\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{AdrianPerogil}
\pdfinfo{
  /Title (pandas-chopito.pdf)
  /Creator (Cheatography)
  /Author (AdrianPerogil)
  /Subject (Pandas - Chopito 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}{A3A3A3}
\definecolor{LightBackground}{HTML}{F3F3F3}
\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{Pandas - Chopito Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{AdrianPerogil} via \textcolor{DarkBackground}{\uline{cheatography.com/195296/cs/44826/}}}
\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}AdrianPerogil \\
  \uline{cheatography.com/adrianperogil} \\
  \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 28th October, 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{2.72 cm} x{5.28 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Init}}  \tn
% Row 0
\SetRowColor{LightBackground}
{\bf{import}} & import pandas as pd \tn 
% Row Count 1 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{1.6 cm} x{6.4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Creating Reading Writing}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{read\_csv()} & \seqsplit{pd.read\_csv('example.csv'}, index\_col=0, usecols={[}'title'{]}, sep=';') \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\seqsplit{to\_csv()} & df.to\_csv('example.csv', index=False, sep=';', header=False) \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
head() & df.head(5) \tn 
% Row Count 6 (+ 1)
% Row 3
\SetRowColor{white}
copy() & df\_copy = df{[}{[}'title', 'year'{]}{]}.copy() \tn 
% Row Count 8 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{index\_col=0}}: La primera columna del df, será el índice. \newline {\bf{ usecols={[}'title'{]}}}: Solo carga del df, la columna title. \newline {\bf{sep=';'}}:Tipo de separador que contiene el CSV. \newline {\bf{header=False}}: No contiene una fila con nombres de la columna, se sustituyen por números. \newline {\bf{index=False}}: Solo se guardan las columnas. \newline {\bf{copy()}}: Cambiar en df\_copy, no afecta a df. Sin copy, crea una referencia de df, cambios en df\_copia puede afectar a df.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.32 cm} x{5.68 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Indexing Selecting Assigning}}  \tn
% Row 0
\SetRowColor{LightBackground}
loc() & df.loc{[}df{[}'year'{]} \textgreater{}= 2018{]} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
loc() with == & df.loc{[}df{[}'title'{]} == 'Black Panther', 'people\_score'{]} = 100 \tn 
% Row Count 4 (+ 3)
% Row 2
\SetRowColor{LightBackground}
loc() with \& & df.loc{[}(df{[}'critic\_score'{]} \textgreater{} 90) \& (df{[}'people\_score'{]} \textgreater{} 80){]} \tn 
% Row Count 7 (+ 3)
% Row 3
\SetRowColor{white}
\seqsplit{str.startswith()} & df.loc{[}df{[}'title'{]}.str.startswith('S'){]} \tn 
% Row Count 9 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{str.contain()} & df.loc{[}df{[}'title'{]}.str.contains('Spider'), 'critic\_score'{]} = 95 \tn 
% Row Count 12 (+ 3)
% Row 5
\SetRowColor{white}
iloc() & df.iloc{[}5:11, {[}0, 1, 3{]}{]} \tn 
% Row Count 13 (+ 1)
% Row 6
\SetRowColor{LightBackground}
subtract & df{[}'critic\_score'{]} - df{[}'people\_score'{]} \tn 
% Row Count 15 (+ 2)
% Row 7
\SetRowColor{white}
median() & df.loc{[}df{[}'critic\_score'{]} \textgreater{} df{[}'critic\_score'{]}.median(){]} \tn 
% Row Count 17 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{loc()}}: Selecciona filas y columnas basado en una etiqueta, en este caso los que cumplan x condición. \newline {\bf{iloc()}}: Selecciona filas y columnas basado en su índice, en este caso las filas del 5 al 10 y las columnas 0, 1, 3. \newline {\bf{str.startswith()}}: En este caso, selecicona las películas cuyo título comience por S. \newline {\bf{str.contains()}}: En este caso, selecicona las películas cuyo título contengan 'Spider'. \newline {\bf{median()}}: Hace la mediana de la columna 'critic\_score'}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.08 cm} x{5.92 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Summary Functions Maps}}  \tn
% Row 0
\SetRowColor{LightBackground}
mean() & df{[}'critic\_score'{]}.mean() \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\seqsplit{describe()} & df.describe() \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{value\_counts()} & df{[}'type'{]}.value\_counts() \tn 
% Row Count 4 (+ 2)
% Row 3
\SetRowColor{white}
min() & df{[}'people\_score'{]}.min() \tn 
% Row Count 5 (+ 1)
% Row 4
\SetRowColor{LightBackground}
max() & df{[}'people\_score'{]}.max() \tn 
% Row Count 6 (+ 1)
% Row 5
\SetRowColor{white}
def & def score\_ratio(row): \tn 
% Row Count 7 (+ 1)
% Row 6
\SetRowColor{LightBackground}
 & newcolumn = row{[}'critic\_score'{]} / row{[}'people\_score'{]} \tn 
% Row Count 9 (+ 2)
% Row 7
\SetRowColor{white}
 & return newcolumn \tn 
% Row Count 10 (+ 1)
% Row 8
\SetRowColor{LightBackground}
apply() & df{[}'score\_ratio'{]} = df.apply(score\_ratio, axis=1) \tn 
% Row Count 12 (+ 2)
% Row 9
\SetRowColor{white}
