빅데이터 시각화 중간고사 대비 정리하기 3

blood.type1 =c("A","B","O","AB")
blood.type2=factor(c("A","B","O","AB"))
blood.type1
blood.type2

<ol class=list-inline> <li>‘A’</li> <li>‘B’</li> <li>‘O’</li> <li>‘AB’</li> </ol>

<ol class=list-inline> <li>A</li> <li>B</li> <li>O</li> <li>AB</li> </ol>

is.character(blood.type1)
is.character(blood.type2)

TRUE

FALSE

is.factor(blood.type1)
is.factor(blood.type2)# factor true

FALSE

TRUE

x = c(1:10)
x=x[seq(2,length(x),2)]
x

<ol class=list-inline> <li>2</li> <li>4</li> <li>6</li> <li>8</li> <li>10</li> </ol>

x=array(1:24,c(4,6))
x
x=x[,seq(1,dim(x)[2],2)]
x

#BMI 계산기
BMI = function(height,weight){
  height = height/100
  bmi = weight /height^2
  return(bmi)
}

BMI(175,65)

21.2244897959184

#NA(결측치)데이터 처리
data <- c(10,20,30,NA,6,3,NA)
data
mean(data)
mean(data, na.rm = T)#NA값을 지워야지 mean값나옴

<ol class=list-inline> <li>10</li> <li>20</li> <li>30</li> <li><NA></li> <li>6</li> <li>3</li> <li><NA></li> </ol>

<NA>

13.8

#벡터 for
score <- c(85,94,96)
name <- c("홍길동","이순신","강감찬")
i<-1 
for (s in score) {
  cat(name[i],"->",s,"\n")
  i<-i+1
  
}
#실행결과
#홍길동 -> 85 
#이순신 -> 94 
#강감찬 -> 96 

홍길동 -> 85 
이순신 -> 94 
강감찬 -> 96 

i=0

while (i<10) {
  i<-i+1
  print(i)
  
}

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

#학점 구하기
score<-scan()
score<-c(80)

if(score>=90){
  result="A학점"
}else if(score >=80){
  result="B학점"
}else if(score>=70){
  result="C학점"
}else if(score>=60){
  result="D학점"
}else{
  result="F학점"
}

cat("당신의 학점은:",result)
print(result)

당신의 학점은: B학점[1] "B학점"

#ifelse "노력" "우수" "우수" "노력"
score <-c(75,95,85,65)
score
ifelse(score>=80,"우수","노력")

<ol class=list-inline> <li>75</li> <li>95</li> <li>85</li> <li>65</li> </ol>

<ol class=list-inline> <li>‘노력’</li> <li>‘우수’</li> <li>‘우수’</li> <li>‘노력’</li> </ol>

#숫자 대소 관계 비교 함수 2개의 숫자중 큰수 출력
mymax <- function(x,y){
  num.max <- x
  if(y>x){
    num.max <-y
  }
  return(num.max)
}

mymax(10,15)
mymax(20,15)

15

20

#data.frame (데이터 프레임)
students <- c("John", "Mary", "Ethan", "Dora") #문자열벡터 
test.results <- c(76, 82, 84, 67) #숫자벡터
test.grade <- c("B", "A", "A", "C") #문자열벡터
third.class.df <- data.frame(students, test.results, test.grade) #데이터 프레임 생성
third.class.df

ncol(third.class.df)
nrow(third.class.df)

3

4

#행이름 지정
rownames(third.class.df) <- c("a transfer1", "a transfer2", "a transfer3", "a transfer4")
third.class.df

#열추가 (cbind)
student_Id <-c("333","111","222","444")
third.class.df<- cbind(third.class.df,student_Id)
third.class.df

#행추가(rbind)
TED<- c("Ted",70,"B","012312")
third.class.df<- rbind(third.class.df,TED)
third.class.df

Warning message in `[<-.factor`(`*tmp*`, ri, value = "Ted"):
"invalid factor level, NA generated"Warning message in `[<-.factor`(`*tmp*`, ri, value = "012312"):
"invalid factor level, NA generated"

#데이터 프레임 열 제거하기
third.class.df[,-3] #3번째 열만 제거
third.class.df

#데이터 프레임 열 제거하기 (subset())
subset(third.class.df,select = -c(students))

#iris 데이터셋
iris

iris[,c(1:2)]

iris[,c(1,3,5)]#1,3,5열의 모든 데이터

iris[,c("Species")]#컬럼이름으로 데이터 조회

<ol class=list-inline> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>setosa</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>versicolor</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> <li>virginica</li> </ol>

#apply 함수적용
apply(iris[,1:4],1,mean)#row방향으로 평균을 구하는 함수
apply(iris[,1:4],2,mean) #col 방향으로 평균을 구하는 함수

