\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{林漪 (kevin123)}
\pdfinfo{
  /Title (r-me-for-final-exam.pdf)
  /Creator (Cheatography)
  /Author (林漪 (kevin123))
  /Subject (R  me for final exam 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}{A3A3A3}
\definecolor{LightBackground}{HTML}{F3F3F3}
\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  me for final exam Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{林漪 (kevin123)} via \textcolor{DarkBackground}{\uline{cheatography.com/148191/cs/32330/}}}
\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}林漪 (kevin123) \\
  \uline{cheatography.com/kevin123} \\
  \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 5th June, 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{1.69218 cm} x{3.28482 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{四则运算}}  \tn
% Row 0
\SetRowColor{LightBackground}
`\textasciicircum{}` & 幂运算 \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`\%\%` & 取余运算 \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`\%/\%` & 整除运算 \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
`round()` & 四舍五入取整数 \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
`floor()` & 向下取整 \tn 
% Row Count 5 (+ 1)
% Row 5
\SetRowColor{white}
`ceiling()` & 向上取整 \tn 
% Row Count 6 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{`round(3.14159,2) `  \# \seqsplit{四舍五入到两位小数} \newline \#\# {[}1{]} 3.14}  \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}{\seqsplit{逻辑运算应该注意的点}}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{判断两个浮点型对象是否完全相同，不能直接采用==和identical()，而应该用all}.equal()% Row Count 3 (+ 3)
} \tn 
\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}{字符型数据的处理}}  \tn
% Row 0
\SetRowColor{LightBackground}
`nchar()` & \seqsplit{计算字符串的长度} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{`toupper()`，`tolower()`} & 转换大小写 \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
`substr(x, start, stop)` & \seqsplit{从x中取出start到stop的子串} \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
`substring(x, start)` & \seqsplit{从x中取出start到末尾的子串} \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
`gsub(pattern, replacement, x)` & \seqsplit{x中与pattern对应的字符替换成replacement} \tn 
% Row Count 11 (+ 3)
% Row 5
\SetRowColor{white}
`paste()` & \seqsplit{连接两个字符型对象，默认用空格连接} \tn 
% Row Count 14 (+ 3)
% Row 6
\SetRowColor{LightBackground}
`strsplit()` & \seqsplit{拆分两个及以上的字符型对象，默认一个个} \tn 
% Row Count 17 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{`substr(x, start, \seqsplit{stop)`还可以代替特定位置} \newline `nchar("R统计软件", type = "bytes")`  \# 以字节为单位 \newline \#\# {[}1{]} 9 \newline ` nchar("code monkey\textbackslash{}t")` \newline \#\# {[}1{]} 12（空格算，\textbackslash{}t算一个） \newline ` paste（）` 中的` sep` \seqsplit{控制用什么连接，要直接连接用'} ' \newline `strsplit()`中的` split` \seqsplit{指示用什么字符拆分}}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{p{0.74655 cm} x{4.23045 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{日期时间类型数据}}  \tn
% Row 0
\SetRowColor{LightBackground}
Date & \seqsplit{一般用整数保存，数值为从1970-1-1经过的天数。} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{POSIXct} & \seqsplit{从1970年1月1日零时到该日期时间的时间间隔秒数} \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{POSIXlt} & \seqsplit{一个包含年、月、日、星期、时、分、秒等成分的列表} \tn 
