R, Python 분석과 프로그래밍의 친구 (by R Friend)

 R 데이터 변환 : (4) 개수 축소 (Sampling)

> sample(1:10, 5, replace = FALSE) # 비복원추출
[1] 9 6 5 7 3

> 
> sample(1:10, 5, replace = TRUE) # 복원추출
[1] 9 3 3 2 3

> sample(1:10, 5, replace = TRUE)
[1] 10  6  9  7 10
> sample(1:10, 5, replace = TRUE)
[1] 1 4 1 4 3

> library(MASS)
> dim(Cars93)
[1] 93 27

> 
> sim_ran_sam <- sample(1:nrow(Cars93), 5)
> Cars93_srs <- Cars93[sim_ran_sam, ]
> dim(Cars93_srs)
[1]  5 27
 
 

> ## data.table 패키지, sampling 패키지 설치 및 호출

> install.packages("data.table")

> install.packages("sampling")
> require(data.table)
> require(sampling)

> set.seed(1)
> n <- 1000
> d.t <- data.table(gender = rbinom(n, 1 , .5),
+                   age = sample(1:5, n, replace=TRUE), 
+                   rebuy_yn = rbinom(n, 1, .2))
 
 
 

> ## Key 색인 지정, 정렬
> setkey(d.t, gender, age)
>
 
 
 
 
> ## 성, 연령대 계층(stratum) 별로 모집단 원소 수 (총 1,000명)
> d.t[ , .N, keyby = list(gender, age)]
    gender age   N
 1:      0   1 113
 2:      0   2 108
 3:      0   3  93
 4:      0   4 106
 5:      0   5 100
 6:      1   1 115
 7:      1   2  86
 8:      1   3  96
 9:      1   4  73
10:      1   5 110

> ## 성별, 연령대 계층별 각 20명씩 층화 임화 추출 
> set.seed(2)
> samp <- data.table(strata(d.t, c("gender", "age"), rep(20, 10), "srswor"))
> 
 
 

> ## 성별, 연령대 계층별 각 표본 개수 (각 20명 씩 표본 추출)
> samp[ , .N, keyby = list(gender, age)]
    gender age  N
 1:      0   1 20
 2:      0   2 20
 3:      0   3 20
 4:      0   4 20
 5:      0   5 20
 6:      1   1 20
 7:      1   2 20
 8:      1   3 20
 9:      1   4 20
10:      1   5 20

> help(strata)

 R 데이터 변환 (3) 범주화 : 이산형화(discretization)

> library(MASS)

> str(Cars93)
'data.frame':	93 obs. of  27 variables:
 $ Manufacturer      : Factor w/ 32 levels "Acura","Audi",..: 1 1 2 2 3 4 4 4 4 5 ...
 $ Model             : Factor w/ 93 levels "100","190E","240",..: 49 56 9 1 6 24 54 74 73 35 ...
 $ Type              : Factor w/ 6 levels "Compact","Large",..: 4 3 1 3 3 3 2 2 3 2 ...
 $ Min.Price         : num  12.9 29.2 25.9 30.8 23.7 14.2 19.9 22.6 26.3 33 ...
 $ Price             : num  15.9 33.9 29.1 37.7 30 15.7 20.8 23.7 26.3 34.7 ...
 $ Max.Price         : num  18.8 38.7 32.3 44.6 36.2 17.3 21.7 24.9 26.3 36.3 ...
 $ MPG.city          : int  25 18 20 19 22 22 19 16 19 16 ...
 $ MPG.highway       : int  31 25 26 26 30 31 28 25 27 25 ...
 $ AirBags           : Factor w/ 3 levels "Driver & Passenger",..: 3 1 2 1 2 2 2 2 2 2 ...
 $ DriveTrain        : Factor w/ 3 levels "4WD","Front",..: 2 2 2 2 3 2 2 3 2 2 ...
 $ Cylinders         : Factor w/ 6 levels "3","4","5","6",..: 2 4 4 4 2 2 4 4 4 5 ...
 $ EngineSize        : num  1.8 3.2 2.8 2.8 3.5 2.2 3.8 5.7 3.8 4.9 ...
 $ Horsepower        : int  140 200 172 172 208 110 170 180 170 200 ...
 $ RPM               : int  6300 5500 5500 5500 5700 5200 4800 4000 4800 4100 ...
 $ Rev.per.mile      : int  2890 2335 2280 2535 2545 2565 1570 1320 1690 1510 ...
 $ Man.trans.avail   : Factor w/ 2 levels "No","Yes": 2 2 2 2 2 1 1 1 1 1 ...
 $ Fuel.tank.capacity: num  13.2 18 16.9 21.1 21.1 16.4 18 23 18.8 18 ...
 $ Passengers        : int  5 5 5 6 4 6 6 6 5 6 ...
 $ Length            : int  177 195 180 193 186 189 200 216 198 206 ...
 $ Wheelbase         : int  102 115 102 106 109 105 111 116 108 114 ...
 $ Width             : int  68 71 67 70 69 69 74 78 73 73 ...
 $ Turn.circle       : int  37 38 37 37 39 41 42 45 41 43 ...
 $ Rear.seat.room    : num  26.5 30 28 31 27 28 30.5 30.5 26.5 35 ...
 $ Luggage.room      : int  11 15 14 17 13 16 17 21 14 18 ...
 $ Weight            : int  2705 3560 3375 3405 3640 2880 3470 4105 3495 3620 ...
 $ Origin            : Factor w/ 2 levels "USA","non-USA": 2 2 2 2 2 1 1 1 1 1 ...
 $ Make              : Factor w/ 93 levels "Acura Integra",..: 1 2 4 3 5 6 7 9 8 10 ..
 
