\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{blueberryshortcake}
\pdfinfo{
  /Title (kaggle-data-science.pdf)
  /Creator (Cheatography)
  /Author (blueberryshortcake)
  /Subject (Kaggle Data Science 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}{D7C3E8}
\definecolor{LightBackground}{HTML}{F5F0F9}
\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{Kaggle Data Science Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{blueberryshortcake} via \textcolor{DarkBackground}{\uline{cheatography.com/162779/cs/43739/}}}
\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}blueberryshortcake \\
  \uline{cheatography.com/blueberryshortcake} \\
  \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 25th June, 2024.\\
   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{4.24 cm} x{3.76 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Creating, Reading, Writing}}  \tn
% Row 0
\SetRowColor{LightBackground}
df = pd.DataFrame(\{"col0": {[}val0, val1{]}, "col1": {[}val0, val1{]}\}, index={[}0, 1{]}) & Create a dataframe \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
series = pd.Series({[}"val0", "val1", "val2"{]}, index={[}0, 1, 2, 3{]}, name="name") & Create a series \tn 
% Row Count 8 (+ 4)
% Row 2
\SetRowColor{LightBackground}
read = \seqsplit{pd.read\_csv("../folder/folder/file.csv"}, index\_col=0) & Read a csv \tn 
% Row Count 11 (+ 3)
% Row 3
\SetRowColor{white}
\seqsplit{save.to\_csv("file.csv")} & Save an existing dataframe as a csv \tn 
% Row Count 13 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.52 cm} x{4.48 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Indexing, Selecting, Assigning}}  \tn
% Row 0
\SetRowColor{LightBackground}
table.head & Show first 5 rows of a dataframe \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
table{[}"col"{]} & Select the col from table \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
table.col.iloc{[}0{]} & Select 1\textasciicircum{}st\textasciicircum{} value of a col from table \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
table.iloc{[}0{]} & Select 1\textasciicircum{}st\textasciicircum{} row of data from table \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
table.col.iloc{[}:10{]} & Select 1\textasciicircum{}st\textasciicircum{} 10 values from col in table (index-based select) \tn 
% Row Count 11 (+ 3)
% Row 5
\SetRowColor{white}
table.col.loc{[}:10{]} & Select 1\textasciicircum{}st\textasciicircum{} 10 values from col in table (label-based select) \tn 
% Row Count 14 (+ 3)
% Row 6
\SetRowColor{LightBackground}
table.loc{[}indices, cols{]} & Select certain rows from certain cols \tn 
% Row Count 16 (+ 2)
% Row 7
\SetRowColor{white}
table{[}table.col == 'val'{]} & Select cols have a certain val (conditional select) \tn 
% Row Count 19 (+ 3)
% Row 8
\SetRowColor{LightBackground}
table.col.isin({[}'val1,' 'val2'{]}) & Select cols have certain vals (conditional select) \tn 
% Row Count 22 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.6 cm} x{4.4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Summary Functions \& Maps}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{table.col.describe()} & Get high-lvl summary of given col's attributes \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
table.col.mean() & Get mean of a col with numerical vals \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{table.col.unique()} & Get each unique val of a col w/ no dupes \tn 
% Row Count 7 (+ 2)
% Row 3
\SetRowColor{white}
\seqsplit{table.col.value\_counts()} & Get frequency of each val in col \tn 
% Row Count 9 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{table.col.map(lambda} p: p - s) & Map function to remap a Series of point vals (p) by using a transformation (p-s) -\textgreater{} returns new Series \tn 
% Row Count 14 (+ 5)
% Row 5
\SetRowColor{white}
table.apply(func, axis='columns') & Apply function to transform entire df by calling custom method (func taking a row) on each row \tn 
% Row Count 19 (+ 5)
