In skysign/KoreaAddressAPI: To Validate, Parse and Correct Korea Address

library(dplyr)

pathPrefix = '../external_data_source/juso.go.kr/'
YYYYMMPrefix = '202004_주소DB_전체분/'
pathPostFix = '지번_서울특별시.txt'
path = paste0(pathPrefix, YYYYMMPrefix, pathPostFix)

txtFiles = c('지번_강원도.txt', '지번_경기도.txt', '지번_경상남도.txt', '지번_경상북도.txt',
             '지번_광주광역시.txt', '지번_대구광역시.txt','지번_대전광역시.txt', '지번_부산광역시.txt',
             '지번_세종특별자치시.txt', '지번_울산광역시.txt', '지번_인천광역시.txt', '지번_전라남도.txt',
             '지번_전라북도.txt', '지번_제주특별자치도.txt', '지번_충청남도.txt', '지번_충청북도.txt')

readJiBeonJuso <- function(path) {
  df <- read.table(path, sep = '|')
  df <- rename(df, "GwanRiBeonHo"="V1",
                  "IlLyeonBeonHo"="V2",
                  "BeopJeongDongKoDeu"="V3",
                  "SiDoMyeong"="V4",
                  "SiGunGuMyeong"="V5",
                  "BeopJeongEupMyeonDongMyeong"="V6",
                  "BeopJeongRiMyeong"="V7",
                  "SanYeoBu"="V8",
                  "JiBeonBonBeon(BeonJi)"="V9",
                  "JiBeonBuBeon(Ho)"="V10",
                  "DaePyoYeoBu"="V11")  
  return(df)
}

# 서울 지번주소 읽기
dfJiBeonJuso = readJiBeonJuso(path)

for(idx in 1:length(txtFiles)) {
  pathPostFix = txtFiles[idx]
  path = paste0(pathPrefix, YYYYMMPrefix, pathPostFix)
  #print(path)
  dfTmp = readJiBeonJuso(path)
  dfJiBeonJuso = rbind(dfJiBeonJuso, dfTmp)
}

head(dfJiBeonJuso)
summary(dfJiBeonJuso)

pathPrefix = '../cleaned/'
YYYYMMPrefix = '202004/'
pathPostFix = 'JiBeon_Korea.csv'
path = paste0(pathPrefix, YYYYMMPrefix, pathPostFix)

write.csv(dfJiBeonJuso, path, row.names = FALSE, fileEncoding = 'UTF-8')

skysign/KoreaAddressAPI documentation built on July 20, 2020, 9:08 p.m.