fox.said <- "what is essential is invisible to the eye"
fox.said## [1] "what is essential is invisible to the eye"strsplit(x=fox.said, split=" ") # 리스트 출력## [[1]]
## [1] "what" "is" "essential" "is" "invisible" "to"
## [7] "the" "eye"fox.said <- "what is essential is invisible to the eye"
fox.said## [1] "what is essential is invisible to the eye"fox.said.words <- unlist(strsplit(fox.said, " "))
fox.said.words## [1] "what" "is" "essential" "is" "invisible" "to"
## [7] "the" "eye"fox.said.words[3]## [1] "essential"fox.said <- "what is essential is invisible to the eye"
fox.said## [1] "what is essential is invisible to the eye"fox.said.words <- strsplit(fox.said, " ")[[1]]
fox.said.words## [1] "what" "is" "essential" "is" "invisible" "to"
## [7] "the" "eye"fox.said.words[3]## [1] "essential"p1 <- "You come at four in the afternoon, then at three I shall begin to be happy"
p2 <- "One runs the risk of weeping a little, if one lets himself be tamed"
p3 <- "What makes the desert beautiful is that somewhere it hides a well"
littleprince <- c(p1, p2, p3)
strsplit(littleprince, " ")## [[1]]
## [1] "You" "come" "at" "four" "in"
## [6] "the" "afternoon," "then" "at" "three"
## [11] "I" "shall" "begin" "to" "be"
## [16] "happy"
##
## [[2]]
## [1] "One" "runs" "the" "risk" "of" "weeping" "a"
## [8] "little," "if" "one" "lets" "himself" "be" "tamed"
##
## [[3]]
## [1] "What" "makes" "the" "desert" "beautiful" "is"
## [7] "that" "somewhere" "it" "hides" "a" "well"strsplit(littleprince, " ")[[3]]## [1] "What" "makes" "the" "desert" "beautiful" "is"
## [7] "that" "somewhere" "it" "hides" "a" "well"strsplit(littleprince, " ")[[3]][5]## [1] "beautiful"fox.said <- "WHAT IS ESSENTIAL is invisible to the Eye"
fox.said.words <- strsplit(fox.said, " ")[[1]]
fox.said.words## [1] "WHAT" "IS" "ESSENTIAL" "is" "invisible" "to"
## [7] "the" "Eye"unique(fox.said.words)## [1] "WHAT" "IS" "ESSENTIAL" "is" "invisible" "to"
## [7] "the" "Eye"unique(tolower(fox.said.words))## [1] "what" "is" "essential" "invisible" "to" "the"
## [7] "eye"#묶이지 않은 원소의 결합 및 결합시 사용할 separator
paste("Everybody", "wants", "to", "fly")## [1] "Everybody wants to fly"paste("Everybody", "wants", "to", "fly", sep=" ")## [1] "Everybody wants to fly"paste("Everybody", "wants", "to", "fly", sep="-")## [1] "Everybody-wants-to-fly"paste("Everybody", "wants", "to", "fly", sep="")## [1] "Everybodywantstofly"paste0("Everybody", "wants", "to", "fly") # paste0는 paste(..., sep="")과 동일## [1] "Everybodywantstofly"paste(pi, sqrt(pi))## [1] "3.14159265358979 1.77245385090552"paste("25 degrees Celsius is", 25*1.8 + 32, "degrees Fahrenheit")## [1] "25 degrees Celsius is 77 degrees Fahrenheit"#paste는 벡터로 묶인 1개의 인수가 주어진 경우, 해당 벡터를 분리후 결합하지 않음
paste(c("Everybody", "wants", "to", "fly")) # 결과 변화 없음## [1] "Everybody" "wants" "to" "fly"fox.said <- "WHAT IS ESSENTIAL is invisible to the Eye"
fox.said.words <- strsplit(fox.said, " ")[[1]]
fox.said.words## [1] "WHAT" "IS" "ESSENTIAL" "is" "invisible" "to"
## [7] "the" "Eye"paste(fox.said.words) # 결과 변화 없음## [1] "WHAT" "IS" "ESSENTIAL" "is" "invisible" "to"
## [7] "the" "Eye"#paste()는 벡터로 묶인 인수와 다른 인수가 주어질 경우, #벡터의 elementwise 결합 및 원소 부족시 확장이 일어남
heroes <- c("Batman", "Captain America", "Hulk")
colors <- c("Black", "Blue", "Green")
paste(colors, heroes)## [1] "Black Batman" "Blue Captain America" "Green Hulk"rank <- c(1,2,3,4)
heroes <- c("Batman", "Captain America", "Hulk")
paste(rank, heroes)## [1] "1 Batman" "2 Captain America" "3 Hulk"
## [4] "4 Batman"paste("Type", 1:5)## [1] "Type 1" "Type 2" "Type 3" "Type 4" "Type 5"heroes <- c("Batman", "Captain America", "Hulk")
paste(heroes, "wants", "to", "fly")## [1] "Batman wants to fly" "Captain America wants to fly"
