | {source:66, target:62, value:2}, 292 | {source:66, target:65, value:2}, 293 | {source:66, target:48, value:1}, 294 | {source:66, target:63, value:1}, 295 | {source:66, target:61, value:1}, 296 | {source:66, target:60, value:1}, 297 | {source:67, target:57, value:3}, 298 | {source:68, target:25, value:5}, 299 | {source:68, target:11, value:1}, 300 | {source:68, target:24, value:1}, 301 | {source:68, target:27, value:1}, 302 | {source:68, target:48, value:1}, 303 | {source:68, target:41, value:1}, 304 | {source:69, target:25, value:6}, 305 | {source:69, target:68, value:6}, 306 | {source:69, target:11, value:1}, 307 | {source:69, target:24, value:1}, 308 | {source:69, target:27, value:2}, 309 | {source:69, target:48, value:1}, 310 | {source:69, target:41, value:1}, 311 | {source:70, target:25, value:4}, 312 | {source:70, target:69, value:4}, 313 | {source:70, target:68, value:4}, 314 | {source:70, target:11, value:1}, 315 | {source:70, target:24, value:1}, 316 | {source:70, target:27, value:1}, 317 | {source:70, target:41, value:1}, 318 | {source:70, target:58, value:1}, 319 | {source:71, target:27, value:1}, 320 | {source:71, target:69, value:2}, 321 | {source:71, target:68, value:2}, 322 | {source:71, target:70, value:2}, 323 | {source:71, target:11, value:1}, 324 | {source:71, target:48, value:1}, 325 | {source:71, target:41, value:1}, 326 | {source:71, target:25, value:1}, 327 | {source:72, target:26, value:2}, 328 | {source:72, target:27, value:1}, 329 | {source:72, target:11, value:1}, 330 | {source:73, target:48, value:2}, 331 | {source:74, target:48, value:2}, 332 | {source:74, target:73, value:3}, 333 | {source:75, target:69, value:3}, 334 | {source:75, target:68, value:3}, 335 | {source:75, target:25, value:3}, 336 | {source:75, target:48, value:1}, 337 | {source:75, target:41, value:1}, 338 | {source:75, target:70, value:1}, 339 | {source:75, target:71, value:1}, 340 | {source:76, target:64, value:1}, 341 | {source:76, target:65, value:1}, 342 | {source:76, target:66, value:1}, 343 | {source:76, target:63, value:1}, 344 | {source:76, target:62, value:1}, 345 | {source:76, target:48, value:1}, 346 | {source:76, target:58, value:1} 347 | ] 348 | }; 349 | -------------------------------------------------------------------------------- /data/plant_catalog.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | Bloodroot 8 | 9 | Sanguinaria canadensis 10 | 11 | 4 12 | 13 | Mostly Shady 14 | 15 | $2.44 16 | 17 | 031599 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | Columbine 26 | 27 | Aquilegia canadensis 28 | 29 | 3 30 | 31 | Mostly Shady 32 | 33 | $9.37 34 | 35 | 030699 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | Marsh Marigold 44 | 45 | Caltha palustris 46 | 47 | 4 48 | 49 | Mostly Sunny 50 | 51 | $6.81 52 | 53 | 051799 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | Cowslip 62 | 63 | Caltha palustris 64 | 65 | 4 66 | 67 | Mostly Shady 68 | 69 | $9.90 70 | 71 | 030699 72 | 73 | 74 | 75 | 76 | 77 | 78 | 79 | Dutchman's-Breeches 80 | 81 | Diecentra cucullaria 82 | 83 | 3 84 | 85 | Mostly Shady 86 | 87 | $6.44 88 | 89 | 012099 90 | 91 | 92 | 93 | 94 | 95 | 96 | 97 | Ginger, Wild 98 | 99 | Asarum canadense 100 | 101 | 3 102 | 103 | Mostly Shady 104 | 105 | $9.03 106 | 107 | 041899 108 | 109 | 110 | 111 | 112 | 113 | 114 | 115 | Hepatica 116 | 117 | Hepatica americana 118 | 119 | 4 120 | 121 | Mostly Shady 122 | 123 | $4.45 124 | 125 | 012699 126 | 127 | 128 | 129 | 130 | 131 | 132 | 133 | Liverleaf 134 | 135 | Hepatica americana 136 | 137 | 4 138 | 139 | Mostly Shady 140 | 141 | $3.99 142 | 143 | 010299 144 | 145 | 146 | 147 | 148 | 149 | 150 | 151 | Jack-In-The-Pulpit 152 | 153 | Arisaema triphyllum 154 | 155 | 4 156 | 157 | Mostly Shady 158 | 159 | $3.23 160 | 161 | 020199 162 | 163 | 164 | 165 | 166 | 167 | 168 | 169 | Mayapple 170 | 171 | Podophyllum peltatum 172 | 173 | 3 