\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{NeuesRos} \pdfinfo{ /Title (pandas-essential.pdf) /Creator (Cheatography) /Author (NeuesRos) /Subject (Pandas\_essential 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}{0B541E} \definecolor{LightBackground}{HTML}{F7F9F7} \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\_essential Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{NeuesRos} via \textcolor{DarkBackground}{\uline{cheatography.com/210773/cs/45541/}}} \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}NeuesRos \\ \uline{cheatography.com/neuesros} \\ \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 26th January, 2025.\\ 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}{1. Pandas importieren}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{import pandas as pd} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{2. Datenstrukturen}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{DataFrame}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}2D-Tabelle (wie eine Excel-Tabelle)} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Series}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}1D-Array (eine Spalte oder Zeile)} \tn % Row Count 4 (+ 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}{3. Daten einlesen}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{CSV-Datei einlesen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df = \seqsplit{pd.read\_csv('datei.csv')}} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Excel-Datei einlesen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df = \seqsplit{pd.read\_excel('datei.xlsx')}} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{JSON-Datei einlesen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df = \seqsplit{pd.read\_json('datei.json')}} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Aus einer Liste erstellen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df = pd.DataFrame({[}{[}'Alice', 25{]}, {[}'Bob', 30{]}{]}, columns={[}'Name', 'Alter'{]})} \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}{4. Daten anzeigen}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Erste 5 Zeilen anzeigen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.head()} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Letzte 5 Zeilen anzeigen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.tail()} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Zuf{\"a}llige Zeilen anzeigen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.sample(3)} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Informationen über den DataFrame (Spalten, Datentypen, etc.)}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.info()} \tn % Row Count 9 (+ 3) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Beschreibende Statistiken (nur numerische Spalten)}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.describe()} \tn % Row Count 12 (+ 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}{5. Daten ausw{\"a}hlen}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Eine Spalte ausw{\"a}hlen (als Series)}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}'Spaltenname'{]}} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Mehrere Spalten ausw{\"a}hlen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}{[}'Spalte1', 'Spalte2'{]}{]}} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Zeilen nach Index ausw{\"a}hlen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.iloc{[}0{]} \# Erste Zeile\{\{nl\}\}df.iloc{[}0:5{]} \# Zeilen 0 bis 4} \tn % Row Count 7 (+ 3) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Zeilen nach Bedingung filtern}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}df{[}'Alter'{]} \textgreater{} 30{]}} \tn % Row Count 9 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Werte in einer Spalte filtern}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}df{[}'Spalte'{]}.isin({[}'Wert1', 'Wert2'{]}){]}} \tn % Row Count 11 (+ 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}{6. Daten bearbeiten}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Neue Spalte hinzufügen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}'NeueSpalte'{]} = df{[}'Spalte1'{]} + df{[}'Spalte2'{]}} \tn % Row Count 3 (+ 3) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Spalte umbenennen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.rename(columns=\{'Alter': 'Age'\}, inplace=True)} \tn % Row Count 6 (+ 3) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Spalte l{\"o}schen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.drop('Spaltenname', axis=1, inplace=True)} \tn % Row Count 8 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Zeilen l{\"o}schen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.drop({[}0, 1{]}, axis=0, inplace=True) \# L{\"o}scht die ersten beiden Zeilen} \tn % Row Count 11 (+ 3) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Fehlende Werte behandeln}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.dropna() \# Zeilen mit fehlenden Werten l{\"o}schen\{\{nl\}\} df.fillna(0) \# Fehlende Werte mit 0 ersetzen} \tn % Row Count 15 (+ 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}{7. Dateien sortieren}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Nach einer Spalte sortieren}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}\seqsplit{df.sort\_values('Spaltenname'}, ascending=False)} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Nach mehreren Spalten sortieren}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.sort\_values({[}'Spalte1', 'Spalte2'{]}, ascending={[}True, False{]})} \tn % Row Count 5 (+ 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}{8. Gruppieren und aggregieren}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Gruppieren und Aggregieren}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.groupby('Spalte'){[}'AndereSpalte'{]}.mean()} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Mehrere Aggregationen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.groupby('Spalte').agg(\{'Spalte1': 'sum', 'Spalte2': 'mean'\})} \tn % Row Count 5 (+ 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}{9. Daten speichern}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Als CSV speichern}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}\seqsplit{df.to\_csv('neue\_datei.csv'}, index=False)} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Als Excel speichern}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}\seqsplit{df.to\_excel('neue\_datei.xlsx'}, index=False)} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Als JSON speichern}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}\seqsplit{df.to\_json('neue\_datei.json')}} \tn % Row Count 6 (+ 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}{10. Nützliche Funktionen}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Duplikate entfernen}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.drop\_duplicates()} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Spalten in einen bestimmten Datentyp umwandeln}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}'Spalte'{]} = df{[}'Spalte'{]}.astype(int)} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Zeilen- und Spaltenanzahl}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df.shape} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Eindeutige Werte in einer Spalte}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}'Spalte'{]}.unique()} \tn % Row Count 8 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Anzahl der eindeutigen Werte}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}'Spalte'{]}.nunique()} \tn % Row Count 10 (+ 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}{11. Daten kombinieren}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Vertikal kombinieren (Zeilen hinzufügen)}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}pd.concat({[}df1, df2{]}, axis=0)} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Horizontal kombinieren (Spalten hinzufügen)}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}pd.concat({[}df1, df2{]}, axis=1)} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Merge (SQL-{\"a}hnlicher Join)}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}pd.merge(df1, df2, on='GemeinsameSpalte', how='inner')} \tn % Row Count 7 (+ 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}{12. Zeitreihen}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Spalte in Datum umwandeln}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}'Datum'{]} = pd.to\_datetime(df{[}'Datum'{]})} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{Nach Datum filtern}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}df{[}df{[}'Datum'{]} \textgreater{} '2023-01-01'{]}} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{Zeitreihen-Gruppierung}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}\seqsplit{df.set\_index('Datum').resample('M').mean()} \# Monatliche Mittelwerte} \tn % Row Count 7 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}