\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{dstark0011} \pdfinfo{ /Title (pandas-cheat-sheet-rev2.pdf) /Creator (Cheatography) /Author (dstark0011) /Subject (Pandas Rev2 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}{3489A3} \definecolor{LightBackground}{HTML}{F2F7F9} \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 Rev2 Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{dstark0011} via \textcolor{DarkBackground}{\uline{cheatography.com/129050/cs/25448/}}} \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}dstark0011 \\ \uline{cheatography.com/dstark0011} \\ \end{tabulary} \vfill \columnbreak \begin{tabulary}{5.8cm}{L} \SetRowColor{FootBackground} \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}} \\ \vspace{-2pt}Published 27th November, 2020.\\ Updated 27th November, 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{4.48 cm} x{3.52 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Import Data}} \tn % Row 0 \SetRowColor{LightBackground} df = \seqsplit{pd.read\_csv('filename.csv')} & Read CSV into a Pandas DataFrame \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} df = \seqsplit{pd.to\_csv('filename.csv')} & Export Pandas DataFrame to CSV \tn % Row Count 4 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \SetRowColor{LightBackground} \mymulticolumn{2}{x{8.4cm}}{Import Options: \newline \newline header=False, Index=False, usecols=(5,6) \newline \newline Can also read CSV / HTML / Excel / JSON} \tn \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Combine multiple files into one (1) DataFrame}} \tn % Row 0 \SetRowColor{LightBackground} all\_files = glob.glob({\emph{*/}}.txt') & Finds all txt files in the \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} df\_raw = {[}pd.read\_csv(f) for f in all\_files{]} & Makes multiple DataFrames \tn % Row Count 5 (+ 3) % Row 2 \SetRowColor{LightBackground} df\_all = pd.concat(df\_raw, ignore\_index=True & Concatenates all the DataFrames into one (1) large DataFrame \tn % Row Count 8 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{1.6 cm} x{6.4 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Select Data}} \tn % Row 0 \SetRowColor{LightBackground} \seqsplit{df.head(5)} & Reads the first 5 rows \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \seqsplit{df.tail(5)} & Reads the last 5 rows \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \seqsplit{df.shape()} & Gives the number of columns and rows in the DataFrame \tn % Row Count 6 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{2.72 cm} x{5.28 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Select Row}} \tn % Row 0 \SetRowColor{LightBackground} data.iloc{[}0{]} & First row of DataFrame \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} data.iloc{[}1{]} & Second row of DataFrame \tn % Row Count 2 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{2.64 cm} x{5.36 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Select Column}} \tn % Row 0 \SetRowColor{LightBackground} data.iloc{[}:0{]} & First column of DataFrame \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} data.iloc{[}:1{]} & Second column of DataFrame \tn % Row Count 2 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{3.76 cm} x{4.24 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Select Column and Row Combined}} \tn % Row 0 \SetRowColor{LightBackground} df.iloc{[}:3, :2{]} & Selecting first 3 rows and first 2 columns \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} df.iloc{[}:3, {[}'Column1', 'Column2'{]}{]} & Selecting first 3 rows and first 2 columns \tn % Row Count 4 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Re-Order Colums}} \tn % Row 0 \SetRowColor{LightBackground} df = df{[}{[}'Column3', 'Column2', 'Column1'{]}{]} & Re-orders the columns to the order specified in this list \tn % Row Count 3 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4.24 cm} x{3.76 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Drop Columns}} \tn % Row 0 \SetRowColor{LightBackground} df= df.drop(columns={[}'Column1'{]}, axis=1) & Drops 'Column1\_Name' from DataFrame \tn % Row Count 2 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{5.2 cm} x{2.8 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Sort Columns}} \tn % Row 0 \SetRowColor{LightBackground} df = df.sort\_values(by={[}'Column1'{]}, ascending=False) & Sort values by Column1 \tn % Row Count 2 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4.4 cm} x{3.6 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Filter Column}} \tn % Row 0 \SetRowColor{LightBackground} df= df{[}(df{[}'Column1'{]} \textgreater{}= some\_number{]} & Filter DataFrame by certain value \tn % Row Count 3 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{3.44 cm} x{4.56 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Rename Columns}} \tn % Row 0 \SetRowColor{LightBackground} df.columns = {[}'A', 'B'{]} & Renamed Columns to 'A' and 'B' \tn % Row Count 2 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4.4 cm} x{3.6 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Merge DataFrames}} \tn % Row 0 \SetRowColor{LightBackground} df1.append(df2) & Joins df1 and df2 \tn % Row Count 1 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{3.84 cm} x{4.16 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Filter on Condition}} \tn % Row 0 \SetRowColor{LightBackground} df = df{[}(df\textgreater{} 2).all(axis=1){]} & Removes any values less than 2 \tn % Row Count 2 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{3.84 cm} x{4.16 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Select Row Based on Condition}} \tn % Row 0 \SetRowColor{LightBackground} row = df{[}df.A \textgreater{} 3{]}.iloc{[}0{]} & Select first row where A \textgreater{} 0 \tn % Row Count 2 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{3.36 cm} x{4.64 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Dealing with NAN values}} \tn % Row 0 \SetRowColor{LightBackground} df= \seqsplit{df.fillna(method='ffill')} & Fills blank values using forward fill method \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} df= \seqsplit{df.fillna(method='bfill')} & Fills blank values using backwards fill method \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \seqsplit{df.dropna(inplace=True)} & Removes rows with no values \tn % Row Count 6 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Padding Values With Zero's}} \tn % Row 0 \SetRowColor{LightBackground} df{[}'Column1'{]} = df{[}'Column1'{]}.astype(str).str.zfill(6) & Sets the numbe to six (6) long, which adds zeros \tn % Row Count 3 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4.96 cm} x{3.04 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Change Column Data Type}} \tn % Row 0 \SetRowColor{LightBackground} df{[}'Column1'{]}= df{[}'Column1'{]}.astype(float) & Change 'Column1' to float \tn % Row Count 2 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Convert Column to Date / Time}} \tn % Row 0 \SetRowColor{LightBackground} df{[}'Time'{]} = df{[}'Time'{]}.apply(pd.to\_datetime) & Converts the time column to a Datetime Series \tn % Row Count 3 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}