map_vis
2023-01-24
shp 파일을 불러와서 시각화하고 행정자료와 결합하기
shp 파일 불러오기
library(rgdal)## 필요한 패키지를 로딩중입니다: sp## Please note that rgdal will be retired during 2023,
## plan transition to sf/stars/terra functions using GDAL and PROJ
## at your earliest convenience.
## See https://r-spatial.org/r/2022/04/12/evolution.html and https://github.com/r-spatial/evolution
## rgdal: version: 1.6-3, (SVN revision 1187)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 3.5.2, released 2022/09/02
## Path to GDAL shared files: C:/Users/manne/AppData/Local/R/win-library/4.2/rgdal/gdal
## GDAL binary built with GEOS: TRUE
## Loaded PROJ runtime: Rel. 8.2.1, January 1st, 2022, [PJ_VERSION: 821]
## Path to PROJ shared files: C:/Users/manne/AppData/Local/R/win-library/4.2/rgdal/proj
## PROJ CDN enabled: FALSE
## Linking to sp version:1.5-1
## To mute warnings of possible GDAL/OSR exportToProj4() degradation,
## use options("rgdal_show_exportToProj4_warnings"="none") before loading sp or rgdal.library(ggplot2)
library(dplyr)##
## 다음의 패키지를 부착합니다: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union## shp 파일을 불러온다.
map <- readOGR("C:\\r_project\\mapping\\sig.shp", encoding = 'CP949')## Warning: OGR support is provided by the sf and terra packages among others## Warning: OGR support is provided by the sf and terra packages among others## Warning: OGR support is provided by the sf and terra packages among others## Warning: GDAL support is provided by the sf and terra packages among others## Warning: GDAL support is provided by the sf and terra packages among others
## Warning: GDAL support is provided by the sf and terra packages among others## Warning: OGR support is provided by the sf and terra packages among others## Warning: OGR support is provided by the sf and terra packages among others## Warning: OGR support is provided by the sf and terra packages among others## Warning: OGR support is provided by the sf and terra packages among others## OGR data source with driver: ESRI Shapefile
## Source: "C:\r_project\mapping\sig.shp", layer: "sig"
## with 250 features
## It has 3 fields## Warning: GDAL support is provided by the sf and terra packages among others## Warning: GDAL support is provided by the sf and terra packages among others
## Warning: GDAL support is provided by the sf and terra packages among others## R에서 사용가능하도록 변환한다.
df_map <- fortify(map)## Regions defined for each Polygonshead(df_map)## long lat order hole piece id group
## 1 956615.5 1953567 1 FALSE 1 0 0.1
## 2 956621.6 1953565 2 FALSE 1 0 0.1
## 3 956626.2 1953564 3 FALSE 1 0 0.1
## 4 956638.8 1953562 4 FALSE 1 0 0.1
## 5 956659.1 1953559 5 FALSE 1 0 0.1
## 6 956661.5 1953558 6 FALSE 1 0 0.1## 기본적인 전국지도를 그려본다.
ggplot(data = df_map, aes(x = long, y = lat, group = group)) +
geom_polygon(fill='white', color='black')
## 축척을 고정한다.
ggplot(data = df_map, aes(x = long, y = lat, group = group)) +
geom_polygon(fill='white', color='black') +
coord_quickmap()
서울만 추출해서 그려보자.
## 지도의 기본데이터만 추출한다.
df_map_info <- map@data
## df_map과 df_map_info의 id를 매칭한다.
df_map_info$id <- 1:nrow(df_map_info) - 1
## 시도 구분 id를 뽑아낸다.
df_map_info$sido <- as.numeric(substr(df_map_info$SIG_CD, start = 1, stop = 2))
head(df_map_info)## SIG_CD SIG_ENG_NM SIG_KOR_NM id sido
## 0 11110 Jongno-gu 종로구 0 11
## 1 11140 Jung-gu 중구 1 11
## 2 11170 Yongsan-gu 용산구 2 11
## 3 11200 Seongdong-gu 성동구 3 11
## 4 11215 Gwangjin-gu 광진구 4 11
## 5 11230 Dongdaemun-gu 동대문구 5 11head(df_map)## long lat order hole piece id group
## 1 956615.5 1953567 1 FALSE 1 0 0.1
## 2 956621.6 1953565 2 FALSE 1 0 0.1
## 3 956626.2 1953564 3 FALSE 1 0 0.1
## 4 956638.8 1953562 4 FALSE 1 0 0.1
## 5 956659.1 1953559 5 FALSE 1 0 0.1
## 6 956661.5 1953558 6 FALSE 1 0 0.1## 서울을 추출해 보자
id_sido <- df_map_info[df_map_info$sido == 11, "id"]
id_sido## [1] 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24## 서울만 추출하여 뽑아낸다.