<ol class=list-inline> <li>2.55</li> <li>2.375</li> <li>2.35</li> <li>2.35</li> <li>2.55</li> <li>2.85</li> <li>2.425</li> <li>2.525</li> <li>2.225</li> <li>2.4</li> <li>2.7</li> <li>2.5</li> <li>2.325</li> <li>2.125</li> <li>2.8</li> <li>3</li> <li>2.75</li> <li>2.575</li> <li>2.875</li> <li>2.675</li> <li>2.675</li> <li>2.675</li> <li>2.35</li> <li>2.65</li> <li>2.575</li> <li>2.45</li> <li>2.6</li> <li>2.6</li> <li>2.55</li> <li>2.425</li> <li>2.425</li> <li>2.675</li> <li>2.725</li> <li>2.825</li> <li>2.425</li> <li>2.4</li> <li>2.625</li> <li>2.5</li> <li>2.225</li> <li>2.55</li> <li>2.525</li> <li>2.1</li> <li>2.275</li> <li>2.675</li> <li>2.8</li> <li>2.375</li> <li>2.675</li> <li>2.35</li> <li>2.675</li> <li>2.475</li> <li>4.075</li> <li>3.9</li> <li>4.1</li> <li>3.275</li> <li>3.85</li> <li>3.575</li> <li>3.975</li> <li>2.9</li> <li>3.85</li> <li>3.3</li> <li>2.875</li> <li>3.65</li> <li>3.3</li> <li>3.775</li> <li>3.35</li> <li>3.9</li> <li>3.65</li> <li>3.4</li> <li>3.6</li> <li>3.275</li> <li>3.925</li> <li>3.55</li> <li>3.8</li> <li>3.7</li> <li>3.725</li> <li>3.85</li> <li>3.95</li> <li>4.1</li> <li>3.725</li> <li>3.2</li> <li>3.2</li> <li>3.15</li> <li>3.4</li> <li>3.85</li> <li>3.6</li> <li>3.875</li> <li>4</li> <li>3.575</li> <li>3.5</li> <li>3.325</li> <li>3.425</li> <li>3.775</li> <li>3.4</li> <li>2.9</li> <li>3.45</li> <li>3.525</li> <li>3.525</li> <li>3.675</li> <li>2.925</li> <li>3.475</li> <li>4.525</li> <li>3.875</li> <li>4.525</li> <li>4.15</li> <li>4.375</li> <li>4.825</li> <li>3.4</li> <li>4.575</li> <li>4.2</li> <li>4.85</li> <li>4.2</li> <li>4.075</li> <li>4.35</li> <li>3.8</li> <li>4.025</li> <li>4.3</li> <li>4.2</li> <li>5.1</li> <li>4.875</li> <li>3.675</li> <li>4.525</li> <li>3.825</li> <li>4.8</li> <li>3.925</li> <li>4.45</li> <li>4.55</li> <li>3.9</li> <li>3.95</li> <li>4.225</li> <li>4.4</li> <li>4.55</li> <li>5.025</li> <li>4.25</li> <li>3.925</li> <li>3.925</li> <li>4.775</li> <li>4.425</li> <li>4.2</li> <li>3.9</li> <li>4.375</li> <li>4.45</li> <li>4.35</li> <li>3.875</li> <li>4.55</li> <li>4.55</li> <li>4.3</li> <li>3.925</li> <li>4.175</li> <li>4.325</li> <li>3.95</li> </ol>

<dl class=dl-horizontal> <dt>Sepal.Length</dt> <dd>5.84333333333333</dd> <dt>Sepal.Width</dt> <dd>3.05733333333333</dd> <dt>Petal.Length</dt> <dd>3.758</dd> <dt>Petal.Width</dt> <dd>1.19933333333333</dd> </dl>

#gapminder
#한 식으로 표현
library(gapminder)
gapminder

gapminder[gapminder$country=="Croatia"&gapminder$year>1992,c("lifeExp","pop")]
#조건식 여러개를 논리 연산자로 결합

#col mean 계산
apply(gapminder[gapminder$country=="Croatia",c("lifeExp","pop")],2,mean)

<dl class=dl-horizontal> <dt>lifeExp</dt> <dd>70.0559166666667</dd> <dt>pop</dt> <dd>4289916.25</dd> </dl>

#select 함수 사용하려면 dplyr 라이브러리 필수임
library(dplyr) 
select(gapminder,country,year,lifeExp)

