514 lines
31 KiB
HTML
514 lines
31 KiB
HTML
<!DOCTYPE html>
|
||
<html lang="" xml:lang="">
|
||
<head>
|
||
|
||
<meta charset="utf-8" />
|
||
<meta http-equiv="X-UA-Compatible" content="IE=edge" />
|
||
<title>R语言数据分析组队学习</title>
|
||
<meta name="description" content="R语言数据分析组队学习" />
|
||
<meta name="generator" content="bookdown 0.22 and GitBook 2.6.7" />
|
||
|
||
<meta property="og:title" content="R语言数据分析组队学习" />
|
||
<meta property="og:type" content="book" />
|
||
|
||
|
||
|
||
|
||
|
||
<meta name="twitter:card" content="summary" />
|
||
<meta name="twitter:title" content="R语言数据分析组队学习" />
|
||
|
||
|
||
|
||
|
||
<meta name="author" content="张晋、杨佳达、牧小熊、杨杨卓然、姚昱君" />
|
||
|
||
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
<meta name="apple-mobile-web-app-capable" content="yes" />
|
||
<meta name="apple-mobile-web-app-status-bar-style" content="black" />
|
||
|
||
|
||
|
||
<link rel="next" href="task-00.html"/>
|
||
<script src="libs/header-attrs-2.9/header-attrs.js"></script>
|
||
<script src="libs/jquery-2.2.3/jquery.min.js"></script>
|
||
<link href="libs/gitbook-2.6.7/css/style.css" rel="stylesheet" />
|
||
<link href="libs/gitbook-2.6.7/css/plugin-table.css" rel="stylesheet" />
|
||
<link href="libs/gitbook-2.6.7/css/plugin-bookdown.css" rel="stylesheet" />
|
||
<link href="libs/gitbook-2.6.7/css/plugin-highlight.css" rel="stylesheet" />
|
||
<link href="libs/gitbook-2.6.7/css/plugin-search.css" rel="stylesheet" />
|
||
<link href="libs/gitbook-2.6.7/css/plugin-fontsettings.css" rel="stylesheet" />
|
||
<link href="libs/gitbook-2.6.7/css/plugin-clipboard.css" rel="stylesheet" />
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<link href="libs/anchor-sections-1.0.1/anchor-sections.css" rel="stylesheet" />
|
||
<script src="libs/anchor-sections-1.0.1/anchor-sections.js"></script>
|
||
|
||
|
||
<style type="text/css">
|
||
pre > code.sourceCode { white-space: pre; position: relative; }
|
||
pre > code.sourceCode > span { display: inline-block; line-height: 1.25; }
|
||
pre > code.sourceCode > span:empty { height: 1.2em; }
|
||
.sourceCode { overflow: visible; }
|
||
code.sourceCode > span { color: inherit; text-decoration: inherit; }
|
||
pre.sourceCode { margin: 0; }
|
||
@media screen {
|
||
div.sourceCode { overflow: auto; }
|
||
}
|
||
@media print {
|
||
pre > code.sourceCode { white-space: pre-wrap; }
|
||
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
|
||
}
|
||
pre.numberSource code
|
||
{ counter-reset: source-line 0; }
|
||
pre.numberSource code > span
|
||
{ position: relative; left: -4em; counter-increment: source-line; }
|
||
pre.numberSource code > span > a:first-child::before
|
||
{ content: counter(source-line);
|
||
position: relative; left: -1em; text-align: right; vertical-align: baseline;
|
||
border: none; display: inline-block;
|
||
-webkit-touch-callout: none; -webkit-user-select: none;
|
||
-khtml-user-select: none; -moz-user-select: none;
|
||
-ms-user-select: none; user-select: none;
|
||
padding: 0 4px; width: 4em;
|
||
color: #aaaaaa;
|
||
}
|
||
pre.numberSource { margin-left: 3em; border-left: 1px solid #aaaaaa; padding-left: 4px; }
|
||
div.sourceCode
|
||
{ }
|
||
@media screen {
|
||
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
|
||
}
|
||
code span.al { color: #ff0000; font-weight: bold; } /* Alert */
|
||
code span.an { color: #60a0b0; font-weight: bold; font-style: italic; } /* Annotation */
|
||
code span.at { color: #7d9029; } /* Attribute */
|
||
code span.bn { color: #40a070; } /* BaseN */
|
||
code span.bu { } /* BuiltIn */
|
||
code span.cf { color: #007020; font-weight: bold; } /* ControlFlow */
|
||
code span.ch { color: #4070a0; } /* Char */
|
||