> ## 고속도로연비(MPG.highway) 히스토그램
> hist(Cars93$MPG.highway)
 
 
 
> ## Model, MPG.highway 두 개 변수만 선택해서 disc_1 데이터 프레임 생성
> disc_1 <- Cars93[,c("Model", "MPG.highway")]
> ## 상위 6개 미리보기
> head(disc_1)
    Model MPG.highway
1 Integra          31
2  Legend          25
3      90          26
4     100          26
5    535i          30
6 Century          31
> 
> 
> ## 6개 범주로 등간격 범주화
 
 
> disc_1 <- within( disc_1, {
+   MPG.highway_cd = character(0)
+   MPG.highway_cd[ MPG.highway >=20 & MPG.highway <25 ] = "20~25"
+   MPG.highway_cd[ MPG.highway >=25 & MPG.highway <30 ] = "25~30"
+   MPG.highway_cd[ MPG.highway >=30 & MPG.highway <35 ] = "30~35"
+   MPG.highway_cd[ MPG.highway >=35 & MPG.highway <40 ] = "35~40"
+   MPG.highway_cd[ MPG.highway >=40 & MPG.highway <45 ] = "40~45"
+   MPG.highway_cd[ MPG.highway >=45 & MPG.highway <=50 ] = "45~50"
+   MPG.highway_cd = factor(MPG.highway_cd, 
+                           level = c("20~25", "25~30", "30~35", 
+                                     "35~40", "40~45", "45~50"))
+   })
> 
> ## 상위 6개 보기
> head(disc_1)
    Model MPG.highway MPG.highway_cd
1 Integra          31          30~35
2  Legend          25          25~30
3      90          26          25~30
4     100          26          25~30
5    535i          30          30~35
6 Century          31          30~35
 
 
 
> attributes(disc_1$MPG.highway_cd)
$levels
[1] "20~25" "25~30" "30~35" "35~40" "40~45" "45~50"

$class
[1] "factor"
 
 
> table(disc_1$MPG.highway_cd) # 분할표 생성

 
20~25 25~30 30~35 35~40 40~45 45~50 
   14    41    27     7     2     2

> summary(disc_1$MPG.highway)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  20.00   26.00   28.00   29.09   31.00   50.00

> 
> # 4분위수의 1Q, 2Q, 3Q, 4Q를 기준으로 4개의 범주 생성
> disc_1 <- within( disc_1, {
+   MPG.highway_cd2 = character(0)
+   MPG.highway_cd2[ MPG.highway <  quantile(MPG.highway, 0.25) ] = "1Q"
+   MPG.highway_cd2[ MPG.highway >= quantile(MPG.highway, 0.25) 
+                    & MPG.highway < quantile(MPG.highway, 0.50) ] = "2Q"
+   MPG.highway_cd2[ MPG.highway >=quantile(MPG.highway, 0.50) 
+                    & MPG.highway < quantile(MPG.highway, 0.75) ] = "3Q"
+   MPG.highway_cd2[ MPG.highway >= quantile(MPG.highway, 0.75) ] = "4Q"
+   MPG.highway_cd2 = factor(MPG.highway_cd2, 
+                           level = c("1Q", "2Q", "3Q", "4Q"))
+ })
> 
> # 상위 6개 보기
> head(disc_1)
    Model MPG.highway MPG.highway_cd MPG.highway_cd2
1 Integra          31          30~35              4Q
2  Legend          25          25~30              1Q
3      90          26          25~30              2Q
4     100          26          25~30              2Q
5    535i          30          30~35              3Q
6 Century          31          30~35              4Q
 