df_map2 <- df_map[df_map$id %in% id_sido, ]
df_map2_info <- df_map_info[df_map_info$id %in% id_sido, ]
summary(df_map2_info)## SIG_CD SIG_ENG_NM SIG_KOR_NM id
## Length:25 Length:25 Length:25 Min. : 0
## Class :character Class :character Class :character 1st Qu.: 6
## Mode :character Mode :character Mode :character Median :12
## Mean :12
## 3rd Qu.:18
## Max. :24
## sido
## Min. :11
## 1st Qu.:11
## Median :11
## Mean :11
## 3rd Qu.:11
## Max. :11head(df_map2_info)## SIG_CD SIG_ENG_NM SIG_KOR_NM id sido
## 0 11110 Jongno-gu 종로구 0 11
## 1 11140 Jung-gu 중구 1 11
## 2 11170 Yongsan-gu 용산구 2 11
## 3 11200 Seongdong-gu 성동구 3 11
## 4 11215 Gwangjin-gu 광진구 4 11
## 5 11230 Dongdaemun-gu 동대문구 5 11head(df_map2)## long lat order hole piece id group
## 1 956615.5 1953567 1 FALSE 1 0 0.1
## 2 956621.6 1953565 2 FALSE 1 0 0.1
## 3 956626.2 1953564 3 FALSE 1 0 0.1
## 4 956638.8 1953562 4 FALSE 1 0 0.1
## 5 956659.1 1953559 5 FALSE 1 0 0.1
## 6 956661.5 1953558 6 FALSE 1 0 0.1## 기본적인 서울 지도를 그려보자.
ggplot(data = df_map2,
aes(x = long, y = lat,
group = group)) +
geom_polygon(color = "black", fill = "white") +
theme(legend.position = "none")
### 서울 행정자료와 결합해 보자
서울 행정자료 불러오기 - 인구 자료
seoul0 <- read.csv("C:\\r_project\\dv\\201812_202212_주민등록인구및세대현황_연간.csv",
fileEncoding = "euc-kr")
seoul0 <- seoul0[-1,]
library(reshape2)
dim(seoul0)## [1] 25 31seoul1 <- melt(seoul0, id.vars = c("행정구역"))
names(seoul1) <- c("id", "index0", "value")
seoul1$year <- as.numeric(substr(seoul1$index0, 2, 5))
seoul1$type <- substr(seoul1$index0, 8, 20)
seoul1 <- seoul1[, -2]
seoul1$value <- as.numeric(gsub(",", "", seoul1$value))
seoul2 <- dcast(seoul1, id + year ~ type)
index0 <- seoul2$id
index1 <- strsplit(index0, " ")
name <- c()
code <- c()
for (i in 1:length(index1))
{
temp_name <- index1[[i]][2]
temp_code <- index1[[i]][3]
name <- append(name, temp_name)
code <- append(code, temp_code)
}
code <- substr(code, 2, 6)
seoul3 <- data.frame(name, code, seoul2[,2:8])
names(seoul3) <- c("gu", "code", "year",
"gender_ratio", "men", "pop_household",
"household", "women", "total")
seoul3$gender_ratio2 <- with(seoul3, men/women)서울 인구를 구별로 시각화하여 나타내보자.
## 서울 인구의 시각화
seoul_map_vis1 <- seoul3 %>%
group_by(gu, code) %>%
summarize(pop = mean(total))## `summarise()` has grouped output by 'gu'. You can override using the `.groups`
## argument.seoul_map_vis1## # A tibble: 25 × 3
## # Groups: gu [25]
## gu code pop
## <chr> <chr> <dbl>
## 1 강남구 11680 537782.
## 2 강동구 11740 449268.
## 3 강북구 11305 306803
## 4 강서구 11500 582482.
## 5 관악구 11620 493912.
## 6 광진구 11215 346201.
## 7 구로구 11530 401528.
## 8 금천구 11545 231783.
## 9 노원구 11350 522877.
## 10 도봉구 11320 325418.
## # … with 15 more rows## 데이터 프레임 병합을 위해 변수명을 바꾼다.
names(seoul_map_vis1) <- c("gu", "SIG_CD", "pop")
