我在R中加载来自MySQL的多边形数据。我编写了一个工作正常的函数。我希望用更快的东西替换我的凌乱循环(应用还是应用?)
这适用于AWS ubuntu服务器,运行MySQL服务器5.7和R编程
# INSTALLING AND LOADING NECESSARY PACKAGES
packages = c("RMySQL","rgeos");
for (package in packages) {
if (package %in% installed.packages()[,"Package"] == FALSE) {
install.packages(package);
}
}
lapply(packages, require, character.only = TRUE)
options(rds = list(
"host" = "avanse-instance.cqzqewynskco.us-east-2.rds.amazonaws.com",
"port" = 3306,
"user" = [user],
"password" = [password]
))
LoadBuildings <- function() {
# Connect to the MySQL database
db <- dbConnect(MySQL(), dbname = "watsan", host = options()$rds$host,
port = options()$rds$port, user = options()$rds$user,
password = options()$rds$password)
# Construct the fetching query
query1 <- paste("SELECT ST_AsText(geom_building) FROM building where zone = 'Charrier_Vertieres_1';")
query2 <- paste("SELECT * FROM building where zone = 'Charrier_Vertieres_1';")
# Submit the fetch query and disconnect
polyg <- dbGetQuery(db, query1)
dt <- dbGetQuery(db, query2)
dbDisconnect(db)
spdf <- SpatialPolygonsDataFrame(readWKT(polyg[1, ]), dt[1, ], match.ID = FALSE)
for (i in 2:nrow(polyg)){
spdf <- rbind(spdf, SpatialPolygonsDataFrame(readWKT(polyg[i, ]), dt[i, ], match.ID = FALSE))
}
return(spdf)
}
有没有其他方法可以解决这个问题的建议,也许使用apply或tapply?谢谢,抱歉讨厌的代码
你的for
循环不是任何缓慢的原因。它正在用rbind
构建你的数据框架,这将减慢你的速度。请尝试使用它
spdf <- vector("list", nrow(polyg))
for (i in seq_along(spdf)){
spdf[[i]] <- SpatialPolygonsDataFrame(readWKT(polyg[i, ]), dt[i, ], match.ID = FALSE)
}
spdf <- do.call("rbind", spdf)
或者,您可以使用下一段代码。但我会惊讶地发现性能差异很大。
spdf <-
lapply(seq_len(nrow(polyg)),
function(i){
SpatialPolygonsDataFrame(readWKT(polyg[i, ]), dt[i, ], match.ID = FALSE)
})
spdf <- do.call("rbind", spdf)