\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{ChesterHsieh}
\pdfinfo{
  /Title (pyspark-all-you-need.pdf)
  /Creator (Cheatography)
  /Author (ChesterHsieh)
  /Subject (pyspark-all you need 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}{25A321}
\definecolor{LightBackground}{HTML}{F1F9F1}
\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{pyspark-all you need Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{ChesterHsieh} via \textcolor{DarkBackground}{\uline{cheatography.com/62727/cs/29780/}}}
\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}ChesterHsieh \\
  \uline{cheatography.com/chesterhsieh} \\
  \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 15th November, 2021.\\
   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*}{2}

\begin{tabularx}{8.4cm}{p{2.16 cm} p{3.6 cm} p{0.72 cm} p{0.72 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{4}{x{8.4cm}}{\bf\textcolor{white}{ETL-1 to 1 relation}}  \tn
% Row 0
\SetRowColor{LightBackground}
asd & asd &  &  \tn 
% Row Count 1 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}----}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{p{0.76 cm} p{0.76 cm} x{6.08 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{8.4cm}}{\bf\textcolor{white}{ETL-map/reduce}}  \tn
% Row 0
\SetRowColor{LightBackground}
udf &  & `@pandas\_udf('long') def \seqsplit{pandas\_plus\_one(series:} pd.Series) -\textgreater{} pd.Series:\{\{nl\}\}     \# Simply plus one by using pandas Series.     return series + 1  \seqsplit{df.select(pandas\_plus\_one(df.a)).show()`} \tn 
% Row Count 6 (+ 6)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{1.672 cm} p{0.76 cm} x{5.168 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{8.4cm}}{\bf\textcolor{white}{ETL - N to 1}}  \tn
% Row 0
\SetRowColor{LightBackground}
groupby &  & \seqsplit{df.groupby('color').avg()} \tn 
% Row Count 1 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{p{0.8 cm} p{0.8 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{ETL - streamming}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{} \tn 
% Row Count 0 (+ 0)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{1.064 cm} x{3.42 cm} x{3.116 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{8.4cm}}{\bf\textcolor{white}{I/O}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{Local\_CSV} & dataset = \seqsplit{spark.read.csv('BostonHousing.csv'},inferSchema=True, header =True) & \seqsplit{inferSchema=Guess} data type from csv \tn 
% Row Count 5 (+ 5)
% Row 1
\SetRowColor{white}
\mymulticolumn{3}{x{8.4cm}}{Local\_Json} \tn 
% Row Count 6 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{3}{x{8.4cm}}{Cloud\_s3} \tn 
% Row Count 7 (+ 1)
% Row 3
\SetRowColor{white}
To SQL table & \seqsplit{df.createOrReplaceTempView("tableA")} &  \tn 
% Row Count 10 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{p{0.76 cm} p{0.76 cm} p{0.76 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{8.4cm}}{\bf\textcolor{white}{Efficiency}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{3}{x{8.4cm}}{repartition} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{3}{x{8.4cm}}{shuffle} \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{3}{x{8.4cm}}{collect} \tn 
% Row Count 3 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{1.216 cm} x{4.028 cm} x{2.356 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{8.4cm}}{\bf\textcolor{white}{Spark All kind of handler}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{SparkContext} & Old man &  \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{SparkSession} & Young boy, that's only entry point got to know for late spark &  \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{SparkConf} & \seqsplit{https://towardsdatascience}.com/sparksession-vs-sparkcontext-vs-sqlcontext-vs-hivecontext-741d50c9486a &  \tn 
% Row Count 10 (+ 5)
% Row 3
\SetRowColor{white}
\seqsplit{spark.sql} & spark.sql("SELECT * FROM p left join e on p.name = e.name") & df.query() -\textgreater{} Dataframe \tn 
% Row Count 13 (+ 3)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{3}{x{8.4cm}}{RDD} \tn 
% Row Count 14 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{1.44 cm} x{2.016 cm} p{0.72 cm} x{3.024 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{4}{x{8.4cm}}{\bf\textcolor{white}{EDA-Get the information for debugging/coding}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{printSchema} & \seqsplit{DataFrame.printSchema()} &  &  \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
columns:List{[}str{]} & \seqsplit{DataFrame.columns} &  &  \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
show() & df.show(1) & \seqsplit{head()} & A action, force the process to finish \tn 
% Row Count 9 (+ 3)
% Row 3
\SetRowColor{white}
take & df.take(1) &  &  \tn 
% Row Count 10 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}----}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}