## [3] "Hulk wants to fly"paste(c("Everybody", "wants", "to", "fly"))## [1] "Everybody" "wants" "to" "fly"paste(c("Everybody", "wants", "to", "fly"), collapse=" ")## [1] "Everybody wants to fly"heroes <- c("Batman", "Captain America", "Hulk")
paste(heroes, "wants", "to", "fly", collapse=", and ")## [1] "Batman wants to fly, and Captain America wants to fly, and Hulk wants to fly"heroes <- c("Batman", "Captain America", "Hulk")
paste(heroes, "wants", "to", "fly", sep="-", collapse="; ")## [1] "Batman-wants-to-fly; Captain America-wants-to-fly; Hulk-wants-to-fly"paste(month.abb, 1:12, sep="_", collapse="-")## [1] "Jan_1-Feb_2-Mar_3-Apr_4-May_5-Jun_6-Jul_7-Aug_8-Sep_9-Oct_10-Nov_11-Dec_12"outer(c(1,2,3), c(100,10,1)) # 2개 집합에 대해 모든 순서쌍의 곱을 수행## [,1] [,2] [,3]
## [1,] 100 10 1
## [2,] 200 20 2
## [3,] 300 30 3asian.countries <- c("Korea", "China", "Japan")
info <- c("GDP", "Population", "Area")
outer(asian.countries, info, FUN=paste, sep="-")## [,1] [,2] [,3]
## [1,] "Korea-GDP" "Korea-Population" "Korea-Area"
## [2,] "China-GDP" "China-Population" "China-Area"
## [3,] "Japan-GDP" "Japan-Population" "Japan-Area"out <- outer(asian.countries, info, FUN=paste, sep="-")
as.vector(out)## [1] "Korea-GDP" "China-GDP" "Japan-GDP" "Korea-Population"
## [5] "China-Population" "Japan-Population" "Korea-Area" "China-Area"
## [9] "Japan-Area"outer(asian.countries, asian.countries, paste, sep="-")## [,1] [,2] [,3]
## [1,] "Korea-Korea" "Korea-China" "Korea-Japan"
## [2,] "China-Korea" "China-China" "China-Japan"
## [3,] "Japan-Korea" "Japan-China" "Japan-Japan"cameraData <- read.csv(“cameras.csv”) str(cameraData) head(cameraData) grep(“Alameda”, cameraData\(intersection) table(grepl("Alameda", cameraData\)intersection)) grep(“Alameda”, cameraData\(intersection, value=TRUE) table(grepl("Alameda", cameraData\)intersection))
head(islands)## Africa Antarctica Asia Australia Axel Heiberg Baffin
## 11506 5500 16988 2968 16 184landmasses <- names(islands)
landmasses## [1] "Africa" "Antarctica" "Asia" "Australia"
## [5] "Axel Heiberg" "Baffin" "Banks" "Borneo"
## [9] "Britain" "Celebes" "Celon" "Cuba"
## [13] "Devon" "Ellesmere" "Europe" "Greenland"
## [17] "Hainan" "Hispaniola" "Hokkaido" "Honshu"
## [21] "Iceland" "Ireland" "Java" "Kyushu"
## [25] "Luzon" "Madagascar" "Melville" "Mindanao"
## [29] "Moluccas" "New Britain" "New Guinea" "New Zealand (N)"
## [33] "New Zealand (S)" "Newfoundland" "North America" "Novaya Zemlya"
## [37] "Prince of Wales" "Sakhalin" "South America" "Southampton"
## [41] "Spitsbergen" "Sumatra" "Taiwan" "Tasmania"
## [45] "Tierra del Fuego" "Timor" "Vancouver" "Victoria"grep(pattern="New", x=landmasses)## [1] 30 31 32 33 34index <- grep("New", landmasses)
landmasses[index]## [1] "New Britain" "New Guinea" "New Zealand (N)" "New Zealand (S)"
## [5] "Newfoundland"grep(pattern="New", x=landmasses, value=TRUE)## [1] "New Britain" "New Guinea" "New Zealand (N)" "New Zealand (S)"
## [5] "Newfoundland"grepl(pattern="New", x=landmasses)## [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [25] FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE
## [37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSEtable(grepl(pattern="New", x=landmasses))##
## FALSE TRUE
## 43 5grepl(pattern="new", x=landmasses)## [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [25] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSElength(grep(pattern="new", x=landmasses))## [1] 0names <- c("김남수","하이연","정진성","김우주","박구수","성우장","박의수", "박수")
grep("^박.*수$",names)## [1] 5 7 8x <- c("Idare","\t")
grep('.',x)## [1] 1 2regmatches(x,regexpr(".",x)) ## [1] "I" "\t"# stringr::str_extract를 사용하면 편리
stringr::str_extract(x,".") ## [1] "I" "\t"x <- c("Idare","i dare","Oh, I dare", "!!??!")