map() & df{[}'type'{]} = df{[}'type'{]}.map(lambda x: x.lower()) \tn 
% Row Count 14 (+ 2)
% Row 10
\SetRowColor{LightBackground}
std() & df{[}'people\_score'{]}.std() \tn 
% Row Count 15 (+ 1)
% Row 11
\SetRowColor{white}
agg() & critic\_score\_agg = df{[}'critic\_score'{]}.agg({[}'mean', 'std'{]}) \tn 
% Row Count 17 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{mean()}}: Calcula la media. \newline {\bf{describe()}}: Resumen estadístico del df. \newline {\bf{value\_counts()}}: Cuenta cuantas películas hay de cada tipo. \newline {\bf{apply()}}: En la columna nueva (score\_ratio) los valores se obtendrán por la función 'score\_ratio'. \newline {\bf{map()}}: Cambia todos los valores a minúscula con {\bf{lower()}}. \newline {\bf{std()}}: Mide la dispersión de los datos respecto a la media. \newline {\bf{agg()}}: Calcula múltiples estadísticas a la vez (mean y std).}  \tn 
\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}
sort\_values() with loc() & \seqsplit{df.sort\_values('year')}.loc{[}:, {[}'title', 'year', 'critic\_score'{]}{]} \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
sort\_values() with agg() & df.groupby('type').agg(\{'critic\_score': {[}'mean', 'std'{]}\}) \tn 
% Row Count 7 (+ 3)
% Row 2
\SetRowColor{LightBackground}
groupby() with sum() & df.groupby('production\_co'){[}'people\_score'{]}.sum() \tn 
% Row Count 10 (+ 3)
% Row 3
\SetRowColor{white}
groupby() with size() & \seqsplit{df.groupby('year').size()} \tn 
% Row Count 12 (+ 2)
% Row 4
\SetRowColor{LightBackground}
groupby() with mean() and sort\_values() and sort\_values() & \seqsplit{df.groupby('production\_co').mean(numeric\_only=True).sort\_values('critic\_score'}, ascending=False) \tn 
% Row Count 17 (+ 5)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{df.groupby('production\_co').mean(numeric\_only=True).sort\_values('critic\_score', ascending=False)}}: Agrupa por columna, calcula la media de columnas numéricas y ordena por la columna 'critic\_score' de mayor a menos.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.56 cm} x{5.44 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Data\_type Missing\_values}}  \tn
% Row 0
\SetRowColor{LightBackground}
astype() & df{[}'year'{]}.astype(str) \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
 & df{[}'critic\_score'{]}.astype(float) \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
isnull() with sum() & df.isnull().sum() \tn 
% Row Count 5 (+ 2)
% Row 3
\SetRowColor{white}
fillna() & df{[}'people\_score'{]}.fillna(df{[}'people\_score'{]}.median()) \tn 
% Row Count 7 (+ 2)
% Row 4
\SetRowColor{LightBackground}
 & df{[}'people\_score'{]}.fillna(0) \tn 
% Row Count 9 (+ 2)
% Row 5
\SetRowColor{white}
dropna() & df.dropna(subset={[}'critic\_score'{]}) \tn 
% Row Count 11 (+ 2)
% Row 6
\SetRowColor{LightBackground}
\seqsplit{str.replace()} & df{[}'release\_date\_(theaters)'{]}.str.replace('wide', \seqsplit{'').str.replace('limited'}, '') \tn 
% Row Count 14 (+ 3)
% Row 7
\SetRowColor{white}
\seqsplit{to\_datetime()} & pd.to\_datetime(df{[}'release\_date\_(theaters)'{]}) \tn 
% Row Count 16 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{astype()}}: convierte una columna a otro tipo de dato. \newline {\bf{isnull()}}: detecta valores nulos en el DataFrame. \newline {\bf{fillna()}}: reemplaza valores nulos con un valor especificado. \newline {\bf{dropna()}}: elimina filas o columnas con valores nulos. \newline {\bf{str.replace()}}: reemplaza patrones en texto dentro de una serie. \newline {\bf{to\_datetime()}}: convierte datos a formato de fecha y hora.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{2.16 cm} x{5.84 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Renaming Combining}}  \tn
% Row 0
\SetRowColor{LightBackground}
rename() & movies.rename(columns=\{'title': 'movie\_title', 'release\_year': 'release\_year'\}, inplace=True) \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
concat() & pd.concat({[}movies\_info, box\_office{]}, axis=1) \tn 
% Row Count 6 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{set\_index()} & movies.set\_index('id') \tn 
% Row Count 8 (+ 2)
% Row 3
\SetRowColor{white}
join() & \seqsplit{movies.join(reviews.set\_index('id'))} \tn 
% Row Count 10 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{df.index.name} & movies.index.name = 'movies\_index' \tn 
% Row Count 12 (+ 2)
% Row 5
\SetRowColor{white}
\seqsplit{df.columns.name} & movies.columns.name = 'movie\_attributes' \tn 
% Row Count 14 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{{\bf{rename()}}: cambia nombres de columnas o índices en el DataFrame. \newline {\bf{concat()}}: une múltiples DataFrames a lo largo de un eje. \newline {\bf{set\_index()}}: establece una columna como índice del DataFrame. \newline {\bf{join()}}: combina DataFrames usando el índice. \newline {\bf{df.index.name}}: asigna o muestra el nombre del índice. \newline {\bf{df.columns.name}}: asigna o muestra el nombre de las columnas.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}