Pg 123. 분석 도전!
ggplot2패키지에는 미국 동북중부 437개 지역의 인구통계 정보를 담은 midwest라는 데이터가 들어있습니다. midwest데이터를 사용해 데이터 분석 문제를 해결해 보세요.
Q1. ggplot2의 midwest데이터를 데이터 프레임 형태로 불러온 다음 데이터의 특징을 파악하세요.
midwest <- as.data.frame(ggplot2::midwest)
summary(midwest)
## PID county state area
## Min. : 561 Length:437 Length:437 Min. :0.00500
## 1st Qu.: 670 Class :character Class :character 1st Qu.:0.02400
## Median :1221 Mode :character Mode :character Median :0.03000
## Mean :1437 Mean :0.03317
## 3rd Qu.:2059 3rd Qu.:0.03800
## Max. :3052 Max. :0.11000
## poptotal popdensity popwhite popblack
## Min. : 1701 Min. : 85.05 Min. : 416 Min. : 0
## 1st Qu.: 18840 1st Qu.: 622.41 1st Qu.: 18630 1st Qu.: 29
## Median : 35324 Median : 1156.21 Median : 34471 Median : 201
## Mean : 96130 Mean : 3097.74 Mean : 81840 Mean : 11024
## 3rd Qu.: 75651 3rd Qu.: 2330.00 3rd Qu.: 72968 3rd Qu.: 1291
## Max. :5105067 Max. :88018.40 Max. :3204947 Max. :1317147
## popamerindian popasian popother percwhite
## Min. : 4.0 Min. : 0 Min. : 0 Min. :10.69
## 1st Qu.: 44.0 1st Qu.: 35 1st Qu.: 20 1st Qu.:94.89
## Median : 94.0 Median : 102 Median : 66 Median :98.03
## Mean : 343.1 Mean : 1310 Mean : 1613 Mean :95.56
## 3rd Qu.: 288.0 3rd Qu.: 401 3rd Qu.: 345 3rd Qu.:99.07
## Max. :10289.0 Max. :188565 Max. :384119 Max. :99.82
## percblack percamerindan percasian percother
## Min. : 0.0000 Min. : 0.05623 Min. :0.0000 Min. :0.00000
## 1st Qu.: 0.1157 1st Qu.: 0.15793 1st Qu.:0.1737 1st Qu.:0.09102
## Median : 0.5390 Median : 0.21502 Median :0.2972 Median :0.17844
## Mean : 2.6763 Mean : 0.79894 Mean :0.4872 Mean :0.47906
## 3rd Qu.: 2.6014 3rd Qu.: 0.38362 3rd Qu.:0.5212 3rd Qu.:0.48050
## Max. :40.2100 Max. :89.17738 Max. :5.0705 Max. :7.52427
## popadults perchsd percollege percprof
## Min. : 1287 Min. :46.91 Min. : 7.336 Min. : 0.5203
## 1st Qu.: 12271 1st Qu.:71.33 1st Qu.:14.114 1st Qu.: 2.9980
## Median : 22188 Median :74.25 Median :16.798 Median : 3.8142
## Mean : 60973 Mean :73.97 Mean :18.273 Mean : 4.4473
## 3rd Qu.: 47541 3rd Qu.:77.20 3rd Qu.:20.550 3rd Qu.: 4.9493
## Max. :3291995 Max. :88.90 Max. :48.079 Max. :20.7913
## poppovertyknown percpovertyknown percbelowpoverty percchildbelowpovert
## Min. : 1696 Min. :80.90 Min. : 2.180 Min. : 1.919
## 1st Qu.: 18364 1st Qu.:96.89 1st Qu.: 9.199 1st Qu.:11.624
## Median : 33788 Median :98.17 Median :11.822 Median :15.270
## Mean : 93642 Mean :97.11 Mean :12.511 Mean :16.447
## 3rd Qu.: 72840 3rd Qu.:98.60 3rd Qu.:15.133 3rd Qu.:20.352
## Max. :5023523 Max. :99.86 Max. :48.691 Max. :64.308
## percadultpoverty percelderlypoverty inmetro category
## Min. : 1.938 Min. : 3.547 Min. :0.0000 Length:437
## 1st Qu.: 7.668 1st Qu.: 8.912 1st Qu.:0.0000 Class :character
## Median :10.008 Median :10.869 Median :0.0000 Mode :character
## Mean :10.919 Mean :11.389 Mean :0.3432
## 3rd Qu.:13.182 3rd Qu.:13.412 3rd Qu.:1.0000
## Max. :43.312 Max. :31.162 Max. :1.0000
Q2. poptotal(전체인구) 변수를 total로, popasian(아시아 인구) 변수를 asian으로 수정하세요.