code span.cn { color: #880000; } /* Constant */
|
||
code span.co { color: #60a0b0; font-style: italic; } /* Comment */
|
||
code span.cv { color: #60a0b0; font-weight: bold; font-style: italic; } /* CommentVar */
|
||
code span.do { color: #ba2121; font-style: italic; } /* Documentation */
|
||
code span.dt { color: #902000; } /* DataType */
|
||
code span.dv { color: #40a070; } /* DecVal */
|
||
code span.er { color: #ff0000; font-weight: bold; } /* Error */
|
||
code span.ex { } /* Extension */
|
||
code span.fl { color: #40a070; } /* Float */
|
||
code span.fu { color: #06287e; } /* Function */
|
||
code span.im { } /* Import */
|
||
code span.in { color: #60a0b0; font-weight: bold; font-style: italic; } /* Information */
|
||
code span.kw { color: #007020; font-weight: bold; } /* Keyword */
|
||
code span.op { color: #666666; } /* Operator */
|
||
code span.ot { color: #007020; } /* Other */
|
||
code span.pp { color: #bc7a00; } /* Preprocessor */
|
||
code span.sc { color: #4070a0; } /* SpecialChar */
|
||
code span.ss { color: #bb6688; } /* SpecialString */
|
||
code span.st { color: #4070a0; } /* String */
|
||
code span.va { color: #19177c; } /* Variable */
|
||
code span.vs { color: #4070a0; } /* VerbatimString */
|
||
code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warning */
|
||
</style>
|
||
|
||
|
||
</head>
|
||
|
||
<body>
|
||
|
||
|
||
|
||
<div class="book without-animation with-summary font-size-2 font-family-1" data-basepath=".">
|
||
|
||
<div class="book-summary">
|
||
<nav role="navigation">
|
||
|
||
<ul class="summary">
|
||
<li><a href="./">R语言数据分析组队学习</a></li>
|
||
|
||
<li class="divider"></li>
|
||
<li class="chapter" data-level="" data-path="index.html"><a href="index.html"><i class="fa fa-check"></i>欢迎！</a>
|
||
<ul>
|
||
<li class="chapter" data-level="" data-path="index.html"><a href="index.html#贡献者信息"><i class="fa fa-check"></i>贡献者信息</a></li>
|
||
<li class="chapter" data-level="" data-path="index.html"><a href="index.html#课程简介"><i class="fa fa-check"></i>课程简介</a></li>
|
||
<li class="chapter" data-level="" data-path="index.html"><a href="index.html#课程大纲"><i class="fa fa-check"></i>课程大纲</a></li>
|
||
<li class="chapter" data-level="" data-path="index.html"><a href="index.html#关于-datawhale"><i class="fa fa-check"></i>关于 Datawhale</a></li>
|
||
</ul></li>
|
||
<li class="part"><span><b>I 准备工作</b></span></li>
|
||
<li class="chapter" data-level="" data-path="task-00.html"><a href="task-00.html"><i class="fa fa-check"></i>熟悉规则与R语言入门</a>
|
||
<ul>
|
||
<li class="chapter" data-level="0.1" data-path="task-00.html"><a href="task-00.html#安装"><i class="fa fa-check"></i><b>0.1</b> 安装</a>
|
||
<ul>
|
||
<li class="chapter" data-level="0.1.1" data-path="task-00.html"><a href="task-00.html#r"><i class="fa fa-check"></i><b>0.1.1</b> R</a></li>
|
||
<li class="chapter" data-level="0.1.2" data-path="task-00.html"><a href="task-00.html#rstudio"><i class="fa fa-check"></i><b>0.1.2</b> RStudio</a></li>
|
||
<li class="chapter" data-level="0.1.3" data-path="task-00.html"><a href="task-00.html#r语言程辑包r-package"><i class="fa fa-check"></i><b>0.1.3</b> R语言程辑包（R Package）</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="0.2" data-path="task-00.html"><a href="task-00.html#环境配置"><i class="fa fa-check"></i><b>0.2</b> 环境配置</a>
|
||
<ul>
|
||
<li class="chapter" data-level="0.2.1" data-path="task-00.html"><a href="task-00.html#项目project"><i class="fa fa-check"></i><b>0.2.1</b> 项目（Project）</a></li>
|
||
<li class="chapter" data-level="0.2.2" data-path="task-00.html"><a href="task-00.html#用户界面"><i class="fa fa-check"></i><b>0.2.2</b> 用户界面</a></li>
|
||
