R - 对于位置数据框，从另一个位置数据框中找到最近的成员

Question

我需要在 DF1（3000 个位置）中获取位置 (Lat/Lon)，然后使用 R 找到到 DF2（1500 个位置）中最近位置的半正弦距离。

我可以通过对 DF2 中的位置进行硬编码或为 DF2 中的每个项目创建一个列来实现这一点，这非常麻烦。

关于如何高效完成此任务的任何想法？

Data structures
DF1
Lat   Lon

DF2
Lat   Lon

Answer 1

试试这个：

# load packages
install.packages("tidyverse")
library(geosphere)
install.packages("rjson")
library(rjson)

# make a function to retrieve test data


get_latlon <- function(x){ 
  url <- paste0("https://api3.geo.admin.ch/rest/services/api/SearchServer?searchText=",paste(x),"&type=locations")
  result <- rjson::fromJSON(file = URLencode(url))


  as_tibble(result$results[[1]]) %>% 
    mutate(attr_names = names(attrs)) %>% 
    spread(attr_names, attrs) %>% 
    unnest(cols = c(detail, featureId, geom_quadindex, geom_st_box2d, label, lat, 
                    lon, num, origin, rank, x, y, zoomlevel)) %>% 
    select(detail,lat,lon)
  }


# retrieve test data

cities1 <- c("spiez","zumikon","winterthur","neuenburg")
cities2 <- c("zurich","bern","lausanne")

cities1 %>% map(get_latlon) %>% bind_rows() -> DF1
cities2 %>% map(get_latlon) %>% bind_rows() -> DF2


# make a combined dataframe 
names(DF1) <- paste0(names(DF1), ".a")
names(DF2) <- paste0(names(DF2), ".b")
crossing(DF1,DF2) -> data

# function to calculate the Harversine distance

haversine <- function(lon1, lat1, lon2, lat2, r = 6378137) {

  if(!is.numeric(c(lon1, lat1, lon2, lat2)))
    stop("Inpust must be numeric")

  # Convert degrees to radians
  lon1 <- lon1 * pi / 180
  lat1 <- lat1 * pi / 180
  lon2 <- lon2 * pi / 180
  lat2 <- lat2 * pi / 180

  delta.lon <- (lon2 - lon1)
  delta.lat <- (lat2 - lat1)
  a <- sin(delta.lat/2)^2 + cos(lat1) * cos(lat2) *
    sin(delta.lon/2)^2
  c <- 2 * asin(min(1,sqrt(a)))
  distance <- r * c

  return(distance) # Distance
}


# find the smallest distances for locations in DF1
data %>%
  group_by(detail.a,detail.b) %>% 
  mutate(haversine=haversine(lat.a,lon.a,lat.b,lon.b)) %>% 
  group_by(detail.a) %>% 
  slice(which.min(haversine))

R - 对于位置数据框，从另一个位置数据框中找到最近的成员

R - For a dataframe of locations, find the nearest member from another dataframe of locations

r

geospatial

latitude-longitude

spatial

haversine