\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-2.pdf) /Creator (Cheatography) /Author (omarffkamel) /Subject (Pandas 2 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 2 Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{omarffkamel} via \textcolor{DarkBackground}{\uline{cheatography.com/152902/cs/33045/}}} \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}Not Yet Published.\\ 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}{Eindeutige Werte und Duplikate}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{isin(): d für jeden Wert einer Serie überprüfen, ob er in einer Liste ist \{\{nl\}\} s.isin({[}'a','b'{]}) penguins{[}penguins{[}'species'{]}.isin({[}'Adelie'{]}){]}} \tn % Row Count 3 (+ 3) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{unique() gibt die eindeutigen Werte aus \{\{nl\}\} import seaborn as sns \{\{nl\}\} penguins{[}"species"{]}.unique()} \tn % Row Count 6 (+ 3) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{duplicated() \{\{nl\}\} gibt eine boolean Serie zurück, ob die Zeile schon vorhanden war \{\{nl\}\} Mit drop\_duplicates() k{\"o}nnen die Duplikate entfernt werden} \tn % Row Count 10 (+ 4) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Apply}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Anwenden einer Funktion spaltenweise oder zeilenweise \{\{nl\}\} df.apply(max) \{\{nl\}\} df.apply(max, axis=1)} \tn % Row Count 3 (+ 3) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{Kombination mit eigener Funktion \{\{nl\}\} \seqsplit{df.apply(meine\_funktion)} \{\{nl\}\} df.apply(meine\_funktion, axis=1)} \tn % Row Count 6 (+ 3) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{Rückgabe von mehreren Elementen \{\{nl\}\} def f(x): \{\{nl\}\} ~ return pd.Series({[}x.min(), x.max(){]}, index={[}'min', 'max'{]}) \{\{nl\}\} df.apply(f, axis=1)} \tn % Row Count 10 (+ 4) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{All, Any}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{all() \{\{nl\}\} prüfen ob alle Elemente einer boolschen Serie True sind. \{\{nl\}\} titanic{[}"who"{]}.isin({[}"child","woman"{]}).all()} \tn % Row Count 3 (+ 3) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{any() prüft, ob es mindestens ein Element einer boolschen Serie gibt, welches den Wert True hat \{\{nl\}\} (titanic{[}"age"{]} \textgreater{} 75).any()} \tn % Row Count 6 (+ 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}{Map und ApplyMap}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{map}} erm{\"o}glicht das Anwenden einer Funktion auf jedes Element einer Serie \{\{nl\}\} f = lambda x: f'\{x:.2f\}' \{\{nl\}\} df{[}'Wert1'{]}.map(format)} \tn % Row Count 3 (+ 3) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{applymap}} wendet eine Funktion auf jedes Element eines DataFrames an \{\{nl\}\} df.applymap(lambda x: f'\{x:.2f\}')} \tn % Row Count 6 (+ 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}{Stichprobe}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{sample()}} : Zuf{\"a}llige Stichprobe\{\{nl\}\} n gibt die Gr{\"o}{\ss}e an \{\{nl\}\}} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{replace=True : eine Zeile mehrfach auswahlen \{\{nl\}\} train\_rate = 0.8 \{\{nl\}\} train\_n = round(train\_rate * coffee.shape{[}0{]}) \{\{nl\}\} train = coffee.sample(n = train\_n) \{\{nl\}\} test = coffee{[}\textasciitilde{}pd.Series(coffee.index).isin(pd.Series(train.index)){]} \{\{nl\}\} print(test.shape)} \tn % Row Count 8 (+ 6) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Kategorien und Ersetzungen}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{value\_counts() gibt die Anzahl der eindeutigen Werte aus} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{cut() sortiert Werte in Intervalle \{\{nl\}\} pd.cut(penguins{[}"body\_mass\_g"{]}, bins=3)} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{replace() : Werte ersetzen \{\{nl\}\} df.replace('alter Wert','neuer Wert') \{\{nl\}\} df.replace({[}'alt1','alt2'{]},'neu') \{\{nl\}\} df.replace(\{'alt1':'neu1','alt2':'neu2'\}, inplace=True)} \tn % Row Count 8 (+ 4) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}