\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{BarplotNorm} \pdfinfo{ /Title (r-commands.pdf) /Creator (Cheatography) /Author (BarplotNorm) /Subject (R Commands 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}{084DCD} \definecolor{LightBackground}{HTML}{EFF3FB} \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 Commands Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{BarplotNorm} via \textcolor{DarkBackground}{\uline{cheatography.com/203294/cs/43288/}}} \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}BarplotNorm \\ \uline{cheatography.com/barplotnorm} \\ \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 31st January, 2025.\\ 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{tabularx}{17.67cm}{x{2.6352 cm} x{5.4351 cm} x{3.6234 cm} x{4.7763 cm} } \SetRowColor{DarkBackground} \mymulticolumn{4}{x{17.67cm}}{\bf\textcolor{white}{Basic Math}} \tn % Row 0 \SetRowColor{LightBackground} \seqsplit{`exp(x)`} & Exponential & \seqsplit{`sum(x)`} & Sum \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \seqsplit{`log(x)`} & Natural log & \seqsplit{`cumsum(x)`} & Cumulative Sum \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \seqsplit{`max(x)`} & Largest element & \seqsplit{`ceil(x)`} & Round up \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \seqsplit{`min(x)`} & Smallest element & \seqsplit{`floor(x)`} & Round down \tn % Row Count 8 (+ 2) % Row 4 \SetRowColor{LightBackground} `x \%\% y` & Modulo & & \tn % Row Count 10 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}----} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Control Flow}} \tn % Row 0 \SetRowColor{LightBackground} `for (variable in sequence) \{...\}` & for-loop. If the loop body contains only a single line, the curly brackets can be omitted. \tn % Row Count 5 (+ 5) % Row 1 \SetRowColor{white} `while (condition) \{...\}` & while-loop \tn % Row Count 7 (+ 2) % Row 2 \SetRowColor{LightBackground} `if (i \textgreater{} 5) \{`\{\{nl\}\}` ...`\{\{nl\}\} `else \{`\{\{nl\}\}` ...`\{\{nl\}\}`\}` & if-else-block \tn % Row Count 11 (+ 4) % Row 3 \SetRowColor{white} `foo = function(arg1, arg2, ...) \{`\{\{nl\}\}` ...`\{\{nl\}\}` return(var)`\{\{nl\}\}`\}` & function \tn % Row Count 15 (+ 4) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{6.5626 cm} x{10.7074 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Vectors}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Creating Vectors}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} `c(2, 4, 6)` & Join elements into a vector \tn % Row Count 3 (+ 2) % Row 2 \SetRowColor{LightBackground} `2:6` & An integer sequence (end inclusive!) \tn % Row Count 5 (+ 2) % Row 3 \SetRowColor{white} `seq(2,3, by=0.5)` & Complex sequence (s. np.linspace) \tn % Row Count 7 (+ 2) % Row 4 \SetRowColor{LightBackground} `rep(1:2, 3)` & Repeat vector \tn % Row Count 8 (+ 1) % Row 5 \SetRowColor{white} `rep(1:2, 3:4)` & Repeat each element \tn % Row Count 9 (+ 1) % Row 6 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Functions}}} \tn % Row Count 10 (+ 1) % Row 7 \SetRowColor{white} `sort(x)` & Return x sorted. \tn % Row Count 11 (+ 1) % Row 8 \SetRowColor{LightBackground} `rev(x)` & Return x reversed. \tn % Row Count 12 (+ 1) % Row 9 \SetRowColor{white} `unique(x)` & See unique values. \tn % Row Count 13 (+ 1) % Row 10 \SetRowColor{LightBackground} `length(x)` & Length of x. \tn % Row Count 14 (+ 1) % Row 11 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Selecting Vector Elements}}} \tn % Row Count 15 (+ 1) % Row 12 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\emph{By Position}}} \tn % Row Count 16 (+ 1) % Row 13 \SetRowColor{white} `x{[}4{]}` & The fourth element \tn % Row Count 17 (+ 1) % Row 14 \SetRowColor{LightBackground} `x{[}-4{]}` & All but the fourth. \tn % Row Count 18 (+ 1) % Row 15 \SetRowColor{white} `x{[}2:4{]}` & Elements two to four \tn % Row Count 19 (+ 1) % Row 16 \SetRowColor{LightBackground} `x{[}-(2:4){]}` & All elements