 
 
> table(disc_1$MPG.highway_cd2)  # 분할표 생성

1Q 2Q 3Q 4Q 
22 17 25 29 

> ## 고속도로연비(MPG.highway) 기준으로 오름차순 정렬

> disc_1 <- disc_1[order(disc_1$MPG.highway), ]

> dim(disc_1) # 93개 관측치, 4개 변수
[1] 93  4

## 관측치 개수

> dim(disc_1)[1]
[1] 93

> 
> disc_1$N <- seq(1:length(disc_1$MPG.highway)) # 1~93까지 순서대로 1씩 증가하는 N이라는 변수 생성
> 
> # 동일 frequency (23개)로 4개 범주 생성
> disc_1 <- within( disc_1, {
+   MPG.highway_cd3 = character(0)
+   MPG.highway_cd3[ N <= 23 ] = "1st_Freq"
+   MPG.highway_cd3[ N >= 24 & N <= 46 ] = "2nd_Freq"
+   MPG.highway_cd3[ N >= 47 & N <= 69 ] = "3rd_Freq"
+   MPG.highway_cd3[ N >= 70 ] = "4th_Freq"
+   MPG.highway_cd3 = factor(MPG.highway_cd3, 
+                            level = c("1st_Freq", "2nd_Freq", "3rd_Freq", "4th_Freq"))
+ })
> 
> head(disc_1)
      Model MPG.highway MPG.highway_cd MPG.highway_cd2 N MPG.highway_cd3
17    Astro          20          20~25              1Q 1        1st_Freq
36 Aerostar          20          20~25              1Q 2        1st_Freq
26  Caravan          21          20~25              1Q 3        1st_Freq
89  Eurovan          21          20~25              1Q 4        1st_Freq
48      Q45          22          20~25              1Q 5        1st_Freq
87   Previa          22          20~25              1Q 6        1st_Freq
 
 
 
 
>
 
 
 
> table(disc_1$MPG.highway_cd3)

1st_Freq 2nd_Freq 3rd_Freq 4th_Freq 
      23       23       23       24

데이터 변환 (1) 표준화 

> ## 한국인, 부시맨 각 성인 1000명 키 데이터 생성
> height_korean <- rnorm(n=1000, mean = 170, sd = 10) 
> height_bushman <- rnorm(n=1000, mean = 150, sd = 8)
> 
> height <- data.frame(height_korean, height_bushman) # 데이터 프레임 생성
> rm(height_korean, height_bushman) # 벡터 삭제
> 
> head(height) # 상위 6개 데이터 확인
  height_korean height_bushman
1      162.7654       132.5271
2      180.5701       135.5497
3      172.6752       142.5168
4      171.8035       156.7872
5      186.5258       154.3027
6      171.4634       156.1118 

> ## 한국인, 부시맨 키 히스토그램
> attach(height)
> par( mfrow = c(1,2))
> hist(height_korean, freq = TRUE, main = "한국인 키 빈도 히스토그램")
> hist(height_korean, freq = FALSE, main = "한국인 키 확률밀도함수 그래프")
> 
 
 

> hist(height_bushman, freq = TRUE, main = "부시맨 키 빈도 히스토그램")
> hist(height_bushman, freq = FALSE, main = "부시맨 키 확률밀도함수 그래프")
 
 

> detach(height)

> ## a. scale() 함수
> 
> height <- transform(height, 
+                     z.height_korean = scale(height_korean), 
+                     z.height_bushman = scale(height_bushman)
+                     )
> 
> head(height)
  height_korean height_bushman z.height_korean z.height_bushman
1        179.19         140.60         0.89308         -1.18393
2        164.54         152.70        -0.60892          0.35689
3        184.18         136.76         1.40477         -1.67426
4        196.37         144.26         2.65531         -0.71833
5        162.61         155.72        -0.80706          0.74198
6        158.02         147.19        -1.27775         -0.34510

