\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{bpilat} \pdfinfo{ /Title (pandas.pdf) /Creator (Cheatography) /Author (bpilat) /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}{A3A3A3} \definecolor{LightBackground}{HTML}{F3F3F3} \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}{bpilat} via \textcolor{DarkBackground}{\uline{cheatography.com/201559/cs/42672/}}} \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}bpilat \\ \uline{cheatography.com/bpilat} \\ \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 9th March, 2024.\\ 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}{Create Objects}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Creating a NumPy array}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`arr = np.array({[}1, 2, 3, 4, 5{]})`} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Creating a Pandas DataFrame}}} \tn % Row Count 3 (+ 1) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`df = pd.DataFrame(\{'A': {[}1, 2, 3{]}, 'B': {[}4, 5, 6{]}\})`} \tn % Row Count 5 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Indexing and Selection:}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Indexing and slicing NumPy array}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`arr{[}0{]}` {\emph{Access element at index 0}}} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{`arr{[}2:4{]}` {\emph{Slice elements from index 2 to 4}}} \tn % Row Count 4 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{{\bf{Indexing and slicing Pandas DataFrame}}} \tn % Row Count 5 (+ 1) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{`df{[}'A'{]}` {\emph{Access column 'A'}}} \tn % Row Count 6 (+ 1) % Row 5 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`df.loc{[}0{]}` {\emph{Access row at label 0}}} \tn % Row Count 7 (+ 1) % Row 6 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{`df.iloc{[}0{]}` {\emph{Access row at index 0}}} \tn % Row Count 8 (+ 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}{Operations}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Arithmetic operations with NumPy arrays}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`np.sum(arr)` {\emph{Sum of all elements}}} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{`np.mean(arr)` {\emph{Mean of all elements}}} \tn % Row Count 3 (+ 1) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{{\bf{Arithmetic operations with Pandas DataFrame}}} \tn % Row Count 4 (+ 1) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{`df.sum()` {\emph{Sum of all elements (column-wise)}}} \tn % Row Count 6 (+ 2) % Row 5 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`df.mean()` {\emph{Mean of all elements (column-wise)}}} \tn % Row Count 8 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Missing Data Handling}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Numpy}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{{\emph{NumPy does not have built-in support for missing data}}} \tn % Row Count 3 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Handling missing data in Pandas DataFrame}}} \tn % Row Count 4 (+ 1) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`df.isnull()` {\emph{Detect missing values}}} \tn % Row Count 5 (+ 1) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{`df.dropna()` {\emph{Drop rows with missing values}}} \tn % Row Count 7 (+ 2) % Row 5 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`df.fillna(value)` {\emph{Fill missing values with specified value}}} \tn % Row Count 9 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Grouping}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Grouping data in a Pandas DataFrame and calculates the Mean value for each group}}} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{\seqsplit{`df.groupby('column\_name').mean()`}} \tn % Row Count 3 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Grouping data in a Pandas DataFrame and calculates the Sum of values for each group}}} \tn % Row Count 5 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{\seqsplit{`df.groupby('column\_name').sum()`}} \tn % Row Count 6 (+ 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}{Aggregation}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Aggregating data in a Pandas DataFrame}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{\seqsplit{`df.groupby('column\_name')}.agg(\{'column\_to\_aggregate': 'aggregate\_function'\})`} \tn % Row Count 3 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Example: Sum of 'values' column for each 'category'}}} \tn % Row Count 5 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`df.groupby('category').agg(\{'values': 'sum'\})`} \tn % Row Count 6 (+ 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}{Filtering}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Filtering data in a Pandas DataFrame}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`df{[}df{[}'column\_name'{]} \textgreater{} threshold{]}`} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Example: Filtering rows where 'values' column is greater than 10}}} \tn % Row Count 4 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{`df{[}df{[}'values'{]} \textgreater{} 10{]}`} \tn % Row Count 5 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{p{0.8 cm} p{0.8 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Indexing}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{} \tn % Row Count 0 (+ 0) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}