174 | 175 | Mostly Shady 176 | 177 | $2.98 178 | 179 | 060599 180 | 181 | 182 | 183 | 184 | 185 | 186 | 187 | Phlox, Woodland 188 | 189 | Phlox divaricata 190 | 191 | 3 192 | 193 | Sun or Shade 194 | 195 | $2.80 196 | 197 | 012299 198 | 199 | 200 | 201 | 202 | 203 | 204 | 205 | Phlox, Blue 206 | 207 | Phlox divaricata 208 | 209 | 3 210 | 211 | Sun or Shade 212 | 213 | $5.59 214 | 215 | 021699 216 | 217 | 218 | 219 | 220 | 221 | 222 | 223 | Spring-Beauty 224 | 225 | Claytonia Virginica 226 | 227 | 7 228 | 229 | Mostly Shady 230 | 231 | $6.59 232 | 233 | 020199 234 | 235 | 236 | 237 | 238 | 239 | 240 | 241 | Trillium 242 | 243 | Trillium grandiflorum 244 | 245 | 5 246 | 247 | Sun or Shade 248 | 249 | $3.90 250 | 251 | 042999 252 | 253 | 254 | 255 | 256 | 257 | 258 | 259 | Wake Robin 260 | 261 | Trillium grandiflorum 262 | 263 | 5 264 | 265 | Sun or Shade 266 | 267 | $3.20 268 | 269 | 022199 270 | 271 | 272 | 273 | 274 | 275 | 276 | 277 | Violet, Dog-Tooth 278 | 279 | Erythronium americanum 280 | 281 | 4 282 | 283 | Shade 284 | 285 | $9.04 286 | 287 | 020199 288 | 289 | 290 | 291 | 292 | 293 | 294 | 295 | Trout Lily 296 | 297 | Erythronium americanum 298 | 299 | 4 300 | 301 | Shade 302 | 303 | $6.94 304 | 305 | 032499 306 | 307 | 308 | 309 | 310 | 311 | 312 | 313 | Adder's-Tongue 314 | 315 | Erythronium americanum 316 | 317 | 4 318 | 319 | Shade 320 | 321 | $9.58 322 | 323 | 041399 324 | 325 | 326 | 327 | 328 | 329 | 330 | 331 | Anemone 332 | 333 | Anemone blanda 334 | 335 | 6 336 | 337 | Mostly Shady 338 | 339 | $8.86 340 | 341 | 122698 342 | 343 | 344 | 345 | 346 | 347 | 348 | 349 | Grecian Windflower 350 | 351 | Anemone blanda 352 | 353 | 6 354 | 355 | Mostly Shady 356 | 357 | $9.16 358 | 359 | 071099 360 | 361 | 362 | 363 | 364 | 365 | 366 | 367 | Bee Balm 368 | 369 | Monarda didyma 370 | 371 | 4 372 | 373 | Shade 374 | 375 | $4.59 376 | 377 | 050399 378 | 379 | 380 | 381 | 382 | 383 | 384 | 385 | Bergamont 386 | 387 | Monarda didyma 388 | 389 | 4 390 | 391 | Shade 392 | 393 | $7.16 394 | 395 | 042799 396 | 397 | 398 | 399 | 400 | 401 | 402 | 403 | Black-Eyed Susan 404 | 405 | Rudbeckia hirta 406 | 407 | Annual 408 | 409 | Sunny 410 | 411 | $9.80 412 | 413 | 061899 414 | 415 | 416 | 417 | 418 | 419 | 420 | 421 | Buttercup 422 | 423 | Ranunculus 424 | 425 | 4 426 | 427 | Shade 428 | 429 | $2.57 430 | 431 | 061099 432 | 433 | 434 | 435 | 436 | 437 | 438 | 439 | Crowfoot 440 | 441 | Ranunculus 442 | 443 | 4 444 | 445 | Shade 446 | 447 | $9.34 448 | 449 | 040399 450 | 451 | 452 | 453 | 454 | 455 | 456 | 457 | Butterfly Weed 458 | 459 | Asclepias tuberosa 460 | 461 | Annual 462 | 463 | Sunny 464 | 465 | $2.78 466 | 467 | 063099 468 | 469 | 470 | 471 | 472 | 473 | 474 | 475 | Cinquefoil 476 | 477 | Potentilla 478 | 479 | Annual 480 | 481 | Shade 482 | 483 | $7.06 484 | 485 | 052599 486 | 487 | 488 | 489 | 490 | 491 | 492 | 493 | Primrose 494 | 495 | Oenothera 496 | 497 | 3 - 5 498 | 499 | Sunny 500 | 501 | $6.56 502 | 503 | 013099 504 | 505 | 506 | 507 | 508 | 509 | 510 | 511 | Gentian 512 | 513 | Gentiana 514 | 515 | 4 516 | 517 | Sun or Shade 518 | 519 | $7.81 520 | 521 | 051899 522 | 523 | 524 | 525 | 526 | 527 | 528 | 529 | Blue Gentian 530 | 531 | Gentiana 532 | 533 | 4 534 | 535 | Sun or Shade 536 | 537 | $8.56 538 | 539 | 050299 540 | 541 | 542 | 543 | 544 | 545 | 546 | 547 | Jacob's Ladder 548 | 549 | Polemonium caeruleum 550 | 551 | Annual 552 | 553 | Shade 554 | 555 | $9.26 556 | 557 | 022199 558 | 559 | 560 | 561 | 562 | 563 | 564 | 565 | Greek Valerian 566 | 567 | Polemonium caeruleum 568 | 569 | Annual 570 | 571 | Shade 572 | 573 | $4.36 574 | 575 | 071499 576 | 577 | 578 | 579 | 580 | 581 | 582 | 583 | California Poppy 584 | 585 | Eschscholzia californica 586 | 587 | Annual 588 | 589 | Sun 590 | 591 | $7.89 592 | 593 | 032799 594 | 595 | 596 | 597 | 598 | 599 | 600 | 601 | Shooting Star 602 | 603 | Dodecatheon 604 | 605 | Annual 606 | 607 | Mostly Shady 608 | 609 | $8.60 610 | 611 | 051399 612 | 613 | 614 | 615 | 616 | 617 | 618 | 619 | Snakeroot 620 | 621 | Cimicifuga 622 | 623 | Annual 624 | 625 | Shade 626 | 627 | $5.63 628 | 629 | 071199 630 | 631 | 632 | 633 | 634 | 635 | 636 | 637 | Cardinal Flower 638 | 639 | Lobelia cardinalis 640 | 641 | 2 642 | 643 | Shade 644 | 645 | $3.02 646 | 647 | 022299 648 | 649 | 650 | 651 | 652 | 653 | -------------------------------------------------------------------------------- /data/rproject_homepage.