\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{LasseBoe (Lasse1618)}
\pdfinfo{
  /Title (python-pandas.pdf)
  /Creator (Cheatography)
  /Author (LasseBoe (Lasse1618))
  /Subject (Python 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}{000987}
\definecolor{LightBackground}{HTML}{F7F7FB}
\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{Python Pandas Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{LasseBoe (Lasse1618)} via \textcolor{DarkBackground}{\uline{cheatography.com/110079/cs/21581/}}}
\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}LasseBoe (Lasse1618) \\
  \uline{cheatography.com/lasse1618} \\
  \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 23rd 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*}{3}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Basics}}  \tn
% Row 0
\SetRowColor{LightBackground}
\%matplotlib inline & plots into notebook \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
df = pd.read\_csv({\emph{path}}, index\_col ='{\emph{name}}') & loads dataframe \tn 
% Row Count 4 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{df.head()} \tn 
% Row Count 5 (+ 1)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{df.tail()} \tn 
% Row Count 6 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{df.values} \tn 
% Row Count 7 (+ 1)
% Row 5
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{df.plot()\{\{nl\}\}df.plot(style='.')} \tn 
% Row Count 8 (+ 1)
% Row 6
\SetRowColor{LightBackground}
df.index & returns row indexes \tn 
% Row Count 9 (+ 1)
% Row 7
\SetRowColor{white}
df{[}{\emph{col}}{]}.loc{[}{\emph{index}}{]} & returns value with given column and index \tn 
% Row Count 12 (+ 3)
% Row 8
\SetRowColor{LightBackground}
df.loc{[}:, 'col\_n+1'{]} = x & referring to a col that doesn't exist creates a new one \tn 
% Row Count 15 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{p{0.4977 cm} p{0.4977 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{STOPPED FILLING AT LECTURE 6 LINE 122}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{} \tn 
% Row Count 0 (+ 0)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Basic Dataframe Analysis}}  \tn
% Row 0
\SetRowColor{LightBackground}
df.isnull() & returns bool \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
df{[}.isnull().sum & returns sum of trues \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
df.isnull().any & checks whether there is a true \tn 
% Row Count 4 (+ 2)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{`df{[}{\emph{col}}{]}.`max()\{\{nl\}\}`df{[}{\emph{col}}{]}.`min()} \tn 
% Row Count 5 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{`df{[}{\emph{col}}{]}.`idxmax()\{\{nl\}\}`df{[}{\emph{col}}{]}.`idxmin()} \tn 
% Row Count 6 (+ 1)
% Row 5
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{`df{[}{\emph{col}}{]}.`median()} \tn 
% Row Count 7 (+ 1)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{`df{[}{\emph{col}}{]}.`mean()} \tn 
% Row Count 8 (+ 1)
% Row 7
\SetRowColor{white}
`df{[}{\emph{col}}{]}.`describe() & gives statistic analysis \tn 
% Row Count 10 (+ 2)
% Row 8
\SetRowColor{LightBackground}
`df{[}{\emph{col}}{]}.`quantile(.5) & 50\% quantile \tn 
% Row Count 12 (+ 2)
% Row 9
\SetRowColor{white}
df.boxplot(by = '{\emph{col}}') & boxplot grouped by column \tn 
% Row Count 14 (+ 2)
% Row 10
\SetRowColor{LightBackground}
df.hist(bins = 20) & histogram in 20 bars \tn 
% Row Count 15 (+ 1)
% Row 11
\SetRowColor{white}
df.plot.scatter(x = '{\emph{name}}', y = '{\emph{name}}') & scatterplot \tn 
% Row Count 18 (+ 3)
% Row 12
\SetRowColor{LightBackground}
\seqsplit{pd.plotting.scatter\_matrix(df)} & multiple scatterplots \tn 
