\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{email2automate}
\pdfinfo{
  /Title (pandas-for-data-analysis.pdf)
  /Creator (Cheatography)
  /Author (email2automate)
  /Subject (Pandas for Data Analysis 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}{088395}
\definecolor{LightBackground}{HTML}{EFF7F8}
\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 for Data Analysis Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{email2automate} via \textcolor{DarkBackground}{\uline{cheatography.com/184557/cs/38509/}}}
\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}email2automate \\
  \uline{cheatography.com/email2automate} \\
  \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 3rd May, 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{tabularx}{17.67cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{17.67cm}}{\bf\textcolor{white}{Shared Attributes}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{17.67cm}}{.head(n) \newline .tail(n) \newline .index \newline .values \newline .shape \newline .axes \newline .info()} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{17.67cm}}{Common attributes shared between pd.Series and pd.DataFrame}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{17.67cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{17.67cm}}{\bf\textcolor{white}{Null Unique Values}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{17.67cm}}{{\bf{Drop Null Values}} \newline % Row Count 1 (+ 1)
`df.dropna(how= any/all, inplace = T/F)` \newline % Row Count 2 (+ 1)
`df.dropna(subset = {[}'col\_name1', 'col\_name2'{]}, how = any/all, inplace = T/F)`  - from specific columns \newline % Row Count 5 (+ 3)
{\bf{Fill Null Values}} \newline % Row Count 6 (+ 1)
`df.fillna(value, inplace = T/F)` - acts on entire data frame. \newline % Row Count 8 (+ 2)
`df{[}'col\_name'{]}.fillna(value = 'fill\_value', inplace = T/F)` - act on selected columns \newline % Row Count 10 (+ 2)
{\bf{Unique Values}} \newline % Row Count 11 (+ 1)
`df{[}'col{]}.unique()`  - Returns unique values as a list(including null values) \newline % Row Count 13 (+ 2)
`df.nunique()` - No of unique Values.(by default doesn't count null) \newline % Row Count 15 (+ 2)
`df.unique(dropna = False)` \newline % Row Count 16 (+ 1)
`df{[}'col'{]}.nunique()` \newline % Row Count 17 (+ 1)
`df{[}'col'{]}.unique(dropna = True/False)` \newline % Row Count 18 (+ 1)
Panda Series \newline % Row Count 19 (+ 1)
`pd.Series.hasnans` \newline % Row Count 20 (+ 1)
`pds.nunique()` - No of unique Values. \newline % Row Count 21 (+ 1)
`pdf.unique(dropna = True/False)` - Returns unique values in a list.% Row Count 23 (+ 2)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{17.67cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{17.67cm}}{\bf\textcolor{white}{Dealing Columns}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{17.67cm}}{`df.columns` -retuns column names as a list \newline % Row Count 1 (+ 1)
`df{[}'new\_col'{]}=list/series` \newline % Row Count 2 (+ 1)
`df.insert{[}loc = n, column= col\_name, value= New\_value/array{]}` -inserts column at desired position / location% Row Count 5 (+ 3)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{17.67cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{17.67cm}}{\bf\textcolor{white}{Sort, Rank, Count}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{17.67cm}}{{\bf{Sort}} \newline % Row Count 1 (+ 1)
\seqsplit{`df.sort\_index(ascending} = True/False)`   - Sort Index \newline % Row Count 3 (+ 2)
\seqsplit{`df.sort\_values(col\_name}, na\_position = "First/Last", ascending = True/False)`   - Sort based on values \newline % Row Count 6 (+ 3)
`df.sort\_values({[}'col\_name, 'col2'{]}, ascending = {[}True, False{]})`  - Sort by Multiple Columns \newline % Row Count 8 (+ 2)
{\bf{Rank}} \newline % Row Count 9 (+ 1)
`df{[}'col'{]}.rank(ascending = True/False)` - Ranks are assigned based on sorted values \newline % Row Count 11 (+ 2)
{\bf{counts}} \newline % Row Count 12 (+ 1)
`df.value\_counts()`  - counts exact rows \newline % Row Count 13 (+ 1)
\seqsplit{`df.value\_counts(normalise} = True)` \newline % Row Count 14 (+ 1)
`pds.value\_counts()`  - pd series% Row Count 15 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{17.67cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{17.67cm}}{\bf\textcolor{white}{Data Type Conversions and Optimization}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{17.67cm}}{`df{[}'col'{]} = pd.to\_datetime(df{[}'col'{]})` \newline % Row Count 1 (+ 1)
or we can parse dates in import itself. \newline % Row Count 2 (+ 1)
`pd.read\_csv(......, parse\_dates = {[}'col1','col2'{]})` \newline % Row Count 4 (+ 2)
`df{[}'col'{]} = df{[}'col'{]}.astype(dtype)` \newline % Row Count 5 (+ 1)
`dtype = bool, category, int`% Row Count 6 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{17.67cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{17.67cm}}{\bf\textcolor{white}{Filtering Data}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{17.67cm}}{{\bf{Multiple Conditional Filtering}} \newline % Row Count 1 (+ 1)
`mask1 = df{[}col1'{]} == 'value'`  - Returns True/False boolean series \newline % Row Count 3 (+ 2)
`mask2 = df{[}col2'{]} \textless{}= 'value'` \newline % Row Count 4 (+ 1)
`mask3 = df{[}col3'{]} \textgreater{}= 'value'` \newline % Row Count 5 (+ 1)
`df{[}(mask1 \& mask2) | mask3{]}` \newline % Row Count 6 (+ 1)
{\bf{Inclusion Check}} \newline % Row Count 7 (+ 1)
`mask = df{[}'col'{]}.isin({[}'val1','val2','val3'{]})` - Check for inclusion using isin() method. \newline % Row Count 9 (+ 2)
`mask1 = df{[}col1'{]} == 'val1'`  - isin method is equal to three conditional checks.  \newline % Row Count 11 (+ 2)
`mask1 = df{[}col1'{]} == 'val2'`  \newline % Row Count 12 (+ 1)
`mask1 = df{[}col1'{]} == 'val3'`  \newline % Row Count 13 (+ 1)
{\bf{For NULL values}} \newline % Row Count 14 (+ 1)
`mask = df{[}'col'{]}.isnull()`  - Returns True/False boolean series \newline % Row Count 16 (+ 2)
`mask = df{[}'col'{]}.notnull()`  - Returns True/False boolean series \newline % Row Count 18 (+ 2)
{\bf{Inclusion Check within a range}} \newline % Row Count 19 (+ 1)
`mask = df{[}'col'{]}.between(val1, val2)` -Returns True/False boolean series. True for values within range. \newline % Row Count 22 (+ 3)
{\bf{Duplicate Values}} \newline % Row Count 23 (+ 1)
`mask = df{[}'col'{]}.duplicated(keep = "First/Last/False")` - Returns boolean series, True for Duplicates \newline % Row Count 26 (+ 3)
`df.drop\_duplicates()`  -Deletes duplicate from df. if applied on df complete row should be identical. \newline % Row Count 29 (+ 3)
\seqsplit{`df.drop\_duplicates(subset} = {[}'col1','col2'{]})` - Drops if the combination of col1 and col2 are identical.% Row Count 32 (+ 3)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{17.67cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{17.67cm}}{\bf\textcolor{white}{Data Extraction}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{17.67cm}}{SET INDEX \newline % Row Count 1 (+ 1)
RESET INDEX \newline % Row Count 2 (+ 1)
LOC ACCESSOR \newline % Row Count 3 (+ 1)
ILOC ACCESSOR \newline % Row Count 4 (+ 1)
`CODE`% Row Count 5 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}



\end{document}