\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{gabriellerab}
\pdfinfo{
  /Title (pandas.pdf)
  /Creator (Cheatography)
  /Author (gabriellerab)
  /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}{246CA3}
\definecolor{LightBackground}{HTML}{F1F5F9}
\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}{gabriellerab} via \textcolor{DarkBackground}{\uline{cheatography.com/61175/cs/15837/}}}
\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}gabriellerab \\
  \uline{cheatography.com/gabriellerab} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Published 18th May, 2018.\\
   Updated 18th May, 2018.\\
   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}{Importing the library}}  \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}{Creating a DataFrame}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{df = pd.DataFrame(\{"a":{[}4, 5, 6{]}, "b":{[}1, 2, 3{]}, "c":{[}7, 8, 9{]}\}) \newline  \newline print(df) \newline   a	b	c \newline 0	4	1	7 \newline 1	5	2	8 \newline 2	6	3	9} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{"a", "b", and "c" are column names \newline 0, 1, and 2 are indexes}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.23965 cm} x{2.73735 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Working with columns}}  \tn
% Row 0
\SetRowColor{LightBackground}
df{[}"column name"{]} & Refer to one column \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
a = df{[}"column name"{]} & Store column in a variable \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
df{[}"new column"{]} = & Add a new column \tn 
% Row Count 4 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Example: \newline df{[}"avg"{]} = df{[}{[}"a", "b", "c"{]}{]}.mean(axis=1) \newline  \newline Add a new column "avg" with the mean of the values across the specified columns.  \newline (axis=0 would find the mean across rows).}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.89126 cm} x{3.08574 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Selecting data}}  \tn
% Row 0
\SetRowColor{LightBackground}
df{[}"a"{]}{[}x{]} & Value in column "a" with index x \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
df{[}"a"{]}.loc{[}df{[}"b"{]} == x{]} & Values in col "a" with value x in col "b" \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{You can store selected values in a variable. Ex: b\_1 = df{[}"a"{]}.loc{[}df{[}"b"{]} == 1{]}}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.68758 cm} x{2.28942 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Sorting a DataFrame}}  \tn
% Row 0
\SetRowColor{LightBackground}
df.sort\_values({[}"a"{]}) & Sort DataFrame based on column "a" \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
df.sort\_values({[}"a"{]}, ascending = False) & Sort in descending order \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{You can store a sorted DataFrame in a variable. \newline Ex: df\_sorted = df.sort\_values({[}"a"{]})}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.58804 cm} x{2.38896 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Reading in and writing data}}  \tn
% Row 0
\SetRowColor{LightBackground}
df = \seqsplit{pd.read\_csv("file.csv")} & Read in CSV file \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
df = \seqsplit{pd.read\_table("file.txt")} & Read in TXT file \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{df.to\_csv("data.csv"}, index=False) & Output CSV file (index optional) \tn 
% Row Count 6 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.24425 cm} x{3.73275 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{pandas functions}}  \tn
% Row 0
\SetRowColor{LightBackground}
len(df) & Number of rows in DataFrame \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\seqsplit{df.head(x)} & First x lines of DataFrame \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
df.dtypes & Data type of each column \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
\seqsplit{df.columns} & DataFrame column names \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{df.count()} & Number of values in each column \tn 
% Row Count 6 (+ 2)
% Row 5
\SetRowColor{white}
df.sum() & Sum of values in each column \tn 
% Row Count 7 (+ 1)
% Row 6
\SetRowColor{LightBackground}
df.min() & Minimum value in each column \tn 
% Row Count 8 (+ 1)
% Row 7
\SetRowColor{white}
df.max() & Maximum value in each column \tn 
% Row Count 9 (+ 1)
% Row 8
\SetRowColor{LightBackground}
df.mean() & Mean value in each column \tn 
% Row Count 10 (+ 1)
% Row 9
\SetRowColor{white}
\seqsplit{df.median()} & Median value in each column \tn 
% Row Count 12 (+ 2)
% Row 10
\SetRowColor{LightBackground}
df.var() & Variance of each column \tn 
% Row Count 13 (+ 1)
% Row 11
\SetRowColor{white}
df.std() & Standard deviation of each column \tn 
% Row Count 15 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Replace df with df{[}"Column Name"{]} or an equivalent variable to use these functions for a single column or set of selected values.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}