head(seoul_map_vis1)## # A tibble: 6 × 3
## # Groups: gu [6]
## gu SIG_CD pop
## <chr> <chr> <dbl>
## 1 강남구 11680 537782.
## 2 강동구 11740 449268.
## 3 강북구 11305 306803
## 4 강서구 11500 582482.
## 5 관악구 11620 493912.
## 6 광진구 11215 346201.head(df_map2_info)## SIG_CD SIG_ENG_NM SIG_KOR_NM id sido
## 0 11110 Jongno-gu 종로구 0 11
## 1 11140 Jung-gu 중구 1 11
## 2 11170 Yongsan-gu 용산구 2 11
## 3 11200 Seongdong-gu 성동구 3 11
## 4 11215 Gwangjin-gu 광진구 4 11
## 5 11230 Dongdaemun-gu 동대문구 5 11df_map2_info <- merge(df_map2_info, seoul_map_vis1, by = "SIG_CD")
df_map2_temp <- df_map2_info[,c("id", "pop")]
head(df_map2_temp)## id pop
## 1 0 147960.2
## 2 1 124014.4
## 3 2 225862.4
## 4 3 293931.2
## 5 4 346200.6
## 6 5 342225.4df_map2_pop <- merge(df_map2, df_map2_temp, by = "id")
## 서울특별시의 자치구별 인구를 시각화해 보자.
ggplot(data = df_map2_pop,
aes(x = long, y = lat, group = group, fill = pop)) +
geom_polygon(color = "black") 
## 색을 제대로 입혀 보자.
ggplot(data = df_map2_pop,
aes(x = long, y = lat,
group = group, fill = pop)) +
geom_polygon(color = "black") +
scale_fill_gradient(low = "#dadaeb", high = "#3f007d")
## 서울 자치구 성비를 시각화하여 나타내보자.
## 서울시 자치구 성비의 시각화
head(seoul3, 0)## [1] gu code year gender_ratio men
## [6] pop_household household women total gender_ratio2
## <0 행> <또는 row.names의 길이가 0입니다>seoul_map_vis2 <- subset(seoul3, year == 2022)
seoul_map_vis2 <- select(seoul_map_vis2, code, gu, gender_ratio2)
head(seoul_map_vis2)## code gu gender_ratio2
## 5 11680 강남구 0.9168279
## 10 11740 강동구 0.9590157
## 15 11305 강북구 0.9435712
## 20 11500 강서구 0.9230985
## 25 11620 관악구 1.0113387
## 30 11215 광진구 0.9294696names(seoul_map_vis2) <- c("SIG_CD", "gu", "gender_ratio2")
head(seoul_map_vis2)## SIG_CD gu gender_ratio2
## 5 11680 강남구 0.9168279
## 10 11740 강동구 0.9590157
## 15 11305 강북구 0.9435712
## 20 11500 강서구 0.9230985
## 25 11620 관악구 1.0113387
## 30 11215 광진구 0.9294696head(df_map2_info)## SIG_CD SIG_ENG_NM SIG_KOR_NM id sido gu pop
## 1 11110 Jongno-gu 종로구 0 11 종로구 147960.2
## 2 11140 Jung-gu 중구 1 11 중구 124014.4
## 3 11170 Yongsan-gu 용산구 2 11 용산구 225862.4
## 4 11200 Seongdong-gu 성동구 3 11 성동구 293931.2
## 5 11215 Gwangjin-gu 광진구 4 11 광진구 346200.6
## 6 11230 Dongdaemun-gu 동대문구 5 11 동대문구 342225.4head(df_map2_info)## SIG_CD SIG_ENG_NM SIG_KOR_NM id sido gu pop
## 1 11110 Jongno-gu 종로구 0 11 종로구 147960.2
## 2 11140 Jung-gu 중구 1 11 중구 124014.4
## 3 11170 Yongsan-gu 용산구 2 11 용산구 225862.4
## 4 11200 Seongdong-gu 성동구 3 11 성동구 293931.2
## 5 11215 Gwangjin-gu 광진구 4 11 광진구 346200.6
## 6 11230 Dongdaemun-gu 동대문구 5 11 동대문구 342225.4df_map3_info <- merge(df_map2_info, seoul_map_vis2, by = "SIG_CD")
df_map3_temp <- df_map3_info[,c("id", "gender_ratio2")]
head(df_map3_temp)## id gender_ratio2
## 1 0 0.9371232
## 2 1 0.9464880
## 3 2 0.9253630
## 4 3 0.9464282
## 5 4 0.9294696
## 6 5 0.9699571df_map2_gender_ratio <- merge(df_map2, df_map3_temp, by = "id")
head(df_map2_gender_ratio)## id long lat order hole piece group gender_ratio2
## 1 0 956615.5 1953567 1 FALSE 1 0.1 0.9371232
## 2 0 956621.6 1953565 2 FALSE 1 0.1 0.9371232
## 3 0 956626.2 1953564 3 FALSE 1 0.1 0.9371232
## 4 0 956638.8 1953562 4 FALSE 1 0.1 0.9371232
## 5 0 956659.1 1953559 5 FALSE 1 0.1 0.9371232
## 6 0 956661.5 1953558 6 FALSE 1 0.1 0.9371232ggplot(data = df_map2_gender_ratio,
aes(x = long, y = lat,
group = group, fill = gender_ratio2)) +
geom_polygon(color = "black") +
scale_fill_gradient(low = "#dadaeb", high = "#3f007d")
## 인구 분포와의 비교
ggplot(data = df_map2_pop,
aes(x = long, y = lat,
group = group, fill = pop)) +
geom_polygon(color = "black") +
scale_fill_gradient(low = "#dadaeb", high = "#3f007d")