> ## b. z=(x-mean(x))/sd(x)
> height <- transform(height, 
+                     z2.height_korean = (height_korean - mean(height_korean))/sd(height_korean), 
+                     z2.height_bushman = (height_bushman - mean(height_bushman))/sd(height_bushman)
+                     )
> 
> head(height)
  height_korean height_bushman z.height_korean z.height_bushman z2.height_korean z2.height_bushman
1        179.19         140.60         0.89308         -1.18393          0.89308          -1.18393
2        164.54         152.70        -0.60892          0.35689         -0.60892           0.35689
3        184.18         136.76         1.40477         -1.67426          1.40477          -1.67426
4        196.37         144.26         2.65531         -0.71833          2.65531          -0.71833
5        162.61         155.72        -0.80706          0.74198         -0.80706           0.74198
6        158.02         147.19        -1.27775         -0.34510         -1.27775          -0.34510 

> hist(height$z.height_korean, freq=TRUE, main="standized freq. of Korean H")
> hist(height$z.height_bushman, freq=TRUE, main="standized  freq. of Bushman H ")

> ## [0-1] transformation
> height <- height[,c(1:2)]
> library(reshape)
> height <- rename(height, c(height_korean = "h_kor", height_bushman = "h_bush"))
> head(height)
   h_kor h_bush
1 179.19 140.60
2 164.54 152.70
3 184.18 136.76
4 196.37 144.26
5 162.61 155.72
6 158.02 147.19

> height <- transform(height, 
+                     h_kor_01 = (h_kor - min(h_kor))/(max(h_kor) - min(h_kor)), 
+                     h_bush_01 = (h_bush - min(h_bush))/(max(h_bush) - min(h_bush))
+                     )
> 
> head(height)
   h_kor h_bush h_kor_01 h_bush_01
1 179.19 140.60  0.64341   0.27053
2 164.54 152.70  0.41760   0.51072
3 184.18 136.76  0.72034   0.19410
4 196.37 144.26  0.90835   0.34311
5 162.61 155.72  0.38781   0.57074
6 158.02 147.19  0.31705   0.40129
> 
> hist(height$h_kor_01)
> hist(height$h_bush_01)

[0-1] 변환 예시 (한국 남성 166cm, 부시맨 남성 156cm) 

 R 데이터 프레임 결합 : rbind(), cbind(), merge()

 R 벡터, 데이터 프레임 정렬 : sort(), order()

> v1 <- c(40, 30, 50, 50, 90, 40, 50)
> v2 <- c(5100, 6500, 2000, 2000, 9000, 4500, 3000)
> v3 <- c("A", "B", "A", "B", "A", "A", "B")
> v123 <- data.frame(v1, v2, v3)
> v123
  v1   v2 v3
1 40 5100  A
2 30 6500  B
3 50 2000  A
4 50 2000  B
5 90 9000  A
6 40 4500  A
7 50 3000  B

벡터의 정렬

> v1
[1] 40 30 50 50 90 40 50
> 
> sort(v1) # 오름차순 정렬
[1] 30 40 40 50 50 50 90
> 
> sort(v1, decreasing = TRUE) # 내림차순 정렬
[1] 90 50 50 50 40 40 30

> v1
[1] 40 30 50 50 90 40 50
> 
> order(v1)
[1] 2 1 6 3 4 7 5
> 
> v1[ order(v1) ]  # sort(v1)과 결과 동일
[1] 30 40 40 50 50 50 90

> rm(v1, v2, v3) # 벡터 v1, v2, v3 제거
> attach(v123) # 데이터 프레임 활성화

> 
> # v123 데이터 프레임의 전체 행을 v1 오름차순, v2 내림차순, v3 오름차순의 순서대로 정렬
> v123_order <- v123[ order(v1, -v2, v3), ]
> 
> v123  # 원래 데이터셋
  v1   v2 v3
1 40 5100  A
2 30 6500  B
3 50 2000  A
4 50 2000  B
5 90 9000  A
6 40 4500  A
7 50 3000  B
> 
> v123_order  # 정렬된 후의 데이터 셋
  v1   v2 v3
2 30 6500  B
1 40 5100  A
6 40 4500  A
7 50 3000  B
3 50 2000  A
4 50 2000  B
5 90 9000  A
> 
> detach(v123) 

> order(v1, -v2, v3)
[1] 2 1 6 7 3 4 5
> 
> row.names(v123_order)
[1] "2" "1" "6" "7" "3" "4" "5" 

> library(plyr)

> arrange(v123, v1, desc(v2), v3)

  v1   v2 v3

1 30 6500  B

2 40 5100  A

3 40 4500  A

4 50 3000  B

5 50 2000  A

6 50 2000  B

7 90 9000  A 

> help(mtcars)

mtcars

Format

A data frame with 32 observations on 11 variables.

