Geographical distance by group - Applying a function on each pair of rows

Question

I want to calculate the average geographical distance between a number of houses per province.

Suppose I have the following data.

df1 <- data.fram         


        

Answer 1

You can use a vectorized version of haversine distance, such as :

dist_haversine_for_dfs <- function (df_x, df_y, lat, r = 6378137) 
{
  if(!all(c("lat", "lon") %in% names(df_x))) {
    stop("parameter df_x does not have column 'lat' and 'lon'")
  }
  if(!all(c("lat", "lon") %in% names(df_y))) {
    stop("parameter df_x does not have column 'lat' and 'lon'")
  }
  toRad <- pi/180
  df_x <- df_x * toRad
  df_y <- df_y * toRad
  dLat <- df_y[["lat"]] - df_x[["lat"]]
  dLon <- df_y[["lon"]] - df_x[["lon"]]
  a <- sin(dLat/2) * sin(dLat/2) + cos(df_x[["lat"]]) * cos(df_y[["lat"]]) * 
    sin(dLon/2) * sin(dLon/2)
  a <- pmin(a, 1)
  dist <- 2 * atan2(sqrt(a), sqrt(1 - a)) * r
  return(dist)
}

Then using data.table and the package arrangements (for faster combinations generation) you can do the following :

library(data.table)
dt <- data.table(df1)
ids <- dt[, {
  comb_mat <- arrangements::combinations(x = house, k = 2)
  list(house_x = comb_mat[, 1],
       house_y = comb_mat[, 2])}, by = province]

jdt <- cbind(ids, 
             dt[ids$house_x, .(lon_x=lon, lat_x=lat)], 
             dt[ids$house_y, .(lon_y=lon, lat_y=lat)])

jdt[, dist := dist_haversine_for_dfs(df_x = jdt[, .(lon = lon.x, lat = lat.x)],
                                     df_y = jdt[, .(lon = lon.y, lat = lat.y)])]

jdt[, .(mean_dist = mean(dist)), by = province]

which outputs

   province mean_dist
1:        1  15379.21
2:        2 793612.04