Ch9_데이터구조_2.데이터 읽고 쓰기

1. 데이터프레임 생성

df <- data.frame(class = c(1, 2, 3, 4), 
+                  korean = c(81, 79, 85, 83), 
+                  english = c(82, 86, 83, 87), 
+                  math = c(78, 79, 81, 80))
> df
  class korean english math
1     1     81      82   78
2     2     79      86   79
3     3     85      83   81
4     4     83      87   80

1.1 데이터 저장

write.csv()

write.csv(df, "class_mean.csv")
write.csv(df, "class_mean.csv") #write.csv(데이터이름, "파일명.csv")

2. 내장 데이터셋 읽어오기

> data("iris")
> write.csv(iris, "iris2.csv" )
> setwd("C:/Users/USER/Dropbox/R/Mybook/data")
> write.csv(iris, "iris2.csv" )

2.2 파일불러오기

### 1. csv파일 불러오기, 별도의 패키지 없이 내장 함수 사용(p202)
> read.csv("class_mean.csv") #단순히 읽음
  X class korean english math
1 1     1     81      82   78
2 2     2     79      86   79
3 3     3     85      83   81
4 4     4     83      87   80
>

> data <- read.csv("class_mean.csv")
> str(data)
'data.frame':	4 obs. of  5 variables:
 $ X      : int  1 2 3 4
 $ class  : int  1 2 3 4
 $ korean : int  81 79 85 83
 $ english: int  82 86 83 87
 $ math   : int  78 79 81 80
> View(data)

2.엑셀파일 불러오기

> install.packages("gapminder")
WARNING: Rtools is required to build R packages but is not currently installed. Please download and install the appropriate version of Rtools before proceeding:

https://cran.rstudio.com/bin/windows/Rtools/
Installing package into ‘C:/Users/USER/Documents/R/win-library/4.0’
(as ‘lib’ is unspecified)
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.0/gapminder_0.3.0.zip'
Content type 'application/zip' length 2031907 bytes (1.9 MB)
downloaded 1.9 MB

package ‘gapminder’ successfully unpacked and MD5 sums checked

The downloaded binary packages are in
	C:\Users\USER\AppData\Local\Temp\RtmpmohEY4\downloaded_packages

install.packages("gapminder")
library(gapminder)

?gapminder

> gapminder <- as.data.frame(gapminder)
> head(gapminder)
      country continent year lifeExp      pop gdpPercap
1 Afghanistan      Asia 1952  28.801  8425333  779.4453
2 Afghanistan      Asia 1957  30.332  9240934  820.8530
3 Afghanistan      Asia 1962  31.997 10267083  853.1007
4 Afghanistan      Asia 1967  34.020 11537966  836.1971
5 Afghanistan      Asia 1972  36.088 13079460  739.9811
6 Afghanistan      Asia 1977  38.438 14880372  786.1134
> tail(gapminder)
      country continent year lifeExp      pop gdpPercap
1699 Zimbabwe    Africa 1982  60.363  7636524  788.8550
1700 Zimbabwe    Africa 1987  62.351  9216418  706.1573
1701 Zimbabwe    Africa 1992  60.377 10704340  693.4208
1702 Zimbabwe    Africa 1997  46.809 11404948  792.4500
1703 Zimbabwe    Africa 2002  39.989 11926563  672.0386
1704 Zimbabwe    Africa 2007  43.487 12311143  469.7093

1. 데이터 추출

> data(iris)
> colnames(iris)
[1] "Sepal.Length" "Sepal.Width"  "Petal.Length" "Petal.Width"  "Species"

iris["Species"]=="setosa"
       Species
  [1,]    TRUE
  [2,]    TRUE
  [3,]    TRUE
  [4,]    TRUE
  [5,]    TRUE
  [6,]    TRUE
  [7,]    TRUE
  [8,]    TRUE
  [9,]    TRUE
 [10,]    TRUE

#library dplyr

library(dplyr)

> filter(iris, Species=="setosa")
   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1           5.1         3.5          1.4         0.2  setosa
2           4.9         3.0          1.4         0.2  setosa
3           4.7         3.2          1.3         0.2  setosa
4           4.6         3.1          1.5         0.2  setosa
5           5.0         3.6          1.4         0.2  setosa
6           5.4         3.9          1.7         0.4  setosa
7           4.6         3.4          1.4         0.3  setosa
8           5.0         3.4          1.5         0.2  setosa
9           4.4         2.9          1.4         0.2  setosa
10          4.9         3.1          1.5         0.1  setosa

> data <- filter(iris, Species=="setosa")
> dim(data)
[1] 50  5
> summary(data)
  Sepal.Length    Sepal.Width     Petal.Length    Petal.Width          Species  
 Min.   :4.300   Min.   :2.300   Min.   :1.000   Min.   :0.100   setosa    :50  
 1st Qu.:4.800   1st Qu.:3.200   1st Qu.:1.400   1st Qu.:0.200   versicolor: 0  
 Median :5.000   Median :3.400   Median :1.500   Median :0.200   virginica : 0  
 Mean   :5.006   Mean   :3.428   Mean   :1.462   Mean   :0.246                  
 3rd Qu.:5.200   3rd Qu.:3.675   3rd Qu.:1.575   3rd Qu.:0.300                  
 Max.   :5.800   Max.   :4.400   Max.   :1.900   Max.   :0.600

