Minimum Distance between lat long across multiple data frames

Question

I have a data frame named A which has lat and long in separate columns. Sample Data

ID   Lat          Long    
a          10.773046   76.6392061   
b          10         


        

Answer 1

Here is a solution using the geosphere library, which calculates the distance in meters (the script does convert to km). If you dataset is a reasonable size (ie < 50,000) performance is acceptable.

a <- data.frame(ID = c("a", "b", "c", "d"),    Lat = c(10.773046, 10.7751978, 12.954027, 12.9608638), 
                Long = c(76.6392061, 76.6392061, 78.988818, 77.521573))    


b <- data.frame(Store = c("a", "b", "c", "d", "e"), Lat = c(21.244769,  9.919337, 10.053961, 13.829922, 23.849729), 
                Long = c(81.63861, 78.14844, 76.32757, 77.49369, 77.93647))

library(geosphere)

#calculate the distance matrix
distmatrix<-distm(a[, c(3, 2)], b[,c(3, 2)])
#find closest column and get distance
closest<-apply(distmatrix, 1, which.min)
a$store<-as.character(b$Store[closest])
a$distance<-apply(distmatrix, 1, min)/1000
a

  ID      Lat     Long store  distance
1  a 10.77305 76.63921     c  86.54914
2  b 10.77520 76.63921     c  86.76789
3  c 12.95403 78.98882     d 188.71751
4  d 12.96086 77.52157     d  96.19473

Solution is based on a similar question: Is there an efficient way to group nearby locations based on longitude and latitude?

Answer 2

you can check this out

    a <- data.frame(ID = c("a", "b", "c", "d"),    Lat = c(10.773046, 10.7751978, 12.954027, 12.9608638), 
                Long = c(76.6392061, 76.6392061, 78.988818, 77.521573))    


b <- data.frame(Store = c("a", "b", "c", "d", "e"), Lat = c(21.244769,  9.919337, 10.053961, 13.829922, 23.849729), 
                Long = c(81.63861, 78.14844, 76.32757, 77.49369, 77.93647))

library(tidyverse)

earth.dist <- function (long1, lat1, long2, lat2)
{
  rad <- pi/180
  a1 <- lat1 * rad
  a2 <- long1 * rad
  b1 <- lat2 * rad
  b2 <- long2 * rad
  dlon <- b2 - a2
  dlat <- b1 - a1
  a <- (sin(dlat/2))^2 + cos(a1) * cos(b1) * (sin(dlon/2))^2
  c <- 2 * atan2(sqrt(a), sqrt(1 - a))
  R <- 6378.145
  d <- R * c
  return(d)
}


a1 <- a %>%
  group_by(ID, Lat, Long) %>%
  summarise(closest = which.min(abs(Lat - b$Lat) + abs(Long - b$Long))) %>%
  mutate(Store  = b$Store[closest],
         Distance = sqrt((Lat - b$Lat[closest])^2 + (Long - b$Long[closest])^2), 
         distKm = earth.dist(Lat, Long, b$Lat[closest],b$Long[closest]))

Which results in:

a1
  ID      Lat  Long closest Store Distance distKm
  <fct> <dbl> <dbl>   <int> <fct>    <dbl>  <dbl>
1 a      10.8  76.6       3 c        0.784   39.4
2 b      10.8  76.6       3 c        0.786   39.4
3 c      13.0  79.0       4 d        1.73   168. 
4 d      13.0  77.5       4 d        0.870   21.2