\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-seaborn.pdf) /Creator (Cheatography) /Author (DarioPittera (aggialavura)) /Subject (Python - Seaborn 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}{408CFF} \definecolor{LightBackground}{HTML}{F3F7FF} \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 - Seaborn Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{DarioPittera (aggialavura)} via \textcolor{DarkBackground}{\uline{cheatography.com/83764/cs/19851/}}} \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 15th 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*}{3} \begin{tabularx}{5.377cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{TO START}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{import seaborn as sns \newline \# If working on a notebook \newline \%matplotlib inline} \tn \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{x{2.83689 cm} x{2.14011 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{DISTRIBUTION PLOTS}} \tn % Row 0 \SetRowColor{LightBackground} {\bf{sns.distplot(df{[}'col'{]})}} & distribution plot \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} - bin = x & number of bins \tn % Row Count 3 (+ 1) % Row 2 \SetRowColor{LightBackground} - kde = False & remove the line \tn % Row Count 4 (+ 1) % Row 3 \SetRowColor{white} {\bf{sns.jointplot(x,y,df)}} & plot 2 variables \tn % Row Count 6 (+ 2) % Row 4 \SetRowColor{LightBackground} - kind = '' & kind of plot* \tn % Row Count 7 (+ 1) % Row 5 \SetRowColor{white} {\bf{sns.pairplot(df)}} & plot all vars combin \tn % Row Count 9 (+ 2) % Row 6 \SetRowColor{LightBackground} - hue='categ var' & distinguish per var \tn % Row Count 11 (+ 2) % Row 7 \SetRowColor{white} - palette='' & set a color palette \tn % Row Count 13 (+ 2) % Row 8 \SetRowColor{LightBackground} {\bf{sns.rugplot(df{[}'col'{]})}} & idea of distribution \tn % Row Count 15 (+ 2) % Row 9 \SetRowColor{white} {\bf{sns.kdeplot(df{[}'col'{]})}} & kde plot \tn % Row Count 17 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{{\bf{"kind="}} E.g.: hex, reg, kde.} \tn \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{x{3.23505 cm} x{1.74195 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{CATEGORICAL PLOTS}} \tn % Row 0 \SetRowColor{LightBackground} {\bf{sns.barplot(x,y,df)}} & bar plot \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} - estimator=''* & bar values \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} {\bf{sns.countplot(x,df)}} & bars = count \tn % Row Count 3 (+ 1) % Row 3 \SetRowColor{white} {\bf{sns.boxplot(x,y,,df)}} & box plot \tn % Row Count 4 (+ 1) % Row 4 \SetRowColor{LightBackground} - hue='categ var' & divide per var \tn % Row Count 5 (+ 1) % Row 5 \SetRowColor{white} - palette='' & set palette \tn % Row Count 6 (+ 1) % Row 6 \SetRowColor{LightBackground} - orient='h' & horiz. plot \tn % Row Count 7 (+ 1) % Row 7 \SetRowColor{white} {\bf{sns.violinplot(x,y,df)}} & violin plot* \tn % Row Count 8 (+ 1) % Row 8 \SetRowColor{LightBackground} - hue='categ var' & divide per var \tn % Row Count 9 (+ 1) % Row 9 \SetRowColor{white} - palette='' & set palette \tn % Row Count 10 (+ 1) % Row 10 \SetRowColor{LightBackground} {\bf{sns.stripplot(x,y,df)}} & bars = scatter \tn % Row Count 11 (+ 1) % Row 11 \SetRowColor{white} - jitter = True & add noise \tn % Row Count 12 (+ 1) % Row 12 \SetRowColor{LightBackground} - hue='categ var' & divide per var \tn % Row Count 13 (+ 1) % Row 13 \SetRowColor{white} - palette='' & set palette \tn % Row Count 14 (+ 1) % Row 14 \SetRowColor{LightBackground} - split = True & split by hue \tn % Row Count 15 (+ 1) % Row 15 \SetRowColor{white} {\bf{sns.swarmplot(x,y,df)}} & swarm plot \tn % Row Count 16 (+ 1) % Row 16 \SetRowColor{LightBackground} - hue='categ var' & divide per var \tn % Row Count 17 (+ 1) % Row 17 \SetRowColor{white} - palette='' & set palette \tn % Row Count 18 (+ 1) % Row 18 \SetRowColor{LightBackground} - split = True & split by hue \tn % Row Count 19 (+ 1) % Row 19 \SetRowColor{white} \mymulticolumn{2}{x{5.377cm}}{** You can alo combine more plots by calling them one after each other.