Source

Henderson and Velleman (1981), Building multiple regression models interactively. Biometrics, 37, 391–411.

> str(mtcars)
'data.frame':	32 obs. of  11 variables:
 $ mpg : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
 $ cyl : num  6 6 4 6 8 6 8 4 4 6 ...
 $ disp: num  160 160 108 258 360 ...
 $ hp  : num  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  : num  0 0 1 1 0 1 0 1 1 1 ...
 $ am  : num  1 1 1 0 0 0 0 0 0 0 ...
 $ gear: num  4 4 4 3 3 3 3 4 4 4 ...
 $ carb: num  4 4 1 1 2 1 4 2 2 4 ...

> 
> head(mtcars)
                   mpg cyl disp  hp drat    wt  qsec vs am gear carb
Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

(1) indexing & which() 함수를 활용한 특정 조건을 만족하는 변수, 관측치 선택

> attach(mtcars)
> 
> # (a) 변속기가 자동이고 & 실린더가 4개, 6개인 자동차의 연비, 실린더, 자동/수동 변수 선별
> mtcars_mart_0 <- mtcars[ which( am == 0 & cyl %in% c(4, 6)), c("mpg", "cyl", "am")]
> mtcars_mart_0
                mpg cyl am
Hornet 4 Drive 21.4   6  0
Valiant        18.1   6  0
Merc 240D      24.4   4  0
Merc 230       22.8   4  0
Merc 280       19.2   6  0
Merc 280C      17.8   6  0
Toyota Corona  21.5   4  0
> 
> mean(mtcars_mart_0$mpg)
[1] 20.74286
> # (b) 변속기가 수동이고 & 실린더가 4개, 6개인 자동차의 연비, 실린더, 자동/수동 변수 선별
> mtcars_mart_1 <- mtcars[ which( am == 1 & cyl %in% c(4, 6)), c("mpg", "cyl", "am")]
> mtcars_mart_1
                mpg cyl am
Mazda RX4      21.0   6  1
Mazda RX4 Wag  21.0   6  1
Datsun 710     22.8   4  1
Fiat 128       32.4   4  1
Honda Civic    30.4   4  1
Toyota Corolla 33.9   4  1
Fiat X1-9      27.3   4  1
Porsche 914-2  26.0   4  1
Lotus Europa   30.4   4  1
Ferrari Dino   19.7   6  1
Volvo 142E     21.4   4  1
> 
> mean(mtcars_mart_1$mpg)
[1] 26.02727
> 
> detach(mtcars)

> mtcars_mart_9 <- mtcars[ which( am == 0 & cyl %in% c(4, 6)), c(1, 2, 9)]
> mtcars_mart_9
                mpg cyl am
Hornet 4 Drive 21.4   6  0
Valiant        18.1   6  0
Merc 240D      24.4   4  0
Merc 230       22.8   4  0
Merc 280       19.2   6  0
Merc 280C      17.8   6  0
Toyota Corona  21.5   4  0

