\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 (machine-learning.pdf)
  /Creator (Cheatography)
  /Author (Molly\_6075)
  /Subject (Machine Learning 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}{306380}
\definecolor{LightBackground}{HTML}{F2F5F7}
\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{Machine Learning Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{Molly\_6075} via \textcolor{DarkBackground}{\uline{cheatography.com/193986/cs/40757/}}}
\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}{Boost Classifier}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{AdaBoost} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
from sklearn.ensemble import AdaBoostClassifier & 导入AdaBoost \tn 
% Row Count 4 (+ 3)
% Row 2
\SetRowColor{LightBackground}
classifier = \seqsplit{AdaBoostClassifier(n\_estimators=3},learning\_rate=0.2, random\_state=0) & 参数设置 \tn 
% Row Count 9 (+ 5)
% Row 3
\SetRowColor{white}
\seqsplit{classifier.fit(x\_train}, y\_train) & y\_pred = \seqsplit{classifier.predict(x\_test)} \tn 
% Row Count 11 (+ 2)
% Row 4
\SetRowColor{LightBackground}
from \seqsplit{sklearn.model\_selection} import GridSearchCV & 最优参数选择 \tn 
% Row Count 14 (+ 3)
% Row 5
\SetRowColor{white}
param\_grid = \{'n\_estimators': {[}1,10,100{]},'learning\_rate': {[}0.2,0.4,0.6,0.8{]}\} & grid = \seqsplit{GridSearchCV(AdaBoostClassifier()},param\_grid, scoring ='accuracy') \tn 
% Row Count 18 (+ 4)
% Row 6
\SetRowColor{LightBackground}
grid.fit(x\_train,y\_train) & \seqsplit{grid.best\_estimator\_}, grid.best\_params\_, grid.cv\_results\_ \tn 
% Row Count 21 (+ 3)
% Row 7
\SetRowColor{white}
\mymulticolumn{2}{x{8.4cm}}{GradientBoost} \tn 
% Row Count 22 (+ 1)
% Row 8
\SetRowColor{LightBackground}
from sklearn.ensemble import \seqsplit{GradientBoostingClassifier} & 导入GradientBoost \tn 
% Row Count 25 (+ 3)
% Row 9
\SetRowColor{white}
classifier = \seqsplit{GradientBoostingClassifier(n\_estimators=1}, learning\_rate=0.4,max\_depth=1, random\_state=0) & \seqsplit{classifier.fit(x\_train}, y\_train) \tn 
% Row Count 31 (+ 6)
\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}{Boost Classifier (cont)}}  \tn
% Row 10
\SetRowColor{LightBackground}
param\_grid = \{'n\_estimators': {[}1,10,100{]},'learning\_rate': {[}0.2,0.4,0.6,0.8{]}\} & grid = \seqsplit{GridSearchCV(GradientBoostingClassifier()},param\_grid, scoring ='accuracy') \tn 
% Row Count 5 (+ 5)
% Row 11
\SetRowColor{white}
grid.fit(x\_train,y\_train) & \seqsplit{grid.best\_estimator\_}, grid.best\_params\_, grid.cv\_results\_ \tn 
% Row Count 8 (+ 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}{SVM}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{标准化处理，将数字型的变量转换为-1到1的区间里} & from \seqsplit{sklearn.preprocessing} import StandardScaler \tn 
% Row Count 4 (+ 4)
% Row 1
\SetRowColor{white}
ss = StandardScaler() & x\_transformd = \seqsplit{ss.fit\_transform(x)} \tn 
