\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{jbjoker}
\pdfinfo{
  /Title (data-analysis-with-r.pdf)
  /Creator (Cheatography)
  /Author (jbjoker)
  /Subject (Data Analysis with 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}{0D12A3}
\definecolor{LightBackground}{HTML}{F7F7FC}
\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 Analysis with R Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{jbjoker} via \textcolor{DarkBackground}{\uline{cheatography.com/181883/cs/37815/}}}
\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}jbjoker \\
  \uline{cheatography.com/jbjoker} \\
  \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 30th May, 2023.\\
   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{1.09494 cm} x{3.88206 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Phases of Data Analysis}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Ask}} & Define the problem you are trying to solve. \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
{\bf{Prepare}} & What data do I need to solve this problem? Do I have access to obtain it? \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
{\bf{Process}} & Clean the data of errors and inaccuracies. \tn 
% Row Count 7 (+ 2)
% Row 3
\SetRowColor{white}
{\bf{Analyze}} & Perform calculations to tell a data story. Exploratory Analysis, Statistical modelling \tn 
% Row Count 10 (+ 3)
% Row 4
\SetRowColor{LightBackground}
{\bf{Share}} & Clear visuals of the data and solution. This includes the reproducible code. \tn 
% Row Count 13 (+ 3)
% Row 5
\SetRowColor{white}
{\bf{Act}} & Provide recommendations based on data. \tn 
% Row Count 15 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.23965 cm} x{2.73735 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{File Manipulation}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Get Working Directory}} & getwd() \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
{\bf{Set Working Directory}} & setwd() \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
{\bf{See Directory Contents}} & dir() \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
{\bf{Create Folder}} & dir.create("tFolder") \tn 
% Row Count 7 (+ 1)
% Row 4
\SetRowColor{LightBackground}
{\bf{Create File}} & \seqsplit{file.create("test.csv")} \tn 
% Row Count 9 (+ 2)
% Row 5
\SetRowColor{white}
{\bf{Copy File}} & file.copy("test.csv", "tFolder") \tn 
% Row Count 11 (+ 2)
% Row 6
\SetRowColor{LightBackground}
{\bf{Edit File}} & myedit(test.R) \tn 
% Row Count 12 (+ 1)
% Row 7
\SetRowColor{white}
{\bf{Delete File}} & unlink("test.csv") \tn 
% Row Count 13 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{3.53367 cm} x{1.44333 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Structure \& Dimensions}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Structure}} & str(data) \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
{\bf{Get \# of Rows \& Columns}} & dim(data) \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
{\bf{Return \# of Rows}} & nrow(data) \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
{\bf{Return \# of Cols}} & ncol(data) \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
{\bf{Return 1st 6 Rows}} & head(data) \tn 
% Row Count 5 (+ 1)
% Row 5
\SetRowColor{white}
{\bf{Get Class Type}} & \seqsplit{class(data)} \tn 
% Row Count 6 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.89126 cm} x{3.08574 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Importing Data}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Web Scraping}} & con = \seqsplit{url("http://google.com")} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
 & htmlCode = readlines(con) \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
 & close(con) \tn 
% Row Count 5 (+ 1)
% Row 3
\SetRowColor{white}
{\bf{Remote File}} & fileUrl \textless{}- \seqsplit{"https://website.com/data.csv"} \tn 
% Row Count 7 (+ 2)
% Row 4
\SetRowColor{LightBackground}
 & download.file(fileUrl, destfile = "./myData.csv", method = "curl") \tn 
% Row Count 10 (+ 3)
% Row 5
\SetRowColor{white}
{\bf{Import Data as Table}} & inData \textless{}- read.table("data.csv", sep = " ", header = TRUE) \tn 
% Row Count 13 (+ 3)
\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}{Applying Functions}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Apply a function over an array}} & {\bf{apply}}(data,Margin,Function) \#1=Rows 2=Cols \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