except 2 to four \tn % Row Count 21 (+ 2) % Row 17 \SetRowColor{white} `x{[}c(1, 5){]}` & Elements one and five. \tn % Row Count 22 (+ 1) % Row 18 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\emph{By Value}}} \tn % Row Count 23 (+ 1) % Row 19 \SetRowColor{white} `x{[}x == 10{]}` & All elements equal to 10 \tn % Row Count 24 (+ 1) % Row 20 \SetRowColor{LightBackground} `x{[}x \textless{} 10{]}` & All elements less than 10. \tn % Row Count 26 (+ 2) % Row 21 \SetRowColor{white} `x{[}x \%in\% c(1, 2, 5){]}` & Elements in the given set. \tn % Row Count 28 (+ 2) % Row 22 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\emph{Named Vectors}}} \tn % Row Count 29 (+ 1) % Row 23 \SetRowColor{white} `x{[}'apple'{]}` & Element with name 'apple'. \tn % Row Count 31 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{7.7715 cm} x{9.4985 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Tables}} \tn % Row 0 \SetRowColor{LightBackground} `table(data)` & get absolute frequencies of values \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} `as.numeric(tab); as.vector(tab)` & Extract values and their absolute frequencies from table \tn % Row Count 5 (+ 3) % Row 2 \SetRowColor{LightBackground} \seqsplit{`tab/length(data)`} & Compute relative frequencies \tn % Row Count 7 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{9.1531 cm} x{8.1169 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Matrices}} \tn % Row 0 \SetRowColor{LightBackground} `m = matrix(x, nrow = 3, ncol = 3)` & Create a matrix from vector `x` \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} `t(m)` & transpose \tn % Row Count 3 (+ 1) % Row 2 \SetRowColor{LightBackground} `m \%*\% n` & Matrix multiplication \tn % Row Count 5 (+ 2) % Row 3 \SetRowColor{white} `solve(m, n)` & Find x in `m * x = n` \tn % Row Count 7 (+ 2) % Row 4 \SetRowColor{LightBackground} `det(m)` & Determinant \tn % Row Count 8 (+ 1) % Row 5 \SetRowColor{white} `eigen(m)` & Find eigen vectors and values \tn % Row Count 10 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Data sets}} \tn % Row 0 \SetRowColor{LightBackground} \seqsplit{Data=data.frame(price=c(11},20,14,15), number=c(40,50,60,20)) & Create a data set \tn % Row Count 3 (+ 3) % Row 1 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Interacting with data sets}}} \tn % Row Count 4 (+ 1) % Row 2 \SetRowColor{LightBackground} `col\_1 = data\$col\_1\_name` & Access column data \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} `Data{[}1,2{]}; Data{[},2{]}; Data{[}{[}1{]}{]}` & Access data with index notation \tn % Row Count 8 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{I/O}}} \tn % Row Count 9 (+ 1) % Row 5 \SetRowColor{white} `data = read.csv("file.csv", header=FALSE, sep="")` & Read csv (function arguments similar to that used in pandas) \tn % Row Count 12 (+ 3) % Row 6 \SetRowColor{LightBackground} `write.csv(data, "data.csv", row.names=FALSE, sep=" ")` & Write data set as csv \tn % Row Count 15 (+ 3) % Row 7 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Filter}}} \tn % Row Count 16 (+ 1) % Row 8 \SetRowColor{LightBackground} `df{[}df\$kids == "Jack",{]}` & Filter data frame \tn % Row Count 18 (+ 2) % Row 9 \SetRowColor{white} `subset(df, kids== "John" \& Grade == 1.3)` & Filter multiple columns \tn % Row Count 21 (+ 3) % Row 10 \SetRowColor{LightBackground} `subset(df, kids \%in\% c("Jack", "John"))` & Filter a column with multiple values \tn % Row Count 24 (+ 3) % Row 11 \SetRowColor{white} `unique(housing{[}, c("State", "region"){]})` & Extract unique rows \tn % Row Count 27 (+ 3) % Row 12 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Sort}}} \tn % Row Count 28 (+ 1) % Row 13 \SetRowColor{white} `housing{[}order(housing\$Home.Value), {]}` & Order data frame in ascending order \tn % Row Count 30 (+ 2) \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Data sets (cont)}} \tn % Row 14 \SetRowColor{LightBackground} `housing{[}order(housing\$Home.Value, decreasing = TRUE), {]}` & order data frame in descending order \tn % Row Count 3 (+ 3) % Row 15 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Meta}}} \tn % Row Count 4 (+ 1) % Row 16 \SetRowColor{LightBackground} `dim(df)` & Check the dimensions of a data frame \tn % Row Count 6 (+ 2) % Row 17 \SetRowColor{white} `colnames(d)` & Return the column names \tn % Row Count 8 (+ 2) % Row 18 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Manipulate data}}} \tn % Row Count 9 (+ 1) % Row 19 \SetRowColor{white} `Data\_Frame\_New \textless{}- Data\_Frame{[}-c(1), -c(1){]}` & Remove columns and/or rows from data frame \tn % Row Count 12 (+ 3) % Row 20 \SetRowColor{LightBackground} `rbdind(df\_1, df\_2)` & Combine data frames vertically \tn % Row Count 14 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.9804 cm} x{8.2896 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{I/O}} \tn % Row 0 \SetRowColor{LightBackground} `write(data, "mydata.dat")` & Write data as binary. \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \seqsplit{`scan("mydata.dat")`} & Read binary data. \tn % Row Count 3 (+ 1) % Row 2 \SetRowColor{LightBackground} `getcwd()` & Current working directory \tn % Row Count 5 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Random Numbers}} \tn % Row 0 \SetRowColor{LightBackground} `sample(1:3,prob=c(1/6,1/3,1/2),replace=TRUE,20)` & Draw 20 balls, labeled from 1 to 3, from box with replacement. \tn % Row Count 4 (+ 4) % Row 1 \SetRowColor{white} `r\textless{}distr. ID\textgreater{}`(n, params) & Draw `n` numbers from distribution `\textless{}distr. ID\textgreater{}` with parameters `params` \tn % Row Count 8 (+ 4) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\emph{(see {\bf{Distributions in R}} for more details)}}} \tn % Row Count 9 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{5.8718 cm} x{11.3982 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Characteristics of data sequences}} \tn % Row 0 \SetRowColor{LightBackground} `mean(x)` & Arithmetic mean of the data sequence \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} `var(x)` & Variance \tn % Row Count 3 (+ 1) % Row 2 \SetRowColor{LightBackground} `median(x)` & Median \tn % Row Count 4 (+ 1) % Row 3 \SetRowColor{white} `quantile(x, type=7)` & Quantile. `type=7` is the default computation algorithm, i.e. the function returns the value at position `k=1+p(n-1)`, if this is an integer. Otherwise, R computes a weighted mean of the two neighboring integers \tn % Row Count 13 (+ 9) % Row 4 \SetRowColor{LightBackground} `quantile(x, type=1)` & General inverse function of the ECDF (smallest p-quantile). Largetst p-quantile can be obtained indirectly by slightly increasing p \tn % Row Count 19 (+ 6) % Row 5 \SetRowColor{white} `summary(x)` & Overview of important measures \tn % Row Count 21 (+ 2) % Row 6 \SetRowColor{LightBackground} `cov(x,y)` & Covariance \tn % Row Count 22 (+ 1) % Row 7 \SetRowColor{white} `cor(x,y)` & Correlation \tn % Row Count 23 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{7.0807 cm} x{10.1893 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Distributions in R}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{General usage}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} `d\textless{}distr. ID\textgreater{}(params)` & density function \tn % Row Count 3 (+ 2) % Row 2 \SetRowColor{LightBackground} `q\textless{}distr. ID\textgreater{}(params)` & quantile function. Always computes the smallest quantile \tn % Row Count 6 (+ 3) % Row 3 \SetRowColor{white} `p\textless{}distr. ID\textgreater{}(params)` & cumulative distribution function \tn % Row Count 8 (+ 2) % Row 4 \SetRowColor{LightBackground} `r\textless{}distr. ID\textgreater{}(params)` & random variate generation \tn % Row Count 10 (+ 2) % Row 5 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Distributions}}} \tn % Row Count 11 (+ 1) % Row 6 \SetRowColor{LightBackground} `dbinom(x, size=p, prob=p)` & Binomial \tn % Row Count 13 (+ 2) % Row 7 \SetRowColor{white} `dchisq(x, df, ncp=0)` & Chi-squared \tn % Row Count 15 (+ 2) % Row 8 \SetRowColor{LightBackground} `dexp(x, rate=1)` & Exponential \tn % Row Count 17 (+ 2) % Row 9 \SetRowColor{white} `dgamma(x, shape=r, rate=l)` & Gamma \tn % Row Count 19 (+ 2) % Row 10 \SetRowColor{LightBackground} `dgeom(x, prob=p)` & Geometric \tn % Row Count 21 (+ 2) % Row 11 \SetRowColor{white} `dnbinom(x, size, prob)` & Negative binomial \tn % Row Count 23 (+ 2) % Row 12 \SetRowColor{LightBackground} `dnorm(x, mean=0, sd=1)` & Normal \tn % Row Count 25 (+ 2) % Row 13 \SetRowColor{white} `dpois(x, lambda)` & Poisson \tn % Row Count 27 (+ 2) % Row 14 \SetRowColor{LightBackground} `dt(x, df, ncp)` & t-distribution \tn % Row Count 28 (+ 1) % Row 15 \SetRowColor{white} `dunif(x, min=0, max=1)` & Uniform \tn % Row Count 30 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Plotting}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Basic plots}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} `plot(data)` & Plot quick overview. \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} `plot(x, y, xlab="mu", ylab="Power", type="l", col="red", ylim=c(0,1), lwd=1.5)` & Plot data with custom style options \tn % Row Count 6 (+ 4) % Row 3 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Lines and curves}}} \tn % Row Count 7 (+ 1) % Row 4 \SetRowColor{LightBackground} `abline(a,b,col="red")` & Add a red line with intercept `a` and slope `b` to the plot. \tn % Row Count 10 (+ 3) % Row 5 \SetRowColor{white} `abline(v=a,col="red")` & add vertical line at `x=a` \tn % Row Count 12 (+ 2) % Row 6 \SetRowColor{LightBackground} `abline(h=b,col="red")` & add horizontal line at `y=b` \tn % Row Count 14 (+ 2) % Row 7 \SetRowColor{white} `lines(x, y, col="green", lwd=1.5)` & Add a generic line \tn % Row Count 16 (+ 2) % Row 8 \SetRowColor{LightBackground} `curve(sin,-pi,pi,add=TRUE)` & Draw a curve of a function over the specified interval \tn % Row Count 19 (+ 3) % Row 9 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Data visualization}}} \tn % Row Count 20 (+ 1) % Row 10 \SetRowColor{LightBackground} `plot.ecdf(data)` & Plot ECDF. \tn % Row Count 21 (+ 1) % Row 11 \SetRowColor{white} `barplot(x, main="Title", xlab="x label")` & Annotated barplot of absolute frequencies \tn % Row Count 24 (+ 3) % Row 12 \SetRowColor{LightBackground} `hist(data, prob=TRUE, breaks=30)` & Histogram of relative frequencies (30 bins). \tn % Row Count 27 (+ 3) % Row 13 \SetRowColor{white} `rug(data)` & 1D-plot \tn % Row Count 28 (+ 1) % Row 14 \SetRowColor{LightBackground} `boxplot(data1, data2, ... ,range=1.5)` & Plot boxplots of one or more data sequences in one window. `range` determines the extend of the whiskers. Default `range=1.5`, i.e. 1.5 x IQR \tn % Row Count 36 (+ 8) \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Plotting (cont)}} \tn % Row 15 \SetRowColor{LightBackground} `qqnorm(x)` & QQ-Plot against standard normal distribution \tn % Row Count 3 (+ 3) % Row 16 \SetRowColor{white} `qqPlot(x, dist="unif",...)` & QQ-Plot against any R-standard distribution. Additional arguments such as `df`, `ncp` can also be specified. \tn % Row Count 9 (+ 6) % Row 17 \SetRowColor{LightBackground} `legend(x,y, legend=c("n=10"),col=c("red"), lty=1, cex=0.8)` & Add legend to plot as position `(x,y)` \tn % Row Count 12 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Statistical hypothesis testing}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{One-Sample tests}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} `t.test(x,mu=mu0,alt="less", \seqsplit{conf.level=1-alpha)`} & Performs one and two sample t-tests on vectors of data. \tn % Row Count 4 (+ 3) % Row 2 \SetRowColor{LightBackground} `power.t.test(n = 100, delta=0.1, sd=2, sig.level=0.1, type="one.sample", alt="one.sided")` & Compute the power of the one- or two- sample t test, or determine parameters to obtain a target