\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{monika.g}
\pdfinfo{
  /Title (pandas-cheat-sheet.pdf)
  /Creator (Cheatography)
  /Author (monika.g)
  /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}{A3570B}
\definecolor{LightBackground}{HTML}{F9F4EF}
\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}{monika.g} via \textcolor{DarkBackground}{\uline{cheatography.com/175674/cs/36874/}}}
\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}monika.g \\
  \uline{cheatography.com/monika-g} \\
  \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 February, 2023.\\
   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}{To Start}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{{\bf{import}} numpy {\bf{as}} np \newline {\bf{import}} pandas {\bf{as}} pd} \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}{Create}}  \tn
% Row 0
\SetRowColor{LightBackground}
`pd.DataFrame(\{\{nl\}\}dict/list, \{\{nl\}\}index = None,  \{\{nl\}\}columns = None)` & \{\{width=50\}\}create DataFrame from list or dictionary \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
`df.index{[}names{]}` & set custom indexes \tn 
% Row Count 5 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`pd.Series(\{\{nl\}\}list/np\_array/dict, \{\{nl\}\}index = None)` & create series from the list or np\_array or dictionary \tn 
% Row Count 8 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{5.36 cm} x{2.64 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Input and Output}}  \tn
% Row 0
\SetRowColor{LightBackground}
`pd.read\_csv('name', \{\{nl\}\}index\_col = None)` & \{\{width=50\}\}read csv \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
`pd.read\_excel('name')` & read excel \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`df.to\_csv('name', \{\{nl\}\}index = False)` & save to csv \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
`df.to\_excel('name', \{\{nl\}\}'sheet\_name = 'name', \{\{nl\}\}index = False)` & save to excel \tn 
% Row Count 8 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Iteration}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{for lab, row in df.{\bf{iterrrows()}}: \newline ~print(lab) \newline ~print(row)} \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}{Functions/Methods}}  \tn
% Row 0
\SetRowColor{LightBackground}
`s.drop(row\_index, axis = 0)` & \{\{width=50\}\}drop values from rows of series \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
`df.drop(col\_name, axis = 0)` & drop values from columns \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
`df.drop(columns={[}col\_names{]})` & drop columns from DataFrame \tn 
% Row Count 7 (+ 2)
% Row 3
\SetRowColor{white}
\seqsplit{`df.drop\_duplicates()`} & remove duplicate rows (only considers columns) \tn 
% Row Count 10 (+ 3)
% Row 4
\SetRowColor{LightBackground}
`df.sort\_index(by = col\_names)` & sort by the values along an axis \tn 
% Row Count 12 (+ 2)
% Row 5
\SetRowColor{white}
`df.sort\_values(\{\{nl\}\}by = col\_names, \{\{nl\}\}ascending = False)` & order rows by values of a column high to low \tn 
% Row Count 16 (+ 4)
% Row 6
\SetRowColor{LightBackground}
`df.rename(columns = \{\{nl\}\}\{'old\_name':'new\_name'\})` & rename the columns of a DataFrame \tn 
% Row Count 19 (+ 3)
% Row 7
\SetRowColor{white}
`df.rank()` & assign ranks to entries \tn 
% Row Count 21 (+ 2)
% Row 8
\SetRowColor{LightBackground}
`pd.concat({[}df1,df2{]})` & append rows of DataFrames \tn 
% Row Count 23 (+ 2)
% Row 9
\SetRowColor{white}
`len(df)` & number of rows in DataFrame \tn 
% Row Count 25 (+ 2)
% Row 10
\SetRowColor{LightBackground}
`df1.join(df2)` & join two DataFrames \tn 
% Row Count 26 (+ 1)
% Row 11
\SetRowColor{white}
`df{[}'col\_name'{]}.unique()` & return unique values from column \tn 
% Row Count 28 (+ 2)
% Row 12
\SetRowColor{LightBackground}
`df{[}col\_name{]}.apply(\{\{nl\}\}func/type.method)` & apply function to column \tn 
% Row Count 31 (+ 3)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Functions/Methods (cont)}}  \tn
% Row 13
\SetRowColor{LightBackground}
\seqsplit{`df.apply(func/type.method)`} & apply function \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}{Extract}}  \tn
