R - ggmap - 通过地理编码计算城市之间的最短距离

Question

我有一个城市和相关信息的列表，我已经放在一个数据框中，如下所示:

library(plyr)
library(dplyr)
library(ggmap)
library(Imap)

cities <- c("washington, dc", "wilmington, de", "amarillo, tx", 
            "denver, co", "needham, ma", "philadelphia, pa", 
            "doylestown, pa", "galveston, tx", "tuscaloosa, al", 
            "hollywood, fl"
            )

id <- c(156952, 154222, 785695, 154423, 971453, 149888, 1356987,
        178946, 169944, 136421)

month <- c(201811, 201811, 201912, 201912, 202005, 202005, 
           202005, 202106, 202106, 202106 )

category<- c("home", "work", "home", "home", "home", "work",
             "cell", "home", "work", "cell")

places <- data.frame(cities, id, category, month)

使用 Imap 和 ggmap 包，我可以检索每个城市的经度和纬度:

lat <- geocode(location = places$cities, source = "google")$lat
lon <- geocode(location = places$cities, source = "google")$lon

places <- cbind(places, lat, lon)

我想做的是以下内容:

按月和类别计算每个城市之间的距离

在 places

的不同列中返回第二个最短距离和相应的城市和 id

我写了一个 for 循环来计算距离:

for (i in 1:nrow(places)) {




dist_list[[i]] <- gdist(lon.1 = places$lon[i], 
                          lat.1 = places$lat[i], 
                          lon.2 = places$lon, 
                          lat.2 = places$lat,
                          units="miles")
  
}

产生以下数据:

dput(dist_list)
list(c(0, 98.3464717885451, 1386.25425677199, 1489.87718040776, 
383.083760289456, 123.232894969413, 140.284537078237, 1209.23510542932, 
706.670452283757, 906.79542720295), c(98.4762434610638, 0, 1472.06660056474, 
1560.93398322985, 285.23618862797, 24.9195071209828, 44.8853561530985, 
1308.60741637919, 805.755084908157, 983.102810248198), c(1389.07354011351, 
1472.06660056474, 0, 356.573530670257, 1712.29111612461, 1493.39302974566, 
1497.2125164277, 579.329313217289, 827.577713357261, 1434.82691622332
), c(1492.80130415651, 1560.93398322985, 356.573530670257, 0, 
1761.3773163288, 1578.71125031146, 1576.80713231756, 923.725006795209, 
1067.04809350934, 1717.32991551111), c(383.551997010915, 285.23618862797, 
1712.29111612461, 1761.3773163288, 0, 260.382178510916, 243.947043197789, 
1588.85470703957, 1088.38640303169, 1230.47219244291), c(123.395655314093, 
24.9195071209827, 1493.39302974566, 1578.71125031146, 260.382178510916, 
0, 24.7382114555287, 1333.29925285915, 830.581742827321, 1002.94777739349
), c(140.431447025301, 44.8853561530986, 1497.2125164277, 1576.80713231756, 
243.947043197789, 24.7382114555285, 0, 1346.44527983873, 844.827513981938, 
1026.98263808807), c(1211.16392416136, 1308.60741637919, 579.329313217289, 
923.725006795209, 1588.85470703957, 1333.29925285915, 1346.44527983873, 
0, 505.292529136012, 925.512554201542), c(707.73957320737, 805.755084908157, 
827.577713357261, 1067.04809350934, 1088.38640303169, 830.581742827321, 
844.827513981938, 505.292529136012, 0, 666.837848781548), c(906.880841903584, 
983.102810248198, 1434.82691622332, 1717.32991551111, 1230.47219244291, 
1002.94777739349, 1026.98263808807, 925.512554201542, 666.837848781548, 
0))

所需的结果如下所示(第一行):

cities          id         category  month      lat        lon   min.dist  closest city  closest city id  
washington, dc  156952     home      201811 38.90719  -77.03687   98.34647  wilmington, de  154222 

通过 nth 中的 Rfast 函数，我可以获得第二小的距离 nth(dist_list[[1]], 2)我遇到的问题是我不知道如何将列表中的信息连接到 df places 。任何帮助或建议将不胜感激。

Answer 1

# get min distance:
min_d <- sapply(dist_list, function(x) sort(x)[2])
places$min_dist <- min_d
# index:
i <- sapply(dist_list, function(x) which(sort(x)[2] == x))
# add name:
places$min_name <- places$cities[i]

分组:

# prepare dist matrix outside loop
m <- t(as.data.frame(dist_list))
row.names(m) <- NULL
diag(m) <- NA

# create grouping variable:
gv <- as.integer(factor(places$month)) # or:
# gv <- as.integer(factor(paste(places$month, places$category)))

# set distance to NA if not in relevant group:
i <- sapply(gv, function(x) gv == x)
m[!i] <- NA

l <- sapply(as.data.frame(t(m)), function(x) {
  if (all(is.na(x))) return(list(NA, NA))
  mv <- min(x, na.rm = T)
  i <- which(x == mv)
  list(mv, i)
})
l
places <- cbind(places, min_dist = unlist(l[1, ]), min_nr = unlist(l[2, ]))

places$min_name <- places$cities[places$min_nr] # add name
places$min_id <- places$id[places$min_nr] # add id
places

结果:

              cities      id category  month  min_dist min_nr         min_name  min_id
V1    washington, dc  156952     home 201811  98.34647      2   wilmington, de  154222
V2    wilmington, de  154222     work 201811  98.47624      1   washington, dc  156952
V3      amarillo, tx  785695     home 201912 356.57353      4       denver, co  154423
V4        denver, co  154423     home 201912 356.57353      3     amarillo, tx  785695
V5       needham, ma  971453     home 202005 243.94704      7   doylestown, pa 1356987
V6  philadelphia, pa  149888     work 202005  24.73821      7   doylestown, pa 1356987
V7    doylestown, pa 1356987     cell 202005  24.73821      6 philadