\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{Jingyi Feng (jenniferfjy)}
\pdfinfo{
  /Title (machine-learning-in-r-and-python.pdf)
  /Creator (Cheatography)
  /Author (Jingyi Feng (jenniferfjy))
  /Subject (Machine Learning in R and 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}{5D66A3}
\definecolor{LightBackground}{HTML}{F4F5F9}
\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{Machine Learning in R and Python Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{Jingyi Feng (jenniferfjy)} via \textcolor{DarkBackground}{\uline{cheatography.com/169260/cs/35433/}}}
\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}Jingyi Feng (jenniferfjy) \\
  \uline{cheatography.com/jenniferfjy} \\
  \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 13th November, 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*}{2}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Introduction}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{This cheat sheet provides a comparison between basic data processing technique as well as machine learning models in both R and Python.} \tn 
% Row Count 3 (+ 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}{Documentations}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{\seqsplit{https://scikit-learn.org/stable/auto\_examples/index.html}} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{\seqsplit{https://seaborn.pydata.org/}} \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{\seqsplit{https://cran.r-project.org/web/packages/rpart/index.html}} \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{\seqsplit{https://cran.r-project.org/web/packages/caret/index.html}} \tn 
% Row Count 7 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{\seqsplit{https://cran.r-project.org/web/packages/randomForest/index.html}} \tn 
% Row Count 9 (+ 2)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{\seqsplit{https://www.rdocumentation.org/packages/stats/versions/3.6.2}} \tn 
% Row Count 11 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.4 cm} x{5.6 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Load dataset in R}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{library(datasets)} & Import packages \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
data(iris) & Load dataset \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
head(iris) & Look up the first 6 rows of the dataset \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
\seqsplit{summary(iris)} & Get summary statistics of each columns \tn 
% Row Count 7 (+ 2)
% Row 4
\SetRowColor{LightBackground}
names(iris) & Get the column names \tn 
% Row Count 8 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Data preprocessing in R}}  \tn
% Row 0
\SetRowColor{LightBackground}
scaling = preProcess(data, method = c('center', 'scale')) & Create scaling based on data \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
data\_scaled = predict(scaling, data) & Apply scaling to data \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
train\_partition = \seqsplit{createDataPartition(y}, p = 0.8, list = FALSE) & Balanced splitting based on the outcome ( 80/20 split) \tn 
% Row Count 9 (+ 4)
% Row 3
\SetRowColor{white}
data\_train = data{[}train\_partition,{]} & Split data into train and test sets \tn 
% Row Count 11 (+ 2)
% Row 4
\SetRowColor{LightBackground}
data\_test = data{[}-train\_partition,{]} & Split data into train and test sets \tn 
% Row Count 13 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Supervised learning models in R}}  \tn
% Row 0
\SetRowColor{LightBackground}
model = lm(data, y \textasciitilde{} x) & Simple linear regression \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
model = lm(data, y \textasciitilde{} x1 + x2 + x3) & Multiple linear regression \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
summary(model) & Print summary statistics from linear model \tn 
% Row Count 7 (+ 3)
% Row 3
\SetRowColor{white}
predictions = predict(object, newdata) & Make prediction based on the model object \tn 
% Row Count 10 (+ 3)
% Row 4
\SetRowColor{LightBackground}
model = glm(data, y \textasciitilde{} x1 + x2 + x3, family = 'binomial') & Logistic regression \tn 
% Row Count 13 (+ 3)
% Row 5
\SetRowColor{white}
model = svm(data, y \textasciitilde{} x1 + x2 + x3, params) & Support vector machines (SVM) \tn 
% Row Count 16 (+ 3)
% Row 6
\SetRowColor{LightBackground}
model = rpart(data, y \textasciitilde{} x1 + x2 + x3, params) & Decision trees \tn 
% Row Count 19 (+ 3)
% Row 7
\SetRowColor{white}
model = randomForest(data, y \textasciitilde{} x1 + x2 + x3, params) & Random forest \tn 
% Row Count 22 (+ 3)
% Row 8
\SetRowColor{LightBackground}
data\_xgb = xgb.DMatrix(data, label) & Transform the data into DMatrix format \tn 
% Row Count 24 (+ 2)
% Row 9
\SetRowColor{white}
model = xgb.train(data\_xgb, label, params) & Gradient boosting models \tn 
% Row Count 27 (+ 3)
% Row 10
\SetRowColor{LightBackground}
predictions = knn(train, test, cl, params) & k-NN with labels cl and parameters (e.g., number of neighbors) \tn 
% Row Count 31 (+ 4)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.36 cm} x{4.64 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Unsupervised learning models}}  \tn
% Row 0
\SetRowColor{LightBackground}
model = kmeans(x, params) & K-Means clustering \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
model = prcomp(x, params) & Principal components analysis (PCA) \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.92 cm} x{4.08 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Model performance in R}}  \tn
% Row 0
\SetRowColor{LightBackground}
RMSE(pred, actual) & Root mean square error \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
R2(pred, actual, form = 'traditional' ) & Proportion of the variance explained by the model \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
mean(actual == pred) & Accuracy (how accurate positive predictions are) \tn 
% Row Count 8 (+ 3)
% Row 3
\SetRowColor{white}
\seqsplit{confusionMatrix(actual}, pred) & Confusion matrix \tn 