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

#filter() 특정 샘플(행) 추출 시 사용 
filter(gapminder,country=="Croatia")

summarise(gapminder,pop_avg=mean(pop))
gapminder

summarise(group_by(gapminder,continent),pop_avg=mean(pop))

summarise(group_by(gapminder,continent,country),pop_avg=mean(pop))

gapminder%>% group_by(continent,country)%>% summarise(pop_avg=mean(pop))

gapminder%>% group_by(continent,country)%>% summarise(pop_avg=mean(pop))

temp1 = filter(gapminder,country=="Croatia")
temp1

temp2 = select(temp1,country,year,lifeExp)
temp2

temp3= apply(temp2[,c("lifeExp")],2,mean)
temp3

lifeExp: 70.0559166666667

# 위에 소스 한 소스로 표현 가능
gapminder %>% filter(country=="Croatia") %>% select(country,year,lifeExp) %>% summarise(lifeExp_avg=mean(lifeExp))

#avocado
avocado <- read.csv("C:/대학원자료/r로배우는데이터과학/Sources/avocado.csv",header=TRUE,sep=",")
avocado

str(avocado)

'data.frame':	18249 obs. of  14 variables:
 $ X           : int  0 1 2 3 4 5 6 7 8 9 ...
 $ Date        : Factor w/ 169 levels "2015-01-04","2015-01-11",..: 52 51 50 49 48 47 46 45 44 43 ...
 $ AveragePrice: num  1.33 1.35 0.93 1.08 1.28 1.26 0.99 0.98 1.02 1.07 ...
 $ Total.Volume: num  64237 54877 118220 78992 51040 ...
 $ X4046       : num  1037 674 795 1132 941 ...
 $ X4225       : num  54455 44639 109150 71976 43838 ...
 $ X4770       : num  48.2 58.3 130.5 72.6 75.8 ...
 $ Total.Bags  : num  8697 9506 8145 5811 6184 ...
 $ Small.Bags  : num  8604 9408 8042 5677 5986 ...
 $ Large.Bags  : num  93.2 97.5 103.1 133.8 197.7 ...
 $ XLarge.Bags : num  0 0 0 0 0 0 0 0 0 0 ...
 $ type        : Factor w/ 2 levels "conventional",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ year        : int  2015 2015 2015 2015 2015 2015 2015 2015 2015 2015 ...
 $ region      : Factor w/ 54 levels "Albany","Atlanta",..: 1 1 1 1 1 1 1 1 1 1 ...

(x_avg = avocado %>% group_by(region) %>% summarise(V_avg =mean(Total.Volume),P_avg=mean(AveragePrice)))

(x_avg = avocado %>% group_by(region,year,type) %>% summarise(V_avg =mean(Total.Volume),P_avg=mean(AveragePrice)))

library(ggplot2)
x_avg%>% filter(region!="TotalUS")%>% ggplot(aes(year,V_avg,col=type))+geom_line() + facet_wrap(~region)

arrange(x_avg,desc(V_avg))

#x=1,y=2를 서로 교환하려고 한다.
x=1
y=2
temp=y
y=x
x=temp
x
y

2

1

#연산의 결과가 NaN으로 나오는 연산 
X=0
y=0
x/y

x=Inf
y=Inf
x/y

Inf

NaN

#수학적인 표현인 1<x<5를 R에서 표현으로 작성하라
X=3
1<X & X<5

TRUE

#!(x%%3==0&x%%4==0)과 같은 의미이면서 or연산자를 활용한 표현식으로 고쳐 써라

x%%3!=0|x%%4!=0 

<NA>

#x=c(1:5)인 벡터가 있다. 이 벡터에 c(6:10)인 벡터를 추가하라
x=c(1:5)
x=c(x,c(6:10))
x

<ol class=list-inline> <li>1</li> <li>2</li> <li>3</li> <li>4</li> <li>5</li> <li>6</li> <li>7</li> <li>8</li> <li>9</li> <li>10</li> </ol>

#x=c(1:10)인 벡터에서 짝수 번째 요소만 남긴 x를 만들어라
x=c(1:10)
x=x[seq(2,length(x),2)]
x

<ol class=list-inline> <li>2</li> <li>4</li> <li>6</li> <li>8</li> <li>10</li> </ol>

#x=c(1:10)인 벡터에서 홀수 번째 요소만 남긴 x를 만들어라
x=c(1:10)
x=x[seq(1,length(x),2)]
x

<ol class=list-inline> <li>1</li> <li>3</li> <li>5</li> <li>7</li> <li>9</li> </ol>

#Titanic 데이터는 4차원 배열 값을 가지고 있다. plot(Titanic)을 수행하여 생존율이 가장 높은 그룹을 유추하라 
plot(Titanic)
Titanic

, , Age = Child, Survived = No

      Sex
Class  Male Female
  1st     0      0
  2nd     0      0
  3rd    35     17
  Crew    0      0

, , Age = Adult, Survived = No

      Sex
Class  Male Female
  1st   118      4
  2nd   154     13
  3rd   387     89
  Crew  670      3