<li class="chapter" data-level="0.2.3" data-path="task-00.html"><a href="task-00.html#r-markdown"><i class="fa fa-check"></i><b>0.2.3</b> R Markdown</a></li>
|
||
<li class="chapter" data-level="0.2.4" data-path="task-00.html"><a href="task-00.html#帮助"><i class="fa fa-check"></i><b>0.2.4</b> 帮助</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="0.3" data-path="task-00.html"><a href="task-00.html#happy-coding"><i class="fa fa-check"></i><b>0.3</b> Happy Coding!</a></li>
|
||
<li class="chapter" data-level="" data-path="task-00.html"><a href="task-00.html#本章作者"><i class="fa fa-check"></i>本章作者</a></li>
|
||
<li class="chapter" data-level="" data-path="task-00.html"><a href="task-00.html#关于datawhale"><i class="fa fa-check"></i>关于Datawhale</a></li>
|
||
</ul></li>
|
||
<li class="part"><span><b>II 开始干活</b></span></li>
|
||
<li class="chapter" data-level="1" data-path="task-01.html"><a href="task-01.html"><i class="fa fa-check"></i><b>1</b> 数据结构与数据集</a>
|
||
<ul>
|
||
<li class="chapter" data-level="1.1" data-path="task-01.html"><a href="task-01.html#准备工作"><i class="fa fa-check"></i><b>1.1</b> 准备工作</a></li>
|
||
<li class="chapter" data-level="1.2" data-path="task-01.html"><a href="task-01.html#编码基础"><i class="fa fa-check"></i><b>1.2</b> 编码基础</a>
|
||
<ul>
|
||
<li class="chapter" data-level="1.2.1" data-path="task-01.html"><a href="task-01.html#算术"><i class="fa fa-check"></i><b>1.2.1</b> 算术</a></li>
|
||
<li class="chapter" data-level="1.2.2" data-path="task-01.html"><a href="task-01.html#赋值"><i class="fa fa-check"></i><b>1.2.2</b> 赋值</a></li>
|
||
<li class="chapter" data-level="1.2.3" data-path="task-01.html"><a href="task-01.html#函数"><i class="fa fa-check"></i><b>1.2.3</b> 函数</a></li>
|
||
<li class="chapter" data-level="1.2.4" data-path="task-01.html"><a href="task-01.html#循环loop"><i class="fa fa-check"></i><b>1.2.4</b> 循环（loop）</a></li>
|
||
<li class="chapter" data-level="1.2.5" data-path="task-01.html"><a href="task-01.html#管道pipe"><i class="fa fa-check"></i><b>1.2.5</b> 管道（pipe）</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="1.3" data-path="task-01.html"><a href="task-01.html#数据类型"><i class="fa fa-check"></i><b>1.3</b> 数据类型</a>
|
||
<ul>
|
||
<li class="chapter" data-level="1.3.1" data-path="task-01.html"><a href="task-01.html#基础数据类型"><i class="fa fa-check"></i><b>1.3.1</b> 基础数据类型</a></li>
|
||
<li class="chapter" data-level="1.3.2" data-path="task-01.html"><a href="task-01.html#向量vector"><i class="fa fa-check"></i><b>1.3.2</b> 向量（vector）</a></li>
|
||
<li class="chapter" data-level="1.3.3" data-path="task-01.html"><a href="task-01.html#特殊数据类型"><i class="fa fa-check"></i><b>1.3.3</b> 特殊数据类型</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="1.4" data-path="task-01.html"><a href="task-01.html#多维数据类型"><i class="fa fa-check"></i><b>1.4</b> 多维数据类型</a>
|
||
<ul>
|
||
<li class="chapter" data-level="1.4.1" data-path="task-01.html"><a href="task-01.html#矩阵matrix"><i class="fa fa-check"></i><b>1.4.1</b> 矩阵（matrix）</a></li>
|
||
<li class="chapter" data-level="1.4.2" data-path="task-01.html"><a href="task-01.html#列表list"><i class="fa fa-check"></i><b>1.4.2</b> 列表（list）</a></li>
|
||
<li class="chapter" data-level="1.4.3" data-path="task-01.html"><a href="task-01.html#数据表data-frame-与-tibble"><i class="fa fa-check"></i><b>1.4.3</b> 数据表（data frame 与 tibble）</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="1.5" data-path="task-01.html"><a href="task-01.html#读写数据"><i class="fa fa-check"></i><b>1.5</b> 读写数据</a>
|
||
<ul>
|
||
<li class="chapter" data-level="1.5.1" data-path="task-01.html"><a href="task-01.html#内置数据集"><i class="fa fa-check"></i><b>1.5.1</b> 内置数据集</a></li>
|
||
<li class="chapter" data-level="1.5.2" data-path="task-01.html"><a href="task-01.html#表格类型数据csv-excel"><i class="fa fa-check"></i><b>1.5.2</b> 表格类型数据（csv, excel)</a></li>
