R (2)

Posted on In

변수 지우기

1
2
3
> rm(list=ls())
> ls()
character(0)
  • ls()는 지금까지 생성한 변수들의 목록을 문자열들로 반환하는 함수(list의 약자)

기본 Data 제공

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
> summary(trees)
     Girth           Height       Volume     
 Min.   : 8.30   Min.   :63   Min.   :10.20  
 1st Qu.:11.05   1st Qu.:72   1st Qu.:19.40  
 Median :12.90   Median :76   Median :24.20  
 Mean   :13.25   Mean   :76   Mean   :30.17  
 3rd Qu.:15.25   3rd Qu.:80   3rd Qu.:37.30  
 Max.   :20.60   Max.   :87   Max.   :77.00  
> summary(chickwts)
     weight             feed   
 Min.   :108.0   casein   :12  
 1st Qu.:204.5   horsebean:10  
 Median :258.0   linseed  :12  
 Mean   :261.3   meatmeal :11  
 3rd Qu.:323.5   soybean  :14  
 Max.   :423.0   sunflower:12  
> summary(cars)
     speed           dist       
 Min.   : 4.0   Min.   :  2.00  
 1st Qu.:12.0   1st Qu.: 26.00  
 Median :15.0   Median : 36.00  
 Mean   :15.4   Mean   : 42.98  
 3rd Qu.:19.0   3rd Qu.: 56.00  
 Max.   :25.0   Max.   :120.00

자료 종류

  • 범주형 : 빈도 chickwts - feed
  • 수치형 : summary() 나머지

기말 - 자료의 종류에 따라서 통계분석 기법은 정해짐

Data package

1
2
3
library(MASS)
install.packages("UsingR")
library(UsingR)
  • Package - 다른사람이 제공하는 Data나 Function을 저장해둔곳
  • library()는 C에서의 #include
  • /Library/Frameworks/R.framework/Versions/3.6/Resources/library
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
> summary(Cars93)
    Manufacturer     Model         Type      Min.Price         Price         Max.Price       MPG.city      MPG.highway   
 Chevrolet: 8    100    : 1   Compact:16   Min.   : 6.70   Min.   : 7.40   Min.   : 7.9   Min.   :15.00   Min.   :20.00  
 Ford     : 8    190E   : 1   Large  :11   1st Qu.:10.80   1st Qu.:12.20   1st Qu.:14.7   1st Qu.:18.00   1st Qu.:26.00  
 Dodge    : 6    240    : 1   Midsize:22   Median :14.70   Median :17.70   Median :19.6   Median :21.00   Median :28.00  
 Mazda    : 5    300E   : 1   Small  :21   Mean   :17.13   Mean   :19.51   Mean   :21.9   Mean   :22.37   Mean   :29.09  
 Pontiac  : 5    323    : 1   Sporty :14   3rd Qu.:20.30   3rd Qu.:23.30   3rd Qu.:25.3   3rd Qu.:25.00   3rd Qu.:31.00  
 Buick    : 4    535i   : 1   Van    : 9   Max.   :45.40   Max.   :61.90   Max.   :80.0   Max.   :46.00   Max.   :50.00  
 (Other)  :57    (Other):87                                                                                              
               AirBags   DriveTrain  Cylinders    EngineSize      Horsepower         RPM        Rev.per.mile  Man.trans.avail
 Driver & Passenger:16   4WD  :10   3     : 3   Min.   :1.000   Min.   : 55.0   Min.   :3800   Min.   :1320   No :32         
 Driver only       :43   Front:67   4     :49   1st Qu.:1.800   1st Qu.:103.0   1st Qu.:4800   1st Qu.:1985   Yes:61         
 None              :34   Rear :16   5     : 2   Median :2.400   Median :140.0   Median :5200   Median :2340                  
                                    6     :31   Mean   :2.668   Mean   :143.8   Mean   :5281   Mean   :2332                  
                                    8     : 7   3rd Qu.:3.300   3rd Qu.:170.0   3rd Qu.:5750   3rd Qu.:2565                  
                                    rotary: 1   Max.   :5.700   Max.   :300.0   Max.   :6500   Max.   :3755                  
                                                                                                                             
