\documentclass[10pt,a4paper]{article}

% Packages
\usepackage{fancyhdr}           % For header and footer
\usepackage{multicol}           % Allows multicols in tables
\usepackage{tabularx}           % Intelligent column widths
\usepackage{tabulary}           % Used in header and footer
\usepackage{hhline}             % Border under tables
\usepackage{graphicx}           % For images
\usepackage{xcolor}             % For hex colours
%\usepackage[utf8x]{inputenc}    % For unicode character support
\usepackage[T1]{fontenc}        % Without this we get weird character replacements
\usepackage{colortbl}           % For coloured tables
\usepackage{setspace}           % For line height
\usepackage{lastpage}           % Needed for total page number
\usepackage{seqsplit}           % Splits long words.
%\usepackage{opensans}          % Can't make this work so far. Shame. Would be lovely.
\usepackage[normalem]{ulem}     % For underlining links
% Most of the following are not required for the majority
% of cheat sheets but are needed for some symbol support.
\usepackage{amsmath}            % Symbols
\usepackage{MnSymbol}           % Symbols
\usepackage{wasysym}            % Symbols
%\usepackage[english,german,french,spanish,italian]{babel}              % Languages

% Document Info
\author{mitcht}
\pdfinfo{
  /Title (r-data-wrangling.pdf)
  /Creator (Cheatography)
  /Author (mitcht)
  /Subject (R data wrangling Cheat Sheet)
}

% Lengths and widths
\addtolength{\textwidth}{6cm}
\addtolength{\textheight}{-1cm}
\addtolength{\hoffset}{-3cm}
\addtolength{\voffset}{-2cm}
\setlength{\tabcolsep}{0.2cm} % Space between columns
\setlength{\headsep}{-12pt} % Reduce space between header and content
\setlength{\headheight}{85pt} % If less, LaTeX automatically increases it
\renewcommand{\footrulewidth}{0pt} % Remove footer line
\renewcommand{\headrulewidth}{0pt} % Remove header line
\renewcommand{\seqinsert}{\ifmmode\allowbreak\else\-\fi} % Hyphens in seqsplit
% This two commands together give roughly
% the right line height in the tables
\renewcommand{\arraystretch}{1.3}
\onehalfspacing

% Commands
\newcommand{\SetRowColor}[1]{\noalign{\gdef\RowColorName{#1}}\rowcolor{\RowColorName}} % Shortcut for row colour
\newcommand{\mymulticolumn}[3]{\multicolumn{#1}{>{\columncolor{\RowColorName}}#2}{#3}} % For coloured multi-cols
\newcolumntype{x}[1]{>{\raggedright}p{#1}} % New column types for ragged-right paragraph columns
\newcommand{\tn}{\tabularnewline} % Required as custom column type in use

% Font and Colours
\definecolor{HeadBackground}{HTML}{333333}
\definecolor{FootBackground}{HTML}{666666}
\definecolor{TextColor}{HTML}{333333}
\definecolor{DarkBackground}{HTML}{80060A}
\definecolor{LightBackground}{HTML}{FBF7F7}
\renewcommand{\familydefault}{\sfdefault}
\color{TextColor}

% Header and Footer
\pagestyle{fancy}
\fancyhead{} % Set header to blank
\fancyfoot{} % Set footer to blank
\fancyhead[L]{
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{C}
    \SetRowColor{DarkBackground}
    \vspace{-7pt}
    {\parbox{\dimexpr\textwidth-2\fboxsep\relax}{\noindent
        \hspace*{-6pt}\includegraphics[width=5.8cm]{/web/www.cheatography.com/public/images/cheatography_logo.pdf}}
    }
\end{tabulary}
\columnbreak
\begin{tabulary}{11cm}{L}
    \vspace{-2pt}\large{\bf{\textcolor{DarkBackground}{\textrm{R data wrangling Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{mitcht} via \textcolor{DarkBackground}{\uline{cheatography.com/50563/cs/14132/}}}
\end{tabulary}
\end{multicols}}

\fancyfoot[L]{ \footnotesize
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{LL}
  \SetRowColor{FootBackground}
  \mymulticolumn{2}{p{5.377cm}}{\bf\textcolor{white}{Cheatographer}}  \\
  \vspace{-2pt}mitcht \\
  \uline{cheatography.com/mitcht} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Not Yet Published.\\
   Updated 29th December, 2017.\\
   Page {\thepage} of \pageref{LastPage}.
\end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Sponsor}}  \\
  \SetRowColor{white}
  \vspace{-5pt}
  %\includegraphics[width=48px,height=48px]{dave.jpeg}
  Measure your website readability!\\
  www.readability-score.com
\end{tabulary}
\end{multicols}}




\begin{document}
\raggedright
\raggedcolumns

% Set font size to small. Switch to any value
% from this page to resize cheat sheet text:
% www.emerson.emory.edu/services/latex/latex_169.html
\footnotesize % Small font.

