[빅데이터 청년인재] DATA Handling
기본 R
##
## 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#wide format data1
wide<-data.frame(subject=c(1,2,3,4),
sex=c('M','F','F','M'),
time1=c(7.9,6.3,9.5,11.5),
time2=c(12.3,10.6,13.1,13.4),
time3=c(10.7,11.1,13.8,12.9))
wide## 'data.frame': 4 obs. of 5 variables:
## $ subject: num 1 2 3 4
## $ sex : Factor w/ 2 levels "F","M": 2 1 1 2
## $ time1 : num 7.9 6.3 9.5 11.5
## $ time2 : num 12.3 10.6 13.1 13.4
## $ time3 : num 10.7 11.1 13.8 12.9데이터 형식 변환
long format data
## 'data.frame': 12 obs. of 4 variables:
## $ subject: num 1 2 3 4 1 2 3 4 1 2 ...
## $ sex : Factor w/ 2 levels "F","M": 2 1 1 2 2 1 1 2 2 1 ...
## $ time : Factor w/ 3 levels "time1","time2",..: 1 1 1 1 2 2 2 2 3 3 ...
## $ value : num 7.9 6.3 9.5 11.5 12.3 10.6 13.1 13.4 10.7 11.1 ...## 'data.frame': 12 obs. of 4 variables:
## $ subject: num 1 2 3 4 1 2 3 4 1 2 ...
## $ sex : Factor w/ 2 levels "F","M": 2 1 1 2 2 1 1 2 2 1 ...
## $ time : Factor w/ 3 levels "1","2","3": 1 1 1 1 2 2 2 2 3 3 ...
## $ value : num 7.9 6.3 9.5 11.5 12.3 10.6 13.1 13.4 10.7 11.1 ...wide format data2
예제 long format으로 바꾸기
yes<-data.frame(subject=c(1,2,3),
name=c("김철수","이영희","박길동"),
middle=c(70,80,90),
final=c(75,70,78))
yes## 'data.frame': 3 obs. of 4 variables:
## $ subject: num 1 2 3
## $ name : Factor w/ 3 levels "김철수","박길동",..: 1 3 2
## $ middle : num 70 80 90
## $ final : num 75 70 78예제 wide format으로 바꾸기
- iris data
## 'data.frame': 150 obs. of 5 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...iris[,"id"]<-1:nrow(iris)
iris_long<-gather(iris,measure,value,colnames(iris)[1:4], factor_key=T)
iris_wide<-spread(iris_long,measure,value)
iris_wide#read.table(file.choose(),)
read.csv("C:/Users/Gyu-ri Kim/Desktop/청년인재/bigdatacampus/data/iris.csv", header=T, encoding="UTF-8")## [1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9 5.4 4.8 4.8 4.3 5.8 5.7 5.4
## [18] 5.1 5.7 5.1 5.4 5.1 4.6 5.1 4.8 5.0 5.0 5.2 5.2 4.7 4.8 5.4 5.2 5.5
## [35] 4.9 5.0 5.5 4.9 4.4 5.1 5.0 4.5 4.4 5.0 5.1 4.8 5.1 4.6 5.3 5.0 7.0
## [52] 6.4 6.9 5.5 6.5 5.7 6.3 4.9 6.6 5.2 5.0 5.9 6.0 6.1 5.6 6.7 5.6 5.8
## [69] 6.2 5.6 5.9 6.1 6.3 6.1 6.4 6.6 6.8 6.7 6.0 5.7 5.5 5.5 5.8 6.0 5.4
## [86] 6.0 6.7 6.3 5.6 5.5 5.5 6.1 5.8 5.0 5.6 5.7 5.7 6.2 5.1 5.7 6.3 5.8
## [103] 7.1 6.3 6.5 7.6 4.9 7.3 6.7 7.2 6.5 6.4 6.8 5.7 5.8 6.4 6.5 7.7 7.7
## [120] 6.0 6.9 5.6 7.7 6.3 6.7 7.2 6.2 6.1 6.4 7.2 7.4 7.9 6.4 6.3 6.1 7.7
## [137] 6.3 6.4 6.0 6.9 6.7 6.9 5.8 6.8 6.7 6.7 6.3 6.5 6.2 5.9## [1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9 5.4 4.8 4.8 4.3 5.8 5.7 5.4
## [18] 5.1 5.7 5.1 5.4 5.1 4.6 5.1 4.8 5.0 5.0 5.2 5.2 4.7 4.8 5.4 5.2 5.5
## [35] 4.9 5.0 5.5 4.9 4.4 5.1 5.0 4.5 4.4 