\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{Nuozhi}
\pdfinfo{
  /Title (spacy.pdf)
  /Creator (Cheatography)
  /Author (Nuozhi)
  /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}{07A3D5}
\definecolor{LightBackground}{HTML}{EFF9FC}
\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}{Nuozhi} via \textcolor{DarkBackground}{\uline{cheatography.com/122797/cs/22963/}}}
\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}Nuozhi \\
  \uline{cheatography.com/nuozhi} \\
  \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 24th May, 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}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Init}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{from spacy.lang.en import English \newline nlp = English()} \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}{Basic}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{doc = nlp("SOME TEXTS") \newline span = doc{[}i:j{]} \newline token = doc{[}i{]}} \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}{Pre-trained Model}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{nlp = \seqsplit{spacy.load('en\_core\_web\_sm')} \newline doc = nlp(MY\_TEXT)} \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}{Name entity}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{doc.ents} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{.text \newline .label\_}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{0.84609 cm} x{4.13091 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{spacy.tokens}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{Doc}} & `Doc(nlp.vocab, words=words, spaces = spaces)` \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
{\bf{Span}} & `Span(doc, i, j, label="PERSON")` \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{{\emph{index}}: i, j \newline {\emph{words}}: a collection of words \newline {\emph{spaces}}: a collecture of booleans}  \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}{Matcher}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{matcher = \seqsplit{spacy.matcher.Matcher(nlp.vocab)} \newline matches = matcher(doc)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{[}(id, start, end){]}}  \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}{Add pattern to matcher}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{pattern = {[} \{ key: value \} {]} \newline matcher.add("PATTERN\_NAME", None, pattern)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Two types of key:  \newline 1. regex pattern \newline 2. label (i.e. POS, entity)}  \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}{Phrase matching}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{matcher = \seqsplit{spacy.matcher.PhraseMatcher(nlp.vocab)} \newline pattern = nlp("Golden Retriever") \newline matcher.add("DOG", None, pattern) \newline  \newline for match\_id, start, end in matcher(doc): \newline     span = doc{[}start:end{]}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.84149 cm} x{3.13551 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Similarity}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{word vector}} & token.vector \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
{\bf{Doc}} & `doc1.similarity(doc2)` \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
{\bf{Span}} & \seqsplit{`span1.similarity(span2)`} \tn 
% Row Count 4 (+ 1)
% Row 3
\SetRowColor{white}
{\bf{Token}} & \seqsplit{`token1.similarity(token2)`} \tn 
% Row Count 6 (+ 2)
% Row 4
\SetRowColor{LightBackground}
{\bf{Doc by Token}} & `doc.similarity(token)` \tn 
% Row Count 8 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{return a similarity score 0\textasciitilde{}1 \newline NOT for small model \newline cosine similarity by default}  \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}{Pipeline}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/nuozhi_1590325284_pipeline.png}}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`nlp.pipe\_names` \newline `nlp.pipeline`}  \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}{Add pipeline component}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{def fn(doc): \newline     \# function body \newline     return doc \newline  \newline nlp.add\_pipe(fn, last, first, before, after)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.4931 cm} x{3.4839 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Set custom attributes}}  \tn
% Row 0
\SetRowColor{LightBackground}
add metadata & `doc.\_.ATTR = "ATTRIBUTE NAME"` \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
register globally & \seqsplit{`Doc.set\_extension("ATTR"}, default=None)` \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{set to doc, tokens, spans \newline access property via `.\_`}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{0.89586 cm} x{4.08114 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Extension attribute types}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{attribute} & \seqsplit{`Token.set\_extension("ATTR"}, defaut=Bool)` \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{property} & \seqsplit{`Span.set\_extension("PROP"}, getter=fn)` \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
method & \seqsplit{`Doc.set\_extension("METHOD"}, method=fn)` \tn 
% Row Count 6 (+ 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}{Boost up}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{nlp.pipe(DATA)} \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}{Passing in context}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{data = {[} ("SOME TEXTS", \{"KEY": "VAL"\}),  (...), {]} \newline  \newline \# Method 1 \newline for doc, ctx in nlp.pipe(data, as\_tuple=True): \newline     print( doc.ATTR, ctx{[}KEY{]} ) \newline  \newline \# Method 2 \newline Doc.set\_extension("KEY", default=None) \newline for doc, ctx in nlp.pipe(data, as\_tuples=True): \newline     doc.\_.KEY = ctx{[}"KEY"{]}} \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}{Using tokenizer only}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\# Method 1 \newline doc = nlp.make\_doc("SOME TEXTS") \newline  \newline \# Method 2 \newline with \seqsplit{nlp.disable\_pipes("tagger"}, "parser"): \newline     doc = nlp(text)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}