library("dplyr")
##
## 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
midwest <- dplyr::rename(midwest, total = poptotal)
midwest <- dplyr::rename(midwest, asian = popasian)
summary(midwest)
## PID county state area
## Min. : 561 Length:437 Length:437 Min. :0.00500
## 1st Qu.: 670 Class :character Class :character 1st Qu.:0.02400
## Median :1221 Mode :character Mode :character Median :0.03000
## Mean :1437 Mean :0.03317
## 3rd Qu.:2059 3rd Qu.:0.03800
## Max. :3052 Max. :0.11000
## total popdensity popwhite popblack
## Min. : 1701 Min. : 85.05 Min. : 416 Min. : 0
## 1st Qu.: 18840 1st Qu.: 622.41 1st Qu.: 18630 1st Qu.: 29
## Median : 35324 Median : 1156.21 Median : 34471 Median : 201
## Mean : 96130 Mean : 3097.74 Mean : 81840 Mean : 11024
## 3rd Qu.: 75651 3rd Qu.: 2330.00 3rd Qu.: 72968 3rd Qu.: 1291
## Max. :5105067 Max. :88018.40 Max. :3204947 Max. :1317147
## popamerindian asian popother percwhite
## Min. : 4.0 Min. : 0 Min. : 0 Min. :10.69
## 1st Qu.: 44.0 1st Qu.: 35 1st Qu.: 20 1st Qu.:94.89
## Median : 94.0 Median : 102 Median : 66 Median :98.03
## Mean : 343.1 Mean : 1310 Mean : 1613 Mean :95.56
## 3rd Qu.: 288.0 3rd Qu.: 401 3rd Qu.: 345 3rd Qu.:99.07
## Max. :10289.0 Max. :188565 Max. :384119 Max. :99.82
## percblack percamerindan percasian percother
## Min. : 0.0000 Min. : 0.05623 Min. :0.0000 Min. :0.00000
## 1st Qu.: 0.1157 1st Qu.: 0.15793 1st Qu.:0.1737 1st Qu.:0.09102
## Median : 0.5390 Median : 0.21502 Median :0.2972 Median :0.17844
## Mean : 2.6763 Mean : 0.79894 Mean :0.4872 Mean :0.47906
## 3rd Qu.: 2.6014 3rd Qu.: 0.38362 3rd Qu.:0.5212 3rd Qu.:0.48050
## Max. :40.2100 Max. :89.17738 Max. :5.0705 Max. :7.52427
## popadults perchsd percollege percprof
## Min. : 1287 Min. :46.91 Min. : 7.336 Min. : 0.5203
## 1st Qu.: 12271 1st Qu.:71.33 1st Qu.:14.114 1st Qu.: 2.9980
## Median : 22188 Median :74.25 Median :16.798 Median : 3.8142
## Mean : 60973 Mean :73.97 Mean :18.273 Mean : 4.4473
## 3rd Qu.: 47541 3rd Qu.:77.20 3rd Qu.:20.550 3rd Qu.: 4.9493
## Max. :3291995 Max. :88.90 Max. :48.079 Max. :20.7913
## poppovertyknown percpovertyknown percbelowpoverty percchildbelowpovert
## Min. : 1696 Min. :80.90 Min. : 2.180 Min. : 1.919
## 1st Qu.: 18364 1st Qu.:96.89 1st Qu.: 9.199 1st Qu.:11.624
## Median : 33788 Median :98.17 Median :11.822 Median :15.270
## Mean : 93642 Mean :97.11 Mean :12.511 Mean :16.447
## 3rd Qu.: 72840 3rd Qu.:98.60 3rd Qu.:15.133 3rd Qu.:20.352
## Max. :5023523 Max. :99.86 Max. :48.691 Max. :64.308
## percadultpoverty percelderlypoverty inmetro category
## Min. : 1.938 Min. : 3.547 Min. :0.0000 Length:437
## 1st Qu.: 7.668 1st Qu.: 8.912 1st Qu.:0.0000 Class :character
## Median :10.008 Median :10.869 Median :0.0000 Mode :character
## Mean :10.919 Mean :11.389 Mean :0.3432
## 3rd Qu.:13.182 3rd Qu.:13.412 3rd Qu.:1.0000
## Max. :43.312 Max. :31.162 Max. :1.0000
Q3. total,asian변수를 이용해 ‘전체 인구 대비 아시아 인구 백분율’ 파생 변수를 만들고, 히스토그램을 만들어 도시들이 어떻게 분호하는지 살펴보세요.
library("dplyr")
midwest$percentage_of_asian <- (midwest$asian/midwest$total)*100
hist(midwest$percentage_of_asian)
Q4. 아시아 인구 백분율 전체 평균을 구하고 평균을 초과하면 “large”, 그외에는 “small”을 부여하는 파생변수 생성
mean(midwest$percentage_of_asian)
## [1] 0.4872462
midwest$test <- ifelse(midwest$percentage_of_asian > 0.4872462, "large", "small")
table(midwest$test)
##
## large small
## 119 318
Q5. “large”와 “small”에 해당하는 지역이 얼마나 되는지 빈도표와 빈도 막대 그래프 만들어서 확인.
library(ggplot2)
##
## Attaching package: 'ggplot2'
## The following object is masked _by_ '.GlobalEnv':
##
## midwest
table(midwest$test)
##
## large small
## 119 318
qplot(midwest$test)