5.0 5.1 4.8 5.1 4.6 5.3 5.0 7.0
## [52] 6.4 6.9 5.5 6.5 5.7 6.3 4.9 6.6 5.2 5.0 5.9 6.0 6.1 5.6 6.7 5.6 5.8
## [69] 6.2 5.6 5.9 6.1 6.3 6.1 6.4 6.6 6.8 6.7 6.0 5.7 5.5 5.5 5.8 6.0 5.4
## [86] 6.0 6.7 6.3 5.6 5.5 5.5 6.1 5.8 5.0 5.6 5.7 5.7 6.2 5.1 5.7 6.3 5.8
## [103] 7.1 6.3 6.5 7.6 4.9 7.3 6.7 7.2 6.5 6.4 6.8 5.7 5.8 6.4 6.5 7.7 7.7
## [120] 6.0 6.9 5.6 7.7 6.3 6.7 7.2 6.2 6.1 6.4 7.2 7.4 7.9 6.4 6.3 6.1 7.7
## [137] 6.3 6.4 6.0 6.9 6.7 6.9 5.8 6.8 6.7 6.7 6.3 6.5 6.2 5.9## [1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9 5.4 4.8 4.8 4.3 5.8 5.7 5.4
## [18] 5.1 5.7 5.1 5.4 5.1 4.6 5.1 4.8 5.0 5.0 5.2 5.2 4.7 4.8 5.4 5.2 5.5
## [35] 4.9 5.0 5.5 4.9 4.4 5.1 5.0 4.5 4.4 5.0 5.1 4.8 5.1 4.6 5.3 5.0 7.0
## [52] 6.4 6.9 5.5 6.5 5.7 6.3 4.9 6.6 5.2 5.0 5.9 6.0 6.1 5.6 6.7 5.6 5.8
## [69] 6.2 5.6 5.9 6.1 6.3 6.1 6.4 6.6 6.8 6.7 6.0 5.7 5.5 5.5 5.8 6.0 5.4
## [86] 6.0 6.7 6.3 5.6 5.5 5.5 6.1 5.8 5.0 5.6 5.7 5.7 6.2 5.1 5.7 6.3 5.8
## [103] 7.1 6.3 6.5 7.6 4.9 7.3 6.7 7.2 6.5 6.4 6.8 5.7 5.8 6.4 6.5 7.7 7.7
## [120] 6.0 6.9 5.6 7.7 6.3 6.7 7.2 6.2 6.1 6.4 7.2 7.4 7.9 6.4 6.3 6.1 7.7
## [137] 6.3 6.4 6.0 6.9 6.7 6.9 5.8 6.8 6.7 6.7 6.3 6.5 6.2 5.9자료 정제
#install.packages("tidyr")
library(tidyr)
widee <- data.frame(name = c("김철수","이영희","박길동"),
middle= c(70,80,90),
final = c(75,70,78))
longg <- gather(widee, time,score,middle:final,factor_key = T)
widee2 <- spread(longg,time,score)
head(iris,10)iris[,"id"] <- 1:nrow(iris)
iris.long <- gather(iris,measure,value,colnames(iris)[1:4],factor_key = T)
iris.wide <- spread(iris.long,measure,value)
head(iris.wide)test <- read.csv("C:/Users/Gyu-ri Kim/Desktop/청년인재/bigdatacampus/data/test.csv")
iris <- iris
orthodont <- read.csv("C:/Users/Gyu-ri Kim/Desktop/청년인재/bigdatacampus/data/orthodont.csv")
iris.txt <- read.table("C:/Users/Gyu-ri Kim/Desktop/청년인재/bigdatacampus/data/iris.txt")
iris[,1]## [1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9 5.4 4.8 4.8 4.3 5.8 5.7 5.4
## [18] 5.1 5.7 5.1 5.4 5.1 4.6 5.1 4.8 5.0 5.0 5.2 5.2 4.7 4.8 5.4 5.2 5.5
## [35] 4.9 5.0 5.5 4.9 4.4 5.1 5.0 4.5 4.4 5.0 5.1 4.8 5.1 4.6 5.3 5.0 7.0
## [52] 6.4 6.9 5.5 6.5 5.7 6.3 4.9 6.6 5.2 5.0 5.9 6.0 6.1 5.6 6.7 5.6 5.8
## [69] 6.2 5.6 5.9 6.1 6.3 6.1 6.4 6.6 6.8 6.7 6.0 5.7 5.5 5.5 5.8 6.0 5.4
## [86] 6.0 6.7 6.3 5.6 5.5 5.5 6.1 5.8 5.0 5.6 5.7 5.7 6.2 5.1 5.7 6.3 5.8
## [103] 7.1 6.3 6.5 7.6 4.9 7.3 6.7 7.2 6.5 6.4 6.8 5.7 5.8 6.4 6.5 7.7 7.7
## [120] 6.0 6.9 5.6 7.7 6.3 6.7 7.2 6.2 6.1 6.4 7.2 7.4 7.9 6.4 6.3 6.1 7.7
## [137] 6.3 6.4 6.0 6.9 6.7 6.9 5.8 6.8 6.7 6.7 6.3 6.5 6.2 5.9filter
## 'data.frame': 150 obs. of 6 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ id : int 1 2 3 4 5 6 7 8 9 10 ...행을 추출하는 함수이다.
