\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{Daryabi}
\pdfinfo{
  /Title (scikit-learn.pdf)
  /Creator (Cheatography)
  /Author (Daryabi)
  /Subject (Scikit Learn 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{Scikit Learn Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{Daryabi} via \textcolor{DarkBackground}{\uline{cheatography.com/181709/cs/37825/}}}
\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}Daryabi \\
  \uline{cheatography.com/daryabi} \\
  \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 21st March, 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*}{2}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Data Preprocessing}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{from sklearn.preprocessing import \textless{}classname\textgreater{} \newline  \newline StandardScaler, MinMaxScaler, RobustScaler \newline QuantileTransformer , PowerTransformer, FunctionTransformer \newline KBinsDiscretizer , PolynomialFeatures , Normalizer \newline scaler = StandardScaler()  \newline  \newline  \newline \# Apply a user-defined function to the data \newline transformer = \seqsplit{FunctionTransformer(np.log1p)} \newline  \newline \#  Discretize features into k bins \newline discretizer = \seqsplit{KBinsDiscretizer(n\_bins=3}, encode='ordinal', strategy='uniform') \newline  \newline poly\_features = \seqsplit{PolynomialFeatures(degree=2)} \newline  \newline X\_scaled = \textless{}object\textgreater{}.fit\_transform(X)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Encoding Categorical Data}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{from sklearn.preprocessing import \textless{}classname\textgreater{} \newline  \newline LabelEncoder , OneHotEncoder , OrdinalEncoder , LabelBinarizer \newline  \newline tb = OneHotEncoder() \newline le = LabelEncoder() \newline lb = LabelBinarizer() \newline  \newline y = le.fit\_transform({[}'Yes', 'No', 'Yes'{]}) \newline y = lb.fit\_transform({[}'Yes', 'No', 'Yes'{]}) \newline  \newline X\_encoded = tb.fit\_transform(X)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Handling missing values}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{from sklearn.impute import  SimpleImputer, KNNImputer , IterativeImputer , MissingIndicator \newline from sklearn.experimental import \seqsplit{enable\_iterative\_imputer} \newline  \newline imputer = \seqsplit{SimpleImputer(strategy='mean')} \newline imputer = \seqsplit{KNNImputer(n\_neighbors=2)} \newline imputer = \seqsplit{IterativeImputer(random\_state=0)} \newline indicator = MissingIndicator() \newline  \newline X\_imputed = \seqsplit{imputer.fit\_transform(X)}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Feature Selection:}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{from \seqsplit{sklearn.feature\_selection} import  \newline  \newline SelectKBest ,SelectPercentile, SelectFromModel, VarianceThreshold, RFE,  RFECV,   \newline SequentialFeatureSelector} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Dimensionality Reduction}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{from sklearn.decomposition import \newline  \newline PCA, IncrementalPCA, TruncatedSVD, KernelPCA, NMF, FastICA, \seqsplit{LatentDirichletAllocation} \newline  \newline pca = PCA(n\_components=2) \newline kpca = \seqsplit{KernelPCA(n\_components=2}, kernel='rbf') \newline tsne = TSNE(n\_components=2) \newline  \newline X\_new = any.fit\_transform(X)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Pipelines:}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{from sklearn.pipeline import \newline  \newline Pipeline \newline FeatureUnion \newline ColumnTransformer} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Supervised Learning Models:}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{Linear Models:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}LinearRegression, Ridge, Lasso, ElasticNet, LogisticRegression, SGDClassifier, SGDRegressor, Perceptron} \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{Naive Bayes:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}GaussianNB, BernoulliNB, MultinomialNB,} \tn 
% Row Count 6 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{Tree-Based Models:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}DecisionTreeClassifier, DecisionTreeRegresso,} \tn 
% Row Count 8 (+ 2)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{Support Vector Machines (SVM):} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}SVC, SVR, LinearSVC, LinearSVR, NuSVC, NuSVR, OneClassSVM} \tn 
% Row Count 11 (+ 3)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{Nearest Neighbors:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}KNeighborsClassifier, KNeighborsRegressor, \seqsplit{RadiusNeighborsClassifier}, RadiusNeighborsRegressor} \tn 
% Row Count 14 (+ 3)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{Neural Networks:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}MLPClassifier, MLPRegressor} \tn 
% Row Count 16 (+ 2)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{Ensemble} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}RandomForestClassifier, RandomForestRegressor, \seqsplit{GradientBoostingClassifier}, \seqsplit{GradientBoostingRegressor}, ExtraTreesClassifier, ExtraTreesRegressor, AdaBoostClassifier, AdaBoostRegressor} \tn 
% Row Count 21 (+ 5)
% Row 7
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{xgboost} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}XGBClassifier, XGBRegressor} \tn 
% Row Count 23 (+ 2)
% Row 8
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{lightgbm} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}LGBMClassifier, LGBMRegressor} \tn 
% Row Count 25 (+ 2)
% Row 9
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{catboost} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}CatBoostClassifier, CatBoostRegressor,} \tn 
% Row Count 27 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{from sklearn.linear\_model import     ,from sklearn.naive\_bayes ,  from sklearn.tree   \newline from sklearn.ensemble , from xgboost import ,    from lightgbm import \newline from catboost import ,   from sklearn.svm  \newline from sklearn.neighbors \newline from sklearn.neural\_network import}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Semi-Supervised Learning:}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{LabelPropagation \newline LabelSpreading} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Unsupervised Learning Models}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{Clustering:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}KMeans, AgglomerativeClustering ,DBSCAN, Birch,  SpectralClustering} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{Dimensionality Reduction:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}PCA, IncrementalPCA, TruncatedSVD, KernelPCA, NMF, FastICA, \seqsplit{LatentDirichletAllocation}} \tn 
% Row Count 6 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Clustering}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{KMeans \newline AgglomerativeClustering \newline DBSCAN \newline Birch \newline SpectralClustering} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Model Evaluation Metrics}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{Regression Metrics:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}mean\_squared\_error, r2\_score, mean\_absolute\_error, \seqsplit{explained\_variance\_score}, median\_absolute\_error, \seqsplit{mean\_squared\_log\_error}} \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{Classification Metrics:} \tn 
\mymulticolumn{1}{x{8.4cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}accuracy\_score, precision\_score, recall\_score, f1\_score, roc\_auc\_score, \seqsplit{average\_precision\_score}, log\_loss, confusion\_matrix, classification\_report} \tn 
% Row Count 9 (+ 5)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{from sklearn.metrics import}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}