% Row Count 6 (+ 2)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{分割训练集和测试集} & from \seqsplit{sklearn.model\_selection} import train\_test\_split \tn 
% Row Count 9 (+ 3)
% Row 3
\SetRowColor{white}
x\_train,x\_test,y\_train,y\_test =  \seqsplit{train\_test\_split(x\_transformd},y,test\_size=0.3,random\_state=0) & \seqsplit{按照训练集70\%划分} \tn 
% Row Count 14 (+ 5)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{支持向量机回归} & from sklearn.svm import SVR \tn 
% Row Count 16 (+ 2)
% Row 5
\SetRowColor{white}
y\_pred\_SVR = \seqsplit{regression.predict(x\_test)} & \seqsplit{用训练集做拟合，测试集预测结果} \tn 
% Row Count 19 (+ 3)
% Row 6
\SetRowColor{LightBackground}
regression = SVR() & \seqsplit{regression.fit(x\_train},y\_train) \tn 
% Row Count 21 (+ 2)
% Row 7
\SetRowColor{white}
\seqsplit{支持向量机分类器} & from sklearn.svm import SVC \tn 
% Row Count 23 (+ 2)
% Row 8
\SetRowColor{LightBackground}
df{[}"y"{]} = pd.cut(x = df.col0, bins={[}0,6,10{]},labels={[}0,1{]}) & \seqsplit{依据col0列的值划分成两组，0-5一组，6-10另一组，并保存在新列中（categorical} \seqsplit{Y适用于分类器）} \tn 
% Row Count 30 (+ 7)
\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}{SVM (cont)}}  \tn
% Row 9
\SetRowColor{LightBackground}
classifier = SVC(kernel=kernel,random\_state=0) & \seqsplit{kernel还可选择'linear'},'poly','rbf','sigmoid'，准确率随之改变 \tn 
% Row Count 4 (+ 4)
% Row 10
\SetRowColor{white}
\seqsplit{classifier.fit(x\_train},y\_train) & y\_pred = \seqsplit{classifier.predict(x\_test)} \tn 
% Row Count 6 (+ 2)
% Row 11
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{结果评估} \tn 
% Row Count 7 (+ 1)
% Row 12
\SetRowColor{white}
回归适用 & from sklearn.metrics import \seqsplit{mean\_squared\_error}, \seqsplit{mean\_absolute\_error} \tn 
% Row Count 11 (+ 4)
% Row 13
\SetRowColor{LightBackground}
\seqsplit{mean\_absolute\_error(y\_test},y\_pred\_SVR) & \seqsplit{MAE预测值和实际值之间绝对误差的平均值} \tn 
% Row Count 14 (+ 3)
% Row 14
\SetRowColor{white}
\seqsplit{mean\_squared\_error(y\_test},y\_pred\_SVR) & \seqsplit{MSE预测值和实际值之间误差的平方的平均值} \tn 
% Row Count 17 (+ 3)
% Row 15
\SetRowColor{LightBackground}
分类适用 & from sklearn.metrics import confusion\_matrix, accuracy\_score, \seqsplit{classification\_report} \tn 
% Row Count 22 (+ 5)
% Row 16
\SetRowColor{white}
\seqsplit{accuracy\_score(y\_test},y\_pred)) & accuracy = \seqsplit{(TP+TN)/(TP+TN+FP+FN)} \tn 
% Row Count 24 (+ 2)
% Row 17
\SetRowColor{LightBackground}
\seqsplit{confusion\_matrix(y\_test}, y\_pred) & 详细的TP, TN, FP, FN的数量 \tn 
% Row Count 26 (+ 2)
% Row 18
\SetRowColor{white}
\seqsplit{classification\_report(y\_test}, y\_pred) & \seqsplit{包括了准确率、召回率、F1分数和支持度等指标} \tn 
% Row Count 30 (+ 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}{Feature Engineering}}  \tn
% Row 0
\SetRowColor{LightBackground}
pip install scikit-image & 安装包 \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
\seqsplit{读取图片并展示} & from skimage import io \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
food = \seqsplit{io.imread("chips1.jpg")} & io.imshow(food) \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