‘행을 추출하는 함수이다.’
arrange
select
mutate
dplyr 실습
1.여성만 선택하기
## 'data.frame': 190 obs. of 10 variables:
## $ Sex : Factor w/ 2 levels "F","M": 1 2 1 1 2 2 2 2 2 2 ...
## $ Age : int 26 30 22 46 41 28 53 60 32 34 ...
## $ Height: num 157 176 161 164 164 ...
## $ Weight: num 43.7 93.3 61.9 68 72.2 79.7 59.4 66.2 63.8 69.6 ...
## $ SBP : int 100 120 110 100 100 130 110 130 110 110 ...
## $ DBP : int 70 70 70 60 70 90 70 90 70 80 ...
## $ Sugar : num 83.5 83.6 86.4 86.5 86.7 86.9 87.4 88 88.1 88.1 ...
## $ Fat : num 123 73.9 56.3 162.3 132.5 ...
## $ Chol : num 188 146 226 146 164 ...
## $ DM : Factor w/ 2 levels "N","Y": 1 1 1 1 1 1 1 1 1 1 ...2.키가 170보다 큰 행
3.키가 170보다 크고 몸무게가 65보다 큰 행
4.이완기혈압이 100보다 큰 행
5.BMI열을 추가하시오
## 'data.frame': 190 obs. of 11 variables:
## $ Sex : Factor w/ 2 levels "F","M": 1 2 1 1 2 2 2 2 2 2 ...
## $ Age : int 26 30 22 46 41 28 53 60 32 34 ...
## $ Height: num 157 176 161 164 164 ...
## $ Weight: num 43.7 93.3 61.9 68 72.2 79.7 59.4 66.2 63.8 69.6 ...
## $ SBP : int 100 120 110 100 100 130 110 130 110 110 ...
## $ DBP : int 70 70 70 60 70 90 70 90 70 80 ...
## $ Sugar : num 83.5 83.6 86.4 86.5 86.7 86.9 87.4 88 88.1 88.1 ...
## $ Fat : num 123 73.9 56.3 162.3 132.5 ...
## $ Chol : num 188 146 226 146 164 ...
## $ DM : Factor w/ 2 levels "N","Y": 1 1 1 1 1 1 1 1 1 1 ...
## $ BMI : num 17.8 30.3 23.8 25.3 27 ...6.BMI가 25보다 큰행
mdis tst
## New names:
## * `` -> ...10## Classes 'tbl_df', 'tbl' and 'data.frame': 285534 obs. of 10 variables:
## $ 사망연월일 : num 1 1 1 1 1 1 1 1 1 1 ...
## $ 사망연령(각세) : num 20170101 20170101 20170101 20170101 20170101 ...
## $ 사망장소 : num 0 0 21 21 24 25 25 28 29 31 ...
## $ 사망원인1 : num 1 2 2 2 5 2 5 5 2 2 ...
## $ 사망원인2 : chr "R99" "P249" "C716" "G809" ...
## $ 사망원인 103항목 분류: chr NA NA NA NA ...
## $ 사망원인 56항목 분류 : num 94 92 42 61 96 101 96 96 94 74 ...
## $ 사망자의 국적구분 : num NA 47 25 NA 50 55 50 50 NA 38 ...
## $ 사망자의 (이전)국적 : num 1 1 1 1 1 1 1 1 1 1 ...
## $ ...10 : logi NA NA NA NA NA NA ...## 'data.frame': 285534 obs. of 10 variables:
## $ 사망연월일 : int 1 1 1 1 1 1 1 1 1 1 ...
## $ 사망연령(각세) : int 20170101 20170101 20170101 20170101 20170101 20170101 20170101 20170101 20170101 20170101 ...
## $ 사망장소 : int 0 0 21 21 24 25 25 28 29 31 ...
## $ 사망원인1 : int 1 2 2 2 5 2 5 5 2 2 ...
## $ 사망원인2 : Factor w/ 2428 levels "A020","A021",..: 1985 1801 410 923 2241 2066 2241 2009 1985 1228 ...
