\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{tscher} \pdfinfo{ /Title (pandas.pdf) /Creator (Cheatography) /Author (tscher) /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}{A2A2A2} \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}{tscher} via \textcolor{DarkBackground}{\uline{cheatography.com/126640/cs/24646/}}} \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}tscher \\ \uline{cheatography.com/tscher} \\ \end{tabulary} \vfill \columnbreak \begin{tabulary}{5.8cm}{L} \SetRowColor{FootBackground} \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}} \\ \vspace{-2pt}Published 5th October, 2020.\\ Updated 5th October, 2020.\\ 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\_excel}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{pd.read\_excel(path, sheet\_name='Sheet2', encoding='utf-16')} \tn % Row Count 2 (+ 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}{Read multiples sheets}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df\_excel = pd.ExcelFile(path)} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{sheets = df\_excel.sheet\_names} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df\_aba = df\_excel.parse(\textless{}nome da aba\textgreater{}, skiprows={[}1,2{]}, header=None)} \tn % Row Count 4 (+ 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}{Read csv}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{pd.read\_csv(path, sep=' ', header=None)} \tn % Row Count 1 (+ 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}{Create a dataframe}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{my\_dict = \{'Computer':1500,'Monitor':300\}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{2}{x{8.4cm}}{df = \seqsplit{pd.DataFrame(list(my\_dict.items())},columns = {[}'Products','Prices'{]})} \tn % Row Count 3 (+ 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}{Iterrows}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{For i, row in df.iterrows():} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{~~~~print(row)} \tn % Row Count 2 (+ 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}{Replace nan to None}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{row = row.replace(\{np.nan: None\})} \tn % Row Count 1 (+ 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}{Find nan}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{pd{[}pd{[}2{]}.isna(){]}} \tn % Row Count 1 (+ 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}{Select observations between two datetimes}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{dt\_inicial = pd.Timestamp(2020, 1, 30)} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{2}{x{8.4cm}}{dt\_final = pd.Timestamp(2020, 1, 31)} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{df.loc{[}str(dt\_inicial):str(dt\_final){]}} \tn % Row Count 3 (+ 1) % Row 3 \SetRowColor{white} \mymulticolumn{2}{x{8.4cm}}{\{\{ac\}\}OR} \tn % Row Count 4 (+ 1) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{df.loc{[}'2002-1-1 01:00:00':'2002-1-1 04:00:00'{]}} \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}{Diff between 2 df}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{diff = df1{[}\textasciitilde{}df1.astype(str).apply(tuple, \seqsplit{1).isin(df2.astype(str).apply(tuple}, 1)){]}} \tn % Row Count 2 (+ 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}{Append new line}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{\seqsplit{df.append(pd.Series(name='new} row'))} \tn % Row Count 1 (+ 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}{New column}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df{[}'new column'{]} = np.nan} \tn % Row Count 1 (+ 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}{Substite values with another value}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df{[}2{]}.map(\{'yes':1, 'no':0\})} \tn % Row Count 1 (+ 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}{Column to datetime}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{pd.to\_datetime(df{[}3{]}, format="\%Y\%m\%d\%H")} \tn % Row Count 1 (+ 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}{Convert decimal with comman to float}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df.iloc{[}:,4{]}.str.replace('.', '').str.replace(',', '.').astype(float, inplace=True)} \tn % Row Count 2 (+ 2) \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}{Datetime64{[}ns{]} to date}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{df{[}3{]}.dt.date} \tn % Row Count 1 (+ 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}{Convert a column to int}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{df.astype(int)} \tn % Row Count 1 (+ 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}{Drop rows}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{f.drop({[}0, 1, 5{]}, inplace=True)} \tn % Row Count 1 (+ 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}{Drop columns}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{df.drop({[}2, 5'{]}, axis=1)} \tn % Row Count 1 (+ 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}{df to dictionary}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{pd.Series(df{[}1{]}.values, index=df{[}0{]}).to\_dict()} \tn % Row Count 1 (+ 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}{Save dataframe}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{\seqsplit{df.to\_csv('file\_out.csv'}, sep='\textbackslash{}t', index=False, encoding='utf-8-sig')} \tn % Row Count 2 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}