\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{sanjeev95}
\pdfinfo{
  /Title (python-pandas.pdf)
  /Creator (Cheatography)
  /Author (sanjeev95)
  /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}{363CFF}
\definecolor{LightBackground}{HTML}{F2F2FF}
\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}{sanjeev95} via \textcolor{DarkBackground}{\uline{cheatography.com/111141/cs/21621/}}}
\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}sanjeev95 \\
  \uline{cheatography.com/sanjeev95} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Published 20th January, 2020.\\
   Updated 22nd January, 2020.\\
   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}{install and import}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{installing pandas \{\{nl\}\} `pip install pandas`} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{pip install pandas \{\{nl\}\} `import pandas as pd`} \tn 
% Row Count 2 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Reading and describing}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{pd -\textgreater{} pandas \{\{nl\}\} df-\textgreater{} dataframe} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{to read a file into a dataframe \{\{nl\}\} `df= \seqsplit{pd.read\_csv('filename')`}} \tn 
% Row Count 3 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{look at the first 5 lines \{\{nl\}\} `df.head()`} \tn 
% Row Count 4 (+ 1)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{to describe df  \{\{nl\}\} `df.describe()`} \tn 
% Row Count 5 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`df.info()`} \tn 
% Row Count 6 (+ 1)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{to print all the column names \{\{nl\}\}`telecom\_data.columns`} \tn 
% Row Count 8 (+ 2)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{to get the dimension of df \{\{nl\}\} `df.shape`} \tn 
% Row Count 9 (+ 1)
\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}{Sorting and filtering}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{{\bf{sort}} \{\{nl\}\} sorting can be done column wise - default is ascending \{\{nl\}\} \seqsplit{`df.sort\_values(by='Total} day charge')`} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\seqsplit{`df.sort\_values(col1)`} & Sort values by col1 in ascending order (use ascending =False for descending sort) \tn 
% Row Count 8 (+ 5)
% Row 2
\SetRowColor{LightBackground}
`df.sort\_values({[}col1,col2{]},ascending={[}True,False{]})` & Sort values by col1 in ascending order then col2 in descending order \tn 
% Row Count 12 (+ 4)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{Filtering  \{\{nl\}\} `df{[}condition{]} ~~~  \#eg: df{[}df{[}'col'{]}\textgreater{}5{]}`} \tn 
% Row Count 14 (+ 2)
% Row 4
\SetRowColor{LightBackground}
`df{[}df{[}'col'{]} \textgreater{} 0.5{]}` & Rows where the column col is greater than 0.5 \tn 
% Row Count 17 (+ 3)
% Row 5
\SetRowColor{white}
`df{[}(df{[}col{]} \textgreater{} 0.5) \& (df{[}col{]} \textless{} 0.7){]}` & Rows where 0.7 \textgreater{} col \textgreater{} 0.5 \tn 
% Row Count 19 (+ 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}{Inplace}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{NOTE}}} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{`df.merge(df2)` gives you a copy of df merged with df2. you may save it to a new variable. ex `df3=df.merge(df2)`} \tn 
% Row Count 4 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{if you want to merge df2 to df right away use inplace. `df.merge(df2,inplace=True)`} \tn 
% Row Count 6 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{p{0.4977 cm} p{0.4977 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Rows and columns}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{to delete a row - {[}axis=0 means rows{]}\{\{nl\}\} `new\_df = df.drop({[}2,3{]},axis = 0)   \#this drops the row with index 2,3`} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{to delete a column- {[}axis=1 means columns{]}\{\{nl\}\} `new\_df = df.drop({[}'col1','col2'{]},axis = 0)   \#this drops the column with name col1 and col2`} \tn 
% Row Count 6 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Df manipulation}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{{\bf{create or edit a new column}} \{\{nl\}\} `df{[}'new\_colname'{]} = 5 ~ \#this creates a new new column with all values as 5`} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{create a new column \{\{nl\}\} `df{[}'new\_colname'{]} = {[}list of values{]} ~ \#this creates a new column with list of values assigned to each corresponding row `} \tn 