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | The R Project for Statistical Computing 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | <h1>The R Project for Statistical Computing</h1> 18 | 19 | Your browser seems not to support frames, 20 | here is the <A href="navbar.html">contents page</A> of the R Project's 21 | website. 22 | 23 | 24 | 25 | 26 | 27 | -------------------------------------------------------------------------------- /data/skulls_data.html: -------------------------------------------------------------------------------- 1 | Egyptian Skulls Datafile 2 | 3 | 4 |
Go to Main Menu
Go to Power Search
Go to Datafile Subjects
5 |
Datafile Name: Egyptian Skulls 6 |
Datafile Subjects: 7 | Archeology 8 | , 9 | 10 | Biology 11 | 12 | 13 |
Story Names: 14 | Egyptian Skull Development 15 | 16 |
Reference: Thomson, A. and Randall-Maciver, R. (1905) Ancient Races of the Thebaid, Oxford: Oxford University Press. 17 | Also found in: Hand, D.J., et al. (1994) A Handbook of Small Data Sets, New York: Chapman & Hall, pp. 299-301. 18 | Manly, B.F.J. (1986) Multivariate Statistical Methods, New York: Chapman & Hall. 19 |
Authorization: Contact Authors 20 |
Description: Four measurements of male Egyptian skulls from 5 different time periods. Thirty skulls are measured from each time period.

21 | 22 | 23 |

Number of cases: 150 24 |
Variable Names: 25 |
    26 |
  1. MB: Maximal Breadth of Skull 27 |
  2. BH: Basibregmatic Height of Skull 28 |
  3. BL: Basialveolar Length of Skull 29 |
  4. NH: Nasal Height of Skull 30 |
  5. Year: Approximate Year of Skull Formation (negative = B.C., positive = A.D.) 31 |
32 |
The Data: 33 | 
 34 | MB	BH	BL	NH	Year
 35 | 131	138	89	49	-4000
 36 | 125	131	92	48	-4000
 37 | 131	132	99	50	-4000
 38 | 119	132	96	44	-4000
 39 | 136	143	100	54	-4000
 40 | 138	137	89	56	-4000
 41 | 139	130	108	48	-4000
 42 | 125	136	93	48	-4000
 43 | 131	134	102	51	-4000
 44 | 134	134	99	51	-4000
 45 | 129	138	95	50	-4000
 46 | 134	121	95	53	-4000
 47 | 126	129	109	51	-4000
 48 | 132	136	100	50	-4000
 49 | 141	140	100	51	-4000
 50 | 131	134	97	54	-4000
 51 | 135	137	103	50	-4000
 52 | 132	133	93	53	-4000
 53 | 139	136	96	50	-4000
 54 | 132	131	101	49	-4000
 55 | 126	133	102	51	-4000
 56 | 135	135	103	47	-4000
 57 | 134	124	93	53	-4000
 58 | 128	134	103	50	-4000
 59 | 130	130	104	49	-4000
 60 | 138	135	100	55	-4000
 61 | 128	132	93	53	-4000
 62 | 127	129	106	48	-4000
 63 | 131	136	114	54	-4000
 64 | 124	138	101	46	-4000
 65 | 124	138	101	48	-3300
 66 | 133	134	97	48	-3300
 67 | 138	134	98	45	-3300
 68 | 148	129	104	51	-3300
 69 | 126	124	95	45	-3300
 70 | 135	136	98	52	-3300
 71 | 132	145	100	54	-3300
 72 | 133	130	102	48	-3300
 73 | 131	134	96	50	-3300
 74 | 133	125	94	46	-3300
 75 | 133	136	103	53	-3300
 76 | 131	139	98	51	-3300
 77 | 131	136	99	56	-3300
 78 | 138	134	98	49	-3300
 79 | 130	136	104	53	-3300
 80 | 131	128	98	45	-3300
 81 | 138	129	107	53	-3300
 82 | 123	131	101	51	-3300
 83 | 130	129	105	47	-3300
 84 | 134	130	93	54	-3300
 85 | 137	136	106	49	-3300
 86 | 126	131	100	48	-3300
 87 | 135	136	97	52	-3300
 88 | 129	126	91	50	-3300
 89 | 134	139	101	49	-3300
 90 | 131	134	90	53	-3300
 91 | 132	130	104	50	-3300
 92 | 130	132	93	52	-3300
 93 | 135	132	98	54	-3300
 94 | 130	128	101	51	-3300
 95 | 137	141	96	52	-1850
 96 | 129	133	93	47	-1850
