计算两个数据集两点之间的距离（最近邻）

Question

我想计算两个不同数据集中两点之间的距离。我不想计算所有点之间的距离 - 只是到 datasetB 的最近点。
一些例子：

数据集 A - 人员
http://pastebin.com/HbaeqACi

数据集 B - 水景：
http://pastebin.com/UdDvNtHs

数据集 C - 城市：
http://pastebin.com/nATnkMRk

所以...我想计算每个人到最近的水景点的距离。
我已经尝试过使用 rgeos 包，在遇到一些预测错误之后，我已经开始使用它了。但是这个计算（至少我假设它）到每个点的所有距离，但是，正如已经说过的，我只对到最近的水景点的距离感兴趣。

# load csv files
persons = read.csv("persons.csv", header = TRUE)
water = read.csv("water.csv", header = TRUE)
# change dataframes to SpatialPointDataFrame and assign a projection
library(sp)
library(rgeos)
coordinates(persons) <- c("POINT_X", "POINT_Y")
proj4string(persons) <- CRS("+proj=utm +datum=WGS84")
coordinates(water) <- c("POINT_X", "POINT_Y")
proj4string(water) <- CRS("+proj=utm +datum=WGS84")

# use rgoes package to calculate the distance
distance <- gDistance(persons, water, byid=TRUE)
# works, but calculates a huge number of distances

有没有我错过的参数。还是我需要使用另一个包或功能？我还查看了 spatstat，它能够计算到最近邻居的距离，但不能计算两个不同数据集的距离：http://hosho.ees.hokudai.ac.jp/~kubo/Rdoc/library/spatstat/html/nndist.html

---

编辑：
完整的 R 脚本，包括绘制数据集：

library(RgoogleMaps)
library(ggplot2)
library(ggmap)
library(sp)
library(fossil)

#load data
persons = read.csv("person.csv", header = TRUE, stringsAsFactors=FALSE)
water = read.csv("water.csv", header =TRUE, stringsAsFactors=FALSE)
city = read.csv("city.csv", header =TRUE)

# plot data
persons_ggplot2 <- persons
city_ggplot2 <- city
water_ggplot2 <- water
gc <- geocode('new york, usa')
center <- as.numeric(gc)  
G <- ggmap(get_googlemap(center = center, color = 'bw', scale = 1, zoom = 11, maptype = "terrain", frame=T), extent="device")
G1 <- G + geom_point(aes(x=POINT_X, y=POINT_Y ),data=city, shape = 22, color="black", fill = "yellow", size = 4) + geom_point(aes(x=POINT_X, y=POINT_Y ),data=persons, shape = 8, color="red", size=2.5) + geom_point(aes(x=POINT_X, y=POINT_Y ),data=water_ggplot2, color="blue", size=1)
plot(G1)

#### calculate distance
# Generate unique coordinates dataframe
UniqueCoordinates <- data.frame(unique(persons[,4:5]))
UniqueCoordinates$Id <- formatC((1:nrow(UniqueCoordinates)), width=3,flag=0)

# Generate a function that looks for the closest waterfeature for each id coordinates
NearestW <- function(id){
tmp <- UniqueCoordinates[UniqueCoordinates$Id==id, 1:2]
WaterFeatures <- rbind(tmp,water[,2:3])
tmp1 <- earth.dist(WaterFeatures, dist=TRUE)[1:(nrow(WaterFeatures)-1)]
tmp1 <- which.min(tmp1)
tmp1 <- water[tmp1,1]
tmp1 <- data.frame(tmp1, WaterFeature=tmp)
return(tmp1)
}

#apply to each id and the merge
CoordinatesWaterFeature <- ldply(UniqueCoordinates$Id, NearestW)
persons <- merge(persons, CoordinatesWaterFeature, by.x=c(4,5), by.y=c(2,3))

Answer 1

编写一个函数来为每个人寻找最近的水景怎么样？

#requires function earth.dist from "fossil" package
require(fossil)

#load data
persons = read.csv("person.csv", header = TRUE, stringsAsFactors=FALSE)
water = read.csv("water.csv", header =TRUE, stringsAsFactors=FALSE)

#Generate unique coordinates dataframe
UniqueCoordinates <- data.frame(unique(persons[,4:5]))
UniqueCoordinates$Id <- formatC((1:nrow(UniqueCoordinates)), width=3,flag=0)


#Generate a function that looks for the closest waterfeature for each id coordinates
NearestW <- function(id){
   tmp <- UniqueCoordinates[UniqueCoordinates$Id==id, 1:2]
   WaterFeatures <- rbind(tmp,water[,2:3])
   tmp1 <- earth.dist(WaterFeatures, dist=TRUE)[1:(nrow(WaterFeatures)-1)]
   tmp1 <- min(tmp1)
   tmp1 <- data.frame(tmp1, WaterFeature=tmp)
   return(tmp1)
 }

#apply to each id and the merge
CoordinatesWaterFeature <- ldply(UniqueCoordinates$Id, NearestW)
persons <- merge(persons, CoordinatesWaterFeature, by.x=c(4,5), by.y=c(2,3))

注意：我在原始 read.csv 中添加了 stringsAsFactors 参数，它使最后的合并更容易

注意：tmp1 列记录了距离最近水景的 METERS 数

Answer 2

也许我来得太晚了，但您可以使用spatstat 来计算两个不同数据集之间的距离。命令是nncross。您必须使用的参数是ppp 类型的两个对象，您可以使用as.ppp() 函数创建它们。