R (3)

Posted on In

시계열 Data

1
2
3
4
5
6
7
> uspop
Time Series:
Start = 1790 
End = 1970 
Frequency = 0.1 
 [1]   3.93   5.31   7.24   9.64  12.90  17.10  23.20  31.40  39.80  50.20  62.90  76.00  92.00 105.70 122.80 131.70 151.30 179.30
[19] 203.20
  • 기댓값 - 가능한 값마다 확률을 곱해서 모두 더한 값(확률변수의 평균)
  • 평균값 - 데이터를 모두 더한 후 데이터의 갯수로 나눈 값
  • 확률변수 - 대문자(소문자는 상수)
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
> airquality
    Ozone Solar.R Wind Temp Month Day
1      41     190  7.4   67     5   1
2      36     118  8.0   72     5   2
3      12     149 12.6   74     5   3
4      18     313 11.5   62     5   4
5      NA      NA 14.3   56     5   5
...
148    14      20 16.6   63     9  25
149    30     193  6.9   70     9  26
150    NA     145 13.2   77     9  27
151    14     191 14.3   75     9  28
152    18     131  8.0   76     9  29
153    20     223 11.5   68     9  30
> str(airquality)
'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 ...
> dim(airquality) #dimension
[1] 153   6
> length(airquality)
[1] 6
> names(airquality)
[1] "Ozone"   "Solar.R" "Wind"    "Temp"    "Month"   "Day"    
> summary(airquality)
     Ozone           Solar.R           Wind             Temp           Month            Day      
 Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00   Min.   :5.000   Min.   : 1.0  
 1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00   1st Qu.:6.000   1st Qu.: 8.0  
 Median : 31.50   Median :205.0   Median : 9.700   Median :79.00   Median :7.000   Median :16.0  
 Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88   Mean   :6.993   Mean   :15.8  
 3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00   3rd Qu.:8.000   3rd Qu.:23.0  
 Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00   Max.   :9.000   Max.   :31.0  
 NA's   :37       NA's   :7 
> summary(airquality$Ozone)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
   1.00   18.00   31.50   42.13   63.25  168.00      37 
> mean(airquality$Ozone)
[1] NA
  • NA - Not Available(결측값)
  • 문자의 결측값 - <NA>

표준화

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
> attach(airquality)
> z.Temp=(Temp-mean(Temp))/sd(Temp);z.Temp #표준화
  [1] -1.14971398 -0.62146702 -0.41016823 -1.67796094 -2.31185730 -1.25536337 -1.36101276 -1.99490912 -1.78361034 -0.93841519
 [11] -0.41016823 -0.93841519 -1.25536337 -1.04406459 -2.10055851 -1.46666216 -1.25536337 -2.20620791 -1.04406459 -1.67796094
 [21] -1.99490912 -0.51581762 -1.78361034 -1.78361034 -2.20620791 -2.10055851 -2.20620791 -1.14971398  0.32937752  0.11807873
 [31] -0.19886945  0.01242934 -0.41016823 -1.14971398  0.64632570  0.75197509  0.11807873  0.43502691  0.96327387  1.28022205
 [41]  0.96327387  1.59717023  1.49152084  0.43502691  0.22372813  0.11807873 -0.09322005 -0.62146702 -1.36101276 -0.51581762
 [51] -0.19886945 -0.09322005 -0.19886945 -0.19886945 -0.19886945 -0.30451884  0.01242934 -0.51581762  0.22372813 -0.09322005
 [61]  0.54067630  0.64632570  0.75197509  0.32937752  0.64632570  0.54067630  0.54067630  1.06892327  1.49152084  1.49152084
 [71]  1.17457266  0.43502691 -0.51581762  0.32937752  1.38587145  0.22372813  0.32937752  0.43502691  0.64632570  0.96327387
 [81]  0.75197509 -0.41016823  0.32937752  0.43502691  0.85762448  0.75197509  0.43502691  0.85762448  1.06892327  0.85762448
 [91]  0.54067630  0.32937752  0.32937752  0.32937752  0.43502691  0.85762448  0.75197509  0.96327387  1.17457266  1.28022205
[101]  1.28022205  1.49152084  0.85762448  0.85762448  0.43502691  0.22372813  0.11807873 -0.09322005  0.11807873 -0.19886945
[111]  0.01242934  0.01242934 -0.09322005 -0.62146702 -0.30451884  0.11807873  0.32937752  0.85762448  1.06892327  2.01976780
[121]  1.70281962  1.91411841  1.70281962  1.38587145  1.49152084  1.59717023  1.59717023  0.96327387  0.64632570  0.22372813
[131]  0.01242934 -0.30451884 -0.51581762  0.32937752 -0.19886945 -0.09322005 -0.72711641 -0.72711641  0.01242934 -1.14971398
[141] -0.19886945 -1.04406459  0.43502691 -1.46666216 -0.72711641  0.32937752 -0.93841519 -1.57231155 -0.83276580 -0.09322005
[151] -0.30451884 -0.19886945 -1.04406459
> str(z.Temp)
 num [1:153] -1.15 -0.621 -0.41 -1.678 -2.312 ...
> airquality2=cbind(airquality,z.Temp);airquality2
    Ozone Solar.R Wind Temp Month Day      z.Temp
1      41     190  7.4   67     5   1 -1.14971398
2      36     118  8.0   72     5   2 -0.62146702
3      12     149 12.6   74     5   3 -0.41016823
4      18     313 11.5   62     5   4 -1.67796094
...
141    13      27 10.3   76     9  18 -0.19886945
142    24     238 10.3   68     9  19 -1.04406459
 [ reached 'max' / getOption("max.print") -- omitted 11 rows ]
> airquality3=data.frame(airquality,z.Temp);airquality3 #cbind()와 same, 이걸 더 많이 씀
    Ozone Solar.R Wind Temp Month Day      z.Temp
1      41     190  7.4   67     5   1 -1.14971398
2      36     118  8.0   72     5   2 -0.62146702
3      12     149 12.6   74     5   3 -0.41016823
4      18     313 11.5   62     5   4 -1.67796094
...
141    13      27 10.3   76     9  18 -0.19886945
142    24     238 10.3   68     9  19 -1.04406459
 [ reached 'max' / getOption("max.print") -- omitted 11 rows ]
> airquality삼=data.frame(airquality,z.Temp);airquality삼 #한글도 가능
    Ozone Solar.R Wind Temp Month Day      z.Temp
1      41     190  7.4   67     5   1 -1.14971398
2      36     118  8.0   72     5   2 -0.62146702
3      12     149 12.6   74     5   3 -0.41016823
4      18     313 11.5   62     5   4 -1.67796094
...
141    13      27 10.3   76     9  18 -0.19886945
142    24     238 10.3   68     9  19 -1.04406459
 [ reached 'max' / getOption("max.print") -- omitted 11 rows ]
  • 새로운 변수를 만들면 반드시 출력해서 확인