 97 | 132	138	87	48	-1850
 98 | 130	134	106	50	-1850
 99 | 134	134	96	45	-1850
100 | 140	133	98	50	-1850
101 | 138	138	95	47	-1850
102 | 136	145	99	55	-1850
103 | 136	131	92	46	-1850
104 | 126	136	95	56	-1850
105 | 137	129	100	53	-1850
106 | 137	139	97	50	-1850
107 | 136	126	101	50	-1850
108 | 137	133	90	49	-1850
109 | 129	142	104	47	-1850
110 | 135	138	102	55	-1850
111 | 129	135	92	50	-1850
112 | 134	125	90	60	-1850
113 | 138	134	96	51	-1850
114 | 136	135	94	53	-1850
115 | 132	130	91	52	-1850
116 | 133	131	100	50	-1850
117 | 138	137	94	51	-1850
118 | 130	127	99	45	-1850
119 | 136	133	91	49	-1850
120 | 134	123	95	52	-1850
121 | 136	137	101	54	-1850
122 | 133	131	96	49	-1850
123 | 138	133	100	55	-1850
124 | 138	133	91	46	-1850
125 | 137	134	107	54	-200
126 | 141	128	95	53	-200
127 | 141	130	87	49	-200
128 | 135	131	99	51	-200
129 | 133	120	91	46	-200
130 | 131	135	90	50	-200
131 | 140	137	94	60	-200
132 | 139	130	90	48	-200
133 | 140	134	90	51	-200
134 | 138	140	100	52	-200
135 | 132	133	90	53	-200
136 | 134	134	97	54	-200
137 | 135	135	99	50	-200
138 | 133	136	95	52	-200
139 | 136	130	99	55	-200
140 | 134	137	93	52	-200
141 | 131	141	99	55	-200
142 | 129	135	95	47	-200
143 | 136	128	93	54	-200
144 | 131	125	88	48	-200
145 | 139	130	94	53	-200
146 | 144	124	86	50	-200
147 | 141	131	97	53	-200
148 | 130	131	98	53	-200
149 | 133	128	92	51	-200
150 | 138	126	97	54	-200
151 | 131	142	95	53	-200
152 | 136	138	94	55	-200
153 | 132	136	92	52	-200
154 | 135	130	100	51	-200
155 | 137	123	91	50	150
156 | 136	131	95	49	150
157 | 128	126	91	57	150
158 | 130	134	92	52	150
159 | 138	127	86	47	150
160 | 126	138	101	52	150
161 | 136	138	97	58	150
162 | 126	126	92	45	150
163 | 132	132	99	55	150
164 | 139	135	92	54	150
165 | 143	120	95	51	150
166 | 141	136	101	54	150
167 | 135	135	95	56	150
168 | 137	134	93	53	150
169 | 142	135	96	52	150
170 | 139	134	95	47	150
171 | 138	125	99	51	150
172 | 137	135	96	54	150
173 | 133	125	92	50	150
174 | 145	129	89	47	150
175 | 138	136	92	46	150
176 | 131	129	97	44	150
177 | 143	126	88	54	150
178 | 134	124	91	55	150
179 | 132	127	97	52	150
180 | 137	125	85	57	150
181 | 129	128	81	52	150
182 | 140	135	103	48	150
183 | 147	129	87	48	150
184 | 136	133	97	51	150
185 | 
186 |
187 | -------------------------------------------------------------------------------- /data/star_wars_json.R: -------------------------------------------------------------------------------- 1 | 2 | [ 3 | { 4 | "Name": "Anakin", 5 | "Gender": "male", 6 | "Homeworld": "Tatooine", 7 | "Born": "41.9BBY", 8 | "Jedi": "yes" 9 | }, 10 | { 11 | "Name": "Luke", 12 | "Gender": "male", 13 | "Homeworld": "Tatooine", 14 | "Born": "19BBY", 15 | "Jedi": "yes" 16 | }, 17 | { 18 | "Name": "Leia", 19 | "Gender": "female", 20 | "Homeworld": "Alderaan", 21 | "Born": "19BBY", 22 | "Jedi": "no" 23 | }, 24 | { 25 | "Name": "Obi-Wan", 26 | "Gender": "male", 27 | "Homeworld": "Stewjon", 28 | "Born": "57BBY", 29 | "Jedi": "yes" 30 | }, 31 | { 32 | "Name": "Han", 33 | "Gender": "male", 34 | "Homeworld": "Corellia", 35 | "Born": "29BBY", 36 | "Jedi": "no" 37 | }, 38 | { 39 | "Name": "Palpatine", 40 | "Gender": "male", 41 | "Homeworld": "Naboo", 42 | "Born": "82BBY", 43 | "Jedi": "no" 44 | }, 45 | { 46 | "Name": "R2-D2", 47 | "Gender": "unknown", 48 | "Homeworld": "Naboo", 49 | "Born": "33BBY", 50 | "Jedi": "no" 51 | } 52 | ] 53 | } -------------------------------------------------------------------------------- /data/taxon.txt: -------------------------------------------------------------------------------- 1 | "Petals" "Internode" "Sepal" "Bract" "Petiole" "Leaf" "Fruit" 2 | "1" 5.621498349 29.48059578 2.462106579 18.2034091 11.27909704 1.128032999 7.876151371 3 | "2" 4.994616997 28.36024706 2.429320759 17.65204912 11.0408378 1.197616585 7.025415554 4 | "3" 4.767504884 27.25431792 2.570497375 19.4083846 10.49072184 1.003808444 7.81747899 5 | "4" 