|
||
<li class="chapter" data-level="1.5.3" data-path="task-01.html"><a href="task-01.html#r的专属类型数据rdata-rds"><i class="fa fa-check"></i><b>1.5.3</b> R的专属类型数据（RData, rds）</a></li>
|
||
<li class="chapter" data-level="1.5.4" data-path="task-01.html"><a href="task-01.html#其他软件spss-stata-sas"><i class="fa fa-check"></i><b>1.5.4</b> 其他软件（SPSS, Stata, SAS）</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="1.6" data-path="task-01.html"><a href="task-01.html#练习题"><i class="fa fa-check"></i><b>1.6</b> 练习题</a>
|
||
<ul>
|
||
<li class="chapter" data-level="1.6.1" data-path="task-01.html"><a href="task-01.html#了解数据集"><i class="fa fa-check"></i><b>1.6.1</b> 了解数据集</a></li>
|
||
<li class="chapter" data-level="1.6.2" data-path="task-01.html"><a href="task-01.html#创造数据集"><i class="fa fa-check"></i><b>1.6.2</b> 创造数据集</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="" data-path="task-01.html"><a href="task-01.html#本章作者-1"><i class="fa fa-check"></i>本章作者</a></li>
|
||
<li class="chapter" data-level="" data-path="task-01.html"><a href="task-01.html#关于datawhale-1"><i class="fa fa-check"></i>关于Datawhale</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="2" data-path="task-02.html"><a href="task-02.html"><i class="fa fa-check"></i><b>2</b> 数据清洗与准备</a>
|
||
<ul>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#环境配置-1"><i class="fa fa-check"></i>环境配置</a></li>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#案例数据"><i class="fa fa-check"></i>案例数据</a>
|
||
<ul>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#数据集1-h1n1流感问卷数据集"><i class="fa fa-check"></i>数据集1 h1n1流感问卷数据集</a></li>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#数据集2-波士顿房价数据集"><i class="fa fa-check"></i>数据集2 波士顿房价数据集</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="2.1" data-path="task-02.html"><a href="task-02.html#重复值处理"><i class="fa fa-check"></i><b>2.1</b> 重复值处理</a></li>
|
||
<li class="chapter" data-level="2.2" data-path="task-02.html"><a href="task-02.html#缺失值识别与处理"><i class="fa fa-check"></i><b>2.2</b> 缺失值识别与处理</a>
|
||
<ul>
|
||
<li class="chapter" data-level="2.2.1" data-path="task-02.html"><a href="task-02.html#缺失值识别"><i class="fa fa-check"></i><b>2.2.1</b> 缺失值识别</a></li>
|
||
<li class="chapter" data-level="2.2.2" data-path="task-02.html"><a href="task-02.html#缺失值处理"><i class="fa fa-check"></i><b>2.2.2</b> 缺失值处理</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="2.3" data-path="task-02.html"><a href="task-02.html#异常值识别与处理"><i class="fa fa-check"></i><b>2.3</b> 异常值识别与处理</a>
|
||
<ul>
|
||
<li class="chapter" data-level="2.3.1" data-path="task-02.html"><a href="task-02.html#异常值识别"><i class="fa fa-check"></i><b>2.3.1</b> 异常值识别</a></li>
|
||
<li class="chapter" data-level="2.3.2" data-path="task-02.html"><a href="task-02.html#可视化图形分布"><i class="fa fa-check"></i><b>2.3.2</b> 可视化图形分布</a></li>
|
||
<li class="chapter" data-level="2.3.3" data-path="task-02.html"><a href="task-02.html#z-score"><i class="fa fa-check"></i><b>2.3.3</b> z-score</a></li>
|
||
<li class="chapter" data-level="2.3.4" data-path="task-02.html"><a href="task-02.html#局部异常因子法"><i class="fa fa-check"></i><b>2.3.4</b> 局部异常因子法</a></li>
|
||
<li class="chapter" data-level="2.3.5" data-path="task-02.html"><a href="task-02.html#异常值处理"><i class="fa fa-check"></i><b>2.3.5</b> 异常值处理</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="2.4" data-path="task-02.html"><a href="task-02.html#特征编码"><i class="fa fa-check"></i><b>2.4</b> 特征编码</a>
|
||
<ul>
|
||
<li class="chapter" data-level="2.4.1" data-path="task-02.html"><a href="task-02.html#独热编码哑编码"><i class="fa fa-check"></i><b>2.4.1</b> 独热编码/哑编码</a></li>
|
||