## $ 사망원인 103항목 분류: Factor w/ 764 levels "","V011","V021",..: 1 1 1 1 62 599 63 57 1 1 ...
## $ 사망원인 56항목 분류 : int 94 92 42 61 96 101 96 96 94 74 ...
## $ 사망자의 국적구분 : int NA 47 25 NA 50 55 50 50 NA 38 ...
## $ 사망자의 (이전)국적 : int 1 1 1 1 1 1 1 1 1 1 ...
## $ NA : int NA NA NA NA NA NA NA NA NA NA ...xlsx,spss파일 불러오기
## 'data.frame': 9 obs. of 3 variables:
## $ x : num 2 4 5 6 6 5 6 7 9
## $ y : num 3 5 6 2 5 8 9 4 10
## $ group: Factor w/ 3 levels "C ","T1","T2": 1 1 1 2 2 2 3 3 3
## - attr(*, "codepage")= int 65001저장 및 로드
문제
곤충학자 A는 오느 숲에서 소나무에 사는 솔잎흑나방의 개체 수를 세어보고 있다. 각 나무에서 발견된 솔잎흑나방의 수는 아래와 같을 때 각 질문에 답하시오.
- 몇 그루의 나무를 살펴보았나?
## [1] 12## num [1:12] 5 6 7 10 10 11 20 2 3 10 ...- 총 몇 마리의 솔잎흑나방ㅇ르 관찰하였나?
## [1] 107- 평균적으로 몇 마리가 발견되었나?
## [1] 8.916667- 발견된 솔잎흑나방 수의 표준편자는?
## [1] 4.851585- 가장 많이 발견된 나무에서는 몇 마리가 관찰되었나?
## [1] 20- 가장 적게 발견된 나무에서는 몇 마리가 관찰되었나?
## [1] 2- 관찰된 솔읲흑나방수의 범위는?
## [1] 2 20- 뉴욕 항공 데이터로 실습하기
## -- Attaching packages ---------------------------------------------- tidyverse 1.2.1 --## √ ggplot2 3.2.0 √ purrr 0.3.2
## √ tibble 2.1.1 √ stringr 1.4.0
## √ readr 1.3.1 √ forcats 0.4.0## -- Conflicts ------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()##
## 1
## 27004## Classes 'tbl_df', 'tbl' and 'data.frame': 336776 obs. of 19 variables:
## $ year : int 2013 2013 2013 2013 2013 2013 2013 2013 2013 2013 ...
## $ month : int 1 1 1 1 1 1 1 1 1 1 ...
## $ day : int 1 1 1 1 1 1 1 1 1 1 ...
## $ dep_time : int 517 533 542 544 554 554 555 557 557 558 ...
## $ sched_dep_time: int 515 529 540 545 600 558 600 600 600 600 ...
## $ dep_delay : num 2 4 2 -1 -6 -4 -5 -3 -3 -2 ...
## $ arr_time : int 830 850 923 1004 812 740 913 709 838 753 ...
## $ sched_arr_time: int 819 830 850 1022 837 728 854 723 846 745 ...
## $ arr_delay : num 11 20 33 -18 -25 12 19 -14 -8 8 ...
## $ carrier : chr "UA" "UA" "AA" "B6" ...
## $ flight : int 1545 1714 1141 725 461 1696 507 5708 79 301 ...
## $ tailnum : chr "N14228" "N24211" "N619AA" "N804JB" ...
## $ origin : chr "EWR" "LGA" "JFK" "JFK" ...
## $ dest : chr "IAH" "IAH" "MIA" "BQN" ...
## $ air_time : num 227 227 160 183 116 150 158 53 140 138 ...
## $ distance : num 1400 1416 1089 1576 762 ...
## $ hour : num 5 5 5 5 6 5 6 6 6 6 ...
## $ minute : num 15 29 40 45 0 58 0 0 0 0 ...
## $ time_hour : POSIXct, format: "2013-01-01 05:00:00" "2013-01-01 05:00:00" ...