% Row Count 7 (+ 4)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{NOTE : `df{[}'new\_colname'{]} = {[}list of values{]}` throws an error if the no of items in {[}list of values{]} doesn't match no of rows} \tn 
% Row Count 10 (+ 3)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{{\bf{create or edit a new row}}} \tn 
% Row Count 11 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{`df.loc{[}index\_of\_row{]} = {[}list of items{]}`} \tn 
% Row Count 12 (+ 1)
% Row 5
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{NOTE : `df.loc{[}index\_of\_row{]} = {[}list of items{]}` throws an error if the no of items doesn't match no of rows} \tn 
% Row Count 15 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.54287 cm} x{3.43413 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Selection}}  \tn
% Row 0
\SetRowColor{LightBackground}
`df{[}col{]}` & Returns column with label col as Series \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
`df{[}{[}col1, col2{]}{]}` & Returns multiple columns as a new DataFrame \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\seqsplit{~~	Country	~~Capital	~~~~~~Population} \{\{nl\}\}1	Belgium~~	Brussels	~~~~11190846 \{\{nl\}\}2	India	~~~~~~~New Delhi	~1303171035 \{\{nl\}\}3	Brazil	~~~~~~Brasilia	~~~~~~207847528} \tn 
% Row Count 11 (+ 7)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{`df.iloc({[}0{]}, {[}0{]})` -{}-\textgreater{}  'Belgium' ~| s.iloc{[}0{]} | Selection by position (0th position on row and column)} \tn 
% Row Count 14 (+ 3)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{`df.loc({[}0{]},  {[}'Country'{]})` -{}-\textgreater{} 'Belgium'} \tn 
% Row Count 15 (+ 1)
% Row 5
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{`df.ix{[}2{]}` -{}-\textgreater{}\{\{nl\}\} Country   ~~~~~~ Brazil \{\{nl\}\}Capital~~~~~~~~    Brasilia \{\{nl\}\}Population ~ 207847528} \tn 
% Row Count 19 (+ 4)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{`df.ix{[}1, 'Capital'{]}` -{}-\textgreater{} 'New Delhi'} \tn 
% Row Count 20 (+ 1)
% Row 7
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{df.iloc{[}0,:{]} | select First row} \tn 
% Row Count 21 (+ 1)
\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}{Data Cleaning}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{df.set\_index('column\_one')} & Change the index with a new column \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
df.columns = {[}'new\_col\_name1','new\_col\_name2','new\_col\_name3'{]} & Rename columns \tn 
% Row Count 6 (+ 4)
% Row 2
\SetRowColor{LightBackground}
pd.isnull() & Checks for null Values, Returns Boolean Arrray \tn 
% Row Count 9 (+ 3)
% Row 3
\SetRowColor{white}
pd.notnull() & Opposite of pd.isnull() \tn 
% Row Count 11 (+ 2)
% Row 4
\SetRowColor{LightBackground}
df.dropna() & Drop all rows that contain null values \tn 
% Row Count 13 (+ 2)
% Row 5
\SetRowColor{white}
df.dropna(axis=1) & Drop all columns that contain null values \tn 
% Row Count 16 (+ 3)
% Row 6
\SetRowColor{LightBackground}
df.dropna(axis=1,thresh=n) & Drop all rows have have less than n non null \tn 
% Row Count 19 (+ 3)
% Row 7
\SetRowColor{white}
df.fillna(x) & Replace all null values with x \tn 
% Row Count 21 (+ 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}{JOIN/COMBINE}}  \tn
% Row 0
\SetRowColor{LightBackground}
`df1.append(df2)` & Adds the rows in df1 to the end of \{\{nl\}\}df2 (columns should \{\{nl\}\}be identical) \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
`pd.concat({[}df1, df2{]},axis=1)` & Adds the columns in \{\{nl\}\}df1 to the end \{\{nl\}\}of df2 (rows should be \{\{nl\}\}identical) \tn 
% Row Count 9 (+ 5)
% Row 2
\SetRowColor{LightBackground}
`df1.join(df2,on=col1,how='inner')` & joins the columns in df1 with the columns on \{\{nl\}\}df2 where the rows \{\{nl\}\}for col have identical \{\{nl\}\}values. how can be \{\{nl\}\}one of 'left', \{\{nl\}\}'right', 'outer', 'inner' \tn 
% Row Count 18 (+ 9)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{left = takes the index of left df\{\{nl\}\}right =takes the index of left  \{\{nl\}\} outer = union of both keys\{\{nl\}\}inner = intersection of both keys} \tn 
% Row Count 21 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}