变化图片颜色 & from skimage.color import* \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{io.imshow(rgb2gray(food))} & \seqsplit{将彩色图片转换为灰色并展示} \tn 
% Row Count 10 (+ 2)
% Row 5
\SetRowColor{white}
给图片加滤镜 & from skimage.filters import * \tn 
% Row Count 12 (+ 2)
% Row 6
\SetRowColor{LightBackground}
\seqsplit{io.imshow(laplace(food},ksize=3, mask=None)) & 使用Laplace \seqsplit{filter并设置内核大小为3} \tn 
% Row Count 15 (+ 3)
% Row 7
\SetRowColor{white}
更改图片尺寸 & from skimage import transform \tn 
% Row Count 17 (+ 2)
% Row 8
\SetRowColor{LightBackground}
image = \seqsplit{transform.resize(image},(2000,2000))  print(image.shape) & \seqsplit{更改为指定尺寸并检查更改后的大小} \tn 
% Row Count 21 (+ 4)
% Row 9
\SetRowColor{white}
主成分分析 & from \seqsplit{sklearn.decomposition} import PCA \tn 
% Row Count 23 (+ 2)
% Row 10
\SetRowColor{LightBackground}
pca = \seqsplit{PCA(n\_components=30)}.fit(chip) & \seqsplit{降维并保留30个主成分，将PCA模型拟合到chip图像数据上} \tn 
% Row Count 27 (+ 4)
% Row 11
\SetRowColor{white}
x\_new = pca.transform(chip) & \seqsplit{使用已经训练好的PCA模型，将chip图像数据投影到新的特征空间中（包含30个重要特征）} \tn 
% Row Count 33 (+ 6)
\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}{Feature Engineering (cont)}}  \tn
% Row 12
\SetRowColor{LightBackground}
recdata = \seqsplit{pca.inverse\_transform(x\_new)} & \seqsplit{建了图像数据，只使用了30个主成分来表示原始图像} \tn 
% Row Count 4 (+ 4)
% Row 13
\SetRowColor{white}
os.listdir(".") & \seqsplit{列出当前工作目录内的所有文件名和目录名} \tn 
% Row Count 7 (+ 3)
% Row 14
\SetRowColor{LightBackground}
\seqsplit{os.chdir("directorypath")} & 改变工作目录 \tn 
% Row Count 9 (+ 2)
% Row 15
\SetRowColor{white}
os.getcwd() & \seqsplit{获取当前的工作目录} \tn 
% Row Count 11 (+ 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}{K-NN}}  \tn
% Row 0
\SetRowColor{LightBackground}
导入K-NN & from sklearn.neighbors import \seqsplit{KNeighborsClassifier} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
classifier = \seqsplit{KNeighborsClassifier(n\_neighbors=6)} & \seqsplit{n\_neighbors的默认值是5} \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
\seqsplit{classifier2.fit(x\_train},y\_train) & 训练模型 \tn 
% Row Count 8 (+ 2)
% Row 3
\SetRowColor{white}
\seqsplit{accuracy\_score(y\_test},classifier2.predict(x\_test)) & 得出准确率 \tn 
% Row Count 11 (+ 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}{Text Analytics}}  \tn
% Row 0
\SetRowColor{LightBackground}
s.strip & \seqsplit{删除尾端全部空格，s为字符串名} \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
a.upper( )/ a.lower & \seqsplit{将字符串a转换成大写、小写形式} \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
分词 Tokenization & import nltk \tn 
% Row Count 7 (+ 1)
% Row 3
\SetRowColor{white}
tokens = \seqsplit{nltk.word\_tokenize(text)} & \seqsplit{读取长文本并根据空格和标点分词} \tn 
% Row Count 10 (+ 3)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{打开文件并读取} & with open ('sample.txt','r',encoding='utf-8') as f:  tokens = \seqsplit{nltk.word\_tokenize(f.read())} \tn 