head & tail

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
> head(airquality)
  Ozone Solar.R Wind Temp Month Day
1    41     190  7.4   67     5   1
2    36     118  8.0   72     5   2
3    12     149 12.6   74     5   3
4    18     313 11.5   62     5   4
5    NA      NA 14.3   56     5   5
6    28      NA 14.9   66     5   6
> tail(airquality)
    Ozone Solar.R Wind Temp Month Day
148    14      20 16.6   63     9  25
149    30     193  6.9   70     9  26
150    NA     145 13.2   77     9  27
151    14     191 14.3   75     9  28
152    18     131  8.0   76     9  29
153    20     223 11.5   68     9  30
> head(airquality2)
  Ozone Solar.R Wind Temp Month Day     z.Temp
1    41     190  7.4   67     5   1 -1.1497140
2    36     118  8.0   72     5   2 -0.6214670
3    12     149 12.6   74     5   3 -0.4101682
4    18     313 11.5   62     5   4 -1.6779609
5    NA      NA 14.3   56     5   5 -2.3118573
6    28      NA 14.9   66     5   6 -1.2553634
> tail(airquality2)
    Ozone Solar.R Wind Temp Month Day      z.Temp
148    14      20 16.6   63     9  25 -1.57231155
149    30     193  6.9   70     9  26 -0.83276580
150    NA     145 13.2   77     9  27 -0.09322005
151    14     191 14.3   75     9  28 -0.30451884
152    18     131  8.0   76     9  29 -0.19886945
153    20     223 11.5   68     9  30 -1.04406459
> head(airquality3)
  Ozone Solar.R Wind Temp Month Day     z.Temp
1    41     190  7.4   67     5   1 -1.1497140
2    36     118  8.0   72     5   2 -0.6214670
3    12     149 12.6   74     5   3 -0.4101682
4    18     313 11.5   62     5   4 -1.6779609
5    NA      NA 14.3   56     5   5 -2.3118573
6    28      NA 14.9   66     5   6 -1.2553634
> tail(airquality3)
    Ozone Solar.R Wind Temp Month Day      z.Temp
148    14      20 16.6   63     9  25 -1.57231155
149    30     193  6.9   70     9  26 -0.83276580
150    NA     145 13.2   77     9  27 -0.09322005
151    14     191 14.3   75     9  28 -0.30451884
152    18     131  8.0   76     9  29 -0.19886945
153    20     223 11.5   68     9  30 -1.04406459
  • 간단히 확인

scan()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
> x=scan()
1: 35
2: 40
3: 45
4: 
Read 3 items
> x
[1] 35 40 45
> y=scan(what="character")
1: kim
2: oh
3: 2
4: ZeaMays
5: 
Read 4 items
> y
[1] "kim"     "oh"      "2"       "ZeaMays"

read.table(“.txt”), read.csv()

