\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{Icey\_cey}
\pdfinfo{
  /Title (data-visualization-in-r-for-gr5293.pdf)
  /Creator (Cheatography)
  /Author (Icey\_cey)
  /Subject (Data Visualization in R for GR5293 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}{7CA370}
\definecolor{LightBackground}{HTML}{F6F9F6}
\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 Visualization in R for GR5293 Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{Icey\_cey} via \textcolor{DarkBackground}{\uline{cheatography.com/145663/cs/31390/}}}
\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}Icey\_cey \\
  \uline{cheatography.com/icey-cey} \\
  \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 1st April, 2022.\\
   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}{{\bf{Histogram}}(L4)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{hist(x, col = "lightblue", ylim = c(a,b), xlim=c(a,b), xlab = "Lab for x axis", right = TRUE, main="Title for the histogram", breaks = seq(m,n,p))} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{x}}: the vector to visualize \newline {\bf{col=}}: change the color of the histogram \newline {\bf{xlim=/ylim=}}: define the range of x/y axis \newline {\bf{xlab=/ylab=}}: rename the label for x/y axis \newline {\bf{right=TRUE/FALSE}}: "TRUE" stands for the right-closed (left-opened) interval. "FALSE" stands for the right-opened (left-closed) interval \newline {\bf{main=}}: name the title for the histogram \newline {\bf{breaks=}}: set up the value of x axis}  \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}{{\bf{Single Boxplot}}(L5)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{boxplot(x, horizontal=TRUE, log="x")} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{x}}: the vector to visualize \newline {\bf{horizontal=TRUE/FALSE}}: make the boxplot horizontally or vertically \newline {\bf{log=}}: if the x value is in the log scale}  \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}{{\bf{Multiple Boxplot}}(L5)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{ggplot(dataset, aes(x= ,y=)) \newline +geom\_boxplot() \newline +labs() \newline + theme(legend.position = "bottom")} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{dataset}}: the dataset to visualize \newline {\bf{aes(x= ,y=)}}: plot by x \& y \newline {\bf{labs()}}: label the element in the boxplot \newline {\bf{theme(legend.position)}}: assign the position of the legend}  \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}{{\bf{Violin Plot}}(L5)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{ggplot(dataset, aes(x= ,y= )) \newline +geom\_violin() \newline +coord\_flip() \newline +labs() \newline +theme()} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{dataset}}: the dataset to visualize \newline {\bf{aes(x= ,y=)}}: plot by x \& y \newline {\bf{geom\_violin}}: get the violin plot \newline {\bf{coord\_flip()}}: flip the x and y coordinate \newline {\bf{theme()}}: customize the non-data component}  \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}{{\bf{Ridgeline Plot}}(L5)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{ggplot(dataset, aes(x= ,y= ))+ \newline geom\_density\_ridges(fill="blue",alpha= ,scale= )} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{dataset}}: the dataset to visualize \newline {\bf{aes(x= ,y= )}}: plot by x \& y \newline {\bf{geom\_density\_ridges()}}: get the Ridgeline plot \newline {\bf{fill= }}: fill the Ridgeline with specific color \newline {\bf{alpha= }}: set the transparency of the area under the Ridgeline}  \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}{{\bf{Q-Q plot (Quantile-Quantile)}}(L6)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{qqnorm(x) \newline qqline(x, col="red")} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{qqnorm()}}:  produce a normal QQ plot of the values in x \newline {\bf{qqline()}}: add a line to a "theoretical", by default normal, quantile-quantile plot}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.74195 cm} x{3.23505 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{{\bf{Types of data}}(L8)}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Numerical data}} & {\bf{Categorical data}} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\textasciitilde{}Discrete & \textasciitilde{}Nominal - no fixed category order \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\textasciitilde{}Continuous & \textasciitilde{}Ordinal - fixed category order \tn 
% Row Count 6 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{{\bf{Tidy Data}}(L10)}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{pivot\_longer(data, cols = , names\_to = ,values\_to = )}}: move selected columns' name to "name" column, and move values to a single "value" column} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{pivot\_wider(data, names\_from = , values\_from = )}}: use the name from a column as the column name, and use the value from select column to be the value in the final Dataframe} \tn 
% Row Count 7 (+ 4)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{row names\_to\_column()}}: add the column name to the rowname in the Dataframe} \tn 
