\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{xeonkai}
\pdfinfo{
  /Title (data-management-in-r.pdf)
  /Creator (Cheatography)
  /Author (xeonkai)
  /Subject (Data management in R 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}{EF5252}
\definecolor{LightBackground}{HTML}{FEF4F4}
\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{Data management in R Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{xeonkai} via \textcolor{DarkBackground}{\uline{cheatography.com/31513/cs/9676/}}}
\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}xeonkai \\
  \uline{cheatography.com/xeonkai} \\
  \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 8th November, 2016.\\
   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*}{3}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Manipulating dataframes}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Adding new columns} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`mydata \textless{}- transform(mydata, sumx = x1 + x2, meanx = (x1 + x2)/2)`} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`total \textless{}- cbind(A,B)` - each object to have same no. of rows and sorted in same order} \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`merge(dfA, dfB, by = c("ID","Country")`} \tn 
% Row Count 6 (+ 1)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{Adding new rows} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`total \textless{}- rbind(A, B)` - each object to have same variables} \tn 
% Row Count 9 (+ 3)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Recoding variables} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`leadership \textless{}- within(leadership, \{ agecat \textless{}- NA  agecat{[}age \textgreater{} 75{]} \textless{}- "Elder"  agecat{[}age \textgreater{}= 55 \& age \textless{}=75{]} \textless{}- "Middle Aged"  agecat{[}age \textless{} 55{]} \textless{}- "Young"\})`} \tn 
% Row Count 14 (+ 5)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}Other recoding functions: `car` package - `recode()`, `doBy` package - `recodevar()`, `cut()` in R} \tn 
% Row Count 17 (+ 3)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Renaming variables} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`reshape` package - `rename()`} \tn 
% Row Count 19 (+ 2)
% Row 7
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`rename(dataframe, c(oldname="newname", oldname="newname",...)`} \tn 
% Row Count 21 (+ 2)
% Row 8
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`names()` - `names(leadership){[}6:8{]} \textless{}- c("item1","item2","item3")`} \tn 
% Row Count 23 (+ 2)
% Row 9
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{Missing values} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`is.na()`, `na.rm=TRUE`, `na.omit()` - deletes any row with missing data} \tn 
% Row Count 26 (+ 3)
% Row 10
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Date values} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`as.Date(x, "input\_format")`} \tn 
% Row Count 28 (+ 2)
% Row 11
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}Default format: yyyy-mm-dd} \tn 
% Row Count 29 (+ 1)
% Row 12
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`Sys.Date()`, `date()`, `difftime(date1, date2, units="weeks")`} \tn 
% Row Count 31 (+ 2)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Manipulating dataframes (cont)}}  \tn
% Row 13
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}Converting character to dates: `help(as.Date)`, `help(strftime)`} \tn 
% Row Count 2 (+ 2)
% Row 14
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}Formatting dates and time: `help(ISOdatetime)`} \tn 
% Row Count 3 (+ 1)
% Row 15
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`lubridate` and `fcalendar` package} \tn 
% Row Count 4 (+ 1)
% Row 16
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Sorting data} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`order()`: default ascending, prepend sorting variable with `-` for descending} \tn 
% Row Count 7 (+ 3)
% Row 17
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}e.g. `df2 \textless{}- df{[}order(df\$gender, -df\$age),{]}`} \tn 
% Row Count 8 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{p{0.54924 cm} x{3.06659 cm} x{0.96117 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Date formats}}  \tn
% Row 0
\SetRowColor{LightBackground}
`\%d` & Day as a number (0-31) & 01-31 \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`\%a` & Abbreviated weekday & Mon \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`\%A` & Unabbreviated weekday & Monday \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
`\%m` & Month (00-12) & 00-12 \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
`\%b` & Abbreviated month & Jan \tn 
% Row Count 5 (+ 1)
% Row 5
\SetRowColor{white}
`\%B` & Unabbreviated month & January \tn 
% Row Count 6 (+ 1)
% Row 6
\SetRowColor{LightBackground}
