R Notebook

ggplot2에 내장된 샘플데이터 mpg 정형화

#table()
table(df.exam$mean)
library(ggplot2)
ggplot2::qplot(df.exam$test)
df.exam$class <- ifelse(df.exam$mean>=80,"A",
                    ifelse(df.exam$mean>=70,"B","C")
                    )
df.exam
ggplot2::qplot(df.exam$)class

####4함수::head ,tail, str ,summary
head(df.mpg)
tail(df.mpg)
str(df.mpg)
summary(df.mpg)
#변수명 수정 
df.mpg %>%   #ctrl+shift+m 파이프라이
  data.table::setnames(
    old = "manufacturer","model","displ","year","cyl ","trans","drv","cty","hwy","fl","class",
    new="제조회사","자동차모델","배기량","생산연도","실린더 개수","변속기 종류","구동방식"  ,"도시연비 ","고속도로 연비","연료종류","자동차 종류"
  )
df.mpg

# 파생변수 생성 
df.mpg$total <-(df.mpg$cty+df.mpg$hwy) 
df.mpg
df.mpg$mean <- (df.mpg$total)/2
df.mpg
df.mpg$test <- ifelse(df.mpg$total>=40, "pass","fail")
df.mpg

#빈도 확인
table(df.mpg$test)
library(ggplot2)
ggplot2::qplot(df.mpg$test)


#####df.midwest
library(ggplot2)
df.midwest <- as.data.frame(ggplot2::midwest)
df.midwest
head(df.midwest)
tail(df.midwest)
str(df.midwest)
summary(df.midwest)

#변수 이름 수정 하기 

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

# 파생변수 생성 

df.midwest$aa <- (df.midwest$popasian/df.midwest$poptotal)*100
df.midwest
hist(df.midwest$aa)
mean(df.midwest$aa)
df.midwest$test <- ifelse(df.midwest$aa>0.4872462,"large","small")
df.midwest