\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}{Grouping \& Sorting}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{table.groupby('col').col.count()} & Group data w/ same vals in the given col -\textgreater{} count frequency of given col (same as value\_counts()) \tn 
% Row Count 5 (+ 5)
% Row 1
\SetRowColor{white}
\seqsplit{table.groupby('col').size()} & Same as above \tn 
% Row Count 7 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{table.groupby('col').apply(lambda} df: df.title.iloc{[}0{]}) & Select name (title) of the 1\textasciicircum{}st\textasciicircum{} thing in col \tn 
% Row Count 10 (+ 3)
% Row 3
\SetRowColor{white}
table.col.idxmax() & Get index of max val in col \tn 
% Row Count 12 (+ 2)
% Row 4
\SetRowColor{LightBackground}
table.groupby({[}'col0'{]}).col1.agg({[}f1, f2, f3{]}) & agg() runs diff. funcs. simultaneously on a df \tn 
% Row Count 15 (+ 3)
% Row 5
\SetRowColor{white}
table.groupby({[}'col0', 'col1'{]}).col2.agg({[}len{]}) & Multi-index output has tiered structure. Require 2 levels of labels to retrieve a val \tn 
% Row Count 20 (+ 5)
% Row 6
\SetRowColor{LightBackground}
df.reset\_index() & Muti-index method used to converting back to regular index \tn 
% Row Count 23 (+ 3)
% Row 7
\SetRowColor{white}
\seqsplit{df.sort\_values(by='col')} & Sort rows of data by vals in col (ascending) \tn 
% Row Count 26 (+ 3)
% Row 8
\SetRowColor{LightBackground}
\seqsplit{df.sort\_values(by='col'}, ascending=False) & Sort rows of data by vals in col (descending) \tn 
% Row Count 29 (+ 3)
% Row 9
\SetRowColor{white}
df.sort\_values(by={[}'col0', 'col1'{]}) & Sort rows by more than 1 col at a time \tn 
% Row Count 31 (+ 2)
\end{tabularx}
\par\addvspace{1.3em}

\vfill
\columnbreak
\begin{tabularx}{8.4cm}{x{4 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Grouping \& Sorting (cont)}}  \tn
% Row 10
\SetRowColor{LightBackground}
df.sort\_index() & Sort rows by index (default order; ascending) \tn 
% Row Count 3 (+ 3)
\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 Types \& Missing Values}}  \tn
% Row 0
\SetRowColor{LightBackground}
table.col.dtype & Get data type of a col \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
table.dtypes & Get data types of each col in table \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{table.col.astype('datatype')} & Convert col to datatype if allowed (e,g, int64 -\textgreater{} float64) \tn 
% Row Count 7 (+ 3)
% Row 3
\SetRowColor{white}
table.index.dtype & Number indices are int64 \tn 
% Row Count 9 (+ 2)
% Row 4
\SetRowColor{LightBackground}
table{[}pd.isnull(table.col){]} & Select NaN entries in a col \tn 
% Row Count 11 (+ 2)
% Row 5
\SetRowColor{white}
\seqsplit{table.col.fillna("filler")} & Replace all NaN vals in a col with a sentinel val ("Unknown", "Undisclosed", "Invalid") or non-null val \tn 
% Row Count 17 (+ 6)
% Row 6
\SetRowColor{LightBackground}
\seqsplit{table.col.replace("init\_val"}, "new\_val") & Replace, in col, all existing vals with new\_vals \tn 
% Row Count 20 (+ 3)
\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}{Renaming \& Combining}}  \tn
% Row 0
\SetRowColor{LightBackground}
table.rename(columns=\{'init': 'new'\}) & Rename col or index col names \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
table.rename(index=\{0: 'firstEntry', 1: 'secondEntry\}) & Rename index or col vals by specifying an index or col param \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{table.rename\_axis("name"}, \seqsplit{axis='rows').rename\_axis("name1"}, axis='columns') & Rename row index \&/or col index \tn 
% Row Count 9 (+ 4)
% Row 3
\SetRowColor{white}
pd.concat(list, of, els) & Smush together the list of elements along an axis \tn 
% Row Count 12 (+ 3)
% Row 4
\SetRowColor{LightBackground}
left.join(right, lsuffix='strL', rsuffix='strR') & Combine diff df objects that have an index in common. left and right are df.s defined beforehand \tn 
% Row Count 17 (+ 5)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}