% Row Count 10 (+ 2)
% Row 4
\SetRowColor{LightBackground}
auc(actual, pred) & Area under the ROC curve \tn 
% Row Count 12 (+ 2)
% Row 5
\SetRowColor{white}
f1Score(actual, pred) & Harmonic mean of precision and recall \tn 
% Row Count 14 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{6.16 cm} x{1.84 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Data visualization in R}}  \tn
% Row 0
\SetRowColor{LightBackground}
geom\_point(x, y, color, size, fill, alpha) & Scatter plot \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
geom\_line(x, y, color, size, fill, alpha, linetype) & Line plot \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
geom\_bar(x, y, color, size, fill, alpha) & Bar chart \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
geom\_boxplot(x, y, color) & Box plot \tn 
% Row Count 7 (+ 1)
% Row 4
\SetRowColor{LightBackground}
geom\_tile(x, y, color, fill) & Heatmap \tn 
% Row Count 8 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Python}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{} \tn 
% Row Count 0 (+ 0)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.64 cm} x{5.36 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Import file in Python}}  \tn
% Row 0
\SetRowColor{LightBackground}
import pandas as pd & Import package \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
df = \seqsplit{pd.read\_csv()} & Read csv files \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
df.head(n) & Look up the first n rows of the dataset \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
\seqsplit{df.describe()} & Get summary statistics of each columns \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
df.columns & Get column names \tn 
% Row Count 9 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Data Processing in Python}}  \tn
% Row 0
\SetRowColor{LightBackground}
X\_train, X\_test, y\_train, y\_test = \seqsplit{train\_test\_split(X}, y, test\_size=0.2, random\_state=0) & Split the dataset into training (80\%) and test (20\%) sets \tn 
% Row Count 5 (+ 5)
% Row 1
\SetRowColor{white}
scaler = StandardScaler() & Standardize features by removing the mean and scaling to unit variance \tn 
% Row Count 9 (+ 4)
% Row 2
\SetRowColor{LightBackground}
X\_train = \seqsplit{scaler.fit\_transform(X\_train)} & Fit and transform scalar on X\_train \tn 
% Row Count 11 (+ 2)
% Row 3
\SetRowColor{white}
X\_test = \seqsplit{scaler.transform(X\_test)} & Transform X\_test \tn 
% Row Count 13 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{4.24 cm} x{3.76 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Supervised learning models in Python}}  \tn
% Row 0
\SetRowColor{LightBackground}
model = LinearRegression() & Linear regression \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
model.fit(X\_train, y\_train) & Fit linear model \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{model.predict(X\_test)} & Predict using the linear model \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
\seqsplit{LogisticRegression().fit(X\_train}, y\_train) & Logistic regression \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{LinearSVC.fit(X\_train}, y\_train) & Train primal SVM \tn 
% Row Count 10 (+ 2)
% Row 5
\SetRowColor{white}
SVC().fit(X\_train, y\_train) & Train dual SVM \tn 
% Row Count 12 (+ 2)
% Row 6
\SetRowColor{LightBackground}
\seqsplit{DecisionTreeClassifier()}.fit(X\_train, y\_train) & Decision tree classifier \tn 
% Row Count 15 (+ 3)
% Row 7
\SetRowColor{white}
\seqsplit{RandomForestClassifier()}.fit(X\_train, y\_train) & Random forest classifier \tn 
% Row Count 18 (+ 3)
% Row 8
\SetRowColor{LightBackground}
\seqsplit{GradientBoostingClassifier()}.fit(X\_train, y\_train) & Gradient boosting for classification \tn 
% Row Count 21 (+ 3)
% Row 9
\SetRowColor{white}
\seqsplit{XGBClassifier().fit(X\_train}, y\_train) & XGboost classifier \tn 
% Row Count 23 (+ 2)
% Row 10
\SetRowColor{LightBackground}
\seqsplit{KNeighborsClassifier()}.fit(X\_train, y\_train) & k-NN \tn 
% Row Count 26 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.48 cm} x{5.52 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Unsupervised learning models}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{KMeans().fit(X)} & K-Means clustering \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{PCA().fit(X)} & Principal component analysis (PCA) \tn 
% Row Count 4 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Model performance in Python}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{metrics.mean\_squared\_error(y\_true}, y\_pred, squared=False) & Root mean squared error \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\seqsplit{metrics.r2\_score(y\_true}, y\_pred) & Proportion of the variance explained by the model \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{metrics.confusion\_matrix(y\_true}, y\_pred) & Confusion matrix \tn 
% Row Count 8 (+ 2)
% Row 3
\SetRowColor{white}
\seqsplit{metrics.accuracy\_score(y\_true}, y\_pred) & Accuracy classification score \tn 
% Row Count 10 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{metrics.roc\_auc\_score()} & Compute ROC-AUC from prediction scores \tn 
% Row Count 12 (+ 2)
% Row 5
\SetRowColor{white}
f1\_score(y\_true, y\_pred, average='macro') & Harmonic mean of the precision and recall \tn 
% Row Count 15 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{6.08 cm} x{1.92 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Data visualization in Python}}  \tn
% Row 0
\SetRowColor{LightBackground}
sns.scatterplot(x, y, hue, size) & Scatter plot \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
sns.lineplot(x, y, hue, size) & Line plot \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
sns.barplot(x, y, hue) & Bar chart \tn 
% Row Count 4 (+ 1)
% Row 3
\SetRowColor{white}
sns.boxplot(x, y, hue) & Box plot \tn 
% Row Count 5 (+ 1)
% Row 4
\SetRowColor{LightBackground}
sns.heatmap(data, linecolor, linewidth) & Heatmap \tn 
% Row Count 7 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}