, , Age = Child, Survived = Yes

      Sex
Class  Male Female
  1st     5      1
  2nd    11     13
  3rd    13     14
  Crew    0      0

, , Age = Adult, Survived = Yes

      Sex
Class  Male Female
  1st    57    140
  2nd    14     80
  3rd    75     76
  Crew  192     20

#room=30을 추가하라 . 
patients = data.frame(name=c("철수","춘향","길동"),age=c(22,20,25),gender=factor(c("M","F","M")),blood.type=factor(c("A","O","B")))

patients

no.patients=data.frame(day=c(1:6),no=c(50,60,55,52,65,58))
no.patients

listPatients = list(patients=patients,no.patients=no.patients)
listPatients

$patients

name	age	gender	blood.type
철수	22	M	A
춘향	20	F	O
길동	25	M	B

$no.patients

day	no
1	50
2	60
3	55
4	52
5	65
6	58

listPatients$room=30
listPatients

$patients

name	age	gender	blood.type
철수	22	M	A
춘향	20	F	O
길동	25	M	B

$no.patients

day	no
1	50
2	60
3	55
4	52
5	65
6	58

$room

30

# 리스트 요소는 '요소명=NULL'형태로 제거할 수 있다. listPatients에 추가한 room을 다시 제거하라 
listPatients$room =NULL
listPatients

$patients

name	age	gender	blood.type
철수	22	M	A
춘향	20	F	O
길동	25	M	B

$no.patients

day	no
1	50
2	60
3	55
4	52
5	65
6	58

print(paste(x,y))
print(paste(x,y,sep="")) #빈칸 제거
print(paste0(x,y))#공백 제거

[1] "안녕 하세요"
[1] "안녕하세요"
[1] "안녕하세요"

#airquality 데이터는 어느 도시의 공기 질을 나타낸 데이터인가?New York
airquality

#평균 오존농도(Ozone)를 구하시오.
mean(airquality$Ozone, na.rm = T) # 정답

42.1293103448276

#airquality 데이터에서 바람이 가장 세게 분 날짜는 언제인가?
maxWind<-max(airquality$Wind)
maxWind

20.7

subset(airquality,Wind==max(airquality$Wind),c('Month','Day'))

#8월20일의 측정치를 조회하시오.

airquality[airquality$Month == 8 & airquality$Day == 20, ]

#온도가 가장 높은 날의 측정치를 조회하시오.
airquality [airquality$Temp == max(airquality$Temp), ]

#9월 평균온도와 바람의세기의 표준편차를 구하시오.

mean(airquality[airquality$Month == 9, ]$Temp)
sd(airquality[airquality$Month == 9, ]$Wind)

#2
a <- subset(airquality, subset = (Month == 9))
a$Temp
mean(a$Temp, na.rm = T)
sd(a$Wind)

76.9

3.46125351022848

<ol class=list-inline> <li>91</li> <li>92</li> <li>93</li> <li>93</li> <li>87</li> <li>84</li> <li>80</li> <li>78</li> <li>75</li> <li>73</li> <li>81</li> <li>76</li> <li>77</li> <li>71</li> <li>71</li> <li>78</li> <li>67</li> <li>76</li> <li>68</li> <li>82</li> <li>64</li> <li>71</li> <li>81</li> <li>69</li> <li>63</li> <li>70</li> <li>77</li> <li>75</li> <li>76</li> <li>68</li> </ol>

76.9

3.46125351022848

#1. 1부터 10까지, 0.5씩 증가시킨 값들로 구성된 벡터를 변수에 저장하시오.

a <-seq(1, 10, .5)

a

<ol class=list-inline> <li>1</li> <li>1.5</li> <li>2</li> <li>2.5</li> <li>3</li> <li>3.5</li> <li>4</li> <li>4.5</li> <li>5</li> <li>5.5</li> <li>6</li> <li>6.5</li> <li>7</li> <li>7.5</li> <li>8</li> <li>8.5</li> <li>9</li> <li>9.5</li> <li>10</li> </ol>

#2. 벡터의 평균, 표준편차를 구하시오
mean(a)
sd(a)

5.5

2.81365716935569

#사용자정의함수로 소수 출력하는 프로그램 
#정수를 입력받아 소수이면 True를,소수가 아니면 False를 반환하는 함수를 작성하라 .
#1부터 10까지 수 중에서 소수를 출력하는 프로그램을 만들어라 

pn <-function(i){
  check=0
  for (j in 1:i) {
    if(i%%j==0){
      check = check+1
    }
  }
  if(check==2){
    return(T)
  }
  else{
    return(F)
  }
}

pn(10) #10은 소수가 아님,FALSE출력

pn(5) # 5는 소수가 맞음,TRUE 출력