Data.txt

1
2
3
4
5
6
Name Score Gender
Kim 23 m
Oh 42 f
zd 21 f
Chat 31 m
Asd 23 m

Data2.txt

1
2
3
4
5
6
Name,Score,Gender
Kim,23,m
Oh,42,f
zd,21,f
Chat,31,m
Asd,23,m
  • setwd()할 directory에 .txt파일 저장
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
> setwd("/Users/zerohertz/Downloads")
> x1=read.table("Data.txt");x1
    V1    V2     V3
1 Name Score Gender
2  Kim    23      m
3   Oh    42      f
4   zd    21      f
5 Chat    31      m
6  Asd    23      m
> x2=read.table("Data2.txt");x2
                 V1
1 Name,Score,Gender
2          Kim,23,m
3           Oh,42,f
4           zd,21,f
5         Chat,31,m
6          Asd,23,m
> x3=read.table("Data.txt",header=T);x3
  Name Score Gender
1  Kim    23      m
2   Oh    42      f
3   zd    21      f
4 Chat    31      m
5  Asd    23      m
> x4=read.table("Data.txt",header=T,stringsAsFactors=F);x4
  Name Score Gender
1  Kim    23      m
2   Oh    42      f
3   zd    21      f
4 Chat    31      m
5  Asd    23      m
> str(x1)
'data.frame':	6 obs. of  3 variables:
 $ V1: Factor w/ 6 levels "Asd","Chat","Kim",..: 4 3 5 6 2 1
 $ V2: Factor w/ 5 levels "21","23","31",..: 5 2 4 1 3 2
 $ V3: Factor w/ 3 levels "f","Gender","m": 2 3 1 1 3 3
> str(x2)
'data.frame':	6 obs. of  1 variable:
 $ V1: Factor w/ 6 levels "Asd,23,m","Chat,31,m",..: 4 3 5 6 2 1
> str(x3)
'data.frame':	5 obs. of  3 variables:
 $ Name  : Factor w/ 5 levels "Asd","Chat","Kim",..: 3 4 5 2 1
 $ Score : int  23 42 21 31 23
 $ Gender: Factor w/ 2 levels "f","m": 2 1 1 2 2
> str(x4)
'data.frame':	5 obs. of  3 variables:
 $ Name  : chr  "Kim" "Oh" "zd" "Chat" ...
 $ Score : int  23 42 21 31 23
 $ Gender: chr  "m" "f" "f" "m" ...
  • setwd()를 통해 directory 지정
  • read.table()으로 .txt import
  • header, stringsAsFactors와 같은 옵션으로 조정
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
> xyz=read.table("Data.txt",header=T);xyz
  Name Score Gender
1  Kim    23      m
2   Oh    42      f
3   zd    21      f
4 Chat    31      m
5  Asd    23      .
> summary(xyz)
   Name       Score    Gender
 Asd :1   Min.   :21   .:1   
 Chat:1   1st Qu.:23   f:2   
 Kim :1   Median :23   m:2   
 Oh  :1   Mean   :28         
 zd  :1   3rd Qu.:31         
          Max.   :42   
> xyz=read.table("Data.txt",header=T);xyz
  Name Score Gender
1  Kim    23      m
2   Oh    42      f
3   zd    21      f
4 Chat     .      m
5  Asd    23      .
> summary(xyz)
   Name   Score  Gender
 Asd :1   . :1   .:1   
 Chat:1   21:1   f:2   
 Kim :1   23:2   m:2   
 Oh  :1   42:1         
 zd  :1                
> xyz=read.table("Data.txt",header=T,na.strings='.');xyz
  Name Score Gender
1  Kim    23      m
2   Oh    42      f
3   zd    21      f
4 Chat    NA      m
5  Asd    23   <NA>
> summary(xyz)
   Name       Score        Gender 
 Asd :1   Min.   :21.00   f   :2  
 Chat:1   1st Qu.:22.50   m   :2  
 Kim :1   Median :23.00   NA's:1  
 Oh  :1   Mean   :27.25           
 zd  :1   3rd Qu.:27.75           
          Max.   :42.00           
          NA's   :1     
> xyz=read.table("Data2.txt",header=T,sep=",");xyz
  Name Score Gender
1  Kim    23      m
2   Oh    42      f
3   zd    21      f
4 Chat     .      m
5  Asd    23      .
> xyz=read.csv("Data2.txt");xyz
  Name Score Gender
1  Kim    23      m
2   Oh    42      f
3   zd    21      f
4 Chat     .      m
5  Asd    23      .
  • Data.txt, Data2.txt 파일에 몇가지 결측값 삽입
  • .은 문자로 인식
  • na.strings로 결측값 선언
  • sep or read.csv로 Separate
  • csv - Comma Separate Value

excel-separate

xlsx

1
> install.packages("xlsx")

기본 경로 설정

1
2
3
4
options("java.home"="/Library/Java/JavaVirtualMachines/jdk1.8.0_231.jdk/Contents/Home/lib")
Sys.setenv(JAVA_HOME = '/Library/Java/JavaVirtualMachines/jdk1.8.0_231.jdk/Contents/Home/jre')
dyn.load('/Library/Java/JavaVirtualMachines/jdk1.8.0_231.jdk/Contents/Home/jre/lib/server/libjvm.dylib')
Sys.setlocale("LC_ALL", "ko_KR.UTF-8")