R (4)

Posted on In

sink()

1
2
3
4
5
6
7
8
setwd("/Users/zerohertz/RData")
air=airquality
str(air)
attach(air)
sink('output.txt') #콘솔창 결과를 외부 파일로 저장
mean(Temp)
sd(Temp)
sink() #끝났다는 표시

output.txt

  • setwd() 해두고 sink() 실행

pdf()

1
2
3
pdf('plot.pdf') #그래프를 pdf파일로 별도저장
plot(Temp,Wind)
dev.off() #끝났다는 표시

plot.pdf

print(), cat()

1
2
3
4
5
6
7
8
> print(pi)
[1] 3.141593
> print('원주율은',pi,'이다')
Error in print.default("원주율은", pi, "이다") : invalid 'quote' argument
> print('dd') #하나만 됨
[1] "dd"
> cat('원주율은',pi,'이다')
원주율은 3.141593 이다
1
cat('x의 평균 : ',mean(x),'\n','x의 표준편차 : ',sd(x),file='output1.txt')

output1.txt

write()

1
2
str(women)
write.table(women,'women.txt') #R에서 생성된 Data를 외부 파일로 보냄

women.txt

xlsx()

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
library(xlsx)
write.xlsx(women,'women.xlsx')
write.xlsx(women,'women1.xlsx',row.names=F)
~~~~

> women.xlsx, women1.xlsx

![](https://user-images.githubusercontent.com/42334717/71569370-f26eaf80-2b11-11ea-8170-a5baac2deab1.png)
***
# seq()

~~~R
> 1:5
[1] 1 2 3 4 5
> -3:3
[1] -3 -2 -1  0  1  2  3
> 5:0
[1] 5 4 3 2 1 0
> seq(0,10,by=0.1)
  [1]  0.0  0.1  0.2  0.3  0.4  0.5  0.6  0.7  0.8  0.9  1.0  1.1  1.2  1.3  1.4  1.5  1.6  1.7  1.8  1.9  2.0  2.1  2.2  2.3  2.4  2.5  2.6  2.7  2.8
 [30]  2.9  3.0  3.1  3.2  3.3  3.4  3.5  3.6  3.7  3.8  3.9  4.0  4.1  4.2  4.3  4.4  4.5  4.6  4.7  4.8  4.9  5.0  5.1  5.2  5.3  5.4  5.5  5.6  5.7
 [59]  5.8  5.9  6.0  6.1  6.2  6.3  6.4  6.5  6.6  6.7  6.8  6.9  7.0  7.1  7.2  7.3  7.4  7.5  7.6  7.7  7.8  7.9  8.0  8.1  8.2  8.3  8.4  8.5  8.6
 [88]  8.7  8.8  8.9  9.0  9.1  9.2  9.3  9.4  9.5  9.6  9.7  9.8  9.9 10.0
> seq(0,10,by=2)
[1]  0  2  4  6  8 10
> seq(0,10,length=3)
[1]  0  5 10

rep()

1
2
3
4
5
6
> rep(1,10)
 [1] 1 1 1 1 1 1 1 1 1 1
> rep(c(1,2),5)
 [1] 1 2 1 2 1 2 1 2 1 2
> rep(c('M','F'),c(2,3))
[1] "M" "M" "F" "F" "F"

Etc.

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
> abs(-10) #absolute
[1] 10
> sqrt(10) #square root
[1] 3.162278
> ceiling(3.475) #올림
[1] 4
> floor(3.475) #버림
[1] 3
> trunc(5.99) #버림
[1] 5
> round(3.475, 2) #반올림
[1] 3.48
> signif(0.00347, 2)
[1] 0.0035
> signif(3.12345, 3)
[1] 3.12
> signif(3.1251, 3)
[1] 3.13
> log(10)
[1] 2.302585
> exp(10)
[1] 22026.47
> 
> x = c(1, 2, 3, 4, 5)
> median(x)
[1] 3
> mean(x)
[1] 3
> IQR(x) #사분위수 범위 3/4수-1/4수(75%-25%)
[1] 2
> sd(x)
[1] 1.581139
> diff(x,lag = 1) #lag-차분, 주식과 같은 시계열 Data에 사용
[1] 1 1 1 1
  • 자기상관이 있으면 시계열 Data(ex. 계절따라 가스 수입)

nchar()

1
2
3
4
> y=c('asdf','zxcv','qwer');y
[1] "asdf" "zxcv" "qwer"
> nchar(y) #각 문자의 개수
[1] 4 4 4

substr()