<li class="chapter" data-level="2.4.2" data-path="task-02.html"><a href="task-02.html#标签编码"><i class="fa fa-check"></i><b>2.4.2</b> 标签编码</a></li>
|
||
<li class="chapter" data-level="2.4.3" data-path="task-02.html"><a href="task-02.html#手动编码"><i class="fa fa-check"></i><b>2.4.3</b> 手动编码</a></li>
|
||
<li class="chapter" data-level="2.4.4" data-path="task-02.html"><a href="task-02.html#日期特征转换"><i class="fa fa-check"></i><b>2.4.4</b> 日期特征转换</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="2.5" data-path="task-02.html"><a href="task-02.html#规范化与偏态数据"><i class="fa fa-check"></i><b>2.5</b> 规范化与偏态数据</a>
|
||
<ul>
|
||
<li class="chapter" data-level="2.5.1" data-path="task-02.html"><a href="task-02.html#规范化"><i class="fa fa-check"></i><b>2.5.1</b> 0-1规范化</a></li>
|
||
<li class="chapter" data-level="2.5.2" data-path="task-02.html"><a href="task-02.html#z-score标准化"><i class="fa fa-check"></i><b>2.5.2</b> Z-score标准化</a></li>
|
||
<li class="chapter" data-level="2.5.3" data-path="task-02.html"><a href="task-02.html#对数转换log-transform"><i class="fa fa-check"></i><b>2.5.3</b> 对数转换(log transform)</a></li>
|
||
<li class="chapter" data-level="2.5.4" data-path="task-02.html"><a href="task-02.html#box-cox"><i class="fa fa-check"></i><b>2.5.4</b> Box-Cox</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="2.6" data-path="task-02.html"><a href="task-02.html#小拓展"><i class="fa fa-check"></i><b>2.6</b> 小拓展</a></li>
|
||
<li class="chapter" data-level="2.7" data-path="task-02.html"><a href="task-02.html#思考与练习"><i class="fa fa-check"></i><b>2.7</b> 思考与练习</a></li>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#附录参考资料"><i class="fa fa-check"></i>附录：参考资料</a>
|
||
<ul>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#理论资料"><i class="fa fa-check"></i>理论资料</a></li>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#r语言函数用法示例"><i class="fa fa-check"></i>R语言函数用法示例</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#本章作者-2"><i class="fa fa-check"></i>本章作者</a></li>
|
||
<li class="chapter" data-level="" data-path="task-02.html"><a href="task-02.html#关于datawhale-2"><i class="fa fa-check"></i>关于Datawhale</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="3" data-path="task-03.html"><a href="task-03.html"><i class="fa fa-check"></i><b>3</b> 基本统计分析</a>
|
||
<ul>
|
||
<li class="chapter" data-level="" data-path="task-03.html"><a href="task-03.html#准备工作-1"><i class="fa fa-check"></i>准备工作</a></li>
|
||
<li class="chapter" data-level="3.1" data-path="task-03.html"><a href="task-03.html#多种方法获取描述性统计量"><i class="fa fa-check"></i><b>3.1</b> 多种方法获取描述性统计量</a>
|
||
<ul>
|
||
<li class="chapter" data-level="3.1.1" data-path="task-03.html"><a href="task-03.html#基础方法"><i class="fa fa-check"></i><b>3.1.1</b> 基础方法</a></li>
|
||
<li class="chapter" data-level="3.1.2" data-path="task-03.html"><a href="task-03.html#拓展包方法"><i class="fa fa-check"></i><b>3.1.2</b> 拓展包方法</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="3.2" data-path="task-03.html"><a href="task-03.html#分组计算描述性统计"><i class="fa fa-check"></i><b>3.2</b> 分组计算描述性统计</a>
|
||
<ul>
|
||
<li class="chapter" data-level="3.2.1" data-path="task-03.html"><a href="task-03.html#基础方法-1"><i class="fa fa-check"></i><b>3.2.1</b> 基础方法</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="3.3" data-path="task-03.html"><a href="task-03.html#频数表和列联表"><i class="fa fa-check"></i><b>3.3</b> 频数表和列联表</a></li>
|
||
<li class="chapter" data-level="3.4" data-path="task-03.html"><a href="task-03.html#相关"><i class="fa fa-check"></i><b>3.4</b> 相关</a>
|
||
<ul>
|
||
<li class="chapter" data-level="3.4.1" data-path="task-03.html"><a href="task-03.html#相关的类型"><i class="fa fa-check"></i><b>3.4.1</b> 相关的类型</a></li>
|
||