% Row Count 7 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\seqsplit{`difftime(as.Date("2021-9-10")}, as.Date("2020-9-10"), units = 'days')` \newline \#\# Time difference of 31.33333 days \newline `difftime(as.Date("2021-9-10"), as.Date("2020-9-10"), units = 'days')` \newline \#\# Time difference of 365 days}  \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}{\seqsplit{从字符串生成日期数据}}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/kevin123_1654427936_.png}}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{3.13551 cm} x{1.84149 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{因子类变量}}  \tn
% Row 0
\SetRowColor{LightBackground}
`factor(c("男", "女"))` & 男 女 Levels: 男 女 \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
`factor(LETTERS{[}1:3{]}, ordered = TRUE)` & A B C Levels: A \textless{} B \textless{} C \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
`factor(LETTERS{[}1:3{]}, ordered = TRUE, levels = c("C","B","A"))` & A B C Levels: C \textless{} B \textless{} A \tn 
% Row Count 7 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\seqsplit{因子的levels()（水平值）属性是一个映射，} 把整数值1,2,映射成这些水平值，因子在保存时会保存成整数值1,2,等与水平值对应的编号。}  \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}{R的数据类型}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{整型(int)：如1L \newline % Row Count 1 (+ 1)
\seqsplit{数值型/双整型(numeric}, double)：如1,1.1 \newline % Row Count 2 (+ 1)
\seqsplit{逻辑型(logical)：只有两个值TRUE和FALSE}, 缺失时为NA。 \newline % Row Count 4 (+ 2)
\seqsplit{字符型(character)：存储一小段文本，用双引号包住，其中单个元素称之为字符串(string)，如"Hello"}, "1" \newline % Row Count 7 (+ 3)
\seqsplit{复数类型(complex)：如1+3i} \newline % Row Count 8 (+ 1)
日期时间类型(Date, POSIXct, POSIXlt)：如Sys.time() \newline % Row Count 10 (+ 2)
因子类型(factor)  \newline % Row Count 11 (+ 1)
特殊符号：NA(Not Avaiable), NaN(Not a Number), Inf(infinite), NULL% Row Count 13 (+ 2)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{typeof()返回数据类型} \newline is.foo()判断是否属于某种类型foo，是返回TRUE，否返回FALSE \newline as.foo()强制转换成foo类型}  \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}{矩阵}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{matrix()函数把矩阵元素以向量的形式输入，用} nrow 和 ncol \seqsplit{规定行数和列数，向量元素填入的缺省次序是按列填入，用} byrow=TRUE \seqsplit{选项可转换成按行填入。} \newline % Row Count 4 (+ 4)
rbind()，cbind() \seqsplit{，diag()，dim()，dimnames()}  \newline % Row Count 5 (+ 1)
\seqsplit{对两个同形状的矩阵，`} * \seqsplit{`表示两个矩阵对应元素相乘，`/} \seqsplit{`表示两个矩阵对应元素相除} \newline % Row Count 8 (+ 3)
`\%*\%` \seqsplit{矩阵乘法，t()转置，det()行列式，solve()逆} \newline % Row Count 10 (+ 2)
solve(A, b) \seqsplit{返回的是线性方程组} Ax=b的解 \newline % Row Count 12 (+ 2)
\seqsplit{矩阵内积自己记一下} \newline % Row Count 13 (+ 1)
apply(A, i, FUN) 把矩阵 A \seqsplit{的每一列分别输入到函数} FUN \seqsplit{中，得到对应于每一维度的结果，其中} i = 1 \seqsplit{表示对行进行运算，} i = 2 \seqsplit{表示对列进行运算。} \newline % Row Count 17 (+ 4)
\seqsplit{矩阵的下标和子集与向量类似。}% Row Count 18 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{p{0.4977 cm} p{0.4977 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{数据框}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{} \tn 
% Row Count 0 (+ 0)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\seqsplit{各列之间允许有不同的类型，同一列中的元素保持相同类型。} \newline 数据框之中有增加行列，命名，访问，with（）的用法，稍后再来搞}  \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}{列表}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{不同于之前，列表(list)是用来保存不同类型的数据。} \newline % Row Count 2 (+ 2)
可通过 names() 来命名 \newline % Row Count 3 (+ 1)
`names(dist) \textless{}- c("a", "b", "c")` \newline % Row Count 4 (+ 1)
\seqsplit{也可在一开始定义的时候就命名好} \newline % Row Count 5 (+ 1)