power. \tn % Row Count 10 (+ 6) % Row 3 \SetRowColor{white} `binom.test(sum(x),n,p0,alt="greater", \seqsplit{conf.level=1-alpha)`} & Performs an exact test of a simple null hypothesis about the probability of success in a Bernoulli experiment. It might happen that the decision based on the p-value differs from that of the confidence interval. Choose the decision based on the p-value in such cases. \tn % Row Count 24 (+ 14) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Two-Sample tests}}} \tn % Row Count 25 (+ 1) % Row 5 \SetRowColor{white} `t.test(shoes\$A,shoes\$B,paired=FALSE, var.equal=TRUE)` & Example for an unpaired sample t-test \tn % Row Count 28 (+ 3) % Row 6 \SetRowColor{LightBackground} `var.test(x,y,conf.level=1-alpha)` & Performs an F test to compare the variances of two samples from normal populations. \tn % Row Count 33 (+ 5) \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Statistical hypothesis testing (cont)}} \tn % Row 7 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{GOF tests}}} \tn % Row Count 1 (+ 1) % Row 8 \SetRowColor{white} `shapiro.test(x)` & Performs the Shapiro-Wilk test of normality. \tn % Row Count 4 (+ 3) % Row 9 \SetRowColor{LightBackground} \seqsplit{`chisq.test(table(x)}, p=p\_0)` & Test for distribution with probabilities `p\_0`. If `p` is not specified, R tests for a uniform distribution \tn % Row Count 10 (+ 6) % Row 10 \SetRowColor{white} \seqsplit{`chisq.test(table(x)}, p=p\_0, \seqsplit{simulate.p.value=TRUE)`} & Do not use Chi\textasciicircum{}2\textasciicircum{}-approximation to calculate the p-value \tn % Row Count 13 (+ 3) % Row 11 \SetRowColor{LightBackground} \seqsplit{`pwr.chisq.test(w=ncp}, df=s-1, sig.level=alpha, power=0.9)` & Determine the number of samples needed to reach the desired power at the given significance level \tn % Row Count 18 (+ 5) % Row 12 \SetRowColor{white} `ks.test(x, "pnorm", 0, 1)` & One-sample Kolmogorov-Smirnov test against hypothetical distribution \tn % Row Count 22 (+ 4) % Row 13 \SetRowColor{LightBackground} `lillie.test(x)` & Lilliefors \seqsplit{(Kolmogorov-Smirnov)} test for the composite hypothesis of normality \tn % Row Count 26 (+ 4) % Row 14 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Tests of independence}}} \tn % Row Count 27 (+ 1) % Row 15 \SetRowColor{LightBackground} `chisq.test(M)` & Chi\textasciicircum{}2\textasciicircum{}-test of independence. M hast to be a matrix! (contingency table) \tn % Row Count 31 (+ 4) \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Statistical hypothesis testing (cont)}} \tn % Row 16 \SetRowColor{LightBackground} `fisher.test(M)` & Exact test of Fisher. If the table entries are too large, use \seqsplit{`simulate.p.value=TRUE`} \tn % Row Count 5 (+ 5) % Row 17 \SetRowColor{white} `runs.test(x)` & Runs test of independence. `x` hast to be a factor (use `as.factor()` if necessary) \tn % Row Count 10 (+ 5) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{5.0083 cm} x{12.2617 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Runs Test of Randomness}} \tn % Row 0 \SetRowColor{LightBackground} `rle(x)` & Compute the lengths and values of runs of equal values in a vector . \tn % Row Count 3 (+ 3) % Row 1 \SetRowColor{white} \seqsplit{`rle(x)\$lengths`} & Vector containing the length of each run. \tn % Row Count 5 (+ 2) % Row 2 \SetRowColor{LightBackground} \seqsplit{`rle(x)\$values`} & Vector of the same length as lengths with the corresponding values. \tn % Row Count 8 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Optimization}} \tn % Row 0 \SetRowColor{LightBackground} `nlm(E2,0.5)` & Carries out a minimization of the function f using a Newton-type algorithm. May not give all solutions. The function must be vectorized \tn % Row Count 7 (+ 7) % Row 1 \SetRowColor{white} `E2vec=Vectorize(E2, \seqsplit{vectorize.args=c("n"))`} & vectorize a function. `vectorize.args`: explicitly state arguments to be vectorized. \tn % Row Count 12 (+ 5) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Distribution Fit}}} \tn % Row Count 13 (+ 1) % Row 3 \SetRowColor{white} `fitdistr(x, "Poisson")` & Maximum-likelihood fitting of univariate distributions, allowing parameters to be held fixed if desired. (`library(MASS)`) \tn % Row Count 20 (+ 7) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Regression}}} \tn % Row Count 21 (+ 1) % Row 5 \SetRowColor{white} `reg=lm(x\textasciitilde{}t)` & Fit a linear function `x=a+bt` \tn % Row Count 23 (+ 2) % Row 6 \SetRowColor{LightBackground} `summary(reg)` & Obtain further information about regression result \{\{nl\}\}{\bf{Important fields:}}\{\{nl\}\}- Residual standard error: sd of residuals (with normalization {\bf{`n-2`}}) \{\{nl\}\}-t value: Test null hypothesis "estimate is 0" with assumption of a normally distributed random mechanism\{\{nl\}\}-multiple R-squared: squared corr. coef. Null hypothesis r\textasciicircum{}2\textasciicircum{}=0 is tested with F-statistic \tn % Row Count 42 (+ 19) \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Optimization (cont)}} \tn % Row 7 \SetRowColor{LightBackground} `reg=lm(x \textasciitilde{} t+ I(t\textasciicircum{}2))` & Fit a polynomial function. `I()`inhibits R from interpreting `t\textasciicircum{}2` as a formula \tn % Row Count 4 (+ 4) % Row 8 \SetRowColor{white} `form=x \textasciitilde{} \seqsplit{a/(1+exp(-b*(t-c)))`} \{\{nl\}\} `reg=nls(form, data=USPop, start=c(a=400,b=0.02,c=2000))` & perform non-linear least-squares regression \tn % Row Count 9 (+ 5) % Row 9 \SetRowColor{LightBackground} `plot(t,predict(reg))` & Plot regression result \tn % Row Count 11 (+ 2) % Row 10 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Root finding}}} \tn % Row Count 12 (+ 1) % Row 11 \SetRowColor{LightBackground} `res = uniroot(func, c(0,10))` & Searches interval for a root of the function `func`. `res\$root` and `res\$f.root` give the location of the root and the value of the function \tn % Row Count 19 (+ 7) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{2.5905 cm} x{14.6795 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Help}} \tn % Row 0 \SetRowColor{LightBackground} \seqsplit{`?sqrt`} & Display documentation of the command `sqrt`` \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \seqsplit{`?'\%\%'`} & use quotation marks for special characters \tn % Row Count 4 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{17.67cm}{x{8.635 cm} x{8.635 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{17.67cm}}{\bf\textcolor{white}{Miscellaneous}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Printing}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} `print("Text")` & Default print \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} `sprintf("Formatted \%s: \%.3f", object, mean)` & Formatted print \tn % Row Count 5 (+ 3) % Row 3 \SetRowColor{white} `(x=3)` & enclose an R command with brackets to directly print the result \tn % Row Count 9 (+ 4) % Row 4 \SetRowColor{LightBackground} `edit(x)` & Invoke text editor on R object \tn % Row Count 11 (+ 2) % Row 5 \SetRowColor{white} \mymulticolumn{2}{x{17.67cm}}{{\bf{Libraries}}} \tn % Row Count 12 (+ 1) % Row 6 \SetRowColor{LightBackground} `library(MASS)` & Load package MASS \tn % Row Count 13 (+ 1) % Row 7 \SetRowColor{white} `uniroot(f, interval)` & find 1D root \tn % Row Count 15 (+ 2) % Row 8 \SetRowColor{LightBackground} \mymulticolumn{2}{x{17.67cm}}{{\bf{Step functions}}} \tn % Row Count 16 (+ 1) % Row 9 \SetRowColor{white} `stepfunc(x,y)` & Given the vectors (x\textasciitilde{}1\textasciitilde{}, ...,x\textasciitilde{}n\textasciitilde{}) and (y\textasciitilde{}0\textasciitilde{},...,y\textasciitilde{}n\textasciitilde{}) (one value more!), returns an interpolating 'step' function \tn % Row Count 22 (+ 6) % Row 10 \SetRowColor{LightBackground} `knots(x)` & returns jump positions of stepfunction \tn % Row Count 24 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \end{document}