\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{mitcht} \pdfinfo{ /Title (pyspark.pdf) /Creator (Cheatography) /Author (mitcht) /Subject (Pyspark 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}{80060A} \definecolor{LightBackground}{HTML}{FBF7F7} \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 Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{mitcht} via \textcolor{DarkBackground}{\uline{cheatography.com/50563/cs/14121/}}} \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}mitcht \\ \uline{cheatography.com/mitcht} \\ \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 29th December, 2017.\\ 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} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Read / Write .csv}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df = \seqsplit{(sqlContext.read.format("com.databricks.spark}.csv")\textbackslash{} \newline .option("header", "true")\textbackslash{} \newline .option("inferschema", "true")\textbackslash{} \newline .option("mode", "DROPMALFORMED")\textbackslash{} \newline \seqsplit{.load("hdfs://file.csv"))} \newline \newline df.write.mode('overwrite'). \newline option("header", "true"). \newline \seqsplit{csv("file://filename.csv")}} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4.8 cm} x{3.2 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Meta Data}} \tn % Row 0 \SetRowColor{LightBackground} `df.printSchema()` & `df.count()` \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} `len(df.columns)` & `df.columns` \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{`df.dtypes`} \tn % Row Count 3 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Arrange}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{\seqsplit{df.withColumnRenamed("col"},"newcol") \newline df.orderBy({[}'var1', 'var2'{]}, ascending = {[}True, False{]}) \newline df.orderBy(df.var1, df.var2.desc())} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Filter}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df.filter(df.var \textgreater{} 10000) \newline df.select('col1', 'col2') \newline df{[}collist{]} \# collist = {[}'var1', ...{]} \newline df.head(5) / df.show(5, truncate=True) / df.take(5) \newline df.drop('var') \newline df.distinct() \newline df.dropDuplicates() \newline df.dropna(subset='var') / df.na.drop() \newline df.isNotNull() \newline df.var.isin("level1", "level2") \newline df.var.like("string") \newline df.var.startswith("m") / df.var.endswith("m") \newline df.sample(False {\emph{with replacement}}, 0.5 {\emph{fraction}}, 12345 {\emph{seed}})} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Useful Functions}} \tn % Row 0 \SetRowColor{LightBackground} \seqsplit{`.describe('optional\_var')`} & `.count()` \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} `.show()` & `.fillna(value)` \tn % Row Count 3 (+ 1) % Row 2 \SetRowColor{LightBackground} `.min() / .max()` & `.mean()` \tn % Row Count 4 (+ 1) % Row 3 \SetRowColor{white} `.stdev() / .variance()` & `.substr(1,3)` \tn % Row Count 6 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{`F.when(df.var \textgreater{} 30, "Y").otherwise("N")`} \tn % Row Count 7 (+ 1) % Row 5 \SetRowColor{white} \mymulticolumn{2}{x{8.4cm}}{`df.var.alias('newvar') \# used to rename something`} \tn % Row Count 9 (+ 2) % Row 6 \SetRowColor{LightBackground} `df.cache() / df.unpersist()` & `.cast('Double')` \tn % Row Count 11 (+ 2) % Row 7 \SetRowColor{white} `.replace(10, 20) \# ????` & `.na.fill(0, subset = 'var')` \tn % Row Count 13 (+ 2) % Row 8 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{`time()`} \tn % Row Count 14 (+ 1) % Row 9 \SetRowColor{white} \mymulticolumn{2}{x{8.4cm}}{`from pyspark.sql import functions as F`} \tn % Row Count 15 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Write Functions / UDF}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{from pyspark.sql.functions import udf \newline F1 = udf(lambda x: '-1' if condition else x, StringType()) \# NB return type \newline df = df.withColumn('newvar', F1(df{[}'invar'{]}))} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Applying Functions}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{\seqsplit{df.select('val').map(lambda} x: x*2)} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Summarise}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df.crosstab('col1', 'col2') \# pair-wise count \newline df.groupby('var').function() \newline df.groupby('var').agg(\{'val' : 'mean'\})} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Join}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df3 = df1.join(df2, {[}df1.var1 == df2.var1, df1.var2 == df2.var2{]}, 'left') \newline xtra = \seqsplit{df1.select('var').subtract(df2.select('var'))} \# anti-join} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Method Chaining}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df \newline .select("col1","col2","col3", ...) \newline .filter(df.col1 \textgreater{} 30 ) \newline .show()} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{New Variable / Column}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df.withColumn('varnew', df.var / 2.0)} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{To SQL / Pandas}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{\seqsplit{df.registerAsTable('df\_tbl')} \newline sqlContext.sql('select var from df\_tbl').show(5) \newline df.toPandas()} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}