\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{LoiVyen}
\pdfinfo{
  /Title (spacy.pdf)
  /Creator (Cheatography)
  /Author (LoiVyen)
  /Subject (spaCy 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}{3345A3}
\definecolor{LightBackground}{HTML}{F2F3F9}
\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{spaCy Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{LoiVyen} via \textcolor{DarkBackground}{\uline{cheatography.com/163788/cs/34314/}}}
\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}LoiVyen \\
  \uline{cheatography.com/loivyen} \\
  \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 2nd October, 2022.\\
   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}{Base Initialization}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`import spacy`} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{`nlp = spacy.blank("en")\{\{nl\}\}nlp = spacy.load("en\_core\_web\_sm")\{\{nl\}\}nlp = spacy.load("en\_core\_web\_md")\{\{nl\}\}nlp = spacy.load("en\_core\_web\_lg")\{\{nl\}\} nlp = \seqsplit{spacy.load("en\_core\_web\_trf")`}} \tn 
% Row Count 5 (+ 4)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`doc = nlp("Insert your text here. This string will be used to create a doc object. For natural language processing.")`} \tn 
% Row Count 8 (+ 3)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{`print("tokens: ", {[}token.text for token in doc{]})`} \tn 
% Row Count 9 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{output:}}\{\{nl\}\}tokens:  {[}'Insert', 'your', 'text', 'here', '.', 'This', 'string', 'will', 'be', 'used', 'to', 'create', 'a', 'doc', 'object', '.', 'For', 'natural', 'language', 'processing', '.'{]}} \tn 
% Row Count 13 (+ 4)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Token Attributes applied}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Remove punctuations for tokens} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{`words = {[}token.text for token in doc if token.is\_stop != True and token.is\_punct != True{]} \{\{nl\}\}print (words)`} \tn 
% Row Count 4 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{output:}} \{\{nl\}\} {[}'Insert', 'text', 'string', 'create', 'doc', 'object', 'natural', 'language', 'processing'{]}} \tn 
% Row Count 7 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{https://spacy.io/api/token}}  \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}{Lemma}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`for token in doc:     \{\{nl\}\}~~~~print("token: ", token, " lemma: ", token.lemma\_)`} \tn 
% Row Count 3 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{token: token object within object \newline lemma: 'base' form of token  \newline (ex. going -{}-\textgreater{} go; was -{}-\textgreater{} be)}  \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}{displaCy Visualizer}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`import spacy \{\{nl\}\}from spacy import displacy`} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{`nlp = \seqsplit{spacy.load("en\_core\_web\_sm")} \{\{nl\}\}doc = nlp("This is a sentence.") \{\{nl\}\}displacy.render(doc, style='dep',jupyter=True)`} \tn 
% Row Count 4 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Sentence}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`list(doc.sents) \{\{nl\}\}print(list(text.sents))`} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{output:}} \{\{nl\}\}{[}Insert your text here., This string will be used to create a doc object., For natural language processing.{]}} \tn 
% Row Count 4 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Word Frequency}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`from collections import Counter`} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{`words = {[}token.text for token in doc if token.is\_stop != True and token.is\_punct != True{]} \{\{nl\}\}word\_freq = Counter(words) \{\{nl\}\}common\_words = \seqsplit{word\_freq.most\_common(5)} \{\{nl\}\}print (common\_words)`} \tn 
% Row Count 5 (+ 4)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{output:} \tn 
% Row Count 6 (+ 1)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{[}('Insert', 1), ('text', 1), ('string', 1), ('create', 1), ('doc', 1){]}} \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{Using textrank component ("custom")}}} \tn 
% Row Count 9 (+ 1)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\seqsplit{`nlp.add\_pipe("textrank")} \{\{nl\}\}doc = nlp("Insert your text here. This string will be used to create a doc object. For natural language processing.")`} \tn 
% Row Count 12 (+ 3)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`for index, token in \seqsplit{enumerate(doc.\_.phrases):}     \{\{nl\}\}~~~~print("index: ", index, "\textbackslash{}ntext: ", token.text)     \{\{nl\}\}~~~~print("rank:", token.rank, " count:", token.count)     \{\{nl\}\}~~~~print("chunks: ", token.chunks)`} \tn 
% Row Count 18 (+ 6)
% Row 7
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{output:} \tn 
% Row Count 19 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{index:  0  \newline text:  natural language processing \newline rank: 0.22805281953000428  count: 1 \newline chunks:  {[}natural language processing{]} \newline index:  1  \newline text:  a doc object \newline rank: 0.1481208925234081  count: 1 \newline chunks:  {[}a doc object{]} \newline index:  2  \newline text:  your text \newline rank: 0.073534568107334  count: 1 \newline chunks:  {[}your text{]} \newline index:  3  \newline text:  This string \newline rank: 0.054063724281900864  count: 1 \newline chunks:  {[}This string{]}}  \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}{Textacy}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`pip install textacy`} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{`import textacy`} \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`metadata = \{      \{\{nl\}\}~~~~"title": "Natural-language processing",      \{\{nl\}\}~~~~"url": \seqsplit{"https://en.wikipedia.org/wiki/Natural-language\_processing"},      \{\{nl\}\}~~~~"source": "wikipedia", \{\{nl\}\}\}doc = \seqsplit{textacy.make\_spacy\_doc((text}, metadata), lang="en\_core\_web\_sm")\{\{nl\}\}print(doc.\_.meta{[}"title"{]})`} \tn 
% Row Count 10 (+ 8)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\emph{output:}} Natural-language processing} \tn 
% Row Count 11 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{"`{\bf{textacy}}` is a Python library for performing a variety of natural language processing (NLP) tasks, built on the highperformance spaCy library" \newline https://github.com/chartbeat-labs/textacy \newline https://textacy.readthedocs.io/en/latest/ \newline  \newline latest version documentation:  \newline https://buildmedia.readthedocs.org/media/pdf/textacy/stable/textacy.pdf \newline https://textacy.readthedocs.io/en/0.12.0/api\_reference/datasets\_resources.html}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}