\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{DarioPittera (aggialavura)}
\pdfinfo{
  /Title (python-linear-regression-model.pdf)
  /Creator (Cheatography)
  /Author (DarioPittera (aggialavura))
  /Subject (Python - Linear Regression Model 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}{3AC990}
\definecolor{LightBackground}{HTML}{F2FBF8}
\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{Python - Linear Regression Model Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{DarioPittera (aggialavura)} via \textcolor{DarkBackground}{\uline{cheatography.com/83764/cs/19917/}}}
\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}DarioPittera (aggialavura) \\
  \uline{cheatography.com/aggialavura} \\
        \uline{\seqsplit{www}.dariopittera.com}
  \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 June, 2019.\\
   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}{TO START}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{\# IMPORT DATA LIBRARIES \newline import pandas as pd \newline import numpy as np \newline  \newline \# IMPORT VIS LIBRARIES \newline import matplotlib.pyplot as plt \newline import seaborn as sns \newline \%matplotlib inline \newline  \newline \# IMPORT MODELLING LIBRARIES \newline from sklearn.model\_selection import train\_test\_split \{\{nobreak\}\} \newline from sklearn.linear\_model import LinearRegression \newline from sklearn import metrics} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{5.2 cm} x{2.8 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{PRELIMINARY OPERATIONS}}  \tn
% Row 0
\SetRowColor{LightBackground}
df = pd.read\_csv('data.csv') & read data \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
df.head() & check head df \tn 
% Row Count 3 (+ 1)
% Row 2
\SetRowColor{LightBackground}
df.info() & check info df \tn 
% Row Count 4 (+ 1)
% Row 3
\SetRowColor{white}
df.describe() & check stats df \tn 
% Row Count 5 (+ 1)
% Row 4
\SetRowColor{LightBackground}
df.columns & check col names \tn 
% Row Count 7 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{5.12 cm} x{2.88 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{VISUALISE DATA}}  \tn
% Row 0
\SetRowColor{LightBackground}
sns.pairplot(df) & pairplot \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
sns.distplot(df{[}'Y'{]}) & distribution plot \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
sns.heatmap(df.corr(), annot=True) & heatmap with values \tn 
% Row Count 5 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{4.64 cm} x{3.36 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{TRAIN MODEL}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{\{\{fa-clone\}\} CREATE X and y}} -{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
X = df{[}{[}'col1','col2',etc.{]}{]} & create df features \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
y = df{[}'col'{]} & create df var to predict \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{8.4cm}}{{\bf{\{\{fa-columns\}\} SPLIT DATASET}} -{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-} \tn 
% Row Count 6 (+ 1)
% Row 4
\SetRowColor{LightBackground}
X\_train, X\_test, y\_train, y\_test = \{\{nl\}\} train\_test\_split(\{\{nl\}\}~~~~~~~~~~~~~~~~~~~~~~~~~X,\{\{nl\}\}~~~~~~~~~~~~~~~~~~~~~~~~~y, \{\{nl\}\}~~~~~~~~~~~~~~~~~~~~~~~~~test\_size=0.3) & split df in train and test df \tn 
% Row Count 30 (+ 24)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{8.4cm}{x{4.64 cm} x{3.36 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{TRAIN MODEL (cont)}}  \tn
% Row 5
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{\{\{fa-signal\}\} FIT THE MODEL}} -{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-} \tn 
% Row Count 1 (+ 1)
% Row 6
\SetRowColor{white}
lm = LinearRegression() & instatiate model \tn 
% Row Count 2 (+ 1)
% Row 7
\SetRowColor{LightBackground}
lm.fit(X\_train, y\_train) & train/fit the model \tn 
% Row Count 4 (+ 2)
% Row 8
\SetRowColor{white}
\mymulticolumn{2}{x{8.4cm}}{{\bf{\{\{fa-eye\}\} SHOW RESULTS}} -{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-{}-} \tn 
% Row Count 5 (+ 1)
% Row 9
\SetRowColor{LightBackground}
lm.intercept\_ & show intercept \tn 
% Row Count 6 (+ 1)
% Row 10
\SetRowColor{white}
lm.coef\_ & show coefficients \tn 
% Row Count 8 (+ 2)
% Row 11
\SetRowColor{LightBackground}
coeff\_df = pd.DataFrame\{\{nl\}\}(lm.coef\_,X.columns,columns={[}'Coeff'{]})* & create coeff df \tn 
% Row Count 11 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{pd.DataFrame}}: pd.DataFrame(data=None, index=None, columns=None, dtype=None, copy=False). {\bf{data}} = values, {\bf{index}}= name index, {\bf{columns}}= name column. This could be useful just to interpret the coefficient of the regression.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{5.28 cm} x{2.72 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{MAKE PREDICTIONS}}  \tn
% Row 0
\SetRowColor{LightBackground}
predictions = lm.predict(X\_test) & create predictions \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
plt.scatter(y\_test,predictions)* & plot predictions \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{sns.distplot((y\_test-predictions)},bins=50)* & distplot of residuals \tn 
% Row Count 6 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{scatter}}: this graph show the difference between actual values and the values predicted by the model we trained. It should resemble as much as possible a {\bf{diagonal line}}. \newline {\bf{distplot}}: this graph shows the distributions of the residual errors, that is, the difference between the actual values minus the predicted values; it should result in an as much as possible {\bf{normal distribution}}. If not, maybe change model!}  \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}{EVALUATION METRICS}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{print('MAE:', {\bf{metrics.mean\_absolute\_error(y\_test, predictions)}})} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{8.4cm}}{print('MSE:', {\bf{metrics.mean\_squared\_error(y\_test, predictions)}})} \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{print('RMSE:', {\bf{np.sqrt(metrics.mean\_squared\_error(y\_test, predictions))}}) \{\{nobreak\}\}} \tn 
% Row Count 6 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{8.4cm}}{{\bf{MAE}} is the easiest to understand, because it's the average error. \newline {\bf{MSE}} is more popular than MAE, because MSE "punishes" larger errors, which tends to be useful in the real world. \newline {\bf{RMSE}} is even more popular than MSE, because RMSE is interpretable in the "y" units.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}