예 : Petal 길이가 평균값 이하인 붓꽃

> summary(iris)
  Sepal.Length    Sepal.Width     Petal.Length    Petal.Width          Species  
 Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100   setosa    :50  
 1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300   versicolor:50  
 Median :5.800   Median :3.000   Median :4.350   Median :1.300   virginica :50  
 Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199                  
 3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800                  
 Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500

> data_1 <- filter(iris, Petal.Length<=3.765)
> dim(data_1)
[1] 57  5
> summary(data_1)
  Sepal.Length    Sepal.Width     Petal.Length    Petal.Width           Species  
 Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.1000   setosa    :50  
 1st Qu.:4.800   1st Qu.:3.000   1st Qu.:1.400   1st Qu.:0.2000   versicolor: 7  
 Median :5.000   Median :3.400   Median :1.500   Median :0.2000   virginica : 0  
 Mean   :5.037   Mean   :3.307   Mean   :1.702   Mean   :0.3456                  
 3rd Qu.:5.200   3rd Qu.:3.600   3rd Qu.:1.600   3rd Qu.:0.4000                  
 Max.   :5.800   Max.   :4.400   Max.   :3.700   Max.   :1.3000

subset()

subset(x, 조건, 열)

#열 작성 않을 시 전체 열

> subset(iris, Species=="setosa")
   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1           5.1         3.5          1.4         0.2  setosa
2           4.9         3.0          1.4         0.2  setosa
3           4.7         3.2          1.3         0.2  setosa
4           4.6         3.1          1.5         0.2  setosa

> subset(iris, Petal.Length<=3.76)
   Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1           5.1         3.5          1.4         0.2     setosa
2           4.9         3.0          1.4         0.2     setosa
3           4.7         3.2          1.3         0.2     setosa
4           4.6         3.1          1.5         0.2     setosa
5           5.0         3.6          1.4         0.2     setosa
6           5.4         3.9          1.7         0.4     setosa
7           4.6         3.4          1.4         0.3     setosa
8           5.0         3.4          1.5         0.2     setosa
9           4.4         2.9          1.4         0.2     setosa
10          4.9         3.1          1.5         0.1     setosa

3.2 일괄처리하기

ifelse()

> x <- c(1:10)
> x
 [1]  1  2  3  4  5  6  7  8  9 10
> ifelse(x%%2==1, T, F)
 [1]  TRUE FALSE  TRUE FALSE  TRUE FALSE  TRUE FALSE  TRUE FALSE
> x[ifelse(x%%2==1, T, F)]
[1] 1 3 5 7 9

> iris$"Petal.Mean" <- ifelse(iris$Petal.Length>=3.76, "above", "below")
> head(iris)
  Sepal.Length Sepal.Width Petal.Length Petal.Width Species Petal.Mean
1          5.1         3.5          1.4         0.2  setosa      below
2          4.9         3.0          1.4         0.2  setosa      below
3          4.7         3.2          1.3         0.2  setosa      below
4          4.6         3.1          1.5         0.2  setosa      below
5          5.0         3.6          1.4         0.2  setosa      below
6          5.4         3.9          1.7         0.4  setosa      below

apply(x, 1(행)or2(열), 함수)

> set.seed(1)
> exams <- data.frame(ID=c(1:10),
+                     ex1=sample(x=60:100, size=10),
+                     ex2=sample(x=50:95, size=10),
+                     ex3=sample(x=70:99, size=10),
+                     ex4=sample(x=63:90, size=10),
+                     ex5=sample(x=70:90, size=10))
> exams
   ID ex1 ex2 ex3 ex4 ex5
1   1  63  91  71  72  76
2   2  98  59  79  68  88
3   3  60  56  94  77  79
4   4  93  58  81  82  75
5   5  82  64  84  87  83
6   6  73  70  70  74  71
7   7  77  86  89  89  82
8   8  92  74  72  70  85
9   9  80  89  75  85  87
10 10  97  87  98  84  84

> exams$ID <- apply(exams[1], 1, as.factor)
> str(exams$ID)
 Factor w/ 10 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10
 
> apply(exams[2:6],2, max)
ex1 ex2 ex3 ex4 ex5 
 98  91  98  89  88 
> apply(exams[2:6],2, min)
ex1 ex2 ex3 ex4 ex5 
 60  56  70  68  71

사용자정의 함수

함수이름 <- function(인자1, 인자2...){
    함수 동작 시 수행할 코드
    return(반환값)
}

myfunc <- function(x){
  result <- ifelse(x>=70, "Pass","Fail")
  return(result)
}

> myfunc(80)
[1] "Pass"
> myfunc(60)
[1] "Fail"
> apply(exams,2,myfunc)
      ID     ex1    ex2    ex3    ex4    ex5   
 [1,] "Fail" "Fail" "Pass" "Pass" "Pass" "Pass"
 [2,] "Fail" "Pass" "Fail" "Pass" "Fail" "Pass"
 [3,] "Fail" "Fail" "Fail" "Pass" "Pass" "Pass"
 [4,] "Fail" "Pass" "Fail" "Pass" "Pass" "Pass"
 [5,] "Fail" "Pass" "Fail" "Pass" "Pass" "Pass"
 [6,] "Fail" "Pass" "Pass" "Pass" "Pass" "Pass"
 [7,] "Fail" "Pass" "Pass" "Pass" "Pass" "Pass"
 [8,] "Pass" "Pass" "Pass" "Pass" "Pass" "Pass"
 [9,] "Pass" "Pass" "Pass" "Pass" "Pass" "Pass"
[10,] "Fail" "Pass" "Pass" "Pass" "Pass" "Pass"