\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{PabloGM}
\pdfinfo{
  /Title (python-pandas.pdf)
  /Creator (Cheatography)
  /Author (PabloGM)
  /Subject (Python - Pandas 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{Python - Pandas Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{PabloGM} via \textcolor{DarkBackground}{\uline{cheatography.com/208640/cs/44743/}}}
\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}PabloGM \\
  \uline{cheatography.com/pablogm} \\
  \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 21st 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*}{3}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Import}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{import pandas as pd} \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}{Leer un archivo (csv)}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{df = \seqsplit{pd.read\_csv("../ruta/mi/archivo.csv")}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.73735 cm} x{2.23965 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Leer ciertos datos}}  \tn
% Row 0
\SetRowColor{LightBackground}
df\_columnas = \seqsplit{pd.read\_csv("../archivo.csv"}, usecols={[}'title', 'critics'{]}) & Lee solo las columnas indicadas \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
df{[}'title'{]}{[}0{]} & Lee el primer valor de la columna \tn 
% Row Count 6 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Guardar un csv}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{df.to\_csv("copia.csv", sep=";",  index=False, header=True)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Por defecto hace el guardado de los nombres de las columnas pero no est mal ponerlo y el separador es un añadido extra.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{0.9954 cm} x{3.9816 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Mostrar los datos}}  \tn
% Row 0
\SetRowColor{LightBackground}
df & Muestra tanto primeros como ultimos \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{df.head()} & Muestra los cinco primeros \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{df.tail()} & Muestra los cinco ultimos \tn 
% Row Count 6 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Uso de datos}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{df\_selection = df{[}{[}'title', 'critic\_score'{]}{]}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Seleccion de datos .loc}}  \tn
% Row 0
\SetRowColor{LightBackground}
df.loc{[}df.year \textgreater{}= 2018{]} & Seleccionas las pelis que son mayor o igual a 2018 \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
df.loc{[}df.title == 'La pantera', 'critics{]} = 100' & Donde el titulo sea 'La pantera', pone el valor de critics a 100 \tn 
% Row Count 7 (+ 4)
% Row 2
\SetRowColor{LightBackground}
df.loc{[}(df.critic\_score \textgreater{} 90) \& (df.people\_score \textgreater{} 80){]} & Coge las filas en las que supere esos dos valores respectivamente \tn 
% Row Count 11 (+ 4)
% Row 3
\SetRowColor{white}
df.loc{[}df.title.str.startswith('S'){]} & Coge las peliculas que empizen por S mayuscula \tn 
% Row Count 14 (+ 3)
% Row 4
\SetRowColor{LightBackground}
df.loc{[}df.critic\_score \textgreater{} df.critic\_score.median(){]} & Coge todas las que la puntuacion sea mayor a la mediana de la columna \tn 
% Row Count 18 (+ 4)
% Row 5
\SetRowColor{white}
df.loc{[}df.title.str.contains("Spider", na=False), 'critic\_score'{]} = 95 & Pone el valor de 95 a aquellas pelis que en el titulo tengan "Spider" \tn 
% Row Count 22 (+ 4)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Seleccion de datos .iloc}}  \tn
% Row 0
\SetRowColor{LightBackground}
df.iloc{[}0{]} & Coge la primera fila \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
df.iloc{[}0:3{]} & Coge del 0 al 2 \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
df.loc{[}:9, 'description'{]} & Coge desde la 0 hasta la 9 de la columna \tn 
% Row Count 4 (+ 2)
% Row 3
\SetRowColor{white}
df.iloc{[}5:11{]}{[}{[}'title', 'year', 'critic\_score'{]}{]} & Coge del 5 al 10 de esas columnas \tn 
% Row Count 7 (+ 3)
% Row 4
\SetRowColor{LightBackground}
df.iloc{[}{[}1, 2, 3, 5, 8{]}{]} & Coge esas filas en especifico \tn 
% Row Count 9 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.33919 cm} x{2.63781 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Summary Functions and Map}}  \tn
% Row 0
\SetRowColor{LightBackground}
df.describe() \# Dentro estan todas & Resumen de las columnas numéricas \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{df.peliculas.unique()} & Coge las peliculas una sola vez \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{df.peliculas.value\_counts()} & Cuenta cuantas veces aparece cada cosa \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
df.critics.mean() & Devuelve la media de la columna \tn 
% Row Count 8 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Hay mas método como el 'std', 'min', 'sum', etc.}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Map Function}}  \tn
% Row 0
\SetRowColor{LightBackground}
centered\_price = \seqsplit{reviews.price.map(lambda} p: p - mean\_price) & A cada fila coge el valor de price que es p y le resta la media de la columna \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
n\_trop = \seqsplit{reviews.description.map(lambda} desc: "tropical" in desc).sum() & Si tiene esa descripcion es True (1) por lo que suma ese uno asi fila por fila \tn 
% Row Count 8 (+ 4)
% Row 2
\SetRowColor{LightBackground}
df{[}'type'{]}.map(lambda valor: valor.lower()) & Pone los datos en type a minusculas \tn 
% Row Count 11 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Map es una función a la cual se recorre cada valor que le pasemos y hace lo que le pongamos}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Apply Function}}  \tn
% Row 0
\SetRowColor{LightBackground}
star\_ratings = reviews.apply(stars, axis='columns') & Hace el metodo 'stars' el cual hace que devuelva un valor a cad fila, dentro del metodo usa reviews.points \tn 
% Row Count 6 (+ 6)
% Row 1
\SetRowColor{white}
df{[}'is\_highly\_rated'{]} = df.apply(lambda fila: fila{[}'critic\_score'{]} \textgreater{} 90, axis=1) & Crea una nueva columna que pone a True si se cumple la condicion \tn 
% Row Count 10 (+ 4)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Agg Function}}  \tn
% Row 0
\SetRowColor{LightBackground}
critic\_score\_agg = df{[}'critic\_score'{]}.agg({[}'mean', 'std'{]}) & Devuelve el valor de los metodos que pongamos dentro \tn 
% Row Count 3 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.34379 cm} x{3.63321 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Métodos}}  \tn
% Row 0
\SetRowColor{LightBackground}
.idmax() & Devuelve el dato mayor \tn 
% Row Count 1 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}