% Row Count 20 (+ 2)
% Row 13
\SetRowColor{white}
\seqsplit{pd.plotting.parallel\_coordinates(df}, '{\emph{name}}') & lines drawn connecting dimensions of an entry \tn 
% Row Count 23 (+ 3)
% Row 14
\SetRowColor{LightBackground}
df{[}'col\_name'{]}.unique & returns list of singled entries \tn 
% Row Count 25 (+ 2)
% Row 15
\SetRowColor{white}
pd.get\_dummies(df, columns={[}'Name'{]}) & dummie column (0 or 1) that indicates whether the entry in another column is a certain entry \tn 
% Row Count 30 (+ 5)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Basic Dataframe Analysis (cont)}}  \tn
% Row 16
\SetRowColor{LightBackground}
np.random.choice(n, x, replace=false) & selects random set \tn 
% Row Count 2 (+ 2)
% Row 17
\SetRowColor{white}
np.setdiff1d(set\_1, set\_2) & New set with only the differing entries \tn 
% Row Count 4 (+ 2)
% Row 18
\SetRowColor{LightBackground}
df.to\_numpy() & gives array of entries \tn 
% Row Count 6 (+ 2)
\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}{Working with a Dataframe}}  \tn
% Row 0
\SetRowColor{LightBackground}
df{[}'{\emph{col1}}'{]} == x & bool if entry is x \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
df{[}df == x{]} = y & replace all values of a kind \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Label-based indexing with .loc / .iloc}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{df.loc{[}{\emph{rowindex}}, {\emph{columnname}}{]}} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
df.loc{[}3, {\emph{col1}}{]}\{\{nl\}\}df.loc{[}3:6, {[}'{\emph{col1}}', '{\emph{col2}}'{]}{]} & 3rd entry of 1st column \tn 
% Row Count 4 (+ 3)
% Row 2
\SetRowColor{LightBackground}
df.loc{[}:, '{\emph{col1}}' {]} == '{\emph{name}}' & column with t/f whether entry in col1 is name \tn 
% Row Count 7 (+ 3)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{} \tn 
% Row Count 7 (+ 0)
% Row 4
\SetRowColor{LightBackground}
df.iloc{[}3:-1, 2:{]} & {[}rows, columns{]} \tn 
% Row Count 8 (+ 1)
% Row 5
\SetRowColor{white}
df.iloc{[}:, {[}3, 1{]}{]} & columns with index 3 \& 1 \tn 
% Row Count 10 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{`.loc` is label based, `.iloc` is integer index based}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Series}}  \tn
% Row 0
\SetRowColor{LightBackground}
s1 = pd.Series({[}1, 2, 3{]}, index={[}'a', 'b', 'c'{]}) & creates a pandas series \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{s1.add(s2, fill\_value=0)} \tn 
% Row Count 4 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{s.isnull() ; s.notnull()} \tn 
% Row Count 5 (+ 1)
% Row 3
\SetRowColor{white}
s.dropna() & drops all rows with missing values \tn 
% Row Count 7 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{s.fillna(x)} \tn 
% Row Count 8 (+ 1)
% Row 5
\SetRowColor{white}
s = pd.DataFrame(\{'Size':s1, 'Weight':s2\}) & Best way to define dataframe out of series:\{\{nl\}\}Give dict out of columns \tn 
% Row Count 12 (+ 4)
% Row 6
\SetRowColor{LightBackground}
'e' in s1 & returns bool \tn 
% Row Count 13 (+ 1)
% Row 7
\SetRowColor{white}
s.name = 'str' & names series \tn 
% Row Count 14 (+ 1)
% Row 8
\SetRowColor{LightBackground}
s.index.name = 'str' & names index\{\{nl\}\}If s doesn't exist, this creates a df \tn 
% Row Count 17 (+ 3)
% Row 9
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{s.columns{[}'Red', 'Green'{]}\{\{nl\}\}s.columns.name = 'Color'} \tn 
% Row Count 19 (+ 2)
% Row 10
\SetRowColor{LightBackground}
s.reindex{[}('m', 'n', 'o'{]}, method = 'ffill') & ffill = forward fill \tn 
% Row Count 22 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}