6.299445616 25.9242382 2.066051345 18.37915478 11.80182252 1.614051727 7.672492324 6 | "5" 6.489375001 25.21130805 2.901582763 17.31304737 10.12159001 1.813333082 7.758443087 7 | "6" 5.7858682 25.52433147 2.655642742 17.07215724 10.5581605 1.955524186 7.880879829 8 | "7" 5.645575295 27.72735671 2.278691288 18.2902189 10.11689319 1.414356176 7.332124408 9 | "8" 4.828953215 27.6381855 2.238467716 19.87376227 10.43071493 1.603331861 7.005136448 10 | "9" 6.783500773 27.88777529 2.202762147 19.85326662 10.47399775 1.533533943 7.656378638 11 | "10" 5.395076839 25.10904979 2.538375992 19.56545356 11.55456651 1.048182185 7.505930435 12 | "11" 4.683617783 29.2459239 2.601945544 18.95335451 11.8203702 1.408570649 7.954125122 13 | "12" 4.444226444 25.48653519 2.918513379 19.52866206 10.27840842 1.783670318 7.674149643 14 | "13" 5.381888649 28.53008566 2.931223681 17.62409776 10.67172405 1.637521266 7.034974714 15 | "14" 4.162398141 27.23922882 2.759099725 17.89805071 11.42458281 1.307677167 7.697990092 16 | "15" 6.546125565 27.73424951 2.329725784 17.38995746 11.25045634 1.908787547 7.172021588 17 | "16" 5.133151769 29.33237736 2.448247009 19.40622249 11.15433346 1.413823925 7.635342975 18 | "17" 6.31750724 28.54598267 2.445203138 18.14507123 11.13155215 1.376095509 7.914687987 19 | "18" 6.872582397 27.36377647 2.551340885 19.37856593 11.39634002 1.845322428 7.362050896 20 | "19" 4.265699548 26.9166827 2.930159411 19.52993241 11.87800257 1.122888175 7.913177055 21 | "20" 4.069245625 28.00872767 2.306900441 18.10018898 10.28587666 1.096098375 7.523188659 22 | "21" 6.695262246 30.98241938 2.280554955 19.58999705 10.01733931 1.993469856 7.447146231 23 | "22" 5.804502115 27.60866985 2.541535351 19.99502062 10.71206051 1.078787122 7.634464001 24 | "23" 5.649255792 26.0145167 2.630009346 19.73151656 11.56895111 1.97965464 7.282278565 25 | "24" 4.975115406 29.83647166 2.533115646 17.85816577 11.09149866 1.399543824 7.469118495 26 | "25" 5.242381538 29.25618227 2.940088125 18.68002039 10.03097795 1.131223326 7.424061646 27 | "26" 5.063066089 30.23405514 2.816805174 17.11427146 10.65715001 1.955607401 7.920755239 28 | "27" 5.006042848 27.92346287 2.054945288 17.89395755 10.29285526 1.231612531 7.948526777 29 | "28" 5.980790831 27.59682027 2.829002908 19.19108937 10.55412055 1.877992273 7.692805714 30 | "29" 5.980731581 29.63982123 2.848883669 17.32272728 10.44058419 1.97344425 7.256240749 31 | "30" 5.398837951 29.95226918 2.097840425 19.13860803 11.39994465 1.407302231 7.751723047 32 | "31" 6.461344123 26.50359879 2.102136053 17.90343004 8.053338501 1.326542324 7.883368163 33 | "32" 6.099551292 27.11167739 2.289501928 19.22044942 8.870216439 1.183490286 7.770059274 34 | "33" 8.327221276 29.05157684 2.409757569 17.66771467 9.029627721 1.26942729 7.963455864 35 | "34" 7.274136516 30.80407453 2.440411699 17.25971466 8.607824909 1.256742194 7.311366419 36 | "35" 5.928707739 28.08394319 2.494621261 18.29162527 9.082412257 1.676413103 7.14092758 37 | "36" 7.472687699 25.67400374 2.886730564 18.68570965 8.004758122 1.264413018 7.261090831 38 | "37" 5.899870198 27.65872973 2.792196101 18.98842213 8.363500697 1.011574618 7.384380377 39 | "38" 6.25920026 25.6526212 2.369232733 18.92776339 9.574328926 1.885649765 7.211005332 40 | "39" 7.239731231 27.66079801 2.446000528 17.19825862 9.118366783 1.177664172 7.494688561 41 | "40" 7.034400661 27.96526566 2.382512697 17.73184505 7.11416084 1.051164699 7.547684363 42 | "41" 6.482874866 30.14202148 2.868524403 17.08417076 9.807589227 1.699837425 7.019451612 43 | "42" 7.948038689 30.06089763 2.989488653 19.2750217 7.967774532 1.314673872 7.245603857 44 | "43" 6.321943933 25.34356215 2.979392008 19.62205449 8.147660414 1.623425712 7.286809896 45 | "44" 8.44534738 28.39186703 2.820234277 19.83109823 7.80691107 1.875239751 7.971314828 46 | "45" 6.390603366 25.79406679 2.73215676 17.84969958 9.307595882 