 Fuel.tank.capacity   Passengers        Length        Wheelbase         Width        Turn.circle    Rear.seat.room   Luggage.room  
 Min.   : 9.20      Min.   :2.000   Min.   :141.0   Min.   : 90.0   Min.   :60.00   Min.   :32.00   Min.   :19.00   Min.   : 6.00  
 1st Qu.:14.50      1st Qu.:4.000   1st Qu.:174.0   1st Qu.: 98.0   1st Qu.:67.00   1st Qu.:37.00   1st Qu.:26.00   1st Qu.:12.00  
 Median :16.40      Median :5.000   Median :183.0   Median :103.0   Median :69.00   Median :39.00   Median :27.50   Median :14.00  
 Mean   :16.66      Mean   :5.086   Mean   :183.2   Mean   :103.9   Mean   :69.38   Mean   :38.96   Mean   :27.83   Mean   :13.89  
 3rd Qu.:18.80      3rd Qu.:6.000   3rd Qu.:192.0   3rd Qu.:110.0   3rd Qu.:72.00   3rd Qu.:41.00   3rd Qu.:30.00   3rd Qu.:15.00  
 Max.   :27.00      Max.   :8.000   Max.   :219.0   Max.   :119.0   Max.   :78.00   Max.   :45.00   Max.   :36.00   Max.   :22.00  
                                                                                                    NA's   :2       NA's   :11     
     Weight         Origin              Make   
 Min.   :1695   USA    :48   Acura Integra: 1  
 1st Qu.:2620   non-USA:45   Acura Legend : 1  
 Median :3040                Audi 100     : 1  
 Mean   :3073                Audi 90      : 1  
 3rd Qu.:3525                BMW 535i     : 1  
 Max.   :4105                Buick Century: 1  
                             (Other)      :87

Work directory

1
2
3
4
5
> getwd()
[1] "/Users/zerohertz/Documents/R"
> setwd("/Users/zerohertz/Downloads")
> getwd()
[1] "/Users/zerohertz/Downloads"
  • ₩, \대신 /사용

save.image()

1
2
3
a=1+1
save.image(file="/Users/zerohertz/Downloads/asd.RData")
load("/Users/zerohertz/Downloads/asd.RData")

no-variable
load

  • 숨김파일은 cmd + . + shift
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
> ls()
character(0)
> a="test"
> a
[1] "test"
> save.image()
> getwd()
[1] "/Users/zerohertz"
> setwd("/Users/zerohertz/Downloads")
> b="Another Work Directory"
> save.image()
> getwd()
[1] "/Users/zerohertz/Downloads"
> rm(list=ls())
> load("/Users/zerohertz/.RData")
> a
[1] "test"
> b
Error: object 'b' not found
> rm(list=ls())
> load("/Users/zerohertz/Downloads/.RData")
> a
[1] "test"
> b
[1] "Another Work Directory"

str()

1
2
3
4
> str(cars)
'data.frame':	50 obs. of  2 variables:
 $ speed: num  4 4 7 7 8 9 10 10 10 11 ...
 $ dist : num  2 10 4 22 16 10 18 26 34 17 ...
  • Structure의 약자

자료형

1
2
3
4
5
6
7
8
> mean(cars)
[1] NA
Warning message:
In mean.default(cars) : argument is not numeric or logical: returning NA
> typeof(cars)
[1] "list"
> typeof(speed)
[1] "double"

attach()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
> mean(cars$speed)
[1] 15.4
> sd(cars$dist)
[1] 25.76938
> mean(speed)
Error in mean(speed) : object 'speed' not found
> sd(dist)
Error in as.double(x) : 
  cannot coerce type 'closure' to vector of type 'double'
> attach(cars)
> mean(cars$speed)
[1] 15.4
> sd(cars$dist)
[1] 25.76938
> mean(speed)
[1] 15.4
> sd(dist)
[1] 25.76938
  • C++의 Using namespace와 유사