% Row Count 15 (+ 5)
% Row 5
\SetRowColor{white}
\seqsplit{词性标签Part-of-speech(POS)} Tagging & \seqsplit{nltk.download('averaged\_perceptron\_tagger')} \tn 
% Row Count 18 (+ 3)
% Row 6
\SetRowColor{LightBackground}
tagged = \seqsplit{nltk.pos\_tag(tokens)} & \seqsplit{给分词后的每个单词加个标签} \tn 
% Row Count 20 (+ 2)
% Row 7
\SetRowColor{white}
删除前后缀 \seqsplit{Stemming(可能产生invalid} word) & from nltk.stem import PorterStemmer \tn 
% Row Count 23 (+ 3)
% Row 8
\SetRowColor{LightBackground}
ps = PorterStemmer() & \seqsplit{print(ps.stem('campaigning'))} \tn 
% Row Count 25 (+ 2)
% Row 9
\SetRowColor{white}
词形还原 Lemmatization (generally valid) & from nltk.stem import WordNetLemmatizer \tn 
% Row Count 28 (+ 3)
% Row 10
\SetRowColor{LightBackground}
wnl = WordNetLemmatizer( ) & \seqsplit{wnl.lemmatize('beaten'},'v') \tn 
% Row Count 30 (+ 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}{Text Analytics (cont)}}  \tn
% Row 11
\SetRowColor{LightBackground}
情感分析 & from \seqsplit{nltk.sentiment.vader} import \seqsplit{SentimentIntensityAnalyzer} \tn 
% Row Count 3 (+ 3)
% Row 12
\SetRowColor{white}
\seqsplit{nltk.download('vader\_lexicon')} & analyzer = \seqsplit{SentimentIntensityAnalyzer(} ) \tn 
% Row Count 5 (+ 2)
% Row 13
\SetRowColor{LightBackground}
analyzer.polarity\_scores(text){[}'compound'{]} & \seqsplit{分析长文本的情感色彩并得出综合分数} \tn 
% Row Count 8 (+ 3)
% Row 14
\SetRowColor{white}
for index, row in df.iterrows( ):     compound\_score = analyzer.polarity\_scores(row{[}'clean\_text'{]}){[}'compound'{]} & \seqsplit{dataframe中按行读取cleaned\_data列的每一条数据，并得出综合得分} \tn 
% Row Count 14 (+ 6)
\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 Series}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{时间格式统一} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
df{[}'Date'{]} = {[}datetime.strptime(x, "\%b-\%y") for x in df.Period{]} & \seqsplit{新建一列存放时间，依据原本period列中} \seqsplit{Jan-2021的日期形式改成2021-01-01的标准形式} \tn 
% Row Count 7 (+ 6)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{df\_b{[}'Date'{]} = {[}datetime.strptime(x, "\%d/\%m/\%y") for x in df\_b.iloc{[}:,0{]}{]}} \tn 
% Row Count 9 (+ 2)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{8.4cm}}{列名操作} \tn 
% Row Count 10 (+ 1)
% Row 4
\SetRowColor{LightBackground}
df.columns = {[}"Period", "GoldPrice", "BondYield"{]} & 更改列名 \tn 
% Row Count 13 (+ 3)
% Row 5
\SetRowColor{white}
df.columns = {[}each.strip() for each in df.columns{]} & \seqsplit{去除列名前后的空格} \tn 
% Row Count 16 (+ 3)
% Row 6
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{数据提取} \tn 
% Row Count 17 (+ 1)
% Row 7
\SetRowColor{white}
df\_gold = df{[}df.Gold.isna() == False{]}.loc{[}:, {[}"Top Producers","Gold"{]}{]} & \seqsplit{取指定列的非空行} \tn 
% Row Count 21 (+ 4)
% Row 8
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{8.4cm}}{绘图} \tn 
% Row Count 22 (+ 1)
% Row 9
\SetRowColor{white}
\seqsplit{df.groupby("Date").Gold.mean().plot(kind="line")} & \seqsplit{按日期分组，统计黄金的均值，并绘制折线图} \tn 