\begin{multicols*}{2}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Read / Write .csv}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{read.csv(file.csv) \newline write.csv(df, file.csv)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.04 cm} x{4.96 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Meta Data}}  \tn
% Row 0
\SetRowColor{LightBackground}
`summary(df)` & `str(df)` \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`ls()` & `dir()` \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`length(df)` & `dim(df)` \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
`class (df)` & `nrow(df) / ncol(df)` \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{`colnames(df)`} \tn 
% Row Count 5 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Arrange}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{rename(df, varold = varnew) \newline select(df, var1, var2) \newline arrange(df, var) / arrange(df, desc(var))} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Filter}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{filter(df, var1 \textgreater{} 10) / df{[}df\$var1 \textgreater{} 10, {]} \newline slice(df, 10:15) / df{[}10:15, {]} \# select rows \newline distinct(df, {\emph{var}}) \newline sample\_frac(df, 0.5, replace = FALSE) / sample\_n(df, 10, replace = FALSE) \newline select(df, col1, col2, ...) / df{[}, c('col1', 'col2'){]} \newline select(df, {\emph{contains() starts\_with() ends\_with()}}) \newline na.omit(df)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.92 cm} x{4.08 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Useful Functions}}  \tn
% Row 0
\SetRowColor{LightBackground}
`min() / max()` & `first() / last()` \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`n() / n\_distinct()` & `mean() / median()` \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
`lead() / lag()` & `var() / sd()` \tn 
% Row Count 4 (+ 1)
% Row 3
\SetRowColor{white}
`between(a, b)` & `cumsum()` \tn 
% Row Count 5 (+ 1)
% Row 4
\SetRowColor{LightBackground}
`is.na()` & `\%in\%` \tn 
% Row Count 6 (+ 1)
% Row 5
\SetRowColor{white}
`if\_else() / case\_when()` & `coalesce()` \tn 
% Row Count 8 (+ 2)
% Row 6
\SetRowColor{LightBackground}
`na\_if()` & `sum(!is.na())` \tn 
% Row Count 9 (+ 1)
% Row 7
\SetRowColor{white}
`quantile(x, probs=)` & `seq(1, 10)` \tn 
% Row Count 11 (+ 2)
% Row 8
\SetRowColor{LightBackground}
`rep(c(1,2,3), 2)` & `is.na() / is.null() / is.numeric()` \tn 
% Row Count 13 (+ 2)
% Row 9
\SetRowColor{white}
`as.character() / as.numeric() ...` & `replace(x, list, values)` \tn 
% Row Count 15 (+ 2)
% Row 10
\SetRowColor{LightBackground}
`round(x, n)` & `mod()` \tn 
% Row Count 16 (+ 1)
% Row 11
\SetRowColor{white}
`abs()` & `corr(x) / corr(x, y)` \tn 
% Row Count 18 (+ 2)
% Row 12
\SetRowColor{LightBackground}
`weighted.mean(x, w)` & `paste(vect, sep) /paste0()` \tn 
% Row Count 20 (+ 2)
% Row 13
\SetRowColor{white}
`substr(x, 1, 3)` & `grep(pat, repl, x)` \tn 
% Row Count 21 (+ 1)
% Row 14
\SetRowColor{LightBackground}
`tolower() / toupper()` & `nchar(x)` \tn 
% Row Count 23 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Write Functions}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{function\_name \textless{}- function(x, y) \{ \newline     if (statement) \{ \newline         do \newline     \} elif (statement) \{ \newline         do \newline     \} \newline     for (year in 201:2015) \{ \newline         do \newline     \} \newline     return(result) \newline \}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Applying Functions}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{mutate\_each(df, funs({\emph{sum}})) \newline summarise\_each(df, funs({\emph{sum}})) \newline apply(x, index, fun) \newline lapply(x, fun) / sapply(x, fun)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Summarise}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{group\_by(df, var) \%\textgreater{}\% \newline     summarise(avg = mean(val))  \newline     count(var, {\emph{wt = weight}}) \newline table(df\$var) \newline aggregate(x, by, fun)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Join}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{left\_join(df1, df2, by = "var") / right\_join(df1, df2, by = "var") \newline inner\_join(df1, df2, by = "var") / full\_join(df1, df2, by = "var") \newline anti\_join(df1, df2, by = "var") / semi\_join(df1, df2, by = "var")} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Method Chaining}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{df = df \%\textgreater{}\% \newline     select(var1, var2) \%\textgreater{}\% \newline     mutate(newvar = var1 + var2)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{New Variable / Column}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{df\$newvar = df\$var1 + df\$var2 \newline mutate(df, newvar = var1 + var2) \newline transmute(df, newvar = var1 + var2) \# drop orig cols} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Reshape Data}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{gather(df, 'var', 'val') \# columns into rows \newline spread(df, var, val) \# rows into columns \newline unite(df, col1, col2, sep) \# sev cols into 1 \newline bind\_rows(df1, df2) / bind\_cols(df1, df2) / rbind(...) / cbind(..) \newline melt() / cast() / recast() / reshape()} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


% That's all folks
\end{multicols*}

\end{document}