객체 Vector/Matrix/data.frame

1
2
3
x=c(1,3,5,4,3,3) #숫자형 벡터
y=c("one","two","three") #문자형 벡터
z=c(TRUE,TRUE,FALSE,F) #논리형 벡터
  • Vector : 숫자, 문자, 논리만의 Vector 가능
  • Matrix : 행과 열/각 열이 숫자, 문자 논리만 가지는 행렬 가능
  • data.frame : 각 열이 숫자, 문자, 논리 혼합 가능(행렬과 같은 2차원 구조 / 모든 데이터가 동일한 유형일 필요 X)
  • 행 = Case, 열 = Variable

Indexing

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
> x[1]
[1] 1
> x[2]
[1] 3
> x[3]
[1] 5
> x[4]
[1] 4
> x[5]
[1] 3
> x[1,3]
Error in x[1, 3] : incorrect number of dimensions
> x[c(1,3)]
[1] 1 5
> x[1:3]
[1] 1 3 5
> cars[1,2] #Matrix[행,열]
[1] 2
> y1=y[c(1,3)];y1
[1] "one"   "three"
> a[2,3] #a is matrix
[1] 8
> a[1,]
[1] 1 4 7
> a[,2]
[1] 4 5 6
  • a[x,y] - Matrix or data.frame

factor()

1
2
3
4
5
6
7
8
9
10
11
12
> gender=c("m","f","m","f");gender
[1] "m" "f" "m" "f"
> str(gender)
 chr [1:4] "m" "f" "m" "f"
> f.gender=factor(gender);f.gender
[1] m f m f
Levels: f m
> str(f.gender)
 Factor w/ 2 levels "f","m": 2 1 2 1
> summary(f.gender)
f m 
2 2
  • 범주형자료는 요인(factor)로 무조건 변경
  • 알파벳순
1
2
3
4
5
6
> f.gender2=factor(gender,order=TRUE,level=c("m",'f'))
> str(f.gender2)
 Ord.factor w/ 2 levels "m"<"f": 1 2 1 2
> summary(f.gender2)
m f 
2 2
  • order=TRUE - 오름차순
  • level - 직접정의, 올바르지 않은 data 찾기

Matrix

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
> a=matrix(1:9,nrow=3);a
     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9
> b=matrix(1:9,nrow=3,byrow=TRUE);b
     [,1] [,2] [,3]
[1,]    1    2    3
[2,]    4    5    6
[3,]    7    8    9
> c=matrix(1:100,nrow=100);c
       [,1]
  [1,]    1
  [2,]    2
  [3,]    3
  [4,]    4
  [5,]    5
...
 [98,]   98
 [99,]   99
[100,]  100
  • small n - 표본
  • nrow - 행의 개수
  • Matrix는 ,가 들어감
1
2
3
4
5
6
7
8
9
> cnames=c("c1","c2","c3");cnames
[1] "c1" "c2" "c3"
> rnames=c("r1","r2","r3");rnames
[1] "r1" "r2" "r3"
> z=matrix(1:9,nrow=3,dimnames=list(rnames,cnames));z
   c1 c2 c3
r1  1  4  7
r2  2  5  8
r3  3  6  9
  • 행과 열의 이름 부여
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
> a
     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9
> a[2,3]
[1] 8
> a[1,]
[1] 1 4 7
> a[,2]
[1] 4 5 6
> mean(a[,2])
[1] 5
> mean(a)
[1] 5
> sum(a)
[1] 45

dim()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
> d=1:24
> dim(d)=c(4,3,2);d
, , 1

