Genome Informatics Laboratory at KRIBB

# " " – 공백 (default: sep=" ")
myname <- "Jason Bourne"
paste("My name is", myname, sep=" ")
# file name
file_id = 1533
paste("Dataset_",file_id, ".txt",sep="")
# vector arguments
paste(LETTERS[1:5],1:5)

# vector 인수들을 원소별로 결합 후 collapse 정의 문자로 구분
# (default) collapse = NULL
paste("A","B",collapse='/')
paste(c("A","B"),collapse='/')
paste(c("A","B"),1:2,collapse='/')
paste(c("A","B"),1:2,sep='?', collapse='/')

# paste(vector1, ..., sep=‘’,collapse= NULL)
paste(c("A","B"),1:2,sep='',collapse='/')
paste0(c("A","B"),1:2,collapse='/')
paste0(LETTERS[1:5],letters[1:5])

test <- c("abcdefg", "AFFY1245820")
nchar(test)

f_name <- "AFFY1245820"
substr(f_name,5,nchar(f_name))

strtrim("ABCDEF",3)
strtrim(rep("abcdef", 3), c(1,4,10))

strsplit(c("a,b,c,d","cd,e"),split=',')
strsplit(c("010-1234-1111","010-1222-3434"),split='-')


x <- c("asfef", "yuiop[", "b", "stuff.blah.yech")
strsplit(x, "e")
strsplit(x,"[a-e]")
strsplit(x,"[aleu]")
unlist(strsplit("a.b.c", "."))
unlist(strsplit("a.b.c", "[.]"))
unlist(strsplit("a.b.c", ".", fixed = TRUE))

test = dir("./")
grep("^[A-Ca-c][a-z]",test,value=T)
grep(".exe$",test,value=T)

dir("./")

getwd()
setwd("../")  
dir()
dir.create('./test'); dir()

x <- c(1,3,2,4)
xmat <- matrix(c(1,2,4,5,2,1),3,2)

dat = data.frame() # 비어있는 데이터 프레임
dat = edit(dat)

a = readline("Input any integer: ")
a
b = readline("Input two integers with comma :")
# Input two integers with comma : 3,5
as.numeric(unlist(strsplit(b,"[,]")))


setwd('/BiO/example/dataset')
x = scan(file="input_noh.txt",what=numeric())
head(x)
x = scan(file="input_noh.txt",what=character())
head(x)
x = scan(file="input_noh.txt")
head(x)
x = scan(file="input_h.txt")
head(x)
x = scan(file="input_h.txt",what=character())
head(x)

dat = read.table(file="input_noh.txt")
dat2 = read.table(file="input_noh.txt",header=T)
dat3 = read.table(file="input_h.txt",header=F)
dat4 = read.table(file="input_h.txt",header=T)

x <- 1:10
cat(x,file="x.txt",sep="\n") # output to a file
cat(x,sep="\t") # output to a screen
cat("\n ",1,"st element of x = ",x[1])
# "\n" – 줄바꿈, "\t" – 탭

x1 <- 1:20
x2 <- rep(c("A","B","B","A"),5)
x3 <- rep(c(T,F),each=10)
dat <- cbind(x1,x2,x3) # 문자열로 모두 변환됨.
dat <- data.frame(x1,x2,x3)
write.table(dat,file="test1.txt",row.names=T,
            col.names=T,quote=T,sep="\t")
write.table(dat,file="test2.txt",row.names=F,
            col.names=F,quote=F,sep="\n")
write.table(dat,file="test3.txt",sep=",")


library(xlsx)
dat = read.xlsx(file='food.xlsx',sheetIndex=1,
                as.data.frame=T,header=T,startRow=1)
head(dat)

save(list=ls(),file='test.rdata')
load(file = 'test.rdata')

x <- matrix(c(NA, 1, 3, NA, NA, 2),3,2)
is.na(x)
sum(is.na(x)) # number of missing values

which(is.na(x)) # 1차원 위치
which(is.na(x),arr.ind = T) # 2 차원 위치
which(is.na(x),T) # 2차원 위치

v = c("a,b,c,b,e","a,b","d,e,f")
lapply(v,nchar)
sp = strsplit(v,',')
sp
lapply(sp,length)
lapply(sp,paste0,3)

v = c("a,b,c,b,e","a,b","d,e,f")
sapply(v,nchar)
sp = strsplit(v,',')
sp
sapply(sp,length)

?mtcars
head(mtcars)
tapply(mtcars$mpg,mtcars$cyl,mean)
tapply(mtcars$mpg,mtcars$am,mean)

library(dplyr)
filter(mtcars,cyl==4,am==1)
filter(mtcars,wt>2,cyl==8)

names(mtcars)
select(mtcars,mpg,cyl,wt)
select(mtcars,mpg,-hp,-gear)

mtf = select(mtcars,mpg,cyl,hp,wt)
mutate(mtf,hw_rat=hp/wt)
mutate(mtf,hw_rat=hp/wt,cw_rat=cyl/wt)

mtf = select(mtcars,mpg,am,cyl,wt)
arrange(mtf,mpg,desc(cyl))
arrange(mtf,am,cyl,wt)

summarize(mtcars,m_mpg=mean(mpg),v_mpg=var(mpg))
summarize(mtcars,md_mpg=median(mpg),md_wt=median(wt))
summarize(mtcars,trows=range(mpg))

mt_gr = group_by(mtcars,cyl)
head(mt_gr)
summarize(mtcars,m_mpg=mean(mpg),m_wt=mean(wt))
summarize(mt_gr,m_mpg=mean(mpg),m_wt=mean(wt))

dat <- group_by(mtcars, cyl)
dat <- select(dat, mpg, wt, cyl)
dat <- summarize(dat, m_mpg = mean(mpg))
dat <- filter(dat, m_mpg > 16)
dat

dat2 <- mtcars %>% 
        group_by(cyl) %>%
        select(mpg, wt, cyl) %>%
        summarize(m_mpg = mean(mpg)) %>%
        filter(m_mpg > 16)
dat2