grep('^[Ii]',x)## [1] 1 2grepl('^[Ii]',x)## [1] TRUE TRUE FALSE FALSEregmatches(x,regexpr('^[Ii]',x)) ## [1] "I" "i"# stringr::str_extract를 사용하면 편리
stringr::str_extract(x,'^[Ii]') ## [1] "I" "i" NA NAx <- c('I dare to love you', 'I dare to love you!', 'Oh1', 'Dear, my love.2', '!!?!')
grep('[[:punct:]]',x) # 문장부호가 포함되어 있는가? ## [1] 2 4 5grep('[[:punct:]1]',x) # 문장부호 또는 1이 포함되어 있는가? ## [1] 2 3 4 5grep('[1[[:punct:]]',x) # 1 또는 문장부호가 포함되어 있는가? ## [1] 2 3 4 5grep('[^[:punct:]]',x) # 문장부호가 아닌 문자가 포함되어 있는가? ## [1] 1 2 3 4x <- c('Idaretoloveyou','I dare to love you!', 'Oh1', 'Dear, my love.1', '!!?!')
grep('\\w',x)## [1] 1 2 3 4grep('\\W',x)## [1] 2 4 5grep('\\s',x)## [1] 2 4grep('\\S',x)## [1] 1 2 3 4 5x <- c('\t','\r')
grep('\\t',x)## [1] 1x <- c("hook", "I have a hook", "He shook me")
grepl("hook",x)## [1] TRUE TRUE TRUEgrepl("\\bhook$",x)## [1] TRUE TRUE FALSEgrepl("\\Bhook$",x)## [1] FALSE FALSE FALSEx <- c("Test On. <h> Hi! </h> Test off.","Test offf")
grepl("<.+>",x)## [1] TRUE FALSEgrepl("<.+?>",x)## [1] TRUE FALSEgrepl("of{1,4}",x)## [1] TRUE TRUEregmatches(x,regexpr("<.+>",x)) # <와 > 사이에 문자가 1개 이상 존재하는 최대 매치## [1] "<h> Hi! </h>"stringr::str_extract(x,"<.+>") # stringr::str_extract를 사용하면 편리## [1] "<h> Hi! </h>" NAregmatches(x,regexpr("<.+?>",x)) # <와 > 사이에 문자가 1개 이상 존재하는 최소 매치## [1] "<h>"stringr::str_extract(x,"<.+?>") # stringr::str_extract를 사용하면 편리## [1] "<h>" NAregmatches(x,regexpr("of{1,4}",x))## [1] "off" "offf"stringr::str_extract(x,"of{1,4}") ## [1] "off" "offf"x <- c("abcxabc","abxab","abcxab","abxabc")
grepl("[abc]{2,3}x[abc]{2,3}",x)## [1] TRUE TRUE TRUE TRUEgrepl("([abc]{2,3})x\\1",x)## [1] TRUE TRUE FALSE TRUEx <- c("abba","2xx2","a22z","xaxx")
grepl("(\\w)(\\w)\\2\\1",x)## [1] TRUE TRUE FALSE FALSEx <- c("axxbba","2xyba","2yyxx2","cxy22c")
grepl("(\\w)(xx|yy)(\\w)\\3\\1",x)## [1] TRUE FALSE TRUE FALSE# More metacharacters : * and -
x <-c("working as MP here 720 MP battallion, 42nd birgade",
"so say 2 or 3 years at college and 4 at uni makes us 23 when and if we fin",
"it went down on several occasions for like, 3 or 4 *days*",
"Mmmm its time 4 me 2 go 2 bed")
grep("[0-9]+(.*)[0-9]+",x)## [1] 1 2 3 4regmatches(x,regexpr("[0-9]+(.*)[0-9]+",x))## [1] "720 MP battallion, 42"
## [2] "2 or 3 years at college and 4 at uni makes us 23"
## [3] "3 or 4"
## [4] "4 me 2 go 2"stringr::str_extract(x,"[0-9]+(.*)[0-9]+") ## [1] "720 MP battallion, 42"
## [2] "2 or 3 years at college and 4 at uni makes us 23"
## [3] "3 or 4"
## [4] "4 me 2 go 2"regmatches(x,regexpr("[0-9]+(.*)[0-9]+",x))## [1] "720 MP battallion, 42"
## [2] "2 or 3 years at college and 4 at uni makes us 23"
## [3] "3 or 4"
## [4] "4 me 2 go 2"stringr::str_extract(x,"[0-9]+(.*)[0-9]+") ## [1] "720 MP battallion, 42"
## [2] "2 or 3 years at college and 4 at uni makes us 23"
## [3] "3 or 4"
## [4] "4 me 2 go 2"x <- as.Date("1970-01-01")
x## [1] "1970-01-01"class(x)## [1] "Date"unclass(x) # 1970년 1월 1일 즉 Julian date 0일 기준으로 계산## [1] 0unclass(as.Date("1970-01-02"))## [1] 1y <- x + 7
