\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{Molly\_6075}
\pdfinfo{
  /Title (pandas.pdf)
  /Creator (Cheatography)
  /Author (Molly\_6075)
  /Subject (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}{52A382}
\definecolor{LightBackground}{HTML}{F4F9F7}
\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 Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{Molly\_6075} via \textcolor{DarkBackground}{\uline{cheatography.com/193986/cs/40407/}}}
\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}Molly\_6075 \\
  \uline{cheatography.com/molly-6075} \\
  \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 16th October, 2023.\\
   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 cm} x{4 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Basic Function}}  \tn
% Row 0
\SetRowColor{LightBackground}
df = \seqsplit{pd.read\_csv("filename")} & 读取csv文件 \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
df.info( ) & \seqsplit{返回每一列的非空行数、数据类型} \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
df.dtypes & \seqsplit{返回每个字段的类型} \tn 
% Row Count 7 (+ 2)
% Row 3
\SetRowColor{white}
df.describe( ) & \seqsplit{返回每一列的数量、均值、方差、最值、四分位值} \tn 
% Row Count 11 (+ 4)
% Row 4
\SetRowColor{LightBackground}
df.columns & 返回所有列名 \tn 
% Row Count 12 (+ 1)
% Row 5
\SetRowColor{white}
df.head(5) & \seqsplit{返回前5行的全部信息} \tn 
% Row Count 14 (+ 2)
% Row 6
\SetRowColor{LightBackground}
df.columns = {[}each.stripe( ), for each in df.columns{]} & \seqsplit{去除列名前后的空格，并更新列名} \tn 
% Row Count 17 (+ 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}{Basic Calculation on One Column}}  \tn
% Row 0
\SetRowColor{LightBackground}
df.loc{[}:,'columnName'{]}.std( ) & \seqsplit{返回某一列的标准差}.var( )表示方差 \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
df.loc{[}:,'columnName'{]}.mean() & \seqsplit{返回某一列的均值} \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
df.ID.unique() & \seqsplit{返回ID列的所有不重复值} \tn 
% Row Count 7 (+ 2)
% Row 3
\SetRowColor{white}
df.ID.nunique() & \seqsplit{不重复的ID值数量} \tn 
% Row Count 9 (+ 2)
% Row 4
\SetRowColor{LightBackground}
df.loc{[}:,'columnName'{]}.max() & \seqsplit{某一列的最大值} \tn 
% Row Count 11 (+ 2)
% Row 5
\SetRowColor{white}
df{[}'columnName'{]}.mode() & 某一列的众数 \tn 
% Row Count 13 (+ 2)
% Row 6
\SetRowColor{LightBackground}
\seqsplit{df.ColumnName.value\_counts()} & \seqsplit{分组统计某一列不同值的数量，并从高到低排序} \tn 
% Row Count 17 (+ 4)
% Row 7
\SetRowColor{white}
df.ColumnName.value\_counts(){[}:1{]} & \seqsplit{取数量最大的一行} \tn 
% Row Count 19 (+ 2)
% Row 8
\SetRowColor{LightBackground}
\seqsplit{df.groupby('col1').col2.sum()} & \seqsplit{根据col1的值分组，统计col2的和} \tn 
% Row Count 22 (+ 3)
% Row 9
\SetRowColor{white}
\seqsplit{df.groupby("col1").col2.mean().sort\_values()} & \seqsplit{分组后取均值，并由低到高排序} \tn 
% Row Count 25 (+ 3)
% Row 10
\SetRowColor{LightBackground}
\seqsplit{df.groupby("month").emp\_combined\_inclow.mean().sort\_values(ascending=False)} & \seqsplit{分组后取均值，由高到低排序} \tn 
% Row Count 29 (+ 4)
% Row 11
\SetRowColor{white}
\seqsplit{df.groupby("col1").col2.mean()}.sort\_values(){[}:1{]} & \seqsplit{排序后取第一个值（最小值）} \tn 
% Row Count 32 (+ 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}{Create new column/ Extract column}}  \tn
% Row 0
\SetRowColor{LightBackground}
df{[}'NewColumn'{]} = \seqsplit{df.ColumnName.apply(lambda} x:"No" if x != 0 else "Yes") & \seqsplit{将某一列的值逻辑判断的结果存放在新列} \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
df{[}'NewColumn'{]} = pd.cut(df.BMI,bins = {[}a,b,c,d,e{]}, labels={[}"label1", "label2", "label3", "4"{]}) & \seqsplit{根据某列值的返回添加标签（a至b属于label1）} \tn 
% Row Count 9 (+ 5)
% Row 2
\SetRowColor{LightBackground}
