\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{Manasa}
\pdfinfo{
  /Title (scikit-learn-python.pdf)
  /Creator (Cheatography)
  /Author (Manasa)
  /Subject (Scikit-Learn Python 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}{A30A0A}
\definecolor{LightBackground}{HTML}{FCF7F7}
\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 Python Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{Manasa} via \textcolor{DarkBackground}{\uline{cheatography.com/121399/cs/22207/}}}
\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}Manasa \\
  \uline{cheatography.com/manasa} \\
  \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 30th March, 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{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Machine Learning}}  \tn
% Row 0
\SetRowColor{LightBackground}
Supervised Learning & Unsupervised learning \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
The model maps input to an output based on the previous input-output pairs & No training is given to the model and it has to discover the features of input by self training mechanism. \tn 
% Row Count 8 (+ 6)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Scikit learn can be used in Classi¬fic¬ation, Regres¬sion, Cluste¬ring, Dimens¬ion¬ality reduct¬ion¬,Model Selection and prepro¬cessing by supervised and unsupe¬rvised training models.}  \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 Commands}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} from sklearn import neighbors, datasets, preprocessing} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} from sklearn.model\_selection import train\_test\_split} \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} from sklearn.metrics import accuracy\_score} \tn 
% Row Count 5 (+ 1)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} iris = datasets.load\_iris()} \tn 
% Row Count 6 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} X, y = iris.data{[}:, :2{]}, iris.target} \tn 
% Row Count 7 (+ 1)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} X\_train, X\_test, y\_train, y\_test = train\_test\_split(X, y, random\_state=33)} \tn 
% Row Count 9 (+ 2)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} scaler = \seqsplit{preprocessing.StandardScaler().fit(X\_train)}} \tn 
% Row Count 11 (+ 2)
% Row 7
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} X\_train = \seqsplit{scaler.transform(X\_train)}} \tn 
% Row Count 12 (+ 1)
% Row 8
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} X\_test = \seqsplit{scaler.transform(X\_test)}} \tn 
% Row Count 13 (+ 1)
% Row 9
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} knn = \seqsplit{neighbors.KNeighborsClassifier(n\_neighbors=5)}} \tn 
% Row Count 15 (+ 2)
% Row 10
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} knn.fit(X\_train, y\_train)} \tn 
% Row Count 16 (+ 1)
% Row 11
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} y\_pred = knn.predict(X\_test)} \tn 
% Row Count 17 (+ 1)
% Row 12
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} accuracy\_score(y\_test, y\_pred)} \tn 
% Row Count 18 (+ 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}{Loading Data example}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} import numpy as np} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} X = np.random.random((20,2))} \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} y = np.array({[}'A','B','C','D','E','F','G','A','C','A','B'{]})} \tn 
% Row Count 4 (+ 2)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} X{[}X \textless{} 0.7{]} = 0} \tn 
% Row Count 5 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{The data being loaded should be numeric and has to be stored as NumPy arrays or SciPy sparse matrices.}  \tn 
\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}{Processing Loaded Data}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{Standardization} & \seqsplit{Normalization} & Binarization \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.preprocessing} import \seqsplit{StandardScaler} & \textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.preprocessing} import Normalizer & \textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.preprocessing} import Binarizer \tn 
% Row Count 6 (+ 4)
% Row 2
\SetRowColor{LightBackground}
\textgreater{}\textgreater{}\textgreater{} scaler = \seqsplit{StandardScaler()}.fit(X\_train) & \textgreater{}\textgreater{}\textgreater{} scaler = \seqsplit{Normalizer().fit(X\_train)} & \textgreater{}\textgreater{}\textgreater{} binarizer = \seqsplit{Binarizer(threshold=0}.0).fit(X) \tn 
% Row Count 10 (+ 4)
% Row 3
\SetRowColor{white}
\textgreater{}\textgreater{}\textgreater{} \seqsplit{standardized\_X} = \seqsplit{scaler.transform(X\_train)} & \textgreater{}\textgreater{}\textgreater{} \seqsplit{normalized\_X} = \seqsplit{scaler.transform(X\_train)} & \textgreater{}\textgreater{}\textgreater{} binary\_X = \seqsplit{binarizer.transform(X)} \tn 
% Row Count 14 (+ 4)
% Row 4
\SetRowColor{LightBackground}
\textgreater{}\textgreater{}\textgreater{} \seqsplit{standardized\_X\_test} = \seqsplit{scaler.transform(X\_test)} & \textgreater{}\textgreater{}\textgreater{} \seqsplit{normalized\_X\_test} = \seqsplit{scaler.transform(X\_test)} &  \tn 
