1、R 软件基础知识与实战第一课：基本知识第二课：基本运算第三课：画图第四课：数据整理和数据分析第五课：统计分析第六课：分布的产生第七课：求导和极值的计算第八课：Bootstrap 方法第九课：MCMC 算法第一课 基本知识一R 的历史与特点Object-oriented 语言二R 系统介绍安装镜像Installing packages library(survival) # 加载程序包library(help=survival) # 显示程序包 survival 里的内容help(mean) #查看关于函数 mean 的帮助search() # 给出系统里已加载的程序包searchpaths()
2、 # 给出系统里已加载的程序包的路径Commands are separated either by semicolon or a new line三Data objects# There are 7 basic types of data objects:# Vector, Matrix, Array, List, Factor, Time series, Data frame# creating vectors# vector type: character, numeric, integer, logical, complexmy1 5/0Inf 0/0NaN # not a numbe
3、r a = c(1,2,3,NA,4) # NA represents missing value mean(a)1 NAa = c(“asia“,“da“,NA) # NA 也可以代表字符型的 missing valuea = c(T,F,T,T, NA)# NULL 代表一个空值a = NULL # a is a empty vectorfor( i in 1: 10) ai = i2# testing and coercingletter = factor (letters) is.vector(letter) # test whether letter is a vector1 FAL
4、SE letter = as.vector(letter) # coerce letter into a vectoris.matrix()as.matrix()is.data.frame()as.data.frame()is.list()as.list()write.table(lizard, “E:/R/new.Rdata“)new = read.table(“E:/R/new.Rdata“)save(a,lizard,new x, file=“E:/R/mydump.rda“)load(file=“E:/R/mydump.rda“)sink(“E:/R/new22.txt“) lizar
5、d ls() sink()四Data manipulation逻辑运算符号符号 意义= = 等于！= 不等于= 大于等于 大于= 30 # 一个逻辑值向量myseqmyseq =30 # 给出 myseq 里大于等于 30 的所有值 x 2x x 2 else sigma - 0sigma smry - function(X) mu - mean(X); sigma - stdv(X); c(mu=mu,sigma=sigma)patients - c(“0071021198307012008001400400150“,“0071201198307213009002000500200“,“00
6、90903198306611007013700300000“,“0050705198307414008201300900000“,“0050115198208018009601402001500“,“0050618198207017008401400800400“,“0050703198306414008401400800200“)id - substr(patients,1,3); date - as.Date(substr(patients,4,11), format = “%m%d%Y“)hr - as.numeric(substr(patients,12,14); sbp - as.n
7、umeric(substr(patients,15,17)dbp - as.numeric(substr(patients,18,20); dx - substr(patients,21,23)docfee - as.numeric(substr(patients,24,27); labfee - as.numeric(substr(patients,28,31)tapply(hr,id,mean); tapply(hr,id,stdv)# 希望将这些结果更紧凑的表现出现PATIENTS - data.frame(id,hr,sbp,dbp,docfee,labfee)str(PATIENTS
8、)smry(PATIENTSid=005,2:6); smry(PATIENTSid=007,2:6); smry(PATIENTSid=009,2:6)by(PATIENTS2:6, id, smry) ; by(PATIENTS2:6, id, summary)# 计算 HR, SBP, DBP 的最后一个观测值和第一个观测值的差HrSbpDbp - data.frame(id,date,hr,sbp,dbp)order(HrSbpDbp$id, HrSbpDbp$date) # order of sorted rowsHrSbpDbpSorted - HrSbpDbporder(HrSb
9、pDbp$id, HrSbpDbp$date), HrSbpDbpSorted # original row numbers still appear at left . ID - HrSbpDbpSorted,1; HR - HrSbpDbpSorted,3; SBP - HrSbpDbpSorted,4; DBP - HrSbpDbpSorted,5which(ID=“005“) # remember which function from r5.R by(HrSbpDbpSorted4, ID, TailHead);by(HrSbpDbpSorted5, ID, TailHead)# n
10、ow want gaps (in days) between every pair of adjacent visitsDATE - HrSbpDbpSorted,2diff(DATEwhich(ID=“005“) # use DATE, not datediff(DATEwhich(ID=“007“); diff(DATEwhich(ID=“009“)by(DATE, ID, diff)五.去掉 duplicated 值attach(cars)carsorder(price), # sort in terms of increasing pricecarsorder(ctympg,hwymp
11、g), # increasing ctymp; increasing hwympgcarsorder(ctympg,-hwympg), # increasing ctymp; decreasing hwympgcars!duplicated(type), # gives exactly one (the first) of each type of cartype1:24duplicated(type1:24) # T if duplicate; F if not!duplicated(type1:24) # opposite of aboveMT - subset(cars,select=c
12、(manu,type); MT1:10,; !duplicated(MT1:10,)cars!duplicated(MT), # gives exactly one (the first) of each (manu,type) of car# another function, unique, at first glance seems like it might do the same.unique(type) detach(cars)第五课 统计分析 一t-test# Daily energy intake in kJ for 11 women (Altman, 1991) daily.
13、intake - c(5260,5470,5640,6180,6390,6515,6805,7515,7515,8230,8770)plot(daily.intake) # unsatisfactoryplot(daily.intake,xlab=“subject“,xaxt=“n“,main=“Energy intake for 11 subjects“)axis(1,at=seq(1,11,1) # puts one tick mark per subject#Does the womens energy intake deviate significantly from a recomm
14、ended value of 7725？t.test(daily.intake, mu=7725) # we reject H0 at 5% significance level# Same question, but want a 99% confidence interval insteadt.test(daily.intake,mu=7725, conf.level=0.99) # we accept H1 at 1% level# Is the womens energy intake significantly less than a recommended value of 7725 kJ?t.test(daily.intake, mu=7725,conf.level=0.99, alt=“l“) # we reject H0 at 1% level # Comparing energy expenditure between lean & obese women# Two-sample t testlibrary(ISwR)