 (2) subset(Data 이름, select = c(변수명), subset = (선별 조건)) 변수, 관측치 선택

> # (a) 변속기가 자동이고 & 실린더가 4개 or 6개인 자동차의 연비, 실린더, 자동/수동 변수 선별
> mtcars_subset_0  <- subset(mtcars, 
+                            select = c(mpg, cyl, am), 
+                            subset = (am == 0 & cyl %in% c(4, 6)))
> mtcars_subset_0
                mpg cyl am
Hornet 4 Drive 21.4   6  0
Valiant        18.1   6  0
Merc 240D      24.4   4  0
Merc 230       22.8   4  0
Merc 280       19.2   6  0
Merc 280C      17.8   6  0
Toyota Corona  21.5   4  0
> mean(mtcars_subset_0$mpg)
[1] 20.74286
> 
> # %in% 대신 수직바 '|' (or) 를 써서 할 수도 있음
> subset(mtcars, 
+        select = c(mpg, cyl, am), 
+        subset = ((am == 0 & cyl == 4) | (am == 0 & cyl == 6)))
                mpg cyl am
Hornet 4 Drive 21.4   6  0
Valiant        18.1   6  0
Merc 240D      24.4   4  0
Merc 230       22.8   4  0
Merc 280       19.2   6  0
Merc 280C      17.8   6  0
Toyota Corona  21.5   4  0
> 
> 
> # (b) 변속기가 수동이고 & 실린더가 4개 or 6개인 자동차의 연비, 실린더, 자동/수동 변수 선별
> mtcars_subset_1  <- subset(mtcars, 
+                            select = c(mpg, cyl, am), 
+                            subset = (am == 1 & cyl %in% c(4, 6)))
> mtcars_subset_1
                mpg cyl am
Mazda RX4      21.0   6  1
Mazda RX4 Wag  21.0   6  1
Datsun 710     22.8   4  1
Fiat 128       32.4   4  1
Honda Civic    30.4   4  1
Toyota Corolla 33.9   4  1
Fiat X1-9      27.3   4  1
Porsche 914-2  26.0   4  1
Lotus Europa   30.4   4  1
Ferrari Dino   19.7   6  1
Volvo 142E     21.4   4  1
> mean(mtcars_subset_1$mpg)
[1] 26.02727

> # 연속 선택 : c(1:5)
> mtcars_subset_1_5 <- subset(mtcars, 
+                           select = c(1:5)
+                           )
> 
> head(mtcars_subset_1_5)
                   mpg cyl disp  hp drat
Mazda RX4         21.0   6  160 110 3.90
Mazda RX4 Wag     21.0   6  160 110 3.90
Datsun 710        22.8   4  108  93 3.85
Hornet 4 Drive    21.4   6  258 110 3.08
Hornet Sportabout 18.7   8  360 175 3.15
Valiant           18.1   6  225 105 2.76
> 
> # 제외 : -c()
> mtcars_subset_6_11 <- subset(mtcars, 
+                              select = -c(1:5)
+                              )
> 
> head(mtcars_subset_6_11)
                     wt  qsec vs am gear carb
Mazda RX4         2.620 16.46  0  1    4    4
Mazda RX4 Wag     2.875 17.02  0  1    4    4
Datsun 710        2.320 18.61  1  1    4    1
Hornet 4 Drive    3.215 19.44  1  0    3    1
Hornet Sportabout 3.440 17.02  0  0    3    2
Valiant           3.460 20.22  1  0    3    1

(3) dplyr 패키지의 select() 로 변수 선택, filter() 로 조건에 맞는 관측치 선택, 

     summarize() 요약 통계량 계산

> install.packages("dplyr")

> library(dplyr)

> # (a) 변속기가 자동(am == 0)이고 & 실린더가 4개 or 6개인 자동차의 평균 연비

> mtcars %>% select(mpg, cyl, am) %>% filter(am == 0 & cyl %in% c(4, 6))

   mpg cyl am

1 21.4   6  0

2 18.1   6  0

3 24.4   4  0

4 22.8   4  0

5 19.2   6  0

6 17.8   6  0

7 21.5   4  0

> 

> mtcars %>% select(mpg, cyl, am) %>% filter(am == 0 & cyl %in% c(4, 6)) %>% summarise(mean(mpg))

  mean(mpg)

1  20.74286

> 

> # (b) 변속기가 수동(am == 1)이고 & 실린더가 4개 or 6개인 자동차의 평균 연비

> mtcars %>% select(mpg, cyl, am) %>% filter(am == 1 & cyl %in% c(4, 6))

    mpg cyl am

1  21.0   6  1

2  21.0   6  1

3  22.8   4  1

4  32.4   4  1

5  30.4   4  1

6  33.9   4  1

7  27.3   4  1

8  26.0   4  1

9  30.4   4  1

10 19.7   6  1

11 21.4   4  1

> 

> mtcars %>% select(mpg, cyl, am) %>% filter(am == 1 & cyl %in% c(4, 6)) %>% summarise(mean(mpg))

  mean(mpg)

1  26.02727

 R 데이터 프레임 신규 변수 생성 : dataframe$variable, transform()