df\_a = df{[}df.Column3.isna() == False{]}.loc{[}:, {[}"Column1","Column2"{]}{]} & \seqsplit{依据条件提取某两列组成新的dataframe} \tn 
% Row Count 13 (+ 4)
% Row 3
\SetRowColor{white}
df = \seqsplit{df.drop('ColumnName'},axis = 1) & 删除某一列 \tn 
% Row Count 15 (+ 2)
\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}{Time-related manupulation}}  \tn
% Row 0
\SetRowColor{LightBackground}
df = \seqsplit{pd.read\_csv("filename"},parse\_dates={[}'Date'{]}) & \seqsplit{读取文件的同时将Date列转化成指定日期格式} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
df = \seqsplit{pd.read\_csv("employment\_rate.csv"},parse\_dates={[}{[}"year","month","day"{]}{]}) & \seqsplit{把分别存放年、月、日的三列合并为同一列} \tn 
% Row Count 7 (+ 4)
% Row 2
\SetRowColor{LightBackground}
df{[}'year'{]} = df.Date.dt.year & \seqsplit{提取Date列的年份存放在新列year} \tn 
% Row Count 10 (+ 3)
% Row 3
\SetRowColor{white}
df{[}'month{]} = df.Date.dt.month & \seqsplit{提取Date列的月份存放在新列month} \tn 
% Row Count 13 (+ 3)
% Row 4
\SetRowColor{LightBackground}
df{[}'day'{]} = df.Date.dt.day & \seqsplit{提取Date列的日期存放在新列day} \tn 
% Row Count 15 (+ 2)
% Row 5
\SetRowColor{white}
df{[}'day\_name'{]} = \seqsplit{df.Date.dt.day\_name()} & \seqsplit{根据Date计算星期信息存放在新列day\_name} \tn 
% Row Count 18 (+ 3)
% Row 6
\SetRowColor{LightBackground}
dfa{[}'Date'{]} = {[}datetime.strptime(x, "\%b-\%y") for x in df.Period{]} & \seqsplit{把形式为Jan-2020的日期列转化成标准日期的格式} \tn 
% Row Count 22 (+ 4)
\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}{Correlation Analysis}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{返回所有列和目标列的相关系数，并按从低到高排序（所有列必须都是数值型，反映两个dataframe之间的相关关系）} & \seqsplit{df.corrwith(df.targetColumn).sort\_values()} \tn 
% Row Count 8 (+ 8)
% Row 1
\SetRowColor{white}
\seqsplit{例子：指定列与目标列的相关系数，并排序} & selected\_col ={[}"a","b","c"{]} \tn 
% Row Count 11 (+ 3)
% Row 2
\SetRowColor{LightBackground}
 & df{[}selected\_col{]}.corrwith(df.targetColumn).sort\_values() \tn 
% Row Count 14 (+ 3)
% Row 3
\SetRowColor{white}
\seqsplit{一个dataframe中，所有列之间的两两相关关系} & df{[}selected\_col{]}.corr(method="spearman") \tn 
% Row Count 17 (+ 3)
% Row 4
\SetRowColor{LightBackground}
 & df.loc{[}:, {[}"a", "b","c"{]}{]}.corr() \tn 
% Row Count 19 (+ 2)
\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}{Plot}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{df.groupby('column1').column2.mean().plot(kind} = 'bar') & 柱状图 \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
\seqsplit{df.column1.plot(kind} = 'hist') & \seqsplit{频数分布直方图} \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
df.plot(kind="line", y="column1", x="column2") & 普通折线图 \tn 
% Row Count 8 (+ 3)
% Row 3
\SetRowColor{white}
\seqsplit{df.groupby("column3").column1.mean(} ).plot( ) & \seqsplit{分组统计后的折线图} \tn 
% Row Count 11 (+ 3)
% Row 4
\SetRowColor{LightBackground}
df.groupby("column4"){[}{[}"column1","column2","column3"{]}{]}.mean().plot() & \seqsplit{多个列用相同标准分组，并将折线展示在同一个图中} \tn 
% Row Count 15 (+ 4)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{8.4cm}{x{3.76 cm} x{4.24 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{8.4cm}}{\bf\textcolor{white}{Complex Plot}}  \tn
% Row 0
\SetRowColor{LightBackground}
from pandas.plotting import lag\_plot & \seqsplit{绘制时间序列数据的滞后图} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
lag\_plot(df, lag = 2) & 默认的滞后期=1,如果数据存在自相关性，将沿着某条对角线分布 \tn 
% Row Count 6 (+ 4)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{from pandas.plotting import*} \tn 
% Row Count 7 (+ 1)
% Row 3
\SetRowColor{white}
\seqsplit{autocorrelation\_plot(df)} & \seqsplit{观察时间序列数据中的自相关性} \tn 
% Row Count 9 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}