y## [1] "1970-01-08"unclass(y) # 1970년 1월 1일 즉 Julian date 0일 기준으로 계산## [1] 7as.integer(y) # 1970년 1월 1일 즉 Julian date 0일 기준으로 계산## [1] 7julian(y) # 1970년 1월 1일 즉 Julian date 0일 기준으로 계산 ## [1] 7
## attr(,"origin")
## [1] "1970-01-01"weekdays(y)## [1] "목요일"months(y)## [1] "1월"quarters(y)## [1] "Q1"y + 1:7## [1] "1970-01-09" "1970-01-10" "1970-01-11" "1970-01-12" "1970-01-13"
## [6] "1970-01-14" "1970-01-15"weekdays(y + 1:7)## [1] "금요일" "토요일" "일요일" "월요일" "화요일" "수요일" "목요일"start <- as.Date("2021-01-01")
end <- as.Date("2021-01-31")
seq(from=start, to=end, by=1)## [1] "2021-01-01" "2021-01-02" "2021-01-03" "2021-01-04" "2021-01-05"
## [6] "2021-01-06" "2021-01-07" "2021-01-08" "2021-01-09" "2021-01-10"
## [11] "2021-01-11" "2021-01-12" "2021-01-13" "2021-01-14" "2021-01-15"
## [16] "2021-01-16" "2021-01-17" "2021-01-18" "2021-01-19" "2021-01-20"
## [21] "2021-01-21" "2021-01-22" "2021-01-23" "2021-01-24" "2021-01-25"
## [26] "2021-01-26" "2021-01-27" "2021-01-28" "2021-01-29" "2021-01-30"
## [31] "2021-01-31"seq(from=start, by=1, length.out=7)## [1] "2021-01-01" "2021-01-02" "2021-01-03" "2021-01-04" "2021-01-05"
## [6] "2021-01-06" "2021-01-07"seq(from=start, by="7 days", length.out=9)## [1] "2021-01-01" "2021-01-08" "2021-01-15" "2021-01-22" "2021-01-29"
## [6] "2021-02-05" "2021-02-12" "2021-02-19" "2021-02-26"seq(from=start, by="week", length.out=9)## [1] "2021-01-01" "2021-01-08" "2021-01-15" "2021-01-22" "2021-01-29"
## [6] "2021-02-05" "2021-02-12" "2021-02-19" "2021-02-26"seq(from=start, by="month", length.out=12)## [1] "2021-01-01" "2021-02-01" "2021-03-01" "2021-04-01" "2021-05-01"
## [6] "2021-06-01" "2021-07-01" "2021-08-01" "2021-09-01" "2021-10-01"
## [11] "2021-11-01" "2021-12-01"seq(from=start, by="3 months", length.out=4)## [1] "2021-01-01" "2021-04-01" "2021-07-01" "2021-10-01"seq(from=start, by="year", length.out=10)## [1] "2021-01-01" "2022-01-01" "2023-01-01" "2024-01-01" "2025-01-01"
## [6] "2026-01-01" "2027-01-01" "2028-01-01" "2029-01-01" "2030-01-01"seq(from=as.Date("2020-01-30"), by="month", length.out=6)## [1] "2020-01-30" "2020-03-01" "2020-03-30" "2020-04-30" "2020-05-30"
## [6] "2020-06-30"start <- as.Date("2020-01-01")
qrt <- seq(from=start, by="3 months", length.out=4)
