# ctrl+alt+i
getwd()
## [1] "D:/21. ADsP자격증/example"
# 디렉토리 옮겨지지 않음.
#setwd('C:/data')
getwd()
## [1] "D:/21. ADsP자격증/example"
# 위에서 6개 읽어오기
#head(iris)
# 밑에서 6개 읽어오기
#tail(iris)
df1<-read.csv("Data1.csv")
head(df1)
## Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 Q19 Q20 Gender
## 1 4 4 2 3 4 2 2 4 4 4 4 4 4 4 4 4 4 4 4 4 0
## 2 4 4 4 4 4 3 2 4 4 4 4 4 4 4 4 4 3 4 2 1 0
## 3 4 4 4 4 2 4 4 4 4 2 4 4 4 4 3 4 4 4 4 3 0
## 4 5 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 0
## 5 4 4 4 4 4 4 4 4 2 4 4 4 4 4 4 4 4 4 4 4 0
## 6 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 0
## EDU BF BM Happiness Peace
## 1 1 3.4 3.2 4.0 4.0
## 2 1 4.0 3.4 4.0 2.8
## 3 2 3.6 3.6 3.8 3.8
## 4 1 4.2 4.0 4.0 4.0
## 5 2 4.0 3.6 4.0 4.0
## 6 1 4.0 4.0 4.0 4.0
tail(df1)
## Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 Q19 Q20
## 1920 4 4 3 4 4 2 2 3 4 2 2 4 3 4 4 3 4 4 3 4
## 1921 2 2 2 1 2 2 2 2 2 2 1 3 2 1 3 2 2 2 2 2
## 1922 3 2 2 2 3 1 1 1 1 1 3 3 3 4 4 4 4 5 2 2
## 1923 5 4 4 4 4 2 2 2 2 3 3 4 3 4 3 3 3 4 4 4
## 1924 4 4 4 2 2 4 2 4 4 3 3 2 3 4 3 4 4 4 3 4
## 1925 3 3 1 1 2 1 1 1 1 1 4 4 3 2 2 3 4 4 3 2
## Gender EDU BF BM Happiness Peace
## 1920 1 3 3.8 2.6 3.4 3.6
## 1921 1 2 1.8 2.0 2.0 2.0
## 1922 0 2 2.4 1.0 3.4 3.4
## 1923 0 2 4.2 2.2 3.4 3.6
## 1924 1 2 3.2 3.4 3.0 3.8
## 1925 0 3 2.0 1.0 3.0 3.2
str(df1)