% Row 0
\SetRowColor{LightBackground}
`df{[}col\_names{]}` & \{\{width=50\}\}series of column \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
`df{[}{[}col\_names{]}{]}` & select column \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
`df{[}start:end{]}` & select many columns \tn 
% Row Count 4 (+ 1)
% Row 3
\SetRowColor{white}
`df.loc{[}index\_name{]}` & select row \tn 
% Row Count 5 (+ 1)
% Row 4
\SetRowColor{LightBackground}
`df.iloc{[}index\_num{]}` & select rows \tn 
% Row Count 6 (+ 1)
% Row 5
\SetRowColor{white}
`df.loc{[}{[}index\_names{]}{]}` & select rows \tn 
% Row Count 8 (+ 2)
% Row 6
\SetRowColor{LightBackground}
`df.iloc{[}{[}index\_nums{]}{]}` & select rows \tn 
% Row Count 10 (+ 2)
% Row 7
\SetRowColor{white}
`df.loc{[}{[}index\_names{]}, \{\{nl\}\}{[}col\_names{]}{]}` & select rows and columns \tn 
% Row Count 13 (+ 3)
% Row 8
\SetRowColor{LightBackground}
`df.loc{[}:, {[}col\_names{]}{]}` & select all rows and few columns \tn 
% Row Count 15 (+ 2)
% Row 9
\SetRowColor{white}
`df.iloc{[}:, {[}col\_nums{]}{]}` & select all rows and few columns \tn 
% Row Count 17 (+ 2)
% Row 10
\SetRowColor{LightBackground}
`df.head(n)` & select first n rows \tn 
% Row Count 18 (+ 1)
% Row 11
\SetRowColor{white}
`df.tail(n)` & select last n rows \tn 
% Row Count 19 (+ 1)
% Row 12
\SetRowColor{LightBackground}
`df.filter(regex = 'regex')` & select columns whose name matches regular expression regex \tn 
% Row Count 22 (+ 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}{Boolean Operators}}  \tn
% Row 0
\SetRowColor{LightBackground}
`df{[}np.{\bf{logical\_and}}(\{\{nl\}\}con1, con2, ...){]}` & \{\{width=50\}\} 1 'and' 2 condition ... \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
`df.loc{[}con1 {\bf{\&}} con2{]}` & 1 'and' 2 condition ... \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
`df{[}np.{\bf{logical\_or}}(\{\{nl\}\}con1, con2, ...){]}` & 1 'or' 2 condition ... \tn 
% Row Count 8 (+ 3)
% Row 3
\SetRowColor{white}
`df.loc{[}con1 {\bf{|}} con2{]}` & 1 'or' 2 condition ... \tn 
% Row Count 10 (+ 2)
% Row 4
\SetRowColor{LightBackground}
`df{[}np.{\bf{logical\_not}}(con){]}` & 'not' condition \tn 
% Row Count 12 (+ 2)
% Row 5
\SetRowColor{white}
`df.loc{[} {\bf{\textasciitilde{}}} con1{]}` & 'not' condition \tn 
% Row Count 13 (+ 1)
% Row 6
\SetRowColor{LightBackground}
`df{[}var{]}` & for condition \tn 
% Row Count 14 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.4 cm} x{5.6 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Get DataFrame Information}}  \tn
% Row 0
\SetRowColor{LightBackground}
`df.shape` & \{\{width=50\}\}(rows, colums) \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
`df.index` & decribe index \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{`df.columns`} & describe DataFrame columns \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
`df.info()` & info on DataFrame \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{`df.count()`} & number of non\_NA values for columns \tn 
% Row Count 6 (+ 2)
% Row 5
\SetRowColor{white}
\seqsplit{`df.describe()`} & summary statics \tn 
% Row Count 8 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.12 cm} x{4.88 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Math}}  \tn
% Row 0
\SetRowColor{LightBackground}
`df.sum()` & \{\{width=50\}\}sum of values for columns \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
`df.cumsum()` & cummulative sum of values \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
`df.min() \{\{nl\}\} df.max()` & minimum values for columns \{\{nl\}\} maximum values for columns \tn 
% Row Count 7 (+ 3)
% Row 3
\SetRowColor{white}
`df.median()` & median of values columns \tn 
% Row Count 8 (+ 1)
% Row 4
\SetRowColor{LightBackground}
`df.mean()` & mean of values for columns \tn 
% Row Count 10 (+ 2)
% Row 5
\SetRowColor{white}
`df.std()` & standard deviation of each object \tn 
% Row Count 12 (+ 2)
% Row 6
\SetRowColor{LightBackground}
`df.var()` & variance of each object \tn 
% Row Count 13 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


% That's all folks
\end{multicols*}

\end{document}