第五章高级数据管理

#5高级数据管理

y<-data.frame(name=character(0),math=numeric(0),science=numeric(0),english=numeric(0))

mydata<-edit(y)

mydata

#5.2数值和字符处理函数

#5.2.1数学函数

#5.2.2统计函数

dada<-scale(mydata)#数据标准化

#5.2.3概率函数

set.seed（）#设定随机种子

runif(5)#生成服从正态分布的伪随机数

#生成服从多元正太分布的数据

library(MASS)

options(digits=3)

set.seed(1234)

mean<-c(230.7,146.7,3.6)

sigma <- matrix(c(15360.8,6721.2,-47.1,

6721.2,4700.9,-16.5,

-47.1,-16.5,0.3),nrow=3,ncol=3)

mydata<-mvrnorm(500,mean,sigma)

mydata<-as.data.frame(mydata)

names(mydata)<-c("y","x1","x2")

dim(mydata)

head(mydata,n=10)

#5.2.4字符处理函数

#5.2.5其他实用函数

#5.2.6将函数应用于矩阵和数据框

#将函数应用于数据对象

a<-5

sqrt(a)

b<- c(1.243,5.654,2.99)

round(b)

c<-matrix(runif(12),nrow=3)

c

log(c)

mean(c)

#将一个函数应用到矩阵的所有行或列中

mydata<-matrix(rnorm(30),nrow=6)

mydata

apply(mydata,1,mean)#计算每行平均值

apply(mydata,2,mean)#计算每列平均值

apply(mydata,2,mean,trim=0.2)#计算每行平均值

#5.3数据处理难题的一套解决方案

options(digits=2)

setwd("e:/r")

library(xlsx)

student<-read.xlsx("student.xlsx",1)

student

roster<-data.frame(student,math,science,english,

stringAsFactor=FASLE)

z<-scale(#未完)

5-6

options(digits=2)

student<-c("J D","A W","B M",

"D J","J M","C C",

"R Y","G K","J E",

"M R")

math<-c(502,600,412,358,495,512,410,625,573,522)

science<-c(95,99,80,82,75,85,80,95,89,86)

english<-c(25,22,18,15,20,28,15,30,27,18)

roster<-data.frame(student,math,science,english,stringAsFactors=FALSE)

z<-scale(roster[,2:4])

score<-apply(z,1,mean)

roster<-cbind(roster,score)

y<-quantile(score,c(.8,.6,.4,.2))

roster$grade[score>=y[1]]<-"A"

roster$grade[score<y[1]&score>=y[2]]<-"B"

roster$grade[score<y[2]&score>=y[3]]<-"C"

roster$grade[score<y[3]&score>=y[4]]<-"D"

roster$grade[score<=y[4]]<-"F"

roster

class(roster$student)

roster$student<-as.character(roster$student)

name <- strsplit((roster$student)," ")#roster$student必须是字符变量才能用strsplit？

LN<-sapply(name, "[",2)

FN<-sapply(name, "[",1)

roster<-cbind(FN,LN,roster[,-1])

roster<-roster[order(LN,FN),]

roster

#5.4控制流

#5.4.1重复和循环

for( i in 1:10) print("H")

i<-10

while(i>0) {print("h");i<- i-1}

#5.4条件执行

#5.4.1 if-else

attach(roster)

if(is.character(math)) math<-as.factor(math)

if(!is.character(LN)) math<-as.factor(LN)else print("gggg")

#5.4.2 ifelse,二元，输入输出均为向量时

attach(roster)

ifelse(score>0.5,print("P"),print("f"))

outcome<-ifelse(score>0.5,"P","f")

5.4.3switch

feelings<-c("s","a")

for(i in feelings)

print(

switch(i,

h="iii",

a="tttt",

s="ccc",

a="ccc"))

#5.5用户自编函数

mystats<-function(x,parametric=TRUE,print=FALSE){

if(parametric){center<-mean(x);spread<-sd(x)

}else{

center<-median(x);spread<-mad(x)

}

if(print&parametric){

cat("mean=",center,"\n","sd=",spread,"\n")

}else{

cat("median=",center,"\n","mad=",spread,"\n")

}

result<-list(center=center,spread=spread)

return(result)

}

#验证

set.seed(1234)

x<-rnorm(500)

y<-mystats(x,parametric=TRUE,print=FALSE)

#自编函数2

mydate<-function(type="long"){

switch(type,

long=format(Sys.time(),"%A %B %d %Y"),

short=format(Sys.time(),"%m-%d-%y"),

cat(type,"is not a recognizede type\n"))}

mydate("long")

mydate("short")

mydate()

mydate("dvsdf")

5.6整合和重构

5.6.1转置

cars<-mtcars[1:5,1:4]

cars

t(cars)

5.6.2整合数据

options(digits=3)

attach(mtcars)

mtcars

aggdata<-aggregate(mtcars,by=list(cyl,gear),FUN=mean,na.rm=TRUE)

aggdata

5.6.3reshape包融合和重铸melt,dcast

library(reshape2)

md<-melt(mydata,id=c("id,time"))