<li class="chapter" data-level="3.4.2" data-path="task-03.html"><a href="task-03.html#相关性的显著性检验"><i class="fa fa-check"></i><b>3.4.2</b> 相关性的显著性检验</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="3.5" data-path="task-03.html"><a href="task-03.html#方差分析"><i class="fa fa-check"></i><b>3.5</b> 方差分析</a>
|
||
<ul>
|
||
<li class="chapter" data-level="3.5.1" data-path="task-03.html"><a href="task-03.html#单因素方差分析"><i class="fa fa-check"></i><b>3.5.1</b> 单因素方差分析</a></li>
|
||
<li class="chapter" data-level="3.5.2" data-path="task-03.html"><a href="task-03.html#多因素方差分析"><i class="fa fa-check"></i><b>3.5.2</b> 多因素方差分析</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="" data-path="task-03.html"><a href="task-03.html#本章作者-3"><i class="fa fa-check"></i>本章作者</a></li>
|
||
<li class="chapter" data-level="" data-path="task-03.html"><a href="task-03.html#关于datawhale-3"><i class="fa fa-check"></i>关于Datawhale</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="4" data-path="task-04.html"><a href="task-04.html"><i class="fa fa-check"></i><b>4</b> 数据可视化</a>
|
||
<ul>
|
||
<li class="chapter" data-level="" data-path="task-04.html"><a href="task-04.html#ggplot2包介绍"><i class="fa fa-check"></i>ggplot2包介绍</a></li>
|
||
<li class="chapter" data-level="4.1" data-path="task-04.html"><a href="task-04.html#环境配置-2"><i class="fa fa-check"></i><b>4.1</b> 环境配置</a>
|
||
<ul>
|
||
<li class="chapter" data-level="" data-path="task-04.html"><a href="task-04.html#案例数据-1"><i class="fa fa-check"></i>案例数据</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="4.2" data-path="task-04.html"><a href="task-04.html#散点图"><i class="fa fa-check"></i><b>4.2</b> 散点图</a></li>
|
||
<li class="chapter" data-level="4.3" data-path="task-04.html"><a href="task-04.html#直方图"><i class="fa fa-check"></i><b>4.3</b> 直方图</a></li>
|
||
<li class="chapter" data-level="4.4" data-path="task-04.html"><a href="task-04.html#柱状图"><i class="fa fa-check"></i><b>4.4</b> 柱状图</a></li>
|
||
<li class="chapter" data-level="4.5" data-path="task-04.html"><a href="task-04.html#饼状图"><i class="fa fa-check"></i><b>4.5</b> 饼状图</a></li>
|
||
<li class="chapter" data-level="4.6" data-path="task-04.html"><a href="task-04.html#折线图"><i class="fa fa-check"></i><b>4.6</b> 折线图</a></li>
|
||
<li class="chapter" data-level="4.7" data-path="task-04.html"><a href="task-04.html#ggplot2扩展包主题"><i class="fa fa-check"></i><b>4.7</b> ggplot2扩展包主题</a></li>
|
||
<li class="chapter" data-level="" data-path="task-04.html"><a href="task-04.html#本章作者-4"><i class="fa fa-check"></i>本章作者</a></li>
|
||
<li class="chapter" data-level="" data-path="task-04.html"><a href="task-04.html#关于datawhale-4"><i class="fa fa-check"></i>关于Datawhale</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="5" data-path="task-05.html"><a href="task-05.html"><i class="fa fa-check"></i><b>5</b> 模型</a>
|
||
<ul>
|
||
<li class="chapter" data-level="5.1" data-path="task-05.html"><a href="task-05.html#前言"><i class="fa fa-check"></i><b>5.1</b> 前言</a>
|
||
<ul>
|
||
<li class="chapter" data-level="5.1.1" data-path="task-05.html"><a href="task-05.html#linear-regression"><i class="fa fa-check"></i><b>5.1.1</b> Linear Regression</a></li>
|
||
<li class="chapter" data-level="5.1.2" data-path="task-05.html"><a href="task-05.html#stepwise-regression"><i class="fa fa-check"></i><b>5.1.2</b> Stepwise Regression</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="5.2" data-path="task-05.html"><a href="task-05.html#分类模型"><i class="fa fa-check"></i><b>5.2</b> 分类模型</a>
|
||
<ul>
|
||
<li class="chapter" data-level="5.2.1" data-path="task-05.html"><a href="task-05.html#logistics-regression"><i class="fa fa-check"></i><b>5.2.1</b> Logistics Regression</a></li>
|