`\%y` & 2-digit year & 07 \tn 
% Row Count 7 (+ 1)
% Row 7
\SetRowColor{white}
`\%Y` & 4-digit year & 2007 \tn 
% Row Count 8 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Type conversions}}  \tn
% Row 0
\SetRowColor{LightBackground}
`is.numeric()` & `as.numeric()` \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`is.character()` & `as.character()` \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`is.vector()` & `as.vector()` \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
`is.matrix()` & `as.matrix()` \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
`is.data.frame()` & `as.data.frame()` \tn 
% Row Count 5 (+ 1)
% Row 5
\SetRowColor{white}
`is.factor()` & `as.factor()` \tn 
% Row Count 6 (+ 1)
% Row 6
\SetRowColor{LightBackground}
`is.logical()` & `as.logical()` \tn 
% Row Count 7 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Subsetting datasets}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Selecting variables} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`new \textless{}- df{[}, c(6:10){]}`} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`new \textless{}- df{[}c("q1","q2","q3"){]}`} \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`myvars \textless{}- paste("q", 1:3, sep="")`} \tn 
% Row Count 4 (+ 1)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`new \textless{}- df{[}myvars{]}`} \tn 
% Row Count 5 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Excluding variables} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`myvars \textless{}- names(leadership) \%in\% c("q1","q2")`} \tn 
% Row Count 7 (+ 2)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`new \textless{}- df{[}!myvars{]}`} \tn 
% Row Count 8 (+ 1)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`new \textless{}- df{[}c(-1,-2){]}`} \tn 
% Row Count 9 (+ 1)
% Row 7
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`df\$q1 \textless{}- NULL`} \tn 
% Row Count 10 (+ 1)
% Row 8
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Selecting observations} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`new \textless{}- df{[}1:3,{]}`} \tn 
% Row Count 12 (+ 2)
% Row 9
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`new \textless{}- df{[}which(df\$q1=="M" \& df\$q2 \textgreater{}30),{]}`} \tn 
% Row Count 13 (+ 1)
% Row 10
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Random Samples} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`mysample \textless{}- df{[}sample(1:nrow(df), 3, replace=FALSE),{]}`} \tn 
% Row Count 16 (+ 3)
% Row 11
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{} \tn 
\mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}`sampling` and `survey` package} \tn 
% Row Count 17 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`subset()` function \newline e.g.  \newline `new \textless{}- subset(df, age \textgreater{}=35 | age \textless{} 24, select = c(q1, q2, q3))` \newline `new \textless{}- subset(df, gender == "M" \& age \textgreater{}25, select = gender:q3)`}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{SQL in R}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{`sqldf` package \newline % Row Count 1 (+ 1)
`library(sqldf)` \newline % Row Count 2 (+ 1)
`new \textless{}- sqldf("select * from mtcars where carb=1 order by mpg", row.names=TRUE)` \newline % Row Count 4 (+ 2)
`sqldf("select avg(mpg) as avg\_mpg, avg(disp) as avg\_disp, gear from mtcars where cyl in (4,6) group by gear")`% Row Count 7 (+ 3)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.14011 cm} x{2.83689 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Mathematical functions}}  \tn
% Row 0
\SetRowColor{LightBackground}
`abs(x)` & Absolute value \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`sqrt(x)` & Square root. Same as `25\textasciicircum{}(0.5)`. \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
`ceiling(x)` & Smallest integer not less than x \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
`floor(x)` & Largest integer not greater than x \tn 
% Row Count 7 (+ 2)
% Row 4
\SetRowColor{LightBackground}
`trunc(x)` & Integer formed by truncating values in `x` towards 0 \tn 
% Row Count 10 (+ 3)
% Row 5
\SetRowColor{white}
`round(x, digits=n)` & Round `x` to the specified number of decimal places \tn 
% Row Count 13 (+ 3)
% Row 6
\SetRowColor{LightBackground}
`signif(x, digits=n)` & Round `x` to the specified number of significant digits \tn 
% Row Count 16 (+ 3)
% Row 7
\SetRowColor{white}
`cos(x), sin(x), tan(x)` & Cosine, sine, and tangent \tn 
% Row Count 18 (+ 2)
% Row 8
\SetRowColor{LightBackground}
`acos(x), asin(x), atan(x)` & Arc-cosine, arc-sine and arc-tangent \tn 
% Row Count 20 (+ 2)
% Row 9
\SetRowColor{white}
`cosh(x), sinh(x), tanh(x)` & Hyperbolic cosine, sine, and tangent \tn 
% Row Count 22 (+ 2)
% Row 10
\SetRowColor{LightBackground}
`acosh(x), asinh(x), atanh(x)` & Hyperbolic arc-cosine, arc-sine, and arc-tangent \tn 