`dist1 \textless{}- list(a = "exponential", b = 7, c = FALSE)` \newline % Row Count 7 (+ 2)
单个列表元素必须用两重方括号格式访问如`dist{[}{[}1{]}{]}` \newline % Row Count 9 (+ 2)
\seqsplit{使用单重方括号对列表取子集结果还是列表而不是列表元素} \newline % Row Count 11 (+ 2)
\seqsplit{直接给列表不存在的元素名定义元素值就添加了新元素} \newline % Row Count 13 (+ 2)
\seqsplit{把某个列表元素赋值为} NULL 就删掉这个元素 \newline % Row Count 15 (+ 2)
\seqsplit{要把已经存在的元素修改为} NULL \seqsplit{值而不是删除此元素，} \seqsplit{或者给列表增加一个取值为} NULL 的元素， \seqsplit{这时需要用单重的方括号取子集，这样的子集会保持其列表类型，给这样的子列表赋值为} list(NULL)。如`dist{[}'was.estimated'{]} \textless{}- list(NULL)` \newline % Row Count 21 (+ 6)
as.list() \seqsplit{将其他转换成列表，unlist()把列表转换成基本向量}% Row Count 23 (+ 2)
} \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}{矩阵注意点}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{提取A的第一行结果为向量，维数会有不同，drop} = FALSE 可保留原有维度。 \newline % Row Count 2 (+ 2)
\seqsplit{寻找矩阵中的最小元素，并返回其位置} \newline % Row Count 4 (+ 2)
`  mat \textless{}- matrix(rnorm(40), 10, 4)  which(mat == min(mat, na.rm=TRUE))  \# \seqsplit{返回的是向量的位置`} \newline % Row Count 7 (+ 3)
` which(mat == min(mat, na.rm=TRUE), arr.ind = TRUE)  \# 返回行号和列号 `% Row Count 9 (+ 2)
} \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}{向量下标}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{正整数下标：访问对应位置的元素和子集} \newline % Row Count 2 (+ 2)
\seqsplit{负整数下标：扣除相应的元素后的子集} \newline % Row Count 4 (+ 2)
下标超界返回NA \newline % Row Count 5 (+ 1)
\seqsplit{下标可以是与向量等长的逻辑表达式} \newline % Row Count 6 (+ 1)
\seqsplit{元素名下标：向量可以为每个元素命名，命名后即可用元素名或者元素名向量作为向量的下标。} \newline % Row Count 9 (+ 3)
\seqsplit{重复下标：R在使用整数或元素名作为向量下标时，允许使用重复下标。}% Row Count 11 (+ 2)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{3.08574 cm} x{1.89126 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{向量}}  \tn
% Row 0
\SetRowColor{LightBackground}
`seq(from = 5, to = 25, by = 5)` & 5 10 15 20 25 \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{`seq(as.Date('2021-10-1')}, by='days', length=2)` & "2021-10-01" "2021-10-02" \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\seqsplit{两个不等长向量的四则运算，规则是每次从头重复利用短的一个} \newline `seq(as.Date('2021-9-8'),to=as.Date('2022-1-1'),by='2 weeks')` \newline 可以把向量看成一个集合，对两个向量进行集合运算，如unique(), setdiff(), setequal(), union(), intersect()}  \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}{读入数据}}  \tn
% Row 0
\SetRowColor{LightBackground}
`d2 \textless{}- \seqsplit{read.csv("covid19.csv"}, header = TRUE, na.strings = "",                 row.names = "序号", nrows = 10)` & header = TRUE \seqsplit{包括列名，na.strings} = x 指定 x \seqsplit{为缺失值，row.names} = x 指定列名为 x \seqsplit{的列为行名，skip} = x 跳过前面 x 行，nrows = x 只读取 x 行，若header = TRUE \seqsplit{则不包括列名那一行} \tn 
% Row Count 11 (+ 11)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\seqsplit{readLines()可以读文本文件} \newline  `   idx.na \textless{}- apply(is.na(d), 1, any) d{[}idx.na, {]}`返回有缺失值的行 \newline head(x, n) 选择数据框 x 的前 n 行 \newline tail(x, n) 选择数据框 x 的倒数 n 行}  \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}{整理数据}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{行号一样直接合并 \newline % Row Count 1 (+ 1)
行号不一样，用 merge(dat1, dat2, by = x) \seqsplit{按照列名为x来合并，只保留x元素相同的行，即同时在两个数据框中的行} \newline % Row Count 4 (+ 3)
用 merge(dat1, dat2, by.x = x, by.y = y) 把 dat1中的x列和 \seqsplit{dat2中的y列作为合并的标准。} \newline % Row Count 7 (+ 3)
如果想要保留 dat1 \seqsplit{中的所有行，则指定} all.x = TRUE。（？） \newline % Row Count 9 (+ 2)
scale() \seqsplit{把每一列都标准化，} \seqsplit{即每一列都减去该列的平均值，然后除以该列的样本标准差。} \newline % Row Count 12 (+ 3)