     [,1] [,2] [,3]
[1,]    1    5    9
[2,]    2    6   10
[3,]    3    7   11
[4,]    4    8   12

, , 2

     [,1] [,2] [,3]
[1,]   13   17   21
[2,]   14   18   22
[3,]   15   19   23
[4,]   16   20   24

data.frame()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
> a1=c(1,2,3,4)
> a2=c('f','m','f','m')
> a12=data.frame(a1,a2);a12
  a1 a2
1  1  f
2  2  m
3  3  f
4  4  m
> a123=data.frame(age=a1,gender=a2);a123
  age gender
1   1      f
2   2      m
3   3      f
4   4      m
  • 옆으로 붙인다는 것을 잘 생각해야함
  • 데이터 문자는 항상 ""해야함

rbind()

1
2
3
4
5
6
7
8
9
10
> a_add=data.frame(age=30,gender='f');a_add
  age gender
1  30      f
> a12t=rbind(a123,a_add);a12t #위 아래로 행을 붙임(Case 추가)
  age gender
1   1      f
2   2      m
3   3      f
4   4      m
5  30      f
  • 위 아래로 행을 붙임(Case 추가)
  • cbind - 옆으로 열을 붙임(변수 추가)

length()/dim()

1
2
3
4
5
6
7
8
> length(a12t)
[1] 2
> dim(a12t
[1] 5 2
> str(a12t)
'data.frame':	5 obs. of  2 variables:
 $ age   : num  1 2 3 4 30
 $ gender: Factor w/ 2 levels "f","m": 1 2 1 2 1
  • length() - 열의 수
  • dim() - 행과 열의 수
  • str() - danawa

정리

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
#전산실습 Day 1
rm(list=ls())

speed=cars$speed;speed
dist=cars$dist;dist
summary(speed)
summary(dist)
mean(speed)
mean(dist)

#전산실습 Day 2
summary(trees)
summary(chickwts)
summary(cars)

library(MASS)
summary(Cars93)

#install.packages("UsingR")
library(UsingR)

ls()

getwd()
setwd("/Users/zerohertz")
#setwd("/Users/zerohertz/Documents/R")
#setwd("/Users/zerohertz/Downloads")
getwd()

summary(cars)
mean(speed)
mean(cars$speed)

str(cars)
cars[1,2]
summary(cars)
attach(cars)
mean(cars$speed)
sd(cars$dist)
mean(speed)
sd(dist)
detach(cars)

save.image()

x=c(1,3,5,4,3,3) #숫자형 벡터
y=c("one","two","three") #문자형 벡터
z=c(TRUE,TRUE,FALSE,F) #논리형 벡터

y1=y[c(1,3)];y1

gender=c("m","f","m","f");gender
str(gender)
f.gender=factor(gender);f.gender
str(f.gender)
summary(f.gender)
f.gender2=factor(gender,order=TRUE,level=c("m",'f'))
str(f.gender2)
summary(f.gender2)

str(Cars93)

a=matrix(1:9,nrow=3);a
b=matrix(1:9,nrow=3,byrow=TRUE);b
c=matrix(1:100,nrow=100);c
cnames=c("c1","c2","c3");cnames
rnames=c("r1","r2","r3");rnames
z=matrix(1:9,nrow=3,dimnames=list(rnames,cnames));z

a[2,3]
a[1,]
a[,2]
mean(a[,2])
mean(a)
sum(a)

d=1:24
dim(d)=c(4,3,2);d

a1=c(1,2,3,4)
a2=c('f','m','f','m')
a12=data.frame(a1,a2);a12
a123=data.frame(age=a1,gender=a2);a123
a_add=data.frame(age=30,gender='f');a_add
a12t=rbind(a123,a_add);a12t #위 아래로 행을 붙임(Case 추가)

length(a12t)
dim(a12t)
str(a12t)

#q()

get data - str() - summary() - 문자면 factor() - level()