R (5)

Posted on In

Data 선택

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
> 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 ...
> attach(Cars93)
> a=Cars93[which(MPG.city>30),'Model'];a #MPG.city>30인 Model변수만 가져옴
[1] Festiva Metro   Civic   LeMans  Justy   Swift   Tercel 
93 Levels: 100 190E 240 300E 323 535i 626 850 90 900 Accord Achieva Aerostar Altima ... Vision
> b=Cars93[which(MPG.city>30),c('Model','Origin')];b
     Model  Origin
31 Festiva     USA
39   Metro non-USA
42   Civic non-USA
73  LeMans     USA
80   Justy non-USA
83   Swift non-USA
84  Tercel non-USA
> c=Cars93[which(MPG.city>30),c('Model','Origin','MPG.city')];c
     Model  Origin MPG.city
31 Festiva     USA       31
39   Metro non-USA       46
42   Civic non-USA       42
73  LeMans     USA       31
80   Justy non-USA       33
83   Swift non-USA       39
84  Tercel non-USA       32
> d=Cars93[which(MPG.city>30),];d #안치면 다나옴
   Manufacturer   Model  Type Min.Price Price Max.Price MPG.city MPG.highway     AirBags DriveTrain
31         Ford Festiva Small       6.9   7.4       7.9       31          33        None      Front
39          Geo   Metro Small       6.7   8.4      10.0       46          50        None      Front
42        Honda   Civic Small       8.4  12.1      15.8       42          46 Driver only      Front
73      Pontiac  LeMans Small       8.2   9.0       9.9       31          41        None      Front
80       Subaru   Justy Small       7.3   8.4       9.5       33          37        None        4WD
83       Suzuki   Swift Small       7.3   8.6      10.0       39          43        None      Front
84       Toyota  Tercel Small       7.8   9.8      11.8       32          37 Driver only      Front
   Cylinders EngineSize Horsepower  RPM Rev.per.mile Man.trans.avail Fuel.tank.capacity Passengers
31         4        1.3         63 5000         3150             Yes               10.0          4
39         3        1.0         55 5700         3755             Yes               10.6          4
42         4        1.5        102 5900         2650             Yes               11.9          4
73         4        1.6         74 5600         3130             Yes               13.2          4
80         3        1.2         73 5600         2875             Yes                9.2          4
83         3        1.3         70 6000         3360             Yes               10.6          4
84         4        1.5         82 5200         3505             Yes               11.9          5
   Length Wheelbase Width Turn.circle Rear.seat.room Luggage.room Weight  Origin           Make
31    141        90    63          33           26.0           12   1845     USA   Ford Festiva
39    151        93    63          34           27.5           10   1695 non-USA      Geo Metro
42    173       103    67          36           28.0           12   2350 non-USA    Honda Civic
73    177        99    66          35           25.5           17   2350     USA Pontiac LeMans
80    146        90    60          32           23.5           10   2045 non-USA   Subaru Justy
83    161        93    63          34           27.5           10   1965 non-USA   Suzuki Swift
84    162        94    65          36           24.0           11   2055 non-USA  Toyota Tercel
> e=Cars93[which(Cylinders==4&Manufacturer=='Hyundai'),c('Model','Min.Price','Max.Price')];e
     Model Min.Price Max.Price
44   Excel       6.8       9.2
45 Elantra       9.0      11.0
46  Scoupe       9.1      11.0
47  Sonata      12.4      15.3
  • Data 중 원하는 Data만 선택
  • Indexing 중요

