\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{{[}deleted{]}}
\pdfinfo{
  /Title (spark.pdf)
  /Creator (Cheatography)
  /Author ({[}deleted{]})
  /Subject (Spark 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}{5DC7A7}
\definecolor{LightBackground}{HTML}{F4FBF9}
\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{Spark Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{{[}deleted{]}} via \textcolor{DarkBackground}{\uline{cheatography.com/30326/cs/9053/}}}
\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}{[}deleted{]} \\
  \uline{cheatography.com/deleted-30326} \\
  \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 8th September, 2016.\\
   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}{x{4 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{SparkSQL - Transformations}}  \tn
% Row 0
\SetRowColor{LightBackground}
`df = \seqsplit{sqlContext.createDataFrame(data)`} & Créer un DataFrame à partir d'une collection Python (liste) \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
`df = \seqsplit{sqlContext.createDataFrame(data}, {[}'name', 'age'{]})` & Créer un DataFrame à partir d'une collection Python (liste) \tn 
% Row Count 8 (+ 4)
% Row 2
\SetRowColor{LightBackground}
`df = \seqsplit{sqlContext.read.text('files.txt')`} & Crér un DataFrame à partir d'un fichier \tn 
% Row Count 11 (+ 3)
% Row 3
\SetRowColor{white}
`ageCol = people.age` & Créer un DataFrame à partie d'une colonne \tn 
% Row Count 14 (+ 3)
% Row 4
\SetRowColor{LightBackground}
`df.select('*')` & Sélectionner toutes les colonnes \tn 
% Row Count 16 (+ 2)
% Row 5
\SetRowColor{white}
`df.select('name', 'age')` & Sélectionne 1 ou plusieurs colonnes \tn 
% Row Count 18 (+ 2)
% Row 6
\SetRowColor{LightBackground}
`df.select(df.name, (df.age + 10).alias('age'))` & Sélectionner 2 colonnes, changer la valeur d'une colonne et renommer la colonne \tn 
% Row Count 22 (+ 4)
% Row 7
\SetRowColor{white}
`df.drop(df.age)` & Suppression d'une colonne. Retourne un nouveau DataFrame \tn 
% Row Count 25 (+ 3)
% Row 8
\SetRowColor{LightBackground}
`lambda a, b : a + b` & Fontion anonyme. 1 expression \tn 
% Row Count 27 (+ 2)
% Row 9
\SetRowColor{white}
`slen = udf(lambda s: len(s), IntergerType())` & Fonction lambda ou nommée et type du retour \tn 
% Row Count 30 (+ 3)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{SparkSQL - Transformations (cont)}}  \tn
% Row 10
\SetRowColor{LightBackground}
\seqsplit{`inledsDF.filter(isComment`} & Retourne un DataFrame dont les lignes respectent la/les condition(s) \tn 
% Row Count 4 (+ 4)
% Row 11
\SetRowColor{white}
`where(function)` & Retourne un DataFrame dont les lignes respectent la/les condition(s) \tn 
% Row Count 8 (+ 4)
% Row 12
\SetRowColor{LightBackground}
`df.distinct()` & Retourne un DataFrame avec les lignes uniques \tn 
% Row Count 11 (+ 3)
% Row 13
\SetRowColor{white}
`orderBy({\emph{cols, }}*kw)` & Retourne un DataFrame dans l'ordre croissant ou décroissant \tn 
% Row Count 14 (+ 3)
% Row 14
\SetRowColor{LightBackground}
`df.sort("age", ascending = False)` & Retourne un DataFrame dans l'ordre croissant ou décroissant \tn 
% Row Count 17 (+ 3)
% Row 15
\SetRowColor{white}
\seqsplit{`df.select(explode(df4.intlist).alias('anInt')`} & Chaque élément est dans une nouvelle ligne \tn 
% Row Count 20 (+ 3)
% Row 16
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{`df.groupBy(df.name).agg(\{'*': 'count'\}).collect()`} \tn 
% Row Count 22 (+ 2)
% Row 17
\SetRowColor{white}
\mymulticolumn{2}{x{8.4cm}}{\seqsplit{`df.groupBy(df.name).count`}} \tn 
% Row Count 23 (+ 1)
% Row 18
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{\seqsplit{`df.groupBy().avg().collect()`}} \tn 
% Row Count 24 (+ 1)
% Row 19
\SetRowColor{white}
\mymulticolumn{2}{x{8.4cm}}{\seqsplit{`df.groupBy('name').avg('age'}, 'grade').collect()`} \tn 
% Row Count 25 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.8 cm} x{5.2 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{SparkSQL - Actions}}  \tn
% Row 0
\SetRowColor{LightBackground}
`df.show(n, truncate)` & Affiche les n premières lignes du DataFrame \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
`df.take(n)` & Affiche les n premières lignes sous forme de une liste \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{`df.collect()`} & Retourne les enregistrements sous forme de liste \tn 
% Row Count 7 (+ 2)
% Row 3
\SetRowColor{white}
`df.count()` & Retourne le nombre de lignes dans le DataFrame \tn 
% Row Count 9 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{`df.describe(*cols)`} & Calcule les statistiques descriptives des colonnes numériques \tn 
% Row Count 12 (+ 3)
% Row 5
\SetRowColor{white}
\seqsplit{`linesDF.cache()`} & Enregistre le DataFrame dans le cache donc pas besoin de réexécuter toutes les transformations et actions. A utiliser si on réutilise souvent le DataFrame. \tn 
% Row Count 19 (+ 7)
% Row 6
\SetRowColor{LightBackground}
\seqsplit{`aDF.unionAll(bDF)`} & Concaténation de deux DataFrame \tn 
% Row Count 21 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{\{\{ac\}\} /!\textbackslash{} ATTENTION /!\textbackslash{}  \newline  \newline - S'assurer qu'on a assez d'espace dans le programme "driver".pour utiliser `collect()`. \newline - Ne jamais utiliser `collect()` en production. Préférer `take(n)`.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}