\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{andreeas26} \pdfinfo{ /Title (clean-ml-code-and-pep8-guidelines.pdf) /Creator (Cheatography) /Author (andreeas26) /Subject (Clean ML code and PEP8 guidelines 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}{ED8A3E} \definecolor{LightBackground}{HTML}{FDF7F2} \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{Clean ML code and PEP8 guidelines Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{andreeas26} via \textcolor{DarkBackground}{\uline{cheatography.com/133480/cs/27273/}}} \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}andreeas26 \\ \uline{cheatography.com/andreeas26} \\ \end{tabulary} \vfill \columnbreak \begin{tabulary}{5.8cm}{L} \SetRowColor{FootBackground} \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}} \\ \vspace{-2pt}Published 25th March, 2021.\\ Updated 26th March, 2021.\\ 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}{Optimizing names}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Reveal an {\bf{intention}}.} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Key concepts names should communicate: \{\{nl\}\} - {\bf{Why}} it exists? \{\{nl\}\} - {\bf{What}} does it do? \{\{nl\}\} - {\bf{How}} is it used?} \tn % Row Count 4 (+ 3) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Differences between variables should be as close to the beginning of the name as possible.} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Avoid noisy labels. Use mature optional typing system.} \tn % Row Count 8 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Make Siri say it. Avoid abbreviation and make your names self-explanatory.} \tn % Row Count 10 (+ 2) % Row 5 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Adding the datatype to a variable should be replaced with typing information. `features: DataFrame` vs. `features\_df`} \tn % Row Count 13 (+ 3) % Row 6 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{No magic numbers. Use constants.} \tn % Row Count 14 (+ 1) % Row 7 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{{\bf{Be consistent!}} Pick a single word per concept, and use it everywhere it fits in.} \tn % Row Count 16 (+ 2) % Row 8 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Use technical names for backend, and domain names as you get closer the customer.} \tn % Row Count 18 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Optimize functions}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Small is beautiful. 3, 5, maybe 5 lines max!} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{{\bf{FUNCTIONS SHOULD DO ONE THING. THEY SHOULD DO IT WELL. THEY SHOULD DO IT ONLY. }}} \tn % Row Count 3 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Stop at maximum 3 arguments!} \tn % Row Count 4 (+ 1) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Avoid boolean arguments. This points to the fact that the function does more than {\emph{one thing}}.} \tn % Row Count 6 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Lengthy list of configuration arguments should be grouped in a configuration object that {\emph{share a concept}}.} \tn % Row Count 9 (+ 3) % Row 5 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{{\bf{Comman Query Separation (CQS)}} \{\{nl\}\} - {\bf{Command:}} a function is changing some external "state". \{\{nl\}\} - {\bf{Query:}} a function is returning some "information".} \tn % Row Count 13 (+ 4) % Row 6 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Avoid side effects in feature engineering pipelines.} \tn % Row Count 15 (+ 2) % Row 7 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Make temporal couplings explicit.} \tn % Row Count 16 (+ 1) % Row 8 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{DRY: Don't Repeat Yourself}} Eliminate Duplicates, Doubles, and Homologues.} \tn % Row Count 18 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{x{1.14 cm} x{3.192 cm} x{3.268 cm} } \SetRowColor{DarkBackground} \mymulticolumn{3}{x{8.4cm}}{\bf\textcolor{white}{Naming conventions}} \tn % Row 0 \SetRowColor{LightBackground} {\bf{Function}} & Use verbs to represent actions. Use `is\_`for functions that return a boolean. & `get\_features, fit, is\_completed` \tn % Row Count 5 (+ 5) % Row 1 \SetRowColor{white} {\bf{Variable}} & See scope length guidelines. & `x, var, my\_variable` \tn % Row Count 8 (+ 3) % Row 2 \SetRowColor{LightBackground} {\bf{Class}} & Use nouns to represent objects. & `Model, DataLoader` \tn % Row Count 10 (+ 2) % Row 3 \SetRowColor{white} {\bf{Method}} & Lowercase word(s). Separate with underscore. & `class\_method, method` \tn % Row Count 13 (+ 3) % Row 4 \SetRowColor{LightBackground} {\bf{Constant}} & Uppercase single letter or word(s). Separate with underscore. & `CONSTANT, MY\_CONSTANT, \seqsplit{MY\_LONG\_CONSTANT`} \tn % Row Count 17 (+ 4) % Row 5 \SetRowColor{white} {\bf{Module}} & Short lowercase word(s). Separate with underscore. & module.py, my\_module.py \tn % Row Count 21 (+ 4) % Row 6 \SetRowColor{LightBackground} {\bf{Package}} & Short lowercase word(s). Do NOT separate with underscore. & package, mypackage \tn % Row Count 25 (+ 4) \hhline{>{\arrayrulecolor{DarkBackground}}---} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{The Scope Length Guidelines}} \tn \SetRowColor{LightBackground} \mymulticolumn{1}{p{8.4cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/andreeas26_1616530681_2021-03-23_22h01_44.png}}} \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}{How to avoid side effects in DataFrames}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Copy any data coming in the function and return a fresh copy, after all the modifications.} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Return only the transformed columns as a separated objects.} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Append-only inside the functions.} \tn % Row Count 5 (+ 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}{Handling Exceptions}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Promote the Happy Path with Exceptions.} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Separate the Happy Path from the Outliers.} \tn % Row Count 2 (+ 1) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Don't reuse unrelated Exceptions types.} \tn % Row Count 3 (+ 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}{Programming recommendations}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Don't compare Boolean values to True or False using the equivalence operator.} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Use the fact that empty sequences are falsy in if statements.} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Use `is not` rather than `not ... is` in `if` statements.} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Don't use `if x:` when you mean `if x is not None:`.} \tn % Row Count 8 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Use `.startswith()` and `.endswith()` instead of slicing strings.} \tn % Row Count 10 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{8.4cm}{X} \SetRowColor{DarkBackground} \mymulticolumn{1}{x{8.4cm}}{\bf\textcolor{white}{Blank lines}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Surround top-level functions and classes with two blank lines.} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Surround method definitions inside classes with a single blank line.} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Use blank lines sparingly inside functions to show clear steps.} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Formulas always break before binary operations.} \tn % Row Count 7 (+ 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}{Whitespaces in Expressions and Statements}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Assignment operators (`=, +=, -=,` and so forth).} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{{\bf{Exception:}} when `=` is used to assign a default value to a function argument, do not surround it with spaces.} \tn % Row Count 4 (+ 3) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Comparisons (`==, !=, \textgreater{}, \textless{}. \textgreater{}=, \textless{}=`) and (`is, is not, in, not in`).} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{It is better to {\bf{only add whitespace around the operators with the lowest priority}}, especially when performing mathematical manipulation.} \tn % Row Count 9 (+ 3) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Booleans (`and, not, or`).} \tn % Row Count 10 (+ 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}{Indentation}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Spaces are the preferred indentation method.}}} \tn % Row Count 1 (+ 1) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Tabs should be used solely to remain consistent with code that is already indented with tabs.} \tn % Row Count 3 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Dictionaries should use the default formatting rules without indentation. Don't try to keep the values aligned.} \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}{Comments}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{{\bf{Don't Hide Bad Code Behind Comments. Let Code Explain Itself! }}} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Limit the line length of comments and docstrings to 72 characters.} \tn % Row Count 4 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Use complete sentences, starting with a capital letter.} \tn % Row Count 6 (+ 2) % Row 3 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Make sure to update comments if you change your code.} \tn % Row Count 8 (+ 2) % Row 4 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Indent block comments to the same level as the code they describe.} \tn % Row Count 10 (+ 2) % Row 5 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Start each line with a \# followed by a single space.} \tn % Row Count 12 (+ 2) % Row 6 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Separate paragraphs by a line containing a single \#.} \tn % Row Count 14 (+ 2) % Row 7 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Write inline comments on the same line as the statement they refer to.} \tn % Row Count 16 (+ 2) % Row 8 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Separate inline comments by two or more spaces from the statement.} \tn % Row Count 18 (+ 2) % Row 9 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Don't use them to explain the obvious.} \tn % Row Count 19 (+ 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}{Tips and tricks}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{Use an IDE or linters, programs that analyze code and flag errors (e.g pycodestyle, flake8)} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{You can use autoformatters that refactor your code to conform with PEP 8 automatically (e.g. black, autopep8, yapf).} \tn % Row Count 5 (+ 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}{Maximum Line Length}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{1}{x{8.4cm}}{PEP 8 suggests lines should be limited to 79 characters.} \tn % Row Count 2 (+ 2) % Row 1 \SetRowColor{white} \mymulticolumn{1}{x{8.4cm}}{Wrap long lines by using Python's implied line continuation inside parentheses, brackets and braces.} \tn % Row Count 4 (+ 2) \hhline{>{\arrayrulecolor{DarkBackground}}-} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}