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
> substr('응용통계학',1,3) #중요
[1] "응용통"
> time='201912311504'
> year=substr(time,1,4);year
[1] "2019"
> month=substr(time,5,6);month
[1] "12"
> day=substr(time,7,8);day
[1] "31"
> hour=substr(time,9,10);hour
[1] "15"
> sec=substr(time,11,12);sec
[1] "04"
> z=c('응용통계학','정보통계학')
> substr(z,c(1,3),c(2,5))
[1] "응용"   "통계학"
> cities=c('New York,NY','Ann Arbor,MI','Chicago,IL')
> states=substr(cities,nchar(cities)-1,nchar(cities));states
[1] "NY" "MI" "IL"
> city=strsplit(cities,split=',');city
[[1]]
[1] "New York" "NY"      

[[2]]
[1] "Ann Arbor" "MI"       

[[3]]
[1] "Chicago" "IL"
  • slicing

산술연산자, 비교연산자, 논리연산자, 배정연산자(우선순위)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
> i=1+2&0+3;i
[1] TRUE
> i=1+2&0;i
[1] FALSE
> x=c(80,88,90,93,95,94,99,78,65)
> cat.x=(x>=100)+(x<90)+(x<80);cat.x
[1] 1 1 0 0 0 0 0 2 2
> cat.x1=factor(cat.x,labels=c('A','B','C'));cat.x1 #0~79/80~89/90~
[1] B B A A A A A C C
Levels: A B C
> 
> cat.x2=(x<=100)+(x<90)+(x<80);cat.x2
[1] 2 2 1 1 1 1 1 3 3
> cat.x3=factor(cat.x2,labels=c('A','B','C'));cat.x3
[1] B B A A A A A C C
Levels: A B C
> 5%%2
[1] 1
  • 산술연산자 : (), ^, **, %%, %/%, %*%, *, /, +, -
  • 비교연산자 : <, <=, >, >=, ==, !=, !
  • 논리연산자 : &, &&, |, ||
  • 배정(할당)연산자 : <-, ->, =

cut()

1
2
3
> cat.x4=cut(x,breaks=c(0,80,90,100),include.lowest=T,right=F,labels=c('C','B','A'));cat.x4
[1] B B A A A A A C C
Levels: C B A

na.rm

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
> air = airquality
> 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 ...
> attach(air)
> mean(Ozone)
[1] NA
> is.na(Ozone)
  [1] FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE
 [17] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE  TRUE
 [33]  TRUE  TRUE  TRUE  TRUE  TRUE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE  TRUE  TRUE FALSE FALSE
 [49] FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE FALSE FALSE
 [65]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE
 [81] FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
 [97] FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE
[113] FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[129] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[145] FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE
> summary(Ozone)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
   1.00   18.00   31.50   42.13   63.25  168.00      37 
> mean(Ozone,na.rm=T)
[1] 42.12931
> sd(Ozone,na.rm=T)
[1] 32.98788

$

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
> x=data.frame(x1=c(1,2,3,4),x2=c(5,6,7,8));x
  x1 x2
1  1  5
2  2  6
3  3  7
4  4  8
> attach(x)
> sum_x=x1+x2;sum_x
[1]  6  8 10 12
> x$sum_x=x1+x2;x
  x1 x2 sum_x
1  1  5     6
2  2  6     8
3  3  7    10
4  4  8    12
> air$cat.Ozone=cut(Ozone,breaks=c(0,35,100000),include.lowest=T,right=F,labels=c('Low','High'));air
    Ozone Solar.R Wind Temp Month Day cat.Ozone
1      41     190  7.4   67     5   1      High
2      36     118  8.0   72     5   2      High
3      12     149 12.6   74     5   3       Low
...      
151    14     191 14.3   75     9  28       Low
152    18     131  8.0   76     9  29       Low
153    20     223 11.5   68     9  30       Low
> air$Ozone_sqrt=sqrt(Ozone);air
    Ozone Solar.R Wind Temp Month Day cat.Ozone Ozone_sqrt
1      41     190  7.4   67     5   1      High   6.403124
2      36     118  8.0   72     5   2      High   6.000000
3      12     149 12.6   74     5   3       Low   3.464102
...
151    14     191 14.3   75     9  28       Low   3.741657
152    18     131  8.0   76     9  29       Low   4.242641
153    20     223 11.5   68     9  30       Low   4.472136
  • $를 이용하면 바로 들어감

sort()