% Row Count 18 (+ 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}{Training And Test Data}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} from sklearn.model\_selection import train\_test\_split} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} X\_train, X\_test, y\_train, y\_test = train\_test\_split(X,y,random\_state=0)} \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.64772 cm} x{1.28156 cm} x{1.64772 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Creating Model}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{3}{x{5.377cm}}{Supervised Learning Estimators} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
Linear Regression & Support Vector Machines (SVM) & Naive Bayes \tn 
% Row Count 4 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.linear\_model} import \seqsplit{LinearRegression} & \textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.svm} import SVC & \textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.naive\_bayes} import GaussianNB \tn 
% Row Count 8 (+ 4)
% Row 3
\SetRowColor{white}
\textgreater{}\textgreater{}\textgreater{} lr = \seqsplit{LinearRegression(normalize=True)} & \textgreater{}\textgreater{}\textgreater{} svc = \seqsplit{SVC(kernel='linear')} & \textgreater{}\textgreater{}\textgreater{} gnb = GaussianNB() \tn 
% Row Count 11 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Creating Model}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Unsupervised Learning Estimators} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
Principal Component Analysis (PCA) & K Means \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.decomposition} import PCA & \textgreater{}\textgreater{}\textgreater{} from sklearn.cluster import KMeans \tn 
% Row Count 6 (+ 3)
% Row 3
\SetRowColor{white}
\textgreater{}\textgreater{}\textgreater{} pca = \seqsplit{PCA(n\_components=0.95)} & \textgreater{}\textgreater{}\textgreater{} k\_means = \seqsplit{KMeans(n\_clusters=3}, random\_state=0) \tn 
% Row Count 9 (+ 3)
\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}{Model Fitting}}  \tn
% Row 0
\SetRowColor{LightBackground}
Supervised Learning & Unsupervised learning \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\textgreater{}\textgreater{}\textgreater{} lr.fit(X, y) & \textgreater{}\textgreater{}\textgreater{} k\_means.fit(X\_train) \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\textgreater{}\textgreater{}\textgreater{} \seqsplit{knn.fit(X\_train}, y\_train) & \textgreater{}\textgreater{}\textgreater{} pca\_model = \seqsplit{pca.fit\_transform(X\_train)} \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} svc.fit(X\_train, y\_train)} \tn 
% Row Count 7 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.63781 cm} x{2.33919 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Predicting output}}  \tn
% Row 0
\SetRowColor{LightBackground}
Supervised Estimators & Unsupervised Estimators \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\textgreater{}\textgreater{}\textgreater{} y\_pred = \seqsplit{svc.predict(np.random.random((2},5))) & \textgreater{}\textgreater{}\textgreater{} y\_pred = \seqsplit{k\_means.predict(X\_test)} \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} y\_pred = lr.predict(X\_test)} \tn 
% Row Count 6 (+ 1)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} y\_pred = \seqsplit{knn.predict\_proba(X\_test))}} \tn 
% Row Count 7 (+ 1)
\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}{Classification Metrics Model Performance}}  \tn
% Row 0
\SetRowColor{LightBackground}
Accuracy Score & \seqsplit{Classification} Report & Confusion Matrix \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\textgreater{}\textgreater{}\textgreater{} \seqsplit{knn.score(X\_test}, y\_test) & \textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.metrics} import \seqsplit{classification\_report} & \textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.metrics} import \seqsplit{confusion\_matrix} \tn 
% Row Count 7 (+ 5)
% Row 2
\SetRowColor{LightBackground}
\textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.metrics} import \seqsplit{accuracy\_score} & \textgreater{}\textgreater{}\textgreater{} \seqsplit{print(classification\_report(y\_test}, y\_pred))) & \textgreater{}\textgreater{}\textgreater{} \seqsplit{print(confusion\_matrix(y\_test}, y\_pred))) \tn 
% Row Count 11 (+ 4)
% Row 3
\SetRowColor{white}
\mymulticolumn{3}{x{5.377cm}}{\textgreater{}\textgreater{}\textgreater{} accuracy\_score(y\_test, y\_pred)} \tn 
% Row Count 12 (+ 1)
\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}{Clustering Metrics Model Performance}}  \tn
% Row 0
\SetRowColor{LightBackground}
Adjusted Rand Index & Homogeneity & \seqsplit{Cross-Validation} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.metrics} import \seqsplit{adjusted\_rand\_score} & \textgreater{}\textgreater{}\textgreater{} from \seqsplit{sklearn.metrics} import \seqsplit{homogeneity\_score} & \textgreater{}\textgreater{}\textgreater{} \seqsplit{print(cross\_val\_score(knn}, X\_train, y\_train, cv=4)) \tn 
% Row Count 7 (+ 5)
% Row 2
\SetRowColor{LightBackground}
\textgreater{}\textgreater{}\textgreater{} \seqsplit{adjusted\_rand\_score(y\_true}, y\_pred)) & \textgreater{}\textgreater{}\textgreater{} \seqsplit{homogeneity\_score(y\_true}, y\_pred)) & \textgreater{}\textgreater{}\textgreater{} \seqsplit{print(cross\_val\_score(lr}, X, y, cv=2)) \tn 
% Row Count 11 (+ 4)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}