R Notebook

ggplot2 에 내장된 샘플데이터 mpg 정형화

# package
library(ggplot2) # 이 파일로 불러오는 것 
df.mpg <- as.data.frame(ggplot2::mpg)

## 4함수 :: headm tail, str, summary
head(df.mpg)
tail(df.mpg)
str(df.mpg)
summary(df.mpg)


# 'data.frame': 234 obs. of  11 variables:
#  $ manufacturer(제조회사): chr  "audi" "audi" "audi" "audi" ...
#  $ model(모델)       : chr  "a4" "a4" "a4" "a4" ...
#  $ displ(배기량)       : num  1.8 1.8 2 2 2.8 2.8 3.1 1.8 1.8 2 ...
#  $ year(생산연도)        : int  1999 1999 2008 2008 1999 1999 2008 1999 1999 2008 ...
#  $ cyl(실린더 개수)         : int  4 4 4 4 6 6 6 4 4 4 ...
#  $ trans(변속기 종류)       : chr  "auto(l5)" "manual(m5)" "manual(m6)" "auto(av)" ...
#  $ drv(구동 방식)         : chr  "f" "f" "f" "f" ...
#  $ cty(도시 연비)         : int  18 21 20 21 16 18 18 18 16 20 ...
#  $ hwy(고속도로 연비)         : int  29 29 31 30 26 26 27 26 25 28 ...
#  $ fl(연료 종류)          : chr  "p" "p" "p" "p" ...
#  $ class(자동차 종류)       : chr  "compact" "compact" "compact" "compact" ...

# > summary(df.mpg)
#  manufacturer          model               displ            year     
#  Length:234         Length:234         Min.   :1.600   Min.   :1999  
#  Class :character   Class :character   1st Qu.:2.400   1st Qu.:1999  
#  Mode  :character   Mode  :character   Median :3.300   Median :2004  
#                                        Mean   :3.472   Mean   :2004  
#                                        3rd Qu.:4.600   3rd Qu.:2008  
#                                        Max.   :7.000   Max.   :2008  
#       cyl           trans               drv                 cty       
#  Min.   :4.000   Length:234         Length:234         Min.   : 9.00  
#  1st Qu.:4.000   Class :character   Class :character   1st Qu.:14.00  
#  Median :6.000   Mode  :character   Mode  :character   Median :17.00  
#  Mean   :5.889                                         Mean   :16.86  
#  3rd Qu.:8.000                                         3rd Qu.:19.00  
#  Max.   :8.000                                         Max.   :35.00  
#       hwy             fl               class          
#  Min.   :12.00   Length:234         Length:234        
#  1st Qu.:18.00   Class :character   Class :character  
#  Median :24.00   Mode  :character   Mode  :character  
#  Mean   :23.44                                        
#  3rd Qu.:27.00                                        
#  Max.   :44.00                       


library(ggplot2)
midwest <- as.data.frame(ggplot2::midwest)

head(midwest)


library(dplyr)
df.midwest %>% 
  data.table::setnames(old = "popasian", new = "asian")
df.midwest

midwest$ratio <- midwest$asian/midwest$total*100
hist(midwest$ratio)

mean(midwest$ratio)

midwest$group <- ifelse(midwest$ratio > 0.4872462, "large", "small")


table(midwest$group)

library(ggplot2)
qplot(midwest$group)