\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{woobidoobi}
\pdfinfo{
  /Title (dl.pdf)
  /Creator (Cheatography)
  /Author (woobidoobi)
  /Subject (DL 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}{8048C9}
\definecolor{LightBackground}{HTML}{F7F3FB}
\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{DL Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{woobidoobi} via \textcolor{DarkBackground}{\uline{cheatography.com/99373/cs/21014/}}}
\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}woobidoobi \\
  \uline{cheatography.com/woobidoobi} \\
  \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 November, 2019.\\
   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{1.14425 cm} x{0.96117 cm} x{2.47158 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Session}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{Interpreter} & \seqsplit{\%jdbc(hive)} & \%livy2.pyspark \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
Create Session &  & "from pyspark\_llap import HiveWarehouseSession hive = \seqsplit{HiveWarehouseSession.session(spark).build()"} \tn 
% Row Count 7 (+ 5)
% Row 2
\SetRowColor{LightBackground}
Connect to database & use \seqsplit{ampb\_sandbox} & \seqsplit{"hive.setDatabase(""dl\_prod\_sandbox\_agi"")} " \tn 
% Row Count 10 (+ 3)
% Row 3
\SetRowColor{white}
List Databases &  & hive.execute("show \seqsplit{databases").show(truncate=False)} \tn 
% Row Count 13 (+ 3)
% Row 4
\SetRowColor{LightBackground}
List Tables & show tables & hive.execute("show \seqsplit{tables").show(truncate=False)} \tn 
% Row Count 16 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{0.82386 cm} x{1.87657 cm} x{1.87657 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Data wrangling}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{function}} & {\bf{ sql equivalient }} & {\bf{ pyspark df }} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{Selecting} \seqsplit{columns} & select \seqsplit{arbetsgivaravgift\_organisationsnummer\_id} as orgnr, \seqsplit{arbetsgivaravgift\_redovisad\_period} as period, \seqsplit{arbetsgivaravgift\_inbetalat\_belopp} as \seqsplit{inbetalt\_belopp} from df\_agavgift & \seqsplit{df\_agavgift.select(}         \seqsplit{col("arbetsgivaravgift\_organisationsnummer\_id")}.alias("orgnr"),         \seqsplit{col("arbetsgivaravgift\_redovisad\_period")}.alias("period"),          \seqsplit{col("arbetsgivaravgift\_inbetalat\_belopp")}.alias("inbetalat\_belopp")     ) \tn 
% Row Count 18 (+ 16)
\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}{Livy2.pyspark}}  \tn
% Row 0
\SetRowColor{LightBackground}
Transfer data from hive to pyspark dataframe & pyspark\_df = \seqsplit{hive.table("hive\_table")} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
Transfer data from pyspark to hive & \seqsplit{pyspark\_df.registerTempTable("hive\_table")} \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
Remove a temp table & hive\_table.drop() \tn 
% Row Count 7 (+ 1)
\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}{Combining data}}  \tn
% Row 0
\SetRowColor{LightBackground}
inner join & df1.join(df2, df1.name == df2.name) \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
left join & df1.join(df2, df1.name == df2.name,how='left') \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
right join & ta.join(tb, ta.name == tb.name,how='right') \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
joining on multiple columns & df1.join(df2, df1.name == df2.name,how='right') \tn 
% Row Count 8 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{in pyspark you need to start by setting an alias for the tables that you want to join  \newline df1 = TableA.alias('df1') \newline df2 = TableB.alias('df2') \newline  \newline  \newline Useful links: \newline http://www.learnbymarketing.com/1100/pyspark-joins-by-example/ \newline http://www.learnbymarketing.com/618/pyspark-rdd-basics-examples/}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}