||
<li class="chapter" data-level="5.2.2" data-path="task-05.html"><a href="task-05.html#knn"><i class="fa fa-check"></i><b>5.2.2</b> KNN</a></li>
|
||
<li class="chapter" data-level="5.2.3" data-path="task-05.html"><a href="task-05.html#decision-tree"><i class="fa fa-check"></i><b>5.2.3</b> Decision Tree</a></li>
|
||
<li class="chapter" data-level="5.2.4" data-path="task-05.html"><a href="task-05.html#random-forest"><i class="fa fa-check"></i><b>5.2.4</b> Random Forest</a></li>
|
||
</ul></li>
|
||
<li class="chapter" data-level="" data-path="task-05.html"><a href="task-05.html#思考与练习-1"><i class="fa fa-check"></i>思考与练习</a></li>
|
||
<li class="chapter" data-level="" data-path="task-05.html"><a href="task-05.html#本章作者-5"><i class="fa fa-check"></i>本章作者</a></li>
|
||
<li class="chapter" data-level="" data-path="task-05.html"><a href="task-05.html#关于datawhale-5"><i class="fa fa-check"></i>关于Datawhale</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
|
||
</nav>
|
||
</div>
|
||
|
||
<div class="book-body">
|
||
<div class="body-inner">
|
||
<div class="book-header" role="navigation">
|
||
<h1>
|
||
<i class="fa fa-circle-o-notch fa-spin"></i><a href="./">R语言数据分析组队学习</a>
|
||
</h1>
|
||
</div>
|
||
|
||
<div class="page-wrapper" tabindex="-1" role="main">
|
||
<div class="page-inner">
|
||
|
||
<section class="normal" id="section-">
|
||
<div id="header">
|
||
<h1 class="title">R语言数据分析组队学习</h1>
|
||
<p class="author"><em>张晋、杨佳达、牧小熊、杨杨卓然、姚昱君</em></p>
|
||
</div>
|
||
<div id="welcome" class="section level1 unnumbered">
|
||
<h1>欢迎！</h1>
|
||
<p>欢迎来到由DataWhale主办的R语言数据分析组队学习课程。</p>
|
||
<div id="贡献者信息" class="section level2 unnumbered">
|
||
<h2>贡献者信息</h2>
|
||
<!-- | 姓名 | 介绍 | 个人主页 | -->
|
||
<!-- | ------ | ------------------------------- | ------------------------------- | -->
|
||
<!-- | 张晋 | Datawhale成员，算法竞赛爱好者 | https://blog.csdn.net/weixin_44585839/ | -->
|
||
<!-- | 杨佳达 | 数据挖掘师，Datawhale成员，目前在国内某第三方数据服务公司做数据分析挖掘及数据产品 | https://github.com/yangjiada | -->
|
||
<!-- | 牧小熊 | 华中农业大学研究生，Datawhale成员，Datawhale优秀原创作者 | https://www.zhihu.com/people/muxiaoxiong| -->
|
||
<!-- | 杨杨卓然 | 混吃等死统计休学穷酸书生 | https://yangzhuoranyang.com | -->
|
||
<!-- | 姚昱君 | 悉尼大学，Datawhale成员 | https://blog.csdn.net/Yao_June | -->
|
||
<table>
|
||
<colgroup>
|
||
<col width="6%" />
|
||
<col width="62%" />
|
||
<col width="31%" />
|
||
</colgroup>
|
||
<thead>
|
||
<tr class="header">
|
||
<th align="left">姓名</th>
|
||
<th align="left">介绍</th>
|
||
<th align="left">个人主页</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr class="odd">
|
||
<td align="left">张晋</td>
|
||
<td align="left">Datawhale成员，算法竞赛爱好者</td>
|
||
<td align="left"><a href="https://blog.csdn.net/weixin_44585839/" class="uri">https://blog.csdn.net/weixin_44585839/</a></td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td align="left">杨佳达</td>
|
||
<td align="left">数据挖掘师，Datawhale成员，目前在国内某第三方数据服务公司做数据分析挖掘及数据产品</td>
|
||
<td align="left"><a href="https://github.com/yangjiada" class="uri">https://github.com/yangjiada</a></td>
|
||
</tr>
|
||
<tr class="odd">
|
||
<td align="left">牧小熊</td>
|
||
<td align="left">华中农业大学研究生，Datawhale成员，Datawhale优秀原创作者</td>
|
||
<td align="left"><a href="https://www.zhihu.com/people/muxiaoxiong" class="uri">https://www.zhihu.com/people/muxiaoxiong</a></td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td align="left">杨杨卓然</td>
|
||
<td align="left">混吃等死统计休学穷酸书生</td>
|
||
<td align="left"><a href="https://yangzhuoranyang.com" class="uri">https://yangzhuoranyang.com</a></td>
|
||
</tr>
|
||
<tr class="odd">
|
||
<td align="left">姚昱君</td>
|
||
<td align="left">悉尼大学，Datawhale成员</td>
|
||