% Row Count 25 (+ 3)
% Row 11
\SetRowColor{white}
`log(x, base=n)` & Logarithm of `x` to the base `n` \tn 
% Row Count 27 (+ 2)
% Row 12
\SetRowColor{LightBackground}
`log(x)` & Natural logarithm \tn 
% Row Count 28 (+ 1)
% Row 13
\SetRowColor{white}
`log10(x)` & Common logarithm \tn 
% Row Count 29 (+ 1)
% Row 14
\SetRowColor{LightBackground}
`exp(x)` & Exponential function \tn 
% Row Count 30 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.33919 cm} x{2.63781 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Statistical functions}}  \tn
% Row 0
\SetRowColor{LightBackground}
`mean(x)` & Mean \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`median(x)` & Median \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`sd(x)` & Standard deviation \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
`var(x)` & Variance \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
`mad(x)` & Mean absolute deviation \tn 
% Row Count 6 (+ 2)
% Row 5
\SetRowColor{white}
`quantile(x, probs)` & Quantiles where `x` is the numeric vector of quantiles and `probs` is a numeric vector with probabilities in {[}0,1{]} \tn 
% Row Count 12 (+ 6)
% Row 6
\SetRowColor{LightBackground}
 & `y \textless{}- quantile(x, c(.3,.84))` \tn 
% Row Count 14 (+ 2)
% Row 7
\SetRowColor{white}
`range(x)` & Range \tn 
% Row Count 15 (+ 1)
% Row 8
\SetRowColor{LightBackground}
 & `diff(range(x))` returns difference between extreme values \tn 
% Row Count 18 (+ 3)
% Row 9
\SetRowColor{white}
`sum(x)` & Sum \tn 
% Row Count 19 (+ 1)
% Row 10
\SetRowColor{LightBackground}
`diff(x, lag=n)` & Lagged differences, with `lag` indicating which lag to use. Default lag is 1. \tn 
% Row Count 23 (+ 4)
% Row 11
\SetRowColor{white}
`min(x)` & Minimum \tn 
% Row Count 24 (+ 1)
% Row 12
\SetRowColor{LightBackground}
`max(x)` & Maximum \tn 
% Row Count 25 (+ 1)
% Row 13
\SetRowColor{white}
`scale(x, center=TRUE, scale=TRUE)` & Column center (`center=TRUE`)  or standardize (`center=TRUE, scale=TRUE`) data object `x`, i.e. to a mean of 0 and std of 1 \tn 
% Row Count 31 (+ 6)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Trimmed mean - dropping top and lowest 5\% and missing values \newline `y \textless{}- mean(x, trim=0.05, na.rm=TRUE)`}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.44333 cm} x{3.53367 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Probability functions}}  \tn
% Row 0
\SetRowColor{LightBackground}
`beta` & Beta \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`binom` & Binomial \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`cauchy` & Cauchy \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
`chisq` & Chi-squared (noncentral) \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
`exp` & Exponential \tn 
% Row Count 5 (+ 1)
% Row 5
\SetRowColor{white}
`f` & F \tn 
% Row Count 6 (+ 1)
% Row 6
\SetRowColor{LightBackground}
`gamma` & Gamma \tn 
% Row Count 7 (+ 1)
% Row 7
\SetRowColor{white}
`geom` & Geometric \tn 
% Row Count 8 (+ 1)
% Row 8
\SetRowColor{LightBackground}
`hyper` & Hypergeometric \tn 
% Row Count 9 (+ 1)
% Row 9
\SetRowColor{white}
`lnorm` & Lognormal \tn 
% Row Count 10 (+ 1)
% Row 10
\SetRowColor{LightBackground}
`logis` & Logistic \tn 
% Row Count 11 (+ 1)
% Row 11
\SetRowColor{white}
`multinom` & Multinomial \tn 
% Row Count 12 (+ 1)
% Row 12
\SetRowColor{LightBackground}
`nbinom` & Negative binomial \tn 
% Row Count 13 (+ 1)
% Row 13
\SetRowColor{white}
`norm` & Normal \tn 
% Row Count 14 (+ 1)
% Row 14
\SetRowColor{LightBackground}
`pois` & Poisson \tn 
% Row Count 15 (+ 1)
% Row 15
\SetRowColor{white}
`signrank` & Wilcoxon Signed Rank \tn 
% Row Count 16 (+ 1)
% Row 16
\SetRowColor{LightBackground}
`t` & T \tn 
% Row Count 17 (+ 1)
% Row 17
\SetRowColor{white}
`unif` & Uniform \tn 
% Row Count 18 (+ 1)
% Row 18
\SetRowColor{LightBackground}
`weibull` & Weibull \tn 
% Row Count 19 (+ 1)
% Row 19
\SetRowColor{white}
`wilcox` & Wilcoxon Rank Sum \tn 
% Row Count 20 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{General form of probability function: `{[}dpqr{]}distribution\_abbreviation()` \newline `d` = density \newline `p` = distribution function \newline `q` = quantile function \newline `r` = random generation (random deviates)}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Character functions}}  \tn
% Row 0
\SetRowColor{LightBackground}
`nchar(x)` & Counts the no. of characters  of `x` \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
`substr(x, start, stop)` & Extract or replace substrings in a character vector \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
 & `x \textless{}- "abcdef"` \tn 
% Row Count 6 (+ 1)
% Row 3
\SetRowColor{white}
 & `substr(x, 2, 4)` returns `"bcd"` \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
 & `substr(x, 2, 4) \textless{}- "22222"` produces `"a222ef` \tn 
% Row Count 11 (+ 3)
% Row 5
\SetRowColor{white}