> height <- c(175, 159, 166, 189, 171, 173, 179, 167, 182, 170)
> weight <- c(62, 55, 59, 75, 61, 64, 63, 65, 70, 60)
> h_w_d.f <- data.frame(height, weight)
> h_w_d.f
   height weight
1     175     62
2     159     55
3     166     59
4     189     75
5     171     61
6     173     64
7     179     63
8     167     65
9     182     70
10    170     60

> options(digits=4)  # 숫자 개수 지정해주는 옵션. 이거 지정 안해주면 소숫점 5~6자리까지 나옴
> h_w_d.f$bmi_1 <- h_w_d.f$weight/(h_w_d.f$height/100)^2
> h_w_d.f
   height weight bmi_1
1     175     62 20.24
2     159     55 21.76
3     166     59 21.41
4     189     75 21.00
5     171     61 20.86
6     173     64 21.38
7     179     63 19.66
8     167     65 23.31
9     182     70 21.13
10    170     60 20.76

> ## transform()
> h_w_d.f <- transform(h_w_d.f, 
+                      bmi_2 = weight/(height/100)^2)
> 
> h_w_d.f
   height weight bmi_1 bmi_2
1     175     62 20.24 20.24
2     159     55 21.76 21.76
3     166     59 21.41 21.41
4     189     75 21.00 21.00
5     171     61 20.86 20.86
6     173     64 21.38 21.38
7     179     63 19.66 19.66
8     167     65 23.31 23.31
9     182     70 21.13 21.13
10    170     60 20.76 20.76

> options(digits=3)
> h_w_d.f <- transform(h_w_d.f, 
+                      bmi_sqrt = sqrt(bmi_2), 
+                      bmi_log10 = log10(bmi_2)
+                      )

> View(h_w_d.f)

 데이터 프레임 변수명 변경 names(), rename()

> ## 데이터 프레임 변수명 변경 rename()
> library(MASS)
> # Cars93 데이터 프레임 내 변수명 확인
> names(Cars93)
 [1] "Manufacturer"       "Model"              "Type"               "Min.Price"          "Price"             
 [6] "Max.Price"          "MPG.city"           "MPG.highway"        "AirBags"            "DriveTrain"        
[11] "Cylinders"          "EngineSize"         "Horsepower"         "RPM"                "Rev.per.mile"      
[16] "Man.trans.avail"    "Fuel.tank.capacity" "Passengers"         "Length"             "Wheelbase"         
[21] "Width"              "Turn.circle"        "Rear.seat.room"     "Luggage.room"       "Weight"            
[26] "Origin"             "Make"              
> 

> 
> Cars93 데이터 프레임의 1~5번째 변수만 선택한 후 names()로 변수명 변경
> Cars93_subset <- Cars93[,c(1:5)]
> names(Cars93_subset)
[1] "Manufacturer" "Model"        "Type"         "Min.Price"    "Price"       
> 

> names(Cars93_subset) <- c("V1", "V2", "V3", "V4", "V5")
> names(Cars93_subset)
[1] "V1" "V2" "V3" "V4" "V5"

> # rename() 
> install.packages("reshape")

> library(reshape)
> 
> Cars93_subset <- rename(Cars93_subset, 
+                         c(V1 = "V1_Manufacturer", 
+                           V2 = "V2_Model", 
+                           V3 = "V3_Type", 
+                           V4 = "V4_Min.Price", 
+                           V5 = "V5_Price"))
 
 

> install.packages("plyr")

> library(plyr)
> Cars93_subset <- rename(Cars93_subset, 
+                         c("V1_Manufacturer" = "Manufacturer", 
+                           "V2_Model" = "Model", 
+                           "V3_Type" = "Type", 
+                           "V4_Min.Price" = "Min.Price", 
+                           "V5_Price" = "Price"))
> View(Cars93_subset)
 
 

# dplyr package, rename(dataframe, new_var1 = old_var1, new_var2 = old_var2, ...)
install.packages("dplyr")
library(dplyr) 

> Cars93_2 <- Cars93[ ,c(1:3)]
> names(Cars93_2)
[1] "Manufacturer" "Model"        "Type"

> Cars93_3 <- rename(Cars93_2, 
+                    New_Manufacturer = Manufacturer,
+                    New_Model = Model, 
+                    New_Type = Type)
> 
> names(Cars93_3)
[1] "New_Manufacturer" "New_Model"        "New_Type"