1
2
3
4
5
6
7
8
9
10
11
12
> sort(air$Temp)
  [1] 56 57 57 57 58 58 59 59 61 61 61 62 62 63 64 64 65 65 66 66 66 67 67 67 67 68 68 68 68 69 69 69
 [33] 70 71 71 71 72 72 72 73 73 73 73 73 74 74 74 74 75 75 75 75 76 76 76 76 76 76 76 76 76 77 77 77
 [65] 77 77 77 77 78 78 78 78 78 78 79 79 79 79 79 79 80 80 80 80 80 81 81 81 81 81 81 81 81 81 81 81
 [97] 82 82 82 82 82 82 82 82 82 83 83 83 83 84 84 84 84 84 85 85 85 85 85 86 86 86 86 86 86 86 87 87
[129] 87 87 87 88 88 88 89 89 90 90 90 91 91 92 92 92 92 92 93 93 93 94 94 96 97
> sort(air$Temp,decreasing=T) #내림차순 설정안하면 오름차순
  [1] 97 96 94 94 93 93 93 92 92 92 92 92 91 91 90 90 90 89 89 88 88 88 87 87 87 87 87 86 86 86 86 86
 [33] 86 86 85 85 85 85 85 84 84 84 84 84 83 83 83 83 82 82 82 82 82 82 82 82 82 81 81 81 81 81 81 81
 [65] 81 81 81 81 80 80 80 80 80 79 79 79 79 79 79 78 78 78 78 78 78 77 77 77 77 77 77 77 76 76 76 76
 [97] 76 76 76 76 76 75 75 75 75 74 74 74 74 73 73 73 73 73 72 72 72 71 71 71 70 69 69 69 68 68 68 68
[129] 67 67 67 67 66 66 66 65 65 64 64 63 62 62 61 61 61 59 59 58 58 57 57 57 56

order()

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
> air$Temp
  [1] 67 72 74 62 56 66 65 59 61 69 74 69 66 68 58 64 66 57 68 62 59 73 61 61 57 58 57 67 81 79 76 78
 [33] 74 67 84 85 79 82 87 90 87 93 92 82 80 79 77 72 65 73 76 77 76 76 76 75 78 73 80 77 83 84 85 81
 [65] 84 83 83 88 92 92 89 82 73 81 91 80 81 82 84 87 85 74 81 82 86 85 82 86 88 86 83 81 81 81 82 86
 [97] 85 87 89 90 90 92 86 86 82 80 79 77 79 76 78 78 77 72 75 79 81 86 88 97 94 96 94 91 92 93 93 87
[129] 84 80 78 75 73 81 76 77 71 71 78 67 76 68 82 64 71 81 69 63 70 77 75 76 68
> sort(air$Temp)
  [1] 56 57 57 57 58 58 59 59 61 61 61 62 62 63 64 64 65 65 66 66 66 67 67 67 67 68 68 68 68 69 69 69
 [33] 70 71 71 71 72 72 72 73 73 73 73 73 74 74 74 74 75 75 75 75 76 76 76 76 76 76 76 76 76 77 77 77
 [65] 77 77 77 77 78 78 78 78 78 78 79 79 79 79 79 79 80 80 80 80 80 81 81 81 81 81 81 81 81 81 81 81
 [97] 82 82 82 82 82 82 82 82 82 83 83 83 83 84 84 84 84 84 85 85 85 85 85 86 86 86 86 86 86 86 87 87
[129] 87 87 87 88 88 88 89 89 90 90 90 91 91 92 92 92 92 92 93 93 93 94 94 96 97
> order(air$Temp)
  [1]   5  18  25  27  15  26   8  21   9  23  24   4  20 148  16 144   7  49   6  13  17   1  28  34
 [25] 140  14  19 142 153  10  12 147 149 137 138 145   2  48 114  22  50  58  73 133   3  11  33  82
 [49]  56 115 132 151  31  51  53  54  55 110 135 141 152  47  52  60 108 113 136 150  32  57 111 112
 [73] 131 139  30  37  46 107 109 116  45  59  76 106 130  29  64  74  77  83  92  93  94 117 134 146
 [97]  38  44  72  78  84  87  95 105 143  61  66  67  91  35  62  65  79 129  36  63  81  86  97  85
[121]  88  90  96 103 104 118  39  41  80  98 128  68  89 119  71  99  40 100 101  75 124  43  69  70
[145] 102 125  42 126 127 121 123 122 120
> air[order(air$Temp),]
    Ozone Solar.R Wind Temp Month Day
5      NA      NA 14.3   56     5   5
18      6      78 18.4   57     5  18
25     NA      66 16.6   57     5  25
27     NA      NA  8.0   57     5  27
15     18      65 13.2   58     5  15
26     NA     266 14.9   58     5  26
8      19      99 13.8   59     5   8
21      1       8  9.7   59     5  21
9       8      19 20.1   61     5   9
23      4      25  9.7   61     5  23
24     32      92 12.0   61     5  24
4      18     313 11.5   62     5   4
20     11      44  9.7   62     5  20
148    14      20 16.6   63     9  25
16     14     334 11.5   64     5  16
144    13     238 12.6   64     9  21
7      23     299  8.6   65     5   7
49     20      37  9.2   65     6  18
6      28      NA 14.9   66     5   6
13     11     290  9.2   66     5  13
17     34     307 12.0   66     5  17
1      41     190  7.4   67     5   1
28     23      13 12.0   67     5  28
34     NA     242 16.1   67     6   3
...
  • order()를 통해 작은 순서대로의 Index 값을 구할 수 있음