\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{datamansam}
\pdfinfo{
  /Title (reg-ex-cheatsheet.pdf)
  /Creator (Cheatography)
  /Author (datamansam)
  /Subject (Reg Ex CheatSheet 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}{A3A3A3}
\definecolor{LightBackground}{HTML}{F3F3F3}
\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{Reg Ex CheatSheet Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{datamansam} via \textcolor{DarkBackground}{\uline{cheatography.com/139410/cs/29846/}}}
\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}datamansam \\
  \uline{cheatography.com/datamansam} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Published 30th November, 2021.\\
   Updated 23rd November, 2021.\\
   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{1.55618 cm} x{1.51041 cm} x{1.51041 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Regex}}  \tn
% Row 0
\SetRowColor{LightBackground}
(*) indicates that the preceding character can occur 0 or more times. & meo*w & mew, meow, meooow, and \seqsplit{meoooooooooooow} \tn 
% Row Count 6 (+ 6)
% Row 1
\SetRowColor{white}
? - character can appear either 0 or 1 time & humou?r & humour   humor \tn 
% Row Count 10 (+ 4)
% Row 2
\SetRowColor{LightBackground}
. and it can match any single character (letter, number, symbol or whitespace) in a piece of text & ......... & any 9-character text \tn 
% Row Count 18 (+ 8)
% Row 3
\SetRowColor{white}
{[}{]} will match any of the characters included within the brackets & con{[}sc{]}en{[}sc{]}us & consensus, concensus, consencus, and concencus \tn 
% Row Count 23 (+ 5)
% Row 4
\SetRowColor{LightBackground}
\{\} contains the exact quantity & roa\{3\}r & roaaar \tn 
% Row Count 26 (+ 3)
% Row 5
\SetRowColor{white}
\{\}n. the quantity range of characters to be matched & roa\{3,6\}r & roaaar, roaaaar, roaaaaar, or roaaaaaar \tn 
% Row Count 30 (+ 4)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{5.377cm}{x{1.55618 cm} x{1.51041 cm} x{1.51041 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Regex (cont)}}  \tn
% Row 6
\SetRowColor{LightBackground}
|, allows for the matching of either of two \seqsplit{subexpressions}. & \seqsplit{baboons|gorillas} & will match the text baboons as well as the text gorillas. \tn 
% Row Count 5 (+ 5)
% Row 7
\SetRowColor{white}
Anchors (hat \textasciicircum{} and dollar sign \$) are used in regular expressions to match text at the start and end of a string, \seqsplit{respectively.} & \textasciicircum{}Monkeys: my mortal enemy\$ & will completely match the text Monkeys: my mortal enemy but not match Spider Monkeys: my mortal enemy or Monkeys: my mortal enemy in the wild \tn 
% Row Count 16 (+ 11)
% Row 8
\SetRowColor{LightBackground}
{[}letter-letter{]} or {[}n-n{]} & a range of characters that can be matched & {[}A-Z{]}. : match any uppercase letter {[}a-z{]}. : match any lowercase letter {[}0-9{]}. : match any digit {[}A-Za-z{]} : match any uppercase or lowercase letter \tn 
% Row Count 28 (+ 12)
% Row 9
\SetRowColor{white}
Shorthand character classes simplify writing regular expressions & \textbackslash{}w represents the regex range {[}A-Za-z0-9\_{]}, \textbackslash{}d represents {[}0-9{]}, & \textbackslash{}W represents {[}\textasciicircum{}A-Za-z0-9\_{]} matching any character not included by \textbackslash{}w, \textbackslash{}D represents {[}\textasciicircum{}0-9{]} matching any character not included by \textbackslash{}d \tn 
% Row Count 39 (+ 11)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{5.377cm}{x{1.55618 cm} x{1.51041 cm} x{1.51041 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Regex (cont)}}  \tn
% Row 10
\SetRowColor{LightBackground}
Negated character set & {[}\textasciicircum{}cdh{]}are & will match the m in mare. \tn 
% Row Count 2 (+ 2)
% Row 11
\SetRowColor{white}
+ ndicates that the preceding character can occur 1 or more times & meo+w & will match meow, meooow, and \seqsplit{meoooooooooooow}, but not match mew \tn 