subset()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
> subset(Cars93,select=Model,subset=(MPG.city>30))
     Model
31 Festiva
39   Metro
42   Civic
73  LeMans
80   Justy
83   Swift
84  Tercel
> subset(Cars93,select=c(Model,Min.Price,Max.Price))
            Model Min.Price Max.Price
1         Integra      12.9      18.8
2          Legend      29.2      38.7
3              90      25.9      32.3
4             100      30.8      44.6
5            535i      23.7      36.2
6         Century      14.2      17.3
7         LeSabre      19.9      21.7
8      Roadmaster      22.6      24.9
9         Riviera      26.3      26.3
10        DeVille      33.0      36.3
11        Seville      37.5      42.7
...
> subset(Cars93,select=c(Model,Min.Price,Max.Price),subset=(Cylinders==4&Manufacturer=='Hyundai'))
     Model Min.Price Max.Price
44   Excel       6.8       9.2
45 Elantra       9.0      11.0
46  Scoupe       9.1      11.0
47  Sonata      12.4      15.3
> subset(Cars93,c(Model,Min.Price,Max.Price),subset=(Cylinders==4&Manufacturer=='Hyundai')) #select= 없어도 됨 , subset= 필수
     Model Min.Price Max.Price
44   Excel       6.8       9.2
45 Elantra       9.0      11.0
46  Scoupe       9.1      11.0
47  Sonata      12.4      15.3
> y=subset(Cars93,select=-Model,subset=(Cylinders==4&Manufacturer=='Hyundai'));y #Model 빼고 다 가져옴
   Manufacturer    Type Min.Price Price Max.Price MPG.city MPG.highway AirBags DriveTrain Cylinders
44      Hyundai   Small       6.8   8.0       9.2       29          33    None      Front         4
45      Hyundai   Small       9.0  10.0      11.0       22          29    None      Front         4
46      Hyundai  Sporty       9.1  10.0      11.0       26          34    None      Front         4
47      Hyundai Midsize      12.4  13.9      15.3       20          27    None      Front         4
   EngineSize Horsepower  RPM Rev.per.mile Man.trans.avail Fuel.tank.capacity Passengers Length
44        1.5         81 5500         2710             Yes               11.9          5    168
45        1.8        124 6000         2745             Yes               13.7          5    172
46        1.5         92 5550         2540             Yes               11.9          4    166
47        2.0        128 6000         2335             Yes               17.2          5    184
   Wheelbase Width Turn.circle Rear.seat.room Luggage.room Weight  Origin            Make
44        94    63          35           26.0           11   2345 non-USA   Hyundai Excel
45        98    66          36           28.0           12   2620 non-USA Hyundai Elantra
46        94    64          34           23.5            9   2285 non-USA  Hyundai Scoupe
47       104    69          41           31.0           14   2885 non-USA  Hyundai Sonata
> subset(Cars93,select=c(Model,Max.Price)) #조건을 안주면 select만으로 가능
            Model Max.Price
1         Integra      18.8
2          Legend      38.7
3              90      32.3
4             100      44.6
5            535i      36.2
6         Century      17.3
7         LeSabre      21.7
8      Roadmaster      24.9
9         Riviera      26.3
10        DeVille      36.3
...
> subset(Cars93,c(Model,Max.Price),subset=T) #조건을 안주면 select만으로 가능
            Model Max.Price
1         Integra      18.8
2          Legend      38.7
3              90      32.3
4             100      44.6
5            535i      36.2
6         Century      17.3
7         LeSabre      21.7
8      Roadmaster      24.9
9         Riviera      26.3
10        DeVille      36.3
...
~~~~
***
# na.omit()

~~~R
> str(air)
'data.frame':	153 obs. of  6 variables:
 $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
 $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
 $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
 $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
 $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
 $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...
> air=na.omit(airquality)
> str(air)
'data.frame':	111 obs. of  6 variables:
 $ Ozone  : int  41 36 12 18 23 19 8 16 11 14 ...
 $ Solar.R: int  190 118 149 313 299 99 19 256 290 274 ...
 $ Wind   : num  7.4 8 12.6 11.5 8.6 13.8 20.1 9.7 9.2 10.9 ...
 $ Temp   : int  67 72 74 62 65 59 61 69 66 68 ...
 $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
 $ Day    : int  1 2 3 4 7 8 9 12 13 14 ...
 - attr(*, "na.action")= 'omit' Named int  5 6 10 11 25 26 27 32 33 34 ...
  ..- attr(*, "names")= chr  "5" "6" "10" "11" ...

