\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{cheatingcvrlo}
\pdfinfo{
  /Title (is450.pdf)
  /Creator (Cheatography)
  /Author (cheatingcvrlo)
  /Subject (is450 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{is450 Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{cheatingcvrlo} via \textcolor{DarkBackground}{\uline{cheatography.com/183658/cs/38238/}}}
\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}cheatingcvrlo \\
  \uline{cheatography.com/cheatingcvrlo} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Published 16th April, 2023.\\
   Updated 17th April, 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{multicols*}{3}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{preprocessing pipeline}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\{\{lang-python\}\}def corpus2docs(corpus): \newline     fids = corpus.fileids() \newline     docs1 = {[}{]} \newline     for fid in fids: \newline         doc\_raw = corpus.raw(fid) \newline         doc = \seqsplit{nltk.word\_tokenize(doc\_raw)} \newline         docs1.append(doc) \newline     docs2 = {[}{[}w.lower() for w in doc{]} for doc in docs1{]} \newline     docs3 = {[}{[}w for w in doc if re.search('\textasciicircum{}{[}a-z{]}+\$', w){]} for doc in docs2{]} \newline     docs4 = {[}{[}w for w in doc if w not in stop\_list{]} for doc in docs3{]} \newline     docs5 = {[}{[}stemmer.stem(w) for w in doc{]} for doc in docs4{]} \newline     return docs5 \newline  \newline def docs2vecs(docs, dictionary): \newline     \# docs is a list of documents returned by corpus2docs. \newline     \# dictionary is a \seqsplit{gensim.corpora.Dictionary} object. \newline     vecs1 = {[}dictionary.doc2bow(doc) for doc in docs{]} \newline     tfidf = \seqsplit{gensim.models.TfidfModel(vecs1)} \newline     vecs2 = {[}tfidf{[}vec{]} for vec in vecs1{]} \newline     return vecs2} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.09034 cm} x{2.88666 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{POS tags}}  \tn
% Row 0
\SetRowColor{LightBackground}
N (noun) & dog, cat, chair \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
V (verb) & read, write, get \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
ADJ (adjective) & pretty, smart, blue \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
ADV (adverb) & gently, carefully, extremely \tn 
% Row Count 5 (+ 2)
% Row 4
\SetRowColor{LightBackground}
P (preposition) & in, on, by, with, about \tn 
% Row Count 6 (+ 1)
% Row 5
\SetRowColor{white}
PRO (pronoun) & I, me, mine, it, they... \tn 
% Row Count 8 (+ 2)
% Row 6
\SetRowColor{LightBackground}
CON (conjunction) & and, or, but, while, because \tn 
% Row Count 10 (+ 2)
% Row 7
\SetRowColor{white}
INT (interjection) & ooh, wow, yeah \tn 
% Row Count 12 (+ 2)
% Row 8
\SetRowColor{LightBackground}
DET (determiner) & all, his, they \tn 
% Row Count 13 (+ 1)
% Row 9
\SetRowColor{white}
AUX (auxiliary verb) & {\bf{have}} done, {\bf{might}} do \tn 
% Row Count 15 (+ 2)
% Row 10
\SetRowColor{LightBackground}
PAR (particle) & look {\bf{up}}, get {\bf{on}} \tn 
% Row Count 16 (+ 1)
% Row 11
\SetRowColor{white}
NUM (numeral) & one, two, three \tn 
% Row Count 17 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Context-free grammar}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Grammar = \{ \newline     objects: {[} \newline         Words/tokens: {\bf{terminals}}, \newline         Right above: {\bf{pos tags}}, \newline         Above: {\bf{syntactic tags}}, \newline         Above: {\bf{sentence}} \newline     {]}; \newline     Rules: {[} \newline         X: node name,    \#eg "VP" (verb phrase) \newline         Y: sequence of objects that make up X    \#eg (V+NP) \newline     {]} \newline \}} \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}{Morphemes}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{stems, affixes (prefix/suffix). Useful for POS tagging and text normalization% Row Count 2 (+ 2)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.9908 cm} x{2.9862 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Semantics}}  \tn
% Row 0
\SetRowColor{LightBackground}
synonyms & diff words, same meaning \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
polyseme & same word, diff meaning \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{hypernym/hyponym} & category \textgreater{}\textgreater{}\textgreater{} specific \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
meronym/metonym & part \textgreater{}\textgreater{}\textgreater{} whole \tn 
% Row Count 4 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{LDA}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/cheatingcvrlo_1681633865_lda.png}}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.34379 cm} x{3.63321 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{LDA}}  \tn
% Row 0
\SetRowColor{LightBackground}
gibbs sampling & 1. random word-to-topic assignment \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
 & 2. re-assign each word to a topic, one by one, {\bf{assuming all other assignments are correct}} \tn 
% Row Count 6 (+ 4)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{hyperparameters} & high \$alpha\$ -{}-\textgreater{} documents feature a mixture of most topics \tn 
% Row Count 9 (+ 3)
% Row 3
\SetRowColor{white}
 & high \$eta\$ -{}-\textgreater{} topics feature a mixture of most words \tn 
% Row Count 11 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{evaluation} & coherence (PMI), human eval \tn 
% Row Count 12 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Sentiment-Topic Model (Plate Notation)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/cheatingcvrlo_1681634916_jst.png}}} \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}{Cluster Purity}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/cheatingcvrlo_1681633634_cluster_purity.png}}} \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}{Overall purity}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/cheatingcvrlo_1681633564_purity.png}}} \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}{Cluster Entropy}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/cheatingcvrlo_1681633787_cluster_entropy.png}}} \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}{Pointwise Mutual Information}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/cheatingcvrlo_1681634733_pmi.png}}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.14011 cm} x{2.83689 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Discourse Markers}}  \tn
% Row 0
\SetRowColor{LightBackground}
causal & because \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
consequence & as a result \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
conditional & if \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
temporal & when \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
additive & and \tn 
% Row Count 5 (+ 1)
% Row 5
\SetRowColor{white}
elaboration & {[}exemplification, re-wording{]} \tn 
% Row Count 7 (+ 2)
% Row 6
\SetRowColor{LightBackground}
\seqsplit{contrastive/concessive} & but \tn 
% Row Count 9 (+ 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}{Preparation for NLTK classifier}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\#doc\_tuple = (doc\_representation, label) \newline % Row Count 1 (+ 1)
\textgreater{} `\{\{lang-python\}\}(\{'police':1, 'lawyer':1, 'court':1\}, 'Crime')`  \newline % Row Count 3 (+ 2)
\#train\_set = {[}doc\_tuple1, doc\_tuple2, ...{]}% Row Count 4 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}