{\bf{Apply a function to each element of list, vector, or DF and return a list}} & {\bf{lapply}}(data, Function) \tn 
% Row Count 7 (+ 4)
% Row 2
\SetRowColor{LightBackground}
{\bf{Same as lapply, but returns a vector instead}} & {\bf{sapply}}(data, Function) \tn 
% Row Count 10 (+ 3)
% Row 3
\SetRowColor{white}
{\bf{Apply a function to a subset specified by the FactorList}} & {\bf{tapply}}(vector, factorList, Function) \tn 
% Row Count 13 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.9908 cm} x{2.9862 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Clean \& Test Data}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Check for NAs}} & colSums(is.na(data)) \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
{\bf{Logical NA Test}} & \seqsplit{all(colSums(is.na(data))} == 0) \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
{\bf{Trim Whitespace}} & trimws(charVector) \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
{\bf{Verify Data Type}} & class(data)  {\bf{or}} str(data) \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
{\bf{Find Specific}} & test{[}test\$someCol \%in\% \tn 
% Row Count 10 (+ 2)
% Row 5
\SetRowColor{white}
 & c("abcdefg", "hello"),{]} \tn 
% Row Count 11 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.18988 cm} x{2.78712 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{String Manipulation}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Uppercase}} & \seqsplit{toupper(names(charVector))} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
{\bf{Lowercase}} & \seqsplit{tolower(names(charVector))} \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
{\bf{String Split}} & \seqsplit{strsplit(names(charVector)}, "\textbackslash{}\textbackslash{}.") \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
{\bf{Find \& Replace 1st}} & sub("\_", "", names(charVector)) \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
{\bf{Find \& Replace All}} & gsub("\_", "", names(charVector)) \tn 
% Row Count 10 (+ 2)
% Row 5
\SetRowColor{white}
{\bf{Get Location of Value}} & grep("F", LETTERS) \tn 
% Row Count 12 (+ 2)
% Row 6
\SetRowColor{LightBackground}
{\bf{Get Value from location}} & grep("F", LETTERS, value=TRUE) \tn 
% Row Count 14 (+ 2)
% Row 7
\SetRowColor{white}
{\bf{Table Count Instances}} & table(grepl("F", LETTERS)) \tn 
% Row Count 16 (+ 2)
% Row 8
\SetRowColor{LightBackground}
{\bf{Get Substring}} & substr(charData, 1, 7) \tn 
% Row Count 17 (+ 1)
% Row 9
\SetRowColor{white}
{\bf{Paste with Space}} & paste("Test", "Message") \tn 
% Row Count 19 (+ 2)
% Row 10
\SetRowColor{LightBackground}
{\bf{Paste Without Space}} & paste0("Test", "Message") \tn 
% Row Count 21 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.63781 cm} x{2.33919 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Statistics}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Statistical Summary}} & summary(data) \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
{\bf{Mean}} & mean(data) \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
{\bf{Standard Deviation}} & sd(vector) \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
{\bf{Variance}} & var(vector) \tn 
% Row Count 6 (+ 1)
% Row 4
\SetRowColor{LightBackground}
{\bf{Range}} & range(vector) \tn 
% Row Count 7 (+ 1)
% Row 5
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{} \tn 
% Row Count 7 (+ 0)
% Row 6
\SetRowColor{LightBackground}
{\bf{Normal Distribution}} & rnorm(n, mean, sd) \tn 
% Row Count 9 (+ 2)
% Row 7
\SetRowColor{white}
{\bf{Binomial Distribution}} & rbinom(n, size, prob) \tn 
% Row Count 11 (+ 2)
% Row 8
\SetRowColor{LightBackground}
{\bf{Poisson Distribution}} & rpois(n, size) \tn 
% Row Count 13 (+ 2)
% Row 9
\SetRowColor{white}
{\bf{Uniform Distribution}} & runif(n, min=0, max=10) \tn 
% Row Count 15 (+ 2)
% Row 10
\SetRowColor{LightBackground}
{\bf{Exponential Distribution}} & rexp(n) \tn 
% Row Count 17 (+ 2)
% Row 11
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{} \tn 
% Row Count 17 (+ 0)
% Row 12
\SetRowColor{LightBackground}
{\bf{K-Means Clustering}} & kmeans(data, centers = 3) \tn 
% Row Count 19 (+ 2)
% Row 13
\SetRowColor{white}
{\bf{Hierarchical Clustering}} & \seqsplit{hclust(dist(data))} \tn 
% Row Count 21 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}