sample()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
> air[sample(1:nrow(airquality),10),]
    Ozone Solar.R Wind Temp Month Day
52     NA     150  6.3   77     6  21
39     NA     273  6.9   87     6   8
91     64     253  7.4   83     7  30
77     48     260  6.9   81     7  16
15     18      65 13.2   58     5  15
146    36     139 10.3   81     9  23
60     NA      31 14.9   77     6  29
10     NA     194  8.6   69     5  10
114     9      36 14.3   72     8  22
94      9      24 13.8   81     8   2
> air[sample(1:nrow(airquality),2),]
    Ozone Solar.R Wind Temp Month Day
72     NA     139  8.6   82     7  11
135    21     259 15.5   76     9  12
> lotto=1:45
> r=lotto[sample(1:45,6)] #Vector이므로 ,없음
> r
[1] 38  3 28 36 18 32
  • nrow()는 행의 개수
  • 랜덤하게 뽑음(하지만 복원추출)

for문

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
> fac.x=1
> for(i in 1:5){
+ 	fac.x=fac.x*i
+ 	cat(i,'!=',fac.x,'\n',sep='')
+ }
1!=1
2!=2
3!=6
4!=24
5!=120
> x=5
> for(i in 1:9){
+ 	y=x*i
+ 	cat(x,'*',i,'=',y,'\n',sep='')
+ }
5*1=5
5*2=10
5*3=15
5*4=20
5*5=25
5*6=30
5*7=35
5*8=40
5*9=45
> for(i in 1:9){
+ 	for(j in 1:9){
+ 		a=i*j
+ 		cat(i,'*',j,'=',a,'\n',sep='')
+ 	}
+ }
1*1=1
1*2=2
1*3=3
...
9*7=63
9*8=72
9*9=81

for

while문

1
2
3
4
5
6
7
8
9
10
11
> fac.x=1;i=1
> while(i<=5){
+ 	fac.x=fac.x*i
+ 	cat(i,'!=',fac.x,'\n',sep='')
+ 	i=i+1
+ }
1!=1
2!=2
3!=6
4!=24
5!=120
  • F면 루프 나감

if문

1
2
3
4
5
6
7
8
9
10
11
12
> a2=1;a1=4;a0=3
> D=a1^2-4*a2*a0
> 
> if(D>0){
+ 	roots=c((-a1+sqrt(D))/(2*a2),(-a1-sqrt(D))/(2*a2))
+ }else if(D==0){
+ 	roots=-a1/(2*a2)
+ }else{
+ 	roots=c('No Root')
+ }
> roots
[1] -1 -3
  • if(){} 뒤에 바로 else if(){} or else{}

function

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
> rt=function(a2,a1,a0){
+ 	D=a1^2-4*a2*a0
+ 	if(D>0){
+ 		roots=c((-a1+sqrt(D))/(2*a2),(-a1-sqrt(D))/(2*a2))
+ 	}else if(D==0){
+ 		roots=-a1/(2*a2)
+ 	}else{
+ 		roots=c('No Root')
+ 	}
+ 	return(roots)
+ }
> rt(1,2,3)
[1] "No Root"
> fac=function(val){
+ 	out=1
+ 	if(val>0){
+ 		for(i in 1:val){
+ 			out=out*i
+ 		}
+ 	}else if(val==0){
+ 		out=1
+ 	}else{
+ 		out='error'
+ 	}
+ 	return(out)
+ }
> fac(-1)
[1] "error"
> fac(0)
[1] 1
> fac(5)
[1] 120

왜도(비대칭도)

확률 이론 및 통계학에서, 비대칭도(非對稱度, skewness) 또는 왜도(歪度)는 실수 값 확률 변수의 확률 분포 비대칭성을 나타내는 지표이다. 왜도의 값은 양수나 음수가 될 수 있으며 정의되지 않을 수도 있다. 왜도가 음수일 경우에는 확률밀도함수의 왼쪽 부분에 긴 꼬리를 가지며 중앙값을 포함한 자료가 오른쪽에 더 많이 분포해 있다. 왜도가 양수일 때는 확률밀도함수의 오른쪽 부분에 긴 꼬리를 가지며 자료가 왼쪽에 더 많이 분포해 있다는 것을 나타낸다. 평균과 중앙값이 같으면 왜도는 0이 된다.

skewness-1
skewness-2