#48_140821_R_COUNT

# COUNT

 

l count를 위한 환경설정

1.     홈페이지 접속 http://www.oracle.com/technetwork/java/javase/downloads/jdk8-downloads-2133151.html   2.     windows x64 다운   3.     library 설치 install.packages("KoNLP") install.packages("wordcloud") install.packages("plyr") library(KoNLP) library(wordcloud) library(plyr)   4.     R 프로그램 다시 시작

 

 

n 예제 활용

> emp <- read.csv("emp.csv",header=TRUE) > count(emp$job)           x freq 1   ANALYST    2 2     CLERK    5 3   MANAGER    3 4 PRESIDENT    1 5  SALESMAN    4

useSejongDic() - 사전활용 mergeUserDic(data.frame(c('안철수', '박근혜', '문제인'), c('nqpc')))  #  추가 시키고 싶은 - 없는 단어 추가 nouns <- extractNoun(ahn)   - 단어단위로 추출 nouns <- nouns[nchar(nouns)>=2] - 2번 잇아 반복되는 단어를 변수에 담는다 cnouns <- count(nouns) - 단어의 개수를 센다 > cnouns                x freq 1             18    1 2             30    1 3       가계부채    1 4           가능    2 5         가능성    1 6           가장    1 7           가치    1 8           각자    1 9           감당    1 10          강력    1 11          개인    1   useSejongDic() mergeUserDic(data.frame(c('안철수', '박근혜', '문제인'), c('nqpc')))  #  추가 시키고 싶은 nouns <- extractNoun(ahn)   nouns <- nouns[nchar(nouns)>=2] cnouns <- count(nouns)   pal <- brewer.pal(6,"Dark2") pal <- pal[-(1)]   windowsFonts(malgun=windowsFont("맑은 고딕")) data.table(words=cnouns$x, freq=cnouns$freq)   wordcloud(words=cnouns$x, freq=cnouns$freq, colors=pal, min.freq=3,           random.order=F, family="malgun")