scale(x, center=TRUE, scale=FALSE) \seqsplit{仅中心化而不标准化。} \newline % Row Count 14 (+ 2)
\seqsplit{仅适用于数值型的变量}% Row Count 15 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.78712 cm} x{2.18988 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{汇总数据}}  \tn
% Row 0
\SetRowColor{LightBackground}
总体信息 & \seqsplit{summary()，table()} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
位置度量 & mean() , median() \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{分散程度（变异性）度量} & sd() , IQR() , mad() \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
分位数 & min() , max() , quantile() \tn 
% Row Count 7 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\seqsplit{对于因子类型的变量，可以通过table()查看其在每一类的频数分布。} \newline 可通过 na.rm = TRUE \seqsplit{将其中NA的数值去除来计算平均值、标准差、中位数等。}}  \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}{分组汇总数据}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{aggregate() \seqsplit{函数对输入的数据框用指定的分组变量（或交叉分组）} \seqsplit{分组进行概括统计。} \newline % Row Count 3 (+ 3)
`aggregate(d{[},c(3:5,7){]}, by = d{[}c("分型","性别"){]}, mean)` \newline % Row Count 5 (+ 2)
tapply() \seqsplit{函数对向量进行分组概括} \newline % Row Count 6 (+ 1)
`tapply(d{[},"性别"{]}, INDEX = d{[}"分型"{]}, table)` \newline % Row Count 8 (+ 2)
可以通过 useNA = "always" 或useNA = "ifany"来把 NA计算在内 \newline % Row Count 10 (+ 2)
\seqsplit{对两个分类变量进行交叉分组计算频数} \newline % Row Count 12 (+ 2)
`table( d{[},"分型"{]}, d{[},"性别"{]})`% Row Count 13 (+ 1)
} \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}{随机数}}  \tn
% Row 0
\SetRowColor{LightBackground}
sample(x, size, replace = FALSE, prob = NULL) & x \seqsplit{用以存储有限集合的向量，size} \seqsplit{指定抽样个数，prob} \seqsplit{=指定以各种权重抽取，默认是等概率。replace} \seqsplit{=指定是否为有放回抽样，TRUE是有放回抽样}, \seqsplit{FALSE是无放回抽样即样本数} \tn 
% Row Count 12 (+ 12)
% Row 1
\SetRowColor{white}
set.seed(seed, kind = NULL, normal.kind = NULL, sample.kind = NULL) & seed = k \seqsplit{指定一个编号为} k的种子，kind \seqsplit{=指定后续程序要使用的随机数发生器名称;normal}.kind= \seqsplit{指定要使用的正态分布随机数发生器名称。} \tn 
% Row Count 21 (+ 9)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\seqsplit{这是古典概型的例子。} \newline 随机排序sample(10) sample(letters) \newline 多项分布的随机抽样 \newline `sample(1:3, size = 100, replace = TRUE, prob = c(.2, .3, .5))`}  \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}{随机数函数}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{每一种分布都有自己的名字，在其前面添加如下的字母分别代表不同的功能} \newline % Row Count 2 (+ 2)
p分布函数 q分位数 d概率密度函数 r随机数 \newline % Row Count 4 (+ 2)
\seqsplit{指数分布的概率密度函数} \newline % Row Count 5 (+ 1)
x \textless{}- seq(0, 8, .05) \newline % Row Count 6 (+ 1)
plot (x, dexp(x), ty="l", main="题目", xlab="x", ylab="f(x)") \newline % Row Count 8 (+ 2)
lines (x, dexp(x, rate=0.5), col="red")  \newline % Row Count 9 (+ 1)
lines (x, dexp(x, rate=0.2), col="blue") \newline % Row Count 10 (+ 1)
legend("topright", legend = paste("lambda = ", c(1, 0.5, 0.2)), col=c("black", "red", "blue"), lty=1, inset = .02) \newline % Row Count 13 (+ 3)
指数分布的随机数 \newline % Row Count 14 (+ 1)
x \textless{}- seq(0, 16, .05) \newline % Row Count 15 (+ 1)
hist(rexp(1000, 0.5), freq = FALSE,  xlab="x", main="题目") \newline % Row Count 17 (+ 2)
lines (x, dexp(x, 0.5), col="red", lwd=2)% Row Count 18 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{runif(n) 产生 n \seqsplit{个标准均匀分布随机数} \newline rnorm(n) 产生 n \seqsplit{个标准正态分布随机数}}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}