% Row Count 25 (+ 3)
% Row 10
\SetRowColor{LightBackground}
df.loc{[}:, {[}"Gold", "Silver","Date"{]}{]}.groupby("Date").mean().plot() & \seqsplit{按日期分组，同时统计黄金、银的均值，并绘制折线图} \tn 
% Row Count 29 (+ 4)
% Row 11
\SetRowColor{white}
df.groupby("month"){[}{[}"column0","column1","column2"{]}{]}.mean().plot() & 写法2 \tn 
% Row Count 33 (+ 4)
\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}{Time Series (cont)}}  \tn
% Row 12
\SetRowColor{LightBackground}
df.plot(kind="line", y="Gold ETF", x="Date") & \seqsplit{指定横纵坐标绘制折线图} \tn 
% Row Count 3 (+ 3)
% Row 13
\SetRowColor{white}
sns.heatmap(df.loc{[}:, {[}"Gold", "Platinum","Silver"{]}{]}.corr(), annot=True) & \seqsplit{先计算黄金银铂金两两之间的相关关系，并依据结果绘制热力图} \tn 
% Row Count 8 (+ 5)
% Row 14
\SetRowColor{LightBackground}
\seqsplit{sns.barplot(data=df\_platinum},y="Platinum", x ="Top Producers") & \seqsplit{运用seaborn绘图（import} seaborn as sns） \tn 
% Row Count 12 (+ 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}{Web scrapping}}  \tn
% Row 0
\SetRowColor{LightBackground}
import request & 用于发送 HTTP 请求 \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
response = request.get(url) & 获取数据 \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
result = response.json( & \seqsplit{加工数据并print} \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
\mymulticolumn{2}{x{8.4cm}}{Beautiful Soup} \tn 
% Row Count 7 (+ 1)
% Row 4
\SetRowColor{LightBackground}
from bs4 import BeautifulSoup & \seqsplit{解析和处理网页} \tn 
% Row Count 9 (+ 2)
% Row 5
\SetRowColor{white}
r = requests.get(url) & \seqsplit{请求网址，其中url为包含网址的变量} \tn 
% Row Count 12 (+ 3)
% Row 6
\SetRowColor{LightBackground}
print(soup.title) & \seqsplit{获取网页的标题} \tn 
% Row Count 14 (+ 2)
% Row 7
\SetRowColor{white}
soup = \seqsplit{BeautifulSoup(r.content}, 'html.parser') & \seqsplit{解析获取到的内容} \tn 
% Row Count 17 (+ 3)
% Row 8
\SetRowColor{LightBackground}
title= soup.find\_all("h6", "h6 \seqsplit{list-object\_\_heading")} & \seqsplit{运用find\_all查找指定内容第一个变量是tag},第二个变量为class（查找新闻标题） \tn 
% Row Count 23 (+ 6)
% Row 9
\SetRowColor{white}
each\_title = title.text & \seqsplit{通过.text获取标题内容} \tn 
% Row Count 25 (+ 2)
% Row 10
\SetRowColor{LightBackground}
each\_title = each\_title.strip() & \seqsplit{删除标题前后的空格，之后print(each\_title)} \tn 
% Row Count 28 (+ 3)
% Row 11
\SetRowColor{white}
data2 = r.json() & \seqsplit{将请求的结果转换成json字符串} \tn 
% Row Count 30 (+ 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}{Web scrapping (cont)}}  \tn
% Row 12
\SetRowColor{LightBackground}
data2.keys() & \seqsplit{查看json中包含的键} \tn 
% Row Count 2 (+ 2)
% Row 13
\SetRowColor{white}
data2{[}'help'{]} & \seqsplit{help是其中一个键名(keys)} \tn 
% Row Count 4 (+ 2)
% Row 14
\SetRowColor{LightBackground}
data2{[}'result'{]}{[}'records'{]} & \seqsplit{直接通过json中的层级关系查找内容} \tn 
% Row Count 7 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


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

\end{document}