% Row Count 7 (+ 5)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.55618 cm} x{1.51041 cm} x{1.51041 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Text Preprocessing}}  \tn
% Row 0
\SetRowColor{LightBackground}
Noise removal & import re          result = re.sub(r'{[}\textbackslash{}.\textbackslash{}?\textbackslash{}!\textbackslash{},\textbackslash{}:\textbackslash{};\textbackslash{}"{]}', '', text) & Removes Punctuation \tn 
% Row Count 5 (+ 5)
% Row 1
\SetRowColor{white}
Tokenization is the text \seqsplit{preprocessing} task of breaking up text into smaller components of text & from \seqsplit{nltk.tokenize} import \seqsplit{word\_tokenize}   text = "This is a text to tokenize" tokenized = \seqsplit{word\_tokenize(text)} & \seqsplit{print(tokenized)} \# {[}"This", "is", "a", "text", "to", "tokenize"{]} \tn 
% Row Count 14 (+ 9)
% Row 2
\SetRowColor{LightBackground}
In natural language processing, \seqsplit{normalization} encompasses many text \seqsplit{preprocessing} tasks including & stemming, \seqsplit{lemmatization}, & upper or lowercasing, and stopwords removal. \tn 
% Row Count 22 (+ 8)
% Row 3
\SetRowColor{white}
Stemming In natural language processing, stemming is the text \seqsplit{preprocessing} \seqsplit{normalization} task concerned with bluntly removing word affixes (prefixes and suffixes). & from nltk.stem import \seqsplit{PorterStemmer}   tokenized = {[}"So", "many", "squids", "are", "jumping"{]}   stemmer = \seqsplit{PorterStemmer()} stemmed = {[}stemmer.stem(token) for token in tokenized{]} & \# {[}'So', 'mani', 'squid', 'are', 'jump'{]} \tn 
% Row Count 36 (+ 14)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{5.377cm}{x{1.55618 cm} x{1.51041 cm} x{1.51041 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Text Preprocessing (cont)}}  \tn
% Row 4
\SetRowColor{LightBackground}
\seqsplit{Lemmatization} In natural language processing, \seqsplit{lemmatization} is the text \seqsplit{preprocessing} \seqsplit{normalization} task concerned with bringing words down to their root forms. & from nltk.stem import \seqsplit{WordNetLemmatizer}   tokenized = {[}"So", "many", "squids", "are", "jumping"{]}   lemmatizer = \seqsplit{WordNetLemmatizer()} lemmatized = {[}lemmatizer.lemmatize(token) for token in tokenized{]} & {[}'So', 'many', 'squid', 'be', 'jump'{]} \tn 
% Row Count 16 (+ 16)
% Row 5
\SetRowColor{white}
stopword removal is the process of removing words from a string that don't provide any information about the tone of a statement. & from nltk.corpus import stopwords    \# define set of English stopwords stop\_words = \seqsplit{set(stopwords}.words('english')) & \# remove stopwords from tokens in dataset \seqsplit{statement\_no\_stop} = {[}word for word in word\_tokens if word not in stop\_words{]} \tn 
% Row Count 27 (+ 11)
% Row 6
\SetRowColor{LightBackground}
parser. \seqsplit{chunk.RegexpParser} & Uses a set of regular expression patterns to specify the behavior of the parser & \{\textless{}DT|JJ\textgreater{}\}  \# chunk determiners and adjectives \tn 
% Row Count 34 (+ 7)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\SetRowColor{LightBackground}
\mymulticolumn{3}{x{5.377cm}}{Token = Smaller Component of Text  \newline Stem = Remove prefix and suffix \newline Lemmatization = Bring down to root \newline Stopword = Remove meaningless}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.69349 cm} x{1.19002 cm} x{1.69349 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Lists and Strings}}  \tn
% Row 0
\SetRowColor{LightBackground}
z = 'Natural Language Processing' & \seqsplit{z.replace('} ', '\textbackslash{}n') & 'Natural\textbackslash{}nLanguage\textbackslash{}nProcessing' \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
 & list(z) & Split text into character tokens \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
 & set(z) & Unique tokens \tn 
% Row Count 7 (+ 1)
% Row 3
\SetRowColor{white}
x = {[}'Natural', 'Language', 'Toolkit'{]} & \seqsplit{x.insert(0}, 'Python') & {[}'Language', 'Natural', 'Python', 'Toolkit'{]} \tn 
% Row Count 12 (+ 5)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}