`grep(pattern, x, ignore.case=FALSE, fixed=FALSE)` & Search for pattern in `x`. `fixed=FALSE` - `pattern` is regex. `fixed=TRUE` - `pattern` is text string. Returns matching indices. \tn 
% Row Count 18 (+ 7)
% Row 6
\SetRowColor{LightBackground}
`sub(pattern, replacement, x, ignore.case=FALSE, fixed=FALSE)` & Find `pattern` in `x` and substitute with `replacement` text \tn 
% Row Count 22 (+ 4)
% Row 7
\SetRowColor{white}
`strsplit(x, split, fixed=FALSE)` & Split the elements of `x` at `split` \tn 
% Row Count 24 (+ 2)
% Row 8
\SetRowColor{LightBackground}
 & `y \textless{}- strsplit("abc", "")` returns 1-component, 3-element list containing `"a" "b" "c"`. \tn 
% Row Count 29 (+ 5)
% Row 9
\SetRowColor{white}
 & `unlist(y){[}2{]}` and `sapply(y, "{[}", 2)` both return "b". \tn 
% Row Count 32 (+ 3)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Character functions (cont)}}  \tn
% Row 10
\SetRowColor{LightBackground}
`paste(..., sep="")` & Concatenate strings after using `sep` string to separate them \tn 
% Row Count 4 (+ 4)
% Row 11
\SetRowColor{white}
 & `paste("x", 1:3, sep="M")` returns `c("xM1","xM2","xM3")` \tn 
% Row Count 7 (+ 3)
% Row 12
\SetRowColor{LightBackground}
`toupper(x)` & Uppercase \tn 
% Row Count 8 (+ 1)
% Row 13
\SetRowColor{white}
`tolower(x)` & Lowercase \tn 
% Row Count 9 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.43873 cm} x{2.53827 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Other useful functions}}  \tn
% Row 0
\SetRowColor{LightBackground}
`length(x)` & Length of object x` \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`seq(from, to, by)` & Generate a sequence \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`rep(x, n)` & Repeat `x n` times \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
`cut(x, n)` & Divide continuous variable `x` into factor with `n` levels. `ordered\_result = TRUE` creates an ordered factor. \tn 
% Row Count 9 (+ 6)
% Row 4
\SetRowColor{LightBackground}
`pretty(x, n)` & Create pretty breakpoints. Divide a continuous variable `x` into `n` intervals, by selecting `n+1` equally spaced rounded values. Often used in plotting. \tn 
% Row Count 17 (+ 8)
% Row 5
\SetRowColor{white}
`cat(..., file="myfile", append=FALSE)` & Concatenates the objects in ... and outputs them to the screen or to a file \tn 
% Row Count 21 (+ 4)
% Row 6
\SetRowColor{LightBackground}
`apply(x, MARGIN, FUN, ...)` & Apply function to data objects \tn 
% Row Count 23 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Escape characters:  \newline `\textbackslash{}n` - new lines \newline `\textbackslash{}t` - tabs \newline `\textbackslash{}'` - single quote \newline `\textbackslash{}b` - backspace}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{p{0.79632 cm} x{4.18068 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Control flow}}  \tn
% Row 0
\SetRowColor{LightBackground}
FOR & `for (var in seq) statement` \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
WHILE & `while (cond) statement` \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{IF-ELSE} & `if (cond) statement` \tn 
% Row Count 4 (+ 2)
% Row 3
\SetRowColor{white}
 & `if (cond) statement1 else statement2` \tn 
% Row Count 6 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{IFELSE} & `ifelse(cond, statement1, statement2)` \tn 
% Row Count 8 (+ 2)
% Row 5
\SetRowColor{white}
\seqsplit{SWITCH} & `switch(expr, ...)` \tn 
% Row Count 9 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{`statement` - single R statement or compound statement enclosed in \{\} and separated by ; \newline `cond` - expression that resolves to `TRUE` or `FALSE` \newline `expr` - statement that evaluates to number or character string \newline `seq` - sequence of numbers or character strings}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Example for `switch`}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{feelings \textless{}- c("sad","afraid") \newline for (i in feelings) \newline   print( \newline      switch(i, \newline          happy = "I am glad you are happy", \newline          afraid = "There is nothing to fear", \newline          sad = "Cheer up", \newline          angry = "Calm down now" \newline             ) \newline         )} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.84149 cm} x{3.13551 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Aggregation and restructuring}}  \tn
% Row 0
\SetRowColor{LightBackground}
`t()` & Transpose \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`aggregate(x, by, FUN)` & Aggregate (`by` variables must be a list) \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
 & `new \textless{}- aggregate(mtcars, by=list(Group.cyl=cyl, Group.gears=gear), FUN=mean, na.rm=TRUE)` \tn 
% Row Count 7 (+ 4)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{`Reshape` package}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/xeonkai_1478598360_Capture.JPG}}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}