<td align="left"><a href="https://blog.csdn.net/Yao_June" class="uri">https://blog.csdn.net/Yao_June</a></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</div>
|
||
<div id="课程简介" class="section level2 unnumbered">
|
||
<h2>课程简介</h2>
|
||
<ul>
|
||
<li>课程设计成员：<strong>张晋</strong>、杨佳达、牧小熊、杨杨卓然、姚昱君</li>
|
||
<li>学习周期：16天，每天平均花费时间1小时-3小时不等，根据个人学习接受能力强弱有所浮动。</li>
|
||
<li>学习形式：理论学习 + 练习</li>
|
||
<li>人群定位：对数据科学有基本了解，希望学习R语言的同学。</li>
|
||
<li>先修内容：无</li>
|
||
<li>难度系数：⭐⭐</li>
|
||
</ul>
|
||
</div>
|
||
<div id="课程大纲" class="section level2 unnumbered">
|
||
<h2>课程大纲</h2>
|
||
<p><strong>Task00：熟悉规则与R语言入门（1天）</strong></p>
|
||
<ul>
|
||
<li>安装</li>
|
||
<li>环境配置</li>
|
||
</ul>
|
||
<p><strong>Task01 数据结构与数据集 （3天）</strong></p>
|
||
<ul>
|
||
<li>编码基础</li>
|
||
<li>数据类型</li>
|
||
<li>特殊数据类型</li>
|
||
<li>table like 数据类型</li>
|
||
<li>加载数据 (csv, rds, excel, Rdata)</li>
|
||
<li>实例</li>
|
||
</ul>
|
||
<p><strong>Task02 数据清洗与准备 （3天）</strong></p>
|
||
<ul>
|
||
<li>重复值处理</li>
|
||
<li>缺失值识别与处理</li>
|
||
<li>异常值识别与处理</li>
|
||
<li>特征处理</li>
|
||
<li>规范化与偏态数据</li>
|
||
</ul>
|
||
<p><strong>Task03 基本统计分析 （3天）</strong></p>
|
||
<ul>
|
||
<li>多种方法获取描述性统计量</li>
|
||
<li>分组计算描述性统计</li>
|
||
<li>频数表和列联表</li>
|
||
<li>相关</li>
|
||
<li>方差分析</li>
|
||
</ul>
|
||
<p><strong>Task04 数据可视化（3天）</strong></p>
|
||
<ul>
|
||
<li>ggplot2包介绍</li>
|
||
<li>散点图</li>
|
||
<li>直方图</li>
|
||
<li>柱状图</li>
|
||
<li>饼状图</li>
|
||
<li>折线图</li>
|
||
<li>ggplot2扩展包主题</li>
|
||
</ul>
|
||
<p><strong>Task05 模型（3天）</strong></p>
|
||
<ul>
|
||
<li>回归模型</li>
|
||
<li>分类模型</li>
|
||
</ul>
|
||
</div>
|
||
<div id="关于-datawhale" class="section level2 unnumbered">
|
||
<h2>关于 Datawhale</h2>
|
||
<p>Datawhale 是一个专注于数据科学与AI领域的开源组织，汇集了众多领域院校和知名企业的优秀学习者，聚合了一群有开源精神和探索精神的团队成员。Datawhale 以 “For the learner，和学习者一起成长” 为愿景，鼓励真实地展现自我、开放包容、互信互助、敢于试错和勇于担当。同时 Datawhale 用开源的理念去探索开源内容、开源学习和开源方案，赋能人才培养，助力人才成长，建立起人与人，人与知识，人与企业和人与未来的联结。 本次数据挖掘路径学习，专题知识将在天池分享，详情可关注 Datawhale：</p>
|
||
<p><img src="image/logo.png" width="129" /></p>
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
</section>
|
||
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<a href="task-00.html" class="navigation navigation-next navigation-unique" aria-label="Next page"><i class="fa fa-angle-right"></i></a>
|
||
</div>
|
||
</div>
|
||
<script src="libs/gitbook-2.6.7/js/app.min.js"></script>
|
||
<script src="libs/gitbook-2.6.7/js/lunr.js"></script>
|
||
<script src="libs/gitbook-2.6.7/js/clipboard.min.js"></script>
|
||
<script src="libs/gitbook-2.6.7/js/plugin-search.js"></script>
|
||
<script src="libs/gitbook-2.6.7/js/plugin-sharing.js"></script>
|
||
<script src="libs/gitbook-2.6.7/js/plugin-fontsettings.js"></script>
|
||
<script src="libs/gitbook-2.6.7/js/plugin-bookdown.js"></script>
|
||
<script src="libs/gitbook-2.6.7/js/jquery.highlight.js"></script>
|
||
<script src="libs/gitbook-2.6.7/js/plugin-clipboard.js"></script>
|
||
<script>
|
||
gitbook.require(["gitbook"], function(gitbook) {
|
||
gitbook.start({
|
||
"sharing": {
|
||
"github": true,
|
||
"facebook": false,
|
||
"twitter": false,
|
||
"linkedin": true,
|
||
"weibo": true,
|
||
"instapaper": false,
|
||
"vk": false,
|
||
"whatsapp": false,
|
||
"all": ["facebook", "twitter", "linkedin", "weibo", "instapaper", "whatsapp"]
|
||
},
|
||
"fontsettings": {
|
||
"theme": "white",
|
||
"family": "sans",
|
||
"size": 2
|
||
},
|
||
"edit": {
|
||
"link": null,
|
||
"text": null
|
||
},
|
||
"history": {
|
||
"link": null,
|
||
"text": null
|
||
},
|
||
"view": {
|
||
"link": "https://github.com/FinYang/RLearning-book/blob/main/index.Rmd",
|
||
"text": null
|
||
},
|
||
"download": ["RLearning.pdf"],
|
||
"toc": {
|
||
"collapse": "subsection"
|
||
}
|
||
});
|
||
});
|
||
</script>
|
||
|
||
</body>
|
||
|
||
</html>
|