months(qrt)## [1] "1월" "4월" "7월" "10월"quarters(qrt)## [1] "Q1" "Q2" "Q3" "Q4"Sys.setlocale("LC_ALL", "English")## [1] "LC_COLLATE=English_United States.1252;LC_CTYPE=English_United States.1252;LC_MONETARY=English_United States.1252;LC_NUMERIC=C;LC_TIME=English_United States.1252"months(qrt)## [1] "January" "April" "July" "October"Sys.setlocale("LC_ALL", "Korean")## [1] "LC_COLLATE=Korean_Korea.949;LC_CTYPE=Korean_Korea.949;LC_MONETARY=Korean_Korea.949;LC_NUMERIC=C;LC_TIME=Korean_Korea.949"months(qrt)## [1] "1월" "4월" "7월" "10월"x <- Sys.time()
x # 현재 POSIXct class## [1] "2020-05-20 05:01:47 KST"p <- as.POSIXlt(x) # POSIXlt class로 변환
p## [1] "2020-05-20 05:01:47 KST"names(unclass(p))## [1] "sec" "min" "hour" "mday" "mon" "year" "wday" "yday"
## [9] "isdst" "zone" "gmtoff"p$year+1900 # 1900을 더해야 실제 연도가 나옴## [1] 2020p$mon +1 # 1을 더해야 실제 월이 나옴 ## [1] 5p$mday## [1] 20p$wday #일요일은 0, 월요일은 1, 화요일은 2, ...## [1] 3p$hour## [1] 5p$min## [1] 1p$sec## [1] 47.91181x <- Sys.time()
x ## 현재 POSIXct class## [1] "2020-05-20 05:01:47 KST"unclass(x)## [1] 1589918508# x$sec # Error
p <- as.POSIXlt(x)
p$sec## [1] 47.94418y <- "2020"
m <- "05"
d <- "10"
ISOdate(y, m, d) # ISODate()함수는 POSIXct객체(날짜정보 초단위 저장) 생성## [1] "2020-05-10 12:00:00 GMT"class(ISOdate(y, m, d))## [1] "POSIXct" "POSIXt"as.Date(ISOdate(y, m, d)) # Date 클래스(날짜정보 일단위 저장)로 전환## [1] "2020-05-10"Sys.setlocale("LC_ALL", "English")## [1] "LC_COLLATE=English_United States.1252;LC_CTYPE=English_United States.1252;LC_MONETARY=English_United States.1252;LC_NUMERIC=C;LC_TIME=English_United States.1252"x <- as.Date("12/31/2020",format="%m/%d/%Y" )
x## [1] "2020-12-31"y <- strptime("9 Jan 2019 11:34:21", "%d %b %Y %H:%M:%S")
# x-y # Error
x <- as.POSIXlt(x) # x를 POSIXlt class로 변환
x-y## Time difference of 721.8928 daysx <- as.Date("12/31/2020",format="%m/%d/%Y") # Date class전환을 위한 format 인식
format(x, format="%B %d, %Y, %A") # format 변환## [1] "December 31, 2020, Thursday"a <- Sys.time() # POSIXct class
a ## [1] "2020-05-20 05:01:48 KST"format(a,format="%B %d, %Y, %a") # format 변환## [1] "May 20, 2020, Wed"#locale 변경
Sys.setlocale("LC_ALL","Korean") # Korean으로 변경 ## [1] "LC_COLLATE=Korean_Korea.949;LC_CTYPE=Korean_Korea.949;LC_MONETARY=Korean_Korea.949;LC_NUMERIC=C;LC_TIME=Korean_Korea.949"format(a,format="%B %d, %Y, %a") # format 변환## [1] "5월 20, 2020, 수"moon <- as.POSIXct("1969/07/20, 20:17:39", format="%Y/%m/%d, %H:%M:%S", tz="UTC")
moon## [1] "1969-07-20 20:17:39 UTC"format(moon, "The time of the Apollo moon landing was %Y-%b-%d, at %H:%M:%S.")## [1] "The time of the Apollo moon landing was 1969-7-20, at 20:17:39."format(moon, "인류 최초의 달 착륙은 %Y년 %m월 %d일, %H시 %M분 %S초에 이루어졌다")## [1] "<U+C778><U+B958> <U+CD5C><U+CD08><U+C758> <U+B2EC> <U+CC29><U+B959><U+C740> 1969<U+B144> 07<U+C6D4> 20<U+C77C>, 20<U+C2DC> 17<U+BD84> 39<U+CD08><U+C5D0> <U+C774><U+B8E8><U+C5B4><U+C84C><U+B2E4>"