% Row Count 9 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{{\bf{Parallel Coordinates}}(L13)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{ggparcoord(dataset, columns = ,scale = ,alphaLines= ,splineFactor= ,groupColumn =  )} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{dataset}}: the dataset to visualize \newline {\bf{columns= }}: select columns of data that will include in the plot \newline {\bf{scale= }}: method to scale the data (default is "std") \newline {\bf{alphaLines= }}: value of alpha scaler for the lines of the parcoord plot or a column name of the data \newline {\bf{splineFactor= }}: logical or numeric operator indicating whether spline interpolation should be used \newline {\bf{groupColumn =  }}: a single variable to group (color) by}  \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}{{\bf{ Biplot }}(L14)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{pca\textless{}- prcomp(dataset) \newline biplot(pca) \newline  \newline draw\_biplot(dataset)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{prcomp()}}: perform a principal components analysis on the given data matrix  \newline {\bf{draw\_biplot()}}:perform PCA on a data frame and draw a biplot}  \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}{{\bf{Cleveland dot plot}}(L15)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{ggplot(dataset, aes(x = , y = fct\_reorder())) \newline +geom\_point(color = ) \newline +theme\_linedraw()} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{fct\_reorder()}}: reorder factor levels by sorting along the variables \newline {\bf{geom\_point()}}: create scatterplots \newline {\bf{theme\_linedraw()}}: add black lines of various widths on white backgrounds}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.55618 cm} x{1.51041 cm} x{1.51041 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{{\bf{ Multivariate Data}}(L15)}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Stacked bar chart}} & {\bf{Grouped bar chart}} & {\bf{Mosaic plot (two variables)}} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
ggplot(data, aes(x= , fill = \seqsplit{))+geom\_bar()+scale\_fill\_manual()} & ggplot(data, aes(x= ,fill= \seqsplit{))+geom\_bar(position} = \seqsplit{"dodge")+scale\_fill\_manual()} & mosaic(x\textasciitilde{}y, direction = c("v","h"),highlighting\_fill= ) \tn 
% Row Count 9 (+ 6)
% Row 2
\SetRowColor{LightBackground}
\textasciitilde{}plot x with different fill in different color & \textasciitilde{}bar plot grouped x filling with different color & \textasciitilde{}direction stands for the direction of different variables. \seqsplit{highlighting\_fill} used for distinguish different group \tn 
% Row Count 18 (+ 9)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Alluvial diagram(L16)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{ggplot(dataset, aes(axis1 = , axis2 = , y = )) + \newline   geom\_alluvium(color = ) + \newline   geom\_stratum() + \newline   geom\_text(stat = "stratum", aes(label = \seqsplit{paste(after\_stat(stratum)}, "\textbackslash{}n", after\_stat(count)))) + \newline   \seqsplit{scale\_x\_discrete(limits} = )} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{geom\_alluvium()}}: plot both the lodes themselves, using geom\_lode(), and the flows between them, using geom\_flow() \newline {\bf{geom\_stratum()}}: plot rectangles for these strata of a provided width \newline {\bf{geom\_text()}}: add only text to the plot \newline {\bf{scale\_x\_discrete()}}: set the values for discrete x scale aesthetics}  \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}{Heatmap(L17)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{ggplot(dataset, aes(x= , y= )) +  \newline   geom\_tile(aes(fill = ), color = ) +  \newline   coord\_fixed()} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{geom\_rect()}}: use the locations of the four corners (xmin, xmax, ymin and ymax) \newline {\bf{geom\_tile()}}: use the center of the tile and its size (x, y, width, height) \newline {\bf{geom\_raster()}}:   a high performance special case for when all the tiles are the same size \newline {\bf{coord\_fixed()}}:  a fixed scale coordinate system forces a specified ratio between data units on the axes}  \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}{{\bf{ Time series}}(L20)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{ggplot(dataset, aes(x= ,y= ,color= )) \newline +geom\_line()+ \newline geom\_smooth(method= ,span= )} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{ggplot(dataset, aes(x= ,y= ,color= ))}}: plot multiple time series by different colors \newline {\bf{geom\_smooth()}}: add a smooth line according to the data \newline {\bf{method= }}: smoothing method (function) to use \newline {\bf{span= }}: control the amount of smoothing for the default loess smoother}  \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}{{\bf{ Factor in R}}}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{fct\_recode()}}: change the name of the factor} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{fct\_inorder()}}: display by each factor in the original order} \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{fct\_relevel(x, "G1", "G2", after = 3)}}: move the factor "G1", "G2" after the third item in factor x} \tn 
% Row Count 6 (+ 3)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{fct\_reorder(color, count, .desc=TRUE)}}: order by decreasing frequency count} \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{fct\_infreq()}}: display by number of observations with each level (default is decreasing order of frequency)} \tn 
% Row Count 11 (+ 3)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{fct\_rev()}}: reverse the order of factor levels} \tn 
% Row Count 12 (+ 1)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{fct\_explicit\_na()}}: turn NAs into a real factor level} \tn 
% Row Count 14 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}