} \tn % Row Count 21 (+ 2) % Row 20 \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{{\bf{sns.factorplot(x,y,df,kind)* }}\{\{nobreak\}\}\{\{ac\}\}\{\{nl\}\} general categorical form of graph} \tn % Row Count 23 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{{\bf{TIP:}} when you call a plot function, press \{\{nl\}\} {\bf{"shift + tab"}} to show the parameters needed. \newline {\bf{estimator=}} can be, mean, std, or whatever function. It will display the bars or whatever you choose. \newline {\bf{General form, kind=:}} e.g., point, bar, violin, etc.} \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}{ON CATEGORICAL PLOTS...}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{What is a violin plot?}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}It has a similar role of a box and whisker plots. It shows the distribution of quantitative data across several levels of one (or more) categorical variables. The violin plot features a kernel density estimation of the underlying distribution.} \tn % Row Count 7 (+ 7) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{5.377cm}}{{\bf{What is a strip plot?}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}It will draw a scatterplot where one variable is categorical. It is also a good complement to a box or violin plot in cases where you want to show all observations along with some representation of the underlying distribution.} \tn % Row Count 13 (+ 6) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{{\bf{What is a swarm plot}}} \tn \mymulticolumn{1}{x{5.377cm}}{\hspace*{6 px}\rule{2px}{6px}\hspace*{6 px}It is similar to a stripplot(), but the points are adjusted (only along the categorical axis) so that they don't overlap. This gives a better representation of the distribution of values, although it does not scale as well to large numbers of observations.} \tn % Row Count 20 (+ 7) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{x{2.9862 cm} x{1.9908 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{MATRIX PLOTS}} \tn % Row 0 \SetRowColor{LightBackground} {\bf{sns.heatmap(df.corr())* }} & heat map plot \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} - annot = True & add actual values \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} - cmap='' & set a color palette \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} - linecolor='' & set borders \tn % Row Count 7 (+ 1) % Row 4 \SetRowColor{LightBackground} - linewidths=x & set border width \tn % Row Count 8 (+ 1) % Row 5 \SetRowColor{white} {\bf{sns.clustermap(matrix)}} & hierarc. clustering \tn % Row Count 10 (+ 2) % Row 6 \SetRowColor{LightBackground} - cmap='' & set a color palette \tn % Row Count 12 (+ 2) % Row 7 \SetRowColor{white} - standard\_scale = 1 & normalise data \tn % Row Count 13 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{{\bf{Heat map plot}} needs a correlation matrix, or more generally, a matrix. You can use the {\bf{pivot\_table(index,columns,values)}} function to convert a dataframe.} \tn \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{x{2.78712 cm} x{2.18988 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{GRIDS}} \tn % Row 0 \SetRowColor{LightBackground} sns.pairplot(df) & plot all vars combination \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} - hue='categ var' & divide per var \tn % Row Count 3 (+ 1) % Row 2 \SetRowColor{LightBackground} - palette='' & set palette \tn % Row Count 4 (+ 1) % Row 3 \SetRowColor{white} g = {\bf{sns.PairGrid(df)}} & set (empty) axis of pairplot \tn % Row Count 6 (+ 2) % Row 4 \SetRowColor{LightBackground} -g.map(plt.scatter) & populate axis with some plot \tn % Row Count 8 (+ 2) % Row 5 \SetRowColor{white} -g.map\_diag(plt.hist) & set diag plots \tn % Row Count 9 (+ 1) % Row 