Question

我有一个数据集，我正在尝试将组位置移到最近的城市。我有数据集1（df1），其中包含经度和纬度的地址位置。我想将这些地址映射到半径50英里以内的所有最近的城市（在数据框df2中）。

g_lat <- c(45.52306, 40.26719, 34.05223, 37.38605, 37.77493)
g_lon <- c(-122.67648,-86.13490, -118.24368, -122.08385, -122.41942)
address <- c(1,2,3,4,5)
df1 <- data.frame(g_lat, g_lon, address)

g_lat <- c(+37.7737185, +45.5222208,+37.77493)
g_lon <- c(-122.2744317,-098.7041549,-122.41942)
msa <- c(1,2,3)
df2 <- data.frame(g_lat, g_lon, msa)

我希望输出如下，显示该地址与之关联的所有msa：

 address g_lat    g_lon         msa 
  5     37.77493  -122.41942     1
  5     37.77493  -122.41942     3

请让我知道如何实现。我尝试了以下方法：

 library(geosphere)
 # create distance matrix
 mat <- distm(df1[,c('g_lon','g_lat')], df2[,c('g_lon','g_lat')], fun=distVincentyEllipsoid)


  error: 
  Error in .pointsToMatrix(y) : longitude < -360

   # assign the name to the point in list1 based on shortest distance in the matrix
   df1$locality <- df2$locality[max.col(-mat)]

Answer 1

可能的解决方案：

library(geosphere)

mat <- distm(df1[,c('g_lon','g_lat')], df2[,c('g_lon','g_lat')], fun=distVincentyEllipsoid)

ri <- row(mat)[mat < 80000]
ci <- col(mat)[mat < 80000]

df3 <- df1[ri,]
df3$msa <- df2[ci, "msa"]

给出：

> df3
       g_lat     g_lon address msa
4   37.38605 -122.0838       4   1
5   37.77493 -122.4194       5   1
4.1 37.38605 -122.0838       4   3
5.1 37.77493 -122.4194       5   3

使用data.table或dplyr：

library(data.table)
setDT(df1)[ri][, msa := df2[ci, "msa"]][]

library(dplyr)
df1 %>% 
  slice(ri) %>% 
  mutate(msa = df2[ci, "msa"])

您可以使用以下方法添加距离：

df3$dist <- mat[cbind(ri, ci)]

给出：

> df3
       g_lat     g_lon address msa     dist
4   37.38605 -122.0838       4   1 46202.74
5   37.77493 -122.4194       5   1 12774.31
4.1 37.38605 -122.0838       4   3 52359.08
5.1 37.77493 -122.4194       5   3     0.00

映射地址到最近的大都市地区

1 个答案: