\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{simona20}
\pdfinfo{
  /Title (pandas-cheat-sheet.pdf)
  /Creator (Cheatography)
  /Author (simona20)
  /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}{36A0B5}
\definecolor{LightBackground}{HTML}{F2F9FA}
\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}{simona20} via \textcolor{DarkBackground}{\uline{cheatography.com/55244/cs/14705/}}}
\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}simona20 \\
  \uline{cheatography.com/simona20} \\
  \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 1st March, 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}{Imports}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{import {\bf{pandas}} as {\bf{pd}} \newline % Row Count 1 (+ 1)
import {\bf{matplotlib}} \newline % Row Count 2 (+ 1)
import {\bf{matplotlib.pyplot}} as {\bf{plt}}  \newline % Row Count 3 (+ 1)
plt.ion() {\emph{setting interactive mode}}% Row Count 4 (+ 1)
} \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}{Load a CSV file}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{pract={\bf{pd.read\_csv}}('practice-dataframe.csv',index\_col=0)% Row Count 2 (+ 2)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\emph{index\_col=0 the first column contains the row names}}}  \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}{Displaying values}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{Example dataframe:}} \newline % Row Count 1 (+ 1)
        age  height     sex \newline % Row Count 2 (+ 1)
Ann      22     170  female \newline % Row Count 3 (+ 1)
Bob      19     182    male \newline % Row Count 4 (+ 1)
Carla    20     165    dona \newline % Row Count 5 (+ 1)
{\bf{For columns:}} \newline % Row Count 6 (+ 1)
df.age  \newline % Row Count 7 (+ 1)
df.height \newline % Row Count 8 (+ 1)
df.sex \newline % Row Count 9 (+ 1)
{\bf{For row names:}} \newline % Row Count 10 (+ 1)
df.index \newline % Row Count 11 (+ 1)
{\bf{Selecting rows that have a particular value in some column:}} \newline % Row Count 13 (+ 2)
df{[}df.age\textless{}22{]} \newline % Row Count 14 (+ 1)
df{[}df.height\textgreater{}170{]} \newline % Row Count 15 (+ 1)
df{[}df.sex==female{]} \newline % Row Count 16 (+ 1)
{\emph{These commands return you all the information for the rows.}} \newline % Row Count 18 (+ 2)
{\bf{If we want only the row names rather than all the information:}} \newline % Row Count 20 (+ 2)
df{[}df.age==22{]}.index \newline % Row Count 21 (+ 1)
{\emph{The second part ('sex') selects the 'sex' column of the dataframe.}} \newline % Row Count 23 (+ 2)
{\bf{If we only want their gender:}} \newline % Row Count 24 (+ 1)
df{[}df.age==22{]}.sex% Row Count 25 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{grad\_values=alladjs.gradGlob}  \newline {\emph{we select the column and assign it to a variable (gradGlob). Then, we can compute statistics for this column.}}}  \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}{If you don't remember...}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/simona20_1518530519_operators.png}}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Here you have the comparison operators}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.28156 cm} x{1.41887 cm} x{1.87657 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Compute the...}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{mean}} & {\bf{median}} & {\bf{standard deviation}} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{variable.mean()} & \seqsplit{variable.median()} & variable.std() \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Visualizing data}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{If we want to return the first rows of the data:}} \newline % Row Count 2 (+ 2)
stud.head() \newline % Row Count 3 (+ 1)
{\bf{If we want to visualize all the data, in a single boxplot:}} \newline % Row Count 5 (+ 2)
stud.boxplot() \newline % Row Count 6 (+ 1)
plt.show() \newline % Row Count 7 (+ 1)
{\emph{IMPORTANT: close the graph window with your mouse to continue or use:}} \newline % Row Count 9 (+ 2)
plt.close() \newline % Row Count 10 (+ 1)
{\bf{If we want to see one boxplot per variable:}} \newline % Row Count 11 (+ 1)
\seqsplit{stud.boxplot(by='teacher')}% Row Count 12 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{We can use the same formulas with {\bf{.histogram}} command}  \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}{Drawing a...}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{Histogram:}} \newline % Row Count 1 (+ 1)
\seqsplit{grad\_small.plot(kind='hist')} \newline % Row Count 2 (+ 1)
{\bf{Boxplot:}} \newline % Row Count 3 (+ 1)
\seqsplit{grad\_small.plot(kind='box')} \newline % Row Count 4 (+ 1)
{\bf{Barplot:}} \newline % Row Count 5 (+ 1)
\seqsplit{grad\_small.plot(kind='bar')} \newline % Row Count 6 (+ 1)
{\bf{Saving a figure:}} \newline % Row Count 7 (+ 1)
\seqsplit{plt.savefig("small-histogram.pdf")}% Row Count 8 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\emph{the command .plot can draw different kinds of plots}}}  \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}{Selecting a...}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{Selecting rows based on +1 condition:}} \newline % Row Count 1 (+ 1)
sm=small{[}(small.semantic\_class=="qualitative") | (small.semantic\_class=="relational"){]}  \newline % Row Count 3 (+ 2)
{\bf{Selecting columns that we need to be able to do a boxplot:}} \newline % Row Count 5 (+ 2)
pred\_and\_dertype=all{[}{[}'predGlob','derType'{]}{]}  \newline % Row Count 6 (+ 1)
{\bf{Selecting all the participial adjectives of the database:}} \newline % Row Count 8 (+ 2)
part=all{[}all.derType=='participi'{]}  \newline % Row Count 9 (+ 1)
{\bf{If you want to check what you obtain:}} \newline % Row Count 10 (+ 1)
pred\_and\_dertype.head() \newline % Row Count 11 (+ 1)
{\bf{If you want to select a concrete variable, for instance, "participial adjectives":}} \newline % Row Count 13 (+ 2)
part=all{[}all.derType=='participi'{]}% Row Count 14 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\emph{symbol ''|'' means 'or'}}}  \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}{How to return a value distribution}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{sex\_var=pract.sex \newline % Row Count 1 (+ 1)
sex\_var.value\_counts()% Row Count 2 (+ 1)
} \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}{Contingency table}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{If we need to compare two categorical variables:}} \newline % Row Count 2 (+ 2)
first.head() \newline % Row Count 3 (+ 1)
\seqsplit{pd.crosstab(first.teacher},first.student\_passed)% Row Count 4 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\emph{we are cross-tabulating the teacher with whether the student passed the exam or not}}}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.09034 cm} x{2.88666 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{How to...}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{sample}} & {\bf{get a random sample}} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\seqsplit{first50=adjs.head(50)} & \seqsplit{random\_sample=adjs.sample(50)} \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
first50.head() & random\_sample.head() \tn 
% Row Count 4 (+ 1)
% Row 3
\SetRowColor{white}
first50.index & random\_sample.index \tn 
% Row Count 5 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}