\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{omarffkamel} \pdfinfo{ /Title (pandas.pdf) /Creator (Cheatography) /Author (omarffkamel) /Subject (Pandas 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}{7F49A3} \definecolor{LightBackground}{HTML}{F7F3F9} \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{Pandas Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{omarffkamel} via \textcolor{DarkBackground}{\uline{cheatography.com/152902/cs/32976/}}} \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}omarffkamel \\ \uline{cheatography.com/omarffkamel} \\ \end{tabulary} \vfill \columnbreak \begin{tabulary}{5.8cm}{L} \SetRowColor{FootBackground} \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}} \\ \vspace{-2pt}Published 6th July, 2022.\\ Updated 6th July, 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} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Installation}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{conda install pandas} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{conda install seaborn} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{conda install pandas seaborn} \tn % Row Count 3 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Export}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{CSV: df.to\_csv(filename)} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Excel: df.to\_excel(filename)} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{SQL: df.to\_sql(table\_name, connection\_object)} \tn % Row Count 3 (+ 1) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{JSON: df.to\_json(filename)} \tn % Row Count 4 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Spalten bearbeiten}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Spalte Hinzufugen:\{\{nl\}\} df{[}'fuenf'{]} = 5 \{\{nl\}\} df {[}'neue Spalte'{]} = 2*df{[}'alte Spalte'{]}} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Spalte l{\"o}schen: \{\{nl\}\} del df{[}'fuenf'{]}} \tn % Row Count 3 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Spalten umbenennen: \{\{nl\}\} df.rename(columns = \{'alt1':'neu1','alt2':'neu2'\}, inplace = True) \{\{nl\}\} df.columns = {[}'neu1', 'neu2', 'neu3', 'neu4'{]}} \tn % Row Count 6 (+ 3) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Rename: Funktionen entgegennehmen \{\{nl\}\} df.rename(columns= str.upper, inplace = True) \{\{nl\}\} df.rename(columns=lambda x: f'T1\_\{x\}', inplace = True)} \tn % Row Count 9 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Broadcasting}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{s1 = \seqsplit{pd.Series(rng.standard\_normal(10))} – 5} \tn % Row Count 1 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Auspr{\"a}gungen}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Index: \{\{nl\}\} df.idxmin() \{\{nl\}\} df.idxmax()} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Max wer zeile :\{\{nl\}\} df.loc{[}df{[}'Wert1'{]}.idxmax(){]}} \tn % Row Count 3 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Position:\{\{nl\}\} argmin() \{\{nl\}\} argmax()} \tn % Row Count 4 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Import}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{CSV: pd.read\_csv(filename)} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Excel: pd.read\_excel(filename)} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{SQL : pd.read\_sql(query, connection\_object)} \tn % Row Count 3 (+ 1) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{JSON: \seqsplit{pd.read\_json(json\_string)}} \tn % Row Count 4 (+ 1) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{HTML: pd.read\_html(url)} \tn % Row Count 5 (+ 1) % Row 5 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Clipboard: pd.read\_clipboard()} \tn % Row Count 6 (+ 1) % Row 6 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{dict: pd.DataFrame(dict)} \tn % Row Count 7 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Dataframes}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{aus Listen: df = pd.DataFrame({[}"rot","grün","blau","gelb"{]}, columns={[}"Farbe"{]})} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{aus Dictionaries: d = \{"Name": {[}'Katja', 'Nina', 'Sven', 'Matthias'{]}, "Alter": {[}32, 32, 36, 31{]}, "Ort":{[}'Berlin', 'München', 'Frankfurt', 'K{\"o}ln'{]} \} \{\{nl\}\} df = pd.DataFrame(d)} \tn % Row Count 6 (+ 4) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{seaborn: import seaborn as sns} \tn % Row Count 7 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Zeilen bearbeiten}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Zeilen anhand des Index l{\"o}schen: \{\{nl\}\} df = df.drop(1) \{\{nl\}\} df = df.drop({[}0,1,2,3{]}) \{\{nl\}\} df.drop('fuenf', axis=1, inplace=True)} \tn % Row Count 3 (+ 3) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Werte anhand von boolscher Bedingung {\"a}ndern: \{\{nl\}\} df.loc{[}df{[}"Alter"{]}\textgreater{}=32,'Ort'{]} = 'Berlin'} \tn % Row Count 5 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Sortieren}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Nach index: \{\{nl\}\} df.sort\_index()} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Nach spaltenwerten \{\{nl\}\} df.sort\_values(by='Wert2') \{\{nl\}\} df.sort\_values(by={[}'Wert2','Wert3'{]}, ascending={[}False, True{]})} \tn % Row Count 4 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Series}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{aus Listen: s = pd.Series({[}"rot","grün","blau","gelb"{]})} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{aus Dictionaries: d = \{'Berlin':3645000, 'München':1472000, 'Hamburg':1841000, 'K{\"o}ln':1086000 \} staedte = pd.Series(d)} \tn % Row Count 5 (+ 3) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{elementen zugriff: wie eine Liste. z.b: zahlen{[}3{]}} \tn % Row Count 6 (+ 1) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Bei einem dictionary werden die Schlüssel zum Index: staedte{[}"Hamburg"{]}} \tn % Row Count 8 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{NaN: Not a Number = fehlende Wert} \tn % Row Count 9 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Dataframes Zugriff:}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Erste zeile: df.head()} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Spalten (über Spaltennamen) :\{\{nl\}\} df.columns \{\{nl\}\} df{[}"Alter"{]} oder df.Alter \{\{nl\}\} df{[}{[}"Name","Alter"{]}{]}} \tn % Row Count 4 (+ 3) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Zeilen und Spalten per iloc \{\{nl\}\} df.iloc{[}0{]} \{\{nl\}\} df.iloc{[}0,0{]} \{\{nl\}\} df.iloc{[}0,0:2{]}} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{über loc per Index-Label: \{\{nl\}\} df.loc{[}:,"Alter"{]} \{\{nl\}\} df.index = df{[}"Name"{]} \{\{nl\}\} df.loc{[}{[}"Nina","Sven"{]},"Ort"{]}} \tn % Row Count 9 (+ 3) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{booleans: \{\{nl\}\} df.loc{[}df{[}"Alter"{]}\textgreater{}=32{]} \{\{nl\}\} df.loc{[}df{[}'Name'{]}.str{[}:1{]}=="M"{]} \{\{nl\}\} df.loc{[}df{[}"Alter"{]}.isnull(){]}} \tn % Row Count 12 (+ 3) % Row 5 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Werten Zuweisung \{\{nl\}\} df.loc{[}'Sven':,'Alter'{]} = 30} \tn % Row Count 14 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}