1.940924043 7.49425656 47 | "46" 7.749643196 30.79793201 2.722867743 19.53359813 8.533136344 1.026353332 7.305005476 48 | "47" 7.879810751 27.75826448 2.495427305 18.10118967 7.566014405 1.027403848 7.67010785 49 | "48" 8.255364481 25.18346837 2.802887568 17.417764 7.4614574 1.344517762 7.340519113 50 | "49" 6.568547436 28.11084956 2.370134919 19.49423984 9.607106978 1.720265129 7.44953805 51 | "50" 6.338346926 25.92147745 2.306362851 18.56344641 7.031611779 1.935156098 7.124513567 52 | "51" 7.539138058 28.097958 2.000888311 18.24113592 9.09326364 1.379369878 7.059071993 53 | "52" 7.508846778 25.31344398 2.935428006 17.82985267 9.576184582 1.002894317 7.357371955 54 | "53" 7.018184544 26.60133135 2.049775809 19.61701848 9.342758935 1.636416932 7.961301791 55 | "54" 6.224390617 26.94316327 2.059549346 18.37249639 8.869481409 1.462019483 7.156218048 56 | "55" 7.374233054 30.07446563 2.04545636 17.92105885 7.810899911 1.704671684 7.428778576 57 | "56" 7.976802218 26.59492923 2.638239679 18.3529387 9.482005914 1.791931152 7.245717475 58 | "57" 6.808560142 30.06794931 2.363214832 17.84496968 8.414059473 1.767168513 7.402652738 59 | "58" 5.503136484 28.59816911 2.344191259 18.08125458 8.112068798 1.573293679 7.663868872 60 | "59" 6.937394391 29.88675626 2.513679642 19.63517869 9.261641463 1.52854488 7.067521849 61 | "60" 7.784294407 25.10122725 2.059090227 19.72386238 7.214786616 1.050597363 7.343408926 62 | "61" 6.189350187 30.42074486 2.536448769 17.68642997 10.38179597 2.263311912 7.8303941 63 | "62" 8.242170264 25.40319237 2.674684154 18.06269239 9.980931297 2.690137127 7.511780312 64 | "63" 5.98814603 26.02021569 2.284407279 17.33593411 9.148920616 2.048049441 7.405769249 65 | "64" 6.216139384 25.80620976 2.375217023 19.84285787 9.972026747 2.10489049 7.271118074 66 | "65" 7.338874124 30.05406054 2.217712598 19.34112232 9.69733753 2.340828959 7.861934811 67 | "66" 5.716748628 30.19655036 2.366749755 17.79633418 9.974531283 2.492533042 7.273110265 68 | "67" 7.822257104 25.58904474 2.060671828 17.43194152 10.29438157 2.378332476 7.427239974 69 | "68" 7.021003978 27.2763774 2.069353885 17.7316552 9.544079797 2.814577363 7.135112514 70 | "69" 6.914044117 26.57036081 2.335833099 18.21972214 10.83033806 2.175609315 7.151322621 71 | "70" 6.461252769 28.781522 2.428194251 17.52506926 9.172738369 2.870407597 7.350791705 72 | "71" 5.597423592 30.59553441 2.507061763 17.3391796 9.886172148 2.484340453 7.336659453 73 | "72" 5.931079555 26.0114503 2.064901525 18.71680604 10.51931692 2.918919159 7.543810325 74 | "73" 6.766287404 29.72137423 2.60920281 18.38606883 10.63409329 2.91638364 7.972527444 75 | "74" 7.342572936 26.88428695 2.192125115 19.21597228 9.852831149 2.01505639 7.403353722 76 | "75" 6.04278248 27.85011969 2.072081927 18.69773011 9.077365602 2.080136988 7.548229539 77 | "76" 5.800720905 27.29347801 2.12793368 17.04141579 9.230232097 2.236683848 7.373628372 78 | "77" 7.513987686 26.51549049 2.647999372 19.37849421 10.53207388 2.683396281 7.615567728 79 | "78" 6.507046241 29.90004717 2.213157546 18.82561505 9.920248309 2.846200572 7.701986765 80 | "79" 8.33510984 29.63126752 2.631581835 18.99938911 9.181298505 2.747139776 7.423347594 81 | "80" 6.747723721 29.94625755 2.976526542 18.63439355 9.955272437 2.871070692 7.908047697 82 | "81" 8.028648134 27.46340936 2.678494903 19.01308293 9.153256302 2.996592027 7.147758571 83 | "82" 5.987304213 27.41131442 2.709766455 18.12145645 10.55279809 2.741626007 7.348252222 84 | "83" 6.94865465 25.78691822 2.827682581 18.45777697 9.452671454 2.720342924 7.396403725 85 | "84" 7.371298063 26.59176315 2.881951981 18.46164212 9.109002619 2.69918695 7.292313893 86 | "85" 6.152259143 28.97388363 2.861728503 17.42120934 9.937376978 2.926358085 7.026069913 87 | "86" 6.971025645 29.77905586 2.246957032 17.33087212 9.401956497 2.974077158 7.243938469 88 | "87" 8.076845237 29.37558012 