6 \SetRowColor{LightBackground} \seqsplit{-g.map\_upper(plt.scatter)} & set upper plots \tn % Row Count 11 (+ 2) % Row 7 \SetRowColor{white} -g.map\_lower(sns.kdeplot)\{\{nobreak\}\} & set lower plots \tn % Row Count 13 (+ 2) % Row 8 \SetRowColor{LightBackground} {\bf{g = sns.FacetGrid(df,c,r)}} & empty axis \tn % Row Count 15 (+ 2) % Row 9 \SetRowColor{white} -g = g.map({\bf{plt}}.hist, "c") & populate axis histograms \tn % Row Count 17 (+ 2) % Row 10 \SetRowColor{LightBackground} -..g.map(sns.distplot, "c") & populate axis with distplots \tn % Row Count 19 (+ 2) % Row 11 \SetRowColor{white} \mymulticolumn{2}{x{5.377cm}}{{\bf{now some more complex stuff}}} \tn % Row Count 20 (+ 1) % Row 12 \SetRowColor{LightBackground} - hue='categ var' & divide per var \tn % Row Count 21 (+ 1) % Row 13 \SetRowColor{white} \mymulticolumn{2}{x{5.377cm}}{-g = g.map(plt.scatter, "c", "c").add\_legend()} \tn % Row Count 22 (+ 1) % Row 14 \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{{\bf{g = sns.JointGrid(x,y,df)}}\{\{ac\}\}\{\{nl\}\} general form of jointplot()} \tn % Row Count 24 (+ 2) % Row 15 \SetRowColor{white} \mymulticolumn{2}{x{5.377cm}}{{\bf{g = g.plot(sns.regplot, sns.distplot)}}\{\{ac\}\}\{\{nl\}\}join two plots} \tn % Row Count 26 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{x{3.43413 cm} x{1.54287 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{REGRESSION PLOTS}} \tn % Row 0 \SetRowColor{LightBackground} {\bf{sns.lmplot(x,y,df)}} & creat reg plot \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} - hue='categ var' & divide per var \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} - palette='' & set palette \tn % Row Count 5 (+ 1) % Row 3 \SetRowColor{white} - markers='' * & set mark shape \tn % Row Count 7 (+ 2) % Row 4 \SetRowColor{LightBackground} - scatter\_kws='dict' * & set marker size \tn % Row Count 9 (+ 2) % Row 5 \SetRowColor{white} sns.lmplot(x,y,df,{\bf{col}}) & create a grid plot \tn % Row Count 11 (+ 2) % Row 6 \SetRowColor{LightBackground} sns.lmplot(x,y,df,{\bf{row,col}})\{\{nobreak\}\} & X*X grid \tn % Row Count 13 (+ 2) % Row 7 \SetRowColor{white} sns.lmplot(x,y,df,{\bf{row,col,hue}})\{\{nobreak\}\} & X*X*X grid \tn % Row Count 15 (+ 2) % Row 8 \SetRowColor{LightBackground} - aspect = x & choose ratio \tn % Row Count 16 (+ 1) % Row 9 \SetRowColor{white} - size = x & set size \tn % Row Count 17 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{{\bf{markers='':}} e.g., o,v,etc. \newline {\bf{scatter\_kws=''}} e.g.: \{'s':100\}, it is a call to matplotlib. It will be hard to remember how to use these special cases, so no worries, you will have a look online.} \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}{continue... (copy)}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{5.377cm}}{} \tn % Row Count 0 (+ 0) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{x{3.08574 cm} x{1.89126 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{STYLE and COLOR}} \tn % Row 0 \SetRowColor{LightBackground} \seqsplit{sns.set\_style('darkgrid')} & apply darkgrid style \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} sns.set\_style('ticks') & apply ticks style \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} sns.despine() & remove borders \tn % Row Count 5 (+ 1) % Row 3 \SetRowColor{white} sns.despine(left=True) & remove left border \tn % Row Count 7 (+ 2) % Row 4 \SetRowColor{LightBackground} plt.figure(figsize=(x,x)) & choose fig size \tn % Row Count 9 (+ 2) % Row 5 \SetRowColor{white} \seqsplit{sns.set\_context('talk')} * & set context \tn % Row Count 11 (+ 2) % Row 6 \SetRowColor{LightBackground} sns.set\_context\{\{nl\}\}(font\_scale) & set font size \tn % Row Count 13 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}--} \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{{\bf{.set\_context(''):}} e.g.: paper, poster, talk, notebook, etc.} \tn \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}