R语言实战笔记后续修改

#2021/6/7 R语言复习检索
#数组 package23
myarry<-array(vector,dimensions,dimnames)
#列如
z<-array(1:24,c(2,3,4),dimnames = list(dim1,dim2,dim30))#中间的dimension中的2表示行数，3表示列数，4表示数组中矩阵的个数

#数据框 package24
#table表示连列表
patientid<-c(1,2,3,4)
admdata<-c("10/15/2009","11/01/2009","10/2/2009","10/28/2009")
age<-c(25,34,28,52)
diabetes<-c("type1","type2","type1","type1")
status<-c("poor","improved","excellent","poor")
patientdata<-data.frame(patientid,admdata,age,diabetes,status)
patientdata
table(patientdata$diabetes,patientdata$status)

#with函数 package26
with(mtcars,{
  print(summary(mpg))
  plot(mpg,disp)
})
#with函数中所有赋值都不生效，除非用<<-
with(mtcars,{
  wsq<-198
})
wsq
#用<<-
with(mtcars,{
  wsq<<-"对象很多"
})
wsq

#实例标识符 packages26
patientdata<-data.frame(patientid,age,diabetes,status,row.names = patientid)
patientdata

#因子 packages27
diabetes<-c("type1","type2","type1","type1")
diabetes<-factor(diabetes)#会将向量储存为1,2,1,1
diabetes
status<-c("poor","improved","excellent","poor")
status<-factor(status,ordered=T)#会将向量编码为3,2,1,3
#赋值编码
status<-factor(status,ordered = T,levels = c("poor","improved","excellent"))#人为赋值,将poor赋值为1，impro赋值为2
sex<-c(1,2)
sex<-factor(sex,levels = c(1,2),labels = c("male","female"))
sex


##使用键盘输入数据 packages31
mydata<-data.frame(age=numeric(0),gender=character(0),weight=numeric(0))
mydata<-edit(mydata)
mydata
fix(mydata)

##带分隔符的文本文件导入数据
#read.table("studentsid.csv",header=T,row.names="studentsid",sep=",",colclasses=c("character","numeric")) studentsid变成了行名

#倒入excel数据,这里用潘老师的readx1包
library(readxl)
read_excel("filename.xls", sheet = NULL, range = NULL, col_names = TRUE)
##读取stata数据packages38
library(foreign)
mydataframe<-read.dta("mydata.dta")

#数据集的标注 packages40
patientdata
names(patientdata)[2]<-"Age at hospitallzation"
patientdata[2]

ls()#显示当前的变量名称
#rm(object,object,...)删除一个或多个对象，rm(list=ls())删除当前工作环境中的所有对象
rm(age)
ls()


#基本数据管理
manager<-c(1,2,3,4,5)
date<-c("10/24/08","10/1/08","10/1/08","10/12/08","5/1/09")
country<-c("US","US","UK","UK","UK")
gender<-c("M","F","F","M","F")
age<-c(32,45,25,39,99)
q1<-c(5,3,3,3,2)
q2<-c(4,5,5,3,2)
q3<-c(5,2,5,4,1)
q4<-c(5,5,5,NA,2)
q5<-c(5,5,2,NA,1)
leadership<-data.frame(manager,date,country,gender,age,q1,q2,q3,q4,q5,stringsAsFactors = F)#stringsASfactor=T默认转为因子型
leadership
#变量的重编码
leadership$age[leadership$age==99]<-NA
leadership
#用within函数，within函数与with函数相似，不过它允许修改数据框
manager<-c(1,2,3,4,5)
date<-c("10/24/08","10/1/08","10/1/08","10/12/08","5/1/09")
country<-c("US","US","UK","UK","UK")
gender<-c("M","F","F","M","F")
age<-c(32,45,25,39,99)
q1<-c(5,3,3,3,2)
q2<-c(4,5,5,3,2)
q3<-c(5,2,5,4,1)
q4<-c(5,5,5,NA,2)
q5<-c(5,5,2,NA,1)
leadership<-data.frame(manager,date,country,gender,age,q1,q2,q3,q4,q5,stringsAsFactors = F)#stringsASfactor=T默认转为因子型
leadership<-within(leadership,{
  agecat<-NA
  agecat[age>75]<-"elder"
  agecat[age>=55&age<=75]<-"Middle Aged"
  agecat[age<55]<-"Young"
})
leadership


##变量的重命名
fix(leadership)
n