## 'data.frame': 1925 obs. of 26 variables:
## $ Q1 : int 4 4 4 5 4 4 4 4 4 4 ...
## $ Q2 : int 4 4 4 4 4 4 2 2 4 4 ...
## $ Q3 : int 2 4 4 4 4 4 4 4 4 2 ...
## $ Q4 : int 3 4 4 4 4 4 4 4 4 2 ...
## $ Q5 : int 4 4 2 4 4 4 4 4 2 4 ...
## $ Q6 : int 2 3 4 4 4 4 4 4 1 2 ...
## $ Q7 : int 2 2 4 4 4 4 4 4 3 4 ...
## $ Q8 : int 4 4 4 4 4 4 5 5 2 2 ...
## $ Q9 : int 4 4 4 4 2 4 5 5 3 4 ...
## $ Q10 : int 4 4 2 4 4 4 5 5 2 4 ...
## $ Q11 : int 4 4 4 4 4 4 5 5 4 4 ...
## $ Q12 : int 4 4 4 4 4 4 5 5 3 4 ...
## $ Q13 : int 4 4 4 4 4 4 5 5 4 4 ...
## $ Q14 : int 4 4 4 4 4 4 5 5 5 4 ...
## $ Q15 : int 4 4 3 4 4 4 4 2 3 4 ...
## $ Q16 : int 4 4 4 4 4 4 5 2 4 4 ...
## $ Q17 : int 4 3 4 4 4 4 2 2 4 4 ...
## $ Q18 : int 4 4 4 4 4 4 4 4 4 4 ...
## $ Q19 : int 4 2 4 4 4 4 4 2 4 2 ...
## $ Q20 : int 4 1 3 4 4 4 4 2 4 2 ...
## $ Gender : int 0 0 0 0 0 0 0 0 1 0 ...
## $ EDU : int 1 1 2 1 2 1 1 1 4 3 ...
## $ BF : num 3.4 4 3.6 4.2 4 4 3.6 3.6 3.6 3.2 ...
## $ BM : num 3.2 3.4 3.6 4 3.6 4 4.6 4.6 2.2 3.2 ...
## $ Happiness: num 4 4 3.8 4 4 4 4.8 4.4 3.8 4 ...
## $ Peace : num 4 2.8 3.8 4 4 4 3.8 2.4 4 3.2 ...
dim(df1)
## [1] 1925 26
# 객체 이름
ls(df1)
## [1] "BF" "BM" "EDU" "Gender" "Happiness" "Peace"
## [7] "Q1" "Q10" "Q11" "Q12" "Q13" "Q14"
## [13] "Q15" "Q16" "Q17" "Q18" "Q19" "Q2"
## [19] "Q20" "Q3" "Q4" "Q5" "Q6" "Q7"
## [25] "Q8" "Q9"
# 변수 모두 삭제
#rm(list = ls())
# 평균
mean(df1$Q10)
## [1] 2.882597
# 중앙값
median(df1$Q10)
## [1] 3
#분산
var(df1$Q10)
## [1] 0.8926544
#분위수
quantile(df1$Q10)
## 0% 25% 50% 75% 100%
## 1 2 3 4 5
#사분위수범위
IQR(df1$Q10)
## [1] 2
# 최소값(min), 최대값 (max), 평균(mean), 1사분위수(1st Qu,25%), 2사분위수(Median, 50%, 중위수), 3사분 위수(3rd Qu, 75%)통계량을 출력
summary(df1)
## Q1 Q2 Q3 Q4
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:2.000 1st Qu.:2.000
## Median :4.000 Median :3.000 Median :3.000 Median :3.000
## Mean :3.536 Mean :3.291 Mean :2.928 Mean :3.061
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## Q5 Q6 Q7 Q8
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000
## Median :3.000 Median :3.000 Median :3.000 Median :3.000
## Mean :3.041 Mean :2.796 Mean :3.086 Mean :3.049
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## Q9 Q10 Q11 Q12 Q13
## Min. :1.000 Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:3.00 1st Qu.:3.000 1st Qu.:3.000
## Median :3.000 Median :3.000 Median :4.00 Median :4.000 Median :4.000
## Mean :3.066 Mean :2.883 Mean :3.47 Mean :3.421 Mean :3.588
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.00 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.00 Max. :5.000 Max. :5.000
## Q14 Q15 Q16 Q17
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:3.000
## Median :4.000 Median :4.000 Median :4.000 Median :4.000
## Mean :3.716 Mean :3.542 Mean :3.791 Mean :3.516
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## Q18 Q19 Q20 Gender
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :0.0000
## 1st Qu.:4.000 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:0.0000
## Median :4.000 Median :3.000 Median :3.000 Median :0.0000
## Mean :3.804 Mean :3.364 Mean :3.349 Mean :0.4099
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:1.0000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :1.0000
## EDU BF BM Happiness
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.400
## 1st Qu.:2.000 1st Qu.:2.600 1st Qu.:2.400 1st Qu.:3.000
## Median :3.000 Median :3.200 Median :3.000 Median :3.600
## Mean :2.616 Mean :3.172 Mean :2.976 Mean :3.547
## 3rd Qu.:3.000 3rd Qu.:3.800 3rd Qu.:3.600 3rd Qu.:4.000
## Max. :4.000 Max. :5.000 Max. :5.000 Max. :5.000
## Peace
## Min. :1.200
## 1st Qu.:3.200
## Median :3.600
## Mean :3.564
## 3rd Qu.:4.000
## Max. :5.000
summary(df1$Q10)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 2.000 3.000 2.883 4.000 5.000
df2 = read.csv("mtcars.csv")
head(df2)
## X mpg cyl disp hp drat wt qsec vs am gear carb
## 1 Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## 2 Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## 3 Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## 4 Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## 5 Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## 6 Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
tail(df2)
## X mpg cyl disp hp drat wt qsec vs am gear carb
## 27 Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.7 0 1 5 2
## 28 Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.9 1 1 5 2
## 29 Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.5 0 1 5 4
## 30 Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.5 0 1 5 6
## 31 Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.6 0 1 5 8
## 32 Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.6 1 1 4 2
str(df2)
## 'data.frame': 32 obs. of 12 variables:
## $ X : chr "Mazda RX4" "Mazda RX4 Wag" "Datsun 710" "Hornet 4 Drive" ...
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : int 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : int 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : int 0 0 1 1 0 1 0 1 1 1 ...
## $ am : int 1 1 1 0 0 0 0 0 0 0 ...
## $ gear: int 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: int 4 4 1 1 2 1 4 2 2 4 ...
# 행, 열
dim(df2)
## [1] 32 12
# 평균
mean(df2$mpg)
## [1] 20.09062
# 중앙값
median(df2$mpg)
## [1] 19.2
#분산
var(df2$mpg)
## [1] 36.3241
#분위수
quantile(df2$mpg)
## 0% 25% 50% 75% 100%
## 10.400 15.425 19.200 22.800 33.900
#사분위수범위
IQR(df2$mpg)
## [1] 7.375
summary(df2)
## X mpg cyl disp
## Length:32 Min. :10.40 Min. :4.000 Min. : 71.1
## Class :character 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8
## Mode :character Median :19.20 Median :6.000 Median :196.3
## Mean :20.09 Mean :6.188 Mean :230.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0
## Max. :33.90 Max. :8.000 Max. :472.0
## hp drat wt qsec
## Min. : 52.0 Min. :2.760 Min. :1.513 Min. :14.50
## 1st Qu.: 96.5 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89
## Median :123.0 Median :3.695 Median :3.325 Median :17.71
## Mean :146.7 Mean :3.597 Mean :3.217 Mean :17.85
## 3rd Qu.:180.0 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90
## Max. :335.0 Max. :4.930 Max. :5.424 Max. :22.90
## vs am gear carb
## Min. :0.0000 Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4375 Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :1.0000 Max. :5.000 Max. :8.000
summary(df2$mpg)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.43 19.20 20.09 22.80 33.90