2.576337903 18.12903218 9.037408763 2.62309522 7.931028548 89 | "88" 8.331049483 26.84027895 2.425871936 17.85904801 10.81411882 2.629485003 7.8426926 90 | "89" 5.870952372 27.64750912 2.699609869 18.34445756 9.883561622 2.383542714 7.295355829 91 | "90" 7.257224788 29.45506325 2.079854473 18.55165296 10.88134734 2.984324609 7.900919241 92 | "91" 7.838623892 27.44410989 4.875696772 19.41770468 10.13486957 1.552253214 7.139197713 93 | "92" 5.759219792 29.87115759 4.771588856 19.91166539 10.97673475 2.093939224 7.272066916 94 | "93" 7.931553974 27.90666051 4.985479701 17.09976526 10.93467364 1.788450114 7.180508525 95 | "94" 6.425555595 30.58079636 4.60747187 19.42863505 9.852475835 1.579892331 7.985552425 96 | "95" 6.015483675 25.2690149 4.192564744 19.25885135 9.587827294 1.333910071 7.321695848 97 | "96" 7.69914912 28.26327575 4.389674216 19.81304523 10.47451101 1.542130715 7.586247189 98 | "97" 6.977485088 28.89913326 4.201805668 17.55115838 10.59530991 1.477074661 7.744972869 99 | "98" 5.515027471 27.65566576 4.144796821 18.5604651 10.96131673 1.561574034 7.589876656 100 | "99" 6.718774072 25.5613872 4.260908895 18.96175282 9.514226606 1.429913491 7.389967247 101 | "100" 5.71413951 25.65169792 4.597587034 18.00840527 9.642150809 1.391718849 7.079658118 102 | "101" 6.198113614 30.59318947 4.113590947 18.18217294 9.985747275 1.282143479 7.533701145 103 | "102" 7.307787677 26.98176133 4.788019614 17.75444073 10.44664262 2.142437297 7.690269845 104 | "103" 6.416752376 25.14595861 4.351955653 19.99634132 10.89978099 2.088022298 7.351471774 105 | "104" 6.559062513 25.72749265 4.767790991 17.7020823 9.171711596 1.678318618 7.015621221 106 | "105" 6.186925417 30.97326578 4.686651733 18.78428263 9.802241344 1.978470826 7.627336054 107 | "106" 8.428503368 27.71123642 4.817998145 18.07368896 10.23489372 1.77331386 7.27871782 108 | "107" 5.965559724 25.32087952 4.771112093 17.33323164 9.313900466 1.926745945 7.499034673 109 | "108" 6.396025508 27.6257377 4.303187957 17.30187428 10.23912682 1.783253844 7.230853544 110 | "109" 7.000499943 25.63787742 4.820256277 18.34124336 10.88719227 1.547329079 7.423978992 111 | "110" 6.543917583 26.86211737 4.94822092 19.98497498 9.537928607 1.530214868 7.109008841 112 | "111" 7.448565118 26.12261657 4.68897906 17.07327913 10.41950036 1.451546791 7.787155226 113 | "112" 5.992008323 29.48528517 4.674676114 17.30827585 10.33565216 1.852362707 7.862799438 114 | "113" 8.147725092 30.25361969 4.205442937 18.21111994 10.86250427 1.265469907 7.764608551 115 | "114" 8.442108113 28.06693931 4.866415406 17.04294427 9.077099209 1.391283444 7.431904122 116 | "115" 7.577757728 26.67892673 4.27702665 19.38963436 10.61398848 2.006028304 7.941713559 117 | "116" 5.792632373 27.00736732 4.890057696 17.23298234 10.40351246 1.415301041 7.780188521 118 | "117" 6.076519894 30.62239201 4.467964057 19.75356813 9.318518737 1.882846129 7.442790334 119 | "118" 7.135864371 25.77989368 4.086331721 18.42657015 9.595171699 1.643162218 7.855196598 120 | "119" 6.957972776 29.6038061 4.075159055 17.97946934 10.60391196 1.707470772 7.097119741 121 | "120" 5.884617388 30.24765427 4.348402848 19.0023999 9.442007855 1.281777917 7.024301479 -------------------------------------------------------------------------------- /data/travelbooks.R: -------------------------------------------------------------------------------- 1 | "travelbooks" <- 2 | structure(list(density = c(0.71, 0.88, 0.83, 1.13, 1.15, 0.91 3 | ), area = c(270.1, 245, 552, 601.4, 928.8, 306.5), type = structure(as.integer(c(1, 4 | 1, 2, 2, 2, 1)), .Label = c("Guide", "Roadmaps"), class = "factor")), .Names = c("density", 5 | "area", "type"), row.names = c("Aird's Guide to Sydney", "Moon's Australia handbook", 6 | "Explore Australia Road Atlas", "Australian Motoring Guide", 7 | "Penguin Touring Atlas", "Canberra - The Guide"), class = "data.frame") -------------------------------------------------------------------------------- /data/usingR.RData: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gastonstat/tutorial-R-web-data/2cdb84b2dc4512d7a33f99afd3ceb8e8a4e63bd0/data/usingR.RData -------------------------------------------------------------------------------- /data/xml_movies_cover.r: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | Good Will Hunting 6 | 7 | Gus 8 | Van Sant 9 | 10 | 1998 11 | drama 12 | 13 | 14 | Y tu mama tambien 15 | 16 | Alfonso 17 | Cuaron 18 | 19 | 2001 20 | drama 21 | 22 | 23 | 24 | 25 | 26 | -------------------------------------------------------------------------------- /header.tex: -------------------------------------------------------------------------------- 1 | 2 | 3 | % define a bunch of colors 4 | \definecolor{gray}{RGB}{110,110,110} 5 | \definecolor{darkgray}{RGB}{100,100,100} 6 | \definecolor{lightgray}{RGB}{200,200,200} 7 | \definecolor{lightgrey}{RGB}{200,200,200} 8 | \definecolor{turquoise}{RGB}{81,193,188} 9 | \definecolor{mamey}{RGB}{255,107,107} 10 | \definecolor{tomato}{RGB}{255,136,136} 11 | \definecolor{mandarina}{RGB}{229,169,25} 12 | \definecolor{lemon}{rgb}{0.81,0.95,0.29} 13 | \definecolor{bluesky}{rgb}{0.71,0.81,0.96} 14 | \definecolor{chiclamino}{RGB}{107,174,214} 15 | \definecolor{violet}{RGB}{133,135,211} 16 | 17 | \definecolor{foreground}{RGB}{81,141,193} 18 | \definecolor{background}{RGB}{246,244,240} 19 | \definecolor{highlight}{RGB}{229,169,25} 20 | \definecolor{lowlight}{RGB}{200,200,200} 21 | 22 | % setting beamer colors 23 | \setbeamercolor{title}{fg=lightgray} 24 | \setbeamercolor{frametitle}{fg=lightgray} 25 | \setbeamercolor{block title}{fg=turquoise} 26 | \setbeamercolor{structure}{fg=turquoise} 27 | \setbeamercolor{titlelike}{fg=title} 28 | \setbeamercolor{subtitle}{fg=turquoise} 29 | \setbeamercolor{institute}{fg=gray} 30 | \setbeamercolor{normal text}{fg=gray,bg=background} 31 | 32 | \setbeamercolor{palette primary}{fg=lightgray} 33 | \setbeamercolor{palette secondary}{fg=lightgray} 34 | \setbeamercolor{palette tertiary}{fg=lightgray} 35 | 36 | \setbeamerfont{itemize/enumerate subbody}{size=\footnotesize} 37 | \setbeamerfont{itemize/enumerate subitem}{size=\footnotesize} 38 | 39 | \hypersetup{ 40 | colorlinks=true, 41 | urlcolor=tomato, 42 | linkcolor=lightgray 43 | } 44 | 45 | % commands 46 | \newcommand{\code}[1]{\texttt{#1}} 47 | \newcommand{\high}[1]{\textcolor{highlight}{#1}} 48 | \newcommand{\low}[1]{\textcolor{lowlight}{#1}} 49 | \newcommand{\highcode}[1]{\textcolor{highlight}{\texttt{#1}}} 50 | 51 | 52 | %\usecolortheme{rose} 53 | \setbeamertemplate{blocks}[rounded] 54 | \setbeamertemplate{footline}[frame number] 55 | \setbeamertemplate{navigation symbols}{} 56 | \setbeamertemplate{frametitle}[default][center] 57 | \useoutertheme{infolines} % add footlines 58 | \setbeamersize{text margin left=25pt,text margin right=25pt} 59 | 60 | 61 | 62 | % to remove empty brackets of \institution 63 | \makeatletter 64 | \setbeamertemplate{footline} 65 | { 66 | \leavevmode% 67 | \hbox{% 68 | \begin{beamercolorbox}[wd=.333333\paperwidth,ht=2.25ex,dp=1ex,center]{author in head/foot}% 69 | \usebeamerfont{author in head/foot}\insertshortauthor%~~\beamer@ifempty{\insertshortinstitute}{}{(\insertshortinstitute)} 70 | \end{beamercolorbox}% 71 | \begin{beamercolorbox}[wd=.333333\paperwidth,ht=2.25ex,dp=1ex,center]{title in head/foot}% 72 | \usebeamerfont{title in head/foot}\insertshorttitle 73 | \end{beamercolorbox}% 74 | \begin{beamercolorbox}[wd=.333333\paperwidth,ht=2.25ex,dp=1ex,right]{date in head/foot}% 75 | \usebeamerfont{date in head/foot}\insertshortdate{}\hspace*{2em} 76 | \insertframenumber{} / \inserttotalframenumber\hspace*{2ex} 77 | \end{beamercolorbox}}% 78 | \vskip0pt% 79 | } 80 | \makeatother 81 | 82 | --------------------------------------------------------------------------------