ex_2

DF <- read.csv("example_cancer.csv")
str(DF)

## 'data.frame':    18310 obs. of  8 variables:
##  $ age            : int  75 52 67 62 70 76 55 72 64 71 ...
##  $ sex            : Factor w/ 2 levels "남","여": 1 2 2 1 1 2 1 1 1 1 ...
##  $ height         : Factor w/ 485 levels "100","130","130.2",..: 252 408 182 262 352 352 467 165 172 232 ...
##  $ weight         : Factor w/ 638 levels "100","101","101.1",..: 333 446 349 263 343 563 463 243 363 248 ...
##  $ dateOfoperation: Factor w/ 351 levels "2011-01-02","2011-01-03",..: 165 134 146 164 154 160 164 147 219 192 ...
##  $ cancerStaging  : Factor w/ 5 levels "I","II","III",..: 1 4 3 1 2 3 2 3 1 2 ...
##  $ hospitalization: int  48 17 10 11 10 10 12 18 15 35 ...
##  $ diseaseCode    : Factor w/ 13 levels "C18","C180","C181",..: 9 9 9 9 4 11 9 4 13 11 ...

#DF$age
DegreeOfAge <- table(cut(DF$age,breaks=(1:11)*10))
DegreeOfAge

## 
##   (10,20]   (20,30]   (30,40]   (40,50]   (50,60]   (60,70]   (70,80] 
##         3        77       482      1917      4558      5679      4598 
##   (80,90]  (90,100] (100,110] 
##       962        33         1

#cut(DF$age,breaks=(1:11)*10)
#cut 함수는 breaks 배열에 따라 범주별로 각 값이 어디에 속하는지로 치환하는 함수다. 
#구간별로 분포를 파악할 때 큰 도움이 됨.
#table 함수는 데이터프레임을 정리해서 group by 해줘서 보기 편하게 해줌. 



rownames(DegreeOfAge) <- paste((1:10)*10,"s",sep="")
DegreeOfAge

## 
##  10s  20s  30s  40s  50s  60s  70s  80s  90s 100s 
##    3   77  482 1917 4558 5679 4598  962   33    1

#rownames 는 헤더의 이름을 지정하는 함수 
#paste 는 문자열을 합치는 함수임. 배열이나 벡터에 적용하면 일괄로 적용됨. 

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 3.3.2

library(ggthemes)

## Warning: package 'ggthemes' was built under R version 3.3.2

ggplot(data=DF, aes(x=age)) + geom_freqpoly(binwidth=10,size=1.4,colour="orange")+theme_wsj()

?ggplot

## starting httpd help server ...

##  done

#<http://docs.ggplot2.org/current/> 여기에서 찾아볼것