方法一:使用aggregate()分组获取描述性统计量

 aggregate(mtcars[vars],by=list(am=mtcars$am),mean)
aggregate(mtcars[vars],by=list(mtcars$am),mean)
aggregate(mtcars[vars],by=list(am=mtcars$am),sd)

aaarticlea/png;base64,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" alt="" />

若有多个分组变量,使用by=list(name1=groupvar1, name2=groupvar2, ... , groupvarN)

这样只能返回单个统计量,若要返回多个统计量,可使用by()函数

R语言笔记006——分组获取描述性统计量的更多相关文章

  1. R语言笔记

    R语言笔记 学习R语言对我来说有好几个地方需要注意的,我觉得这样的经验也适用于学习其他的新的语言. 语言的目标 我理解语言的目标就是这个语言是用来做什么的,为什么样的任务服务的,也就是设计这个语言的动 ...

  2. R语言笔记4--可视化

    接R语言笔记3--实例1 R语言中的可视化函数分为两大类,探索性可视化(陌生数据集,不了解,需要探索里面的信息:偏重于快速,方便的工具)和解释性可视化(完全了解数据集,里面的故事需要讲解别人:偏重全面 ...

  3. R语言笔记005——计算描述性统计量

    数据的分布特征: 分布的集中趋势,反应各数据向其中心值靠拢或聚集的程度(平均数,中位数,四分位数,众数) 分布的离散程度,反应各数据远离其中心值的趋势(极差,四分位差,方差,标准差,离散系数) 分布的 ...

  4. R 分组计算描述性统计量

    统计学区内各个小区的房价均值 数据格式 id|community_name|house_area|house_structure|house_total|house_avg|agency_name|h ...

  5. R语言笔记完整版

    [R笔记]R语言函数总结   R语言与数据挖掘:公式:数据:方法 R语言特征 对大小写敏感 通常,数字,字母,. 和 _都是允许的(在一些国家还包括重音字母).不过,一个命名必须以 . 或者字母开头, ...

  6. R语言与概率统计(一) 描述性统计分析

      #查看已安装的包,查看已载入的包,查看包的介绍 ########例题3.1 #向量的输入方法 w<-c(75.0, 64.0, 47.4, 66.9, 62.2, 62.2, 58.7, 6 ...

  7. R语言笔记:快速入门

    1.简单会话 > x<-c(1,2,4) > x [1] 1 2 4 R语言的标准赋值运算符是<-.也可以用=,不过不建议用它,有些情况会失灵.其中c表示连接(concaten ...

  8. 使用R语言的RTCGA包获取TCGA数据--转载

    转载生信技能树 https://mp.weixin.qq.com/s/JB_329LCWqo5dY6MLawfEA TCGA数据源 - R包RTCGA的简单介绍 - 首先安装及加载包 - 指定任意基因 ...

  9. 初探R语言——R语言笔记

    R语言使用 <-  赋值 # 作为注释符号 c()函数用于作为向量赋值,例如age<-c(1,2,3,4,5) mean()用于求向量的平均值 sd()求向量的标准差 cor(a,b)求a ...

随机推荐

  1. PHPFastCGI进程管理器PHP

    PHP-FPM是一个PHPFastCGI进程管理器,是只用于PHP的.      PHP-FPM其实是PHP源代码的一个补丁,旨在将FastCGI进程管理整合进PHP包中.必须将它patch到你的PH ...

  2. windows下 兼容Python2和Python3

    windows下同时安装了python2和python3时,都可以配置环境变量,如果在命令行里输入python命令,windows会去环境变量里寻找Python的安装位置,如果先找到pytoon2的, ...

  3. 【BZOJ1266】[AHOI2006]上学路线route Floyd+最小割

    [BZOJ1266][AHOI2006]上学路线route Description 可可和卡卡家住合肥市的东郊,每天上学他们都要转车多次才能到达市区西端的学校.直到有一天他们两人参加了学校的信息学奥林 ...

  4. Stolz–Cesàro theorem

    w http://planetmath.org/sites/default/files/texpdf/33795.pdf Stolz–Cesàro theorem - Wikipedia  https ...

  5. 解决Mysql报错缺少libaio.so.1

    解决Mysql报错缺少libaio.so.1 报错如上图,需要安装libaio.so.1 64位系统安装: wget http://mirror.centos.org/centos/6/os/x86_ ...

  6. Testlink安装:Notice:Undefined index: type in C:\inetpub\wwwroot\testlink-1.9.3\install\installCheck.php on line 41

    问题现象:

  7. 常用代码块:java使用系统浏览器打开url

    方法一:用于windows try { Runtime.getRuntime().exec("rundll32 url.dll,FileProtocolHandler "+url) ...

  8. [LeetCode-21]Construct Binary Tree from Preorder and Inorder Traversal

    Given preorder and inorder traversal of a tree, construct the binary tree. Note: You may assume that ...

  9. Java并发—线程常用方法总结

    1.join()方法 join —— 让一个线程等待另一个线程完成才继续执行.如A线程线程执行体中调用B线程的join()方法,则A线程被阻塞,知道B线程执行完为止,A才能得以继续执行. public ...

  10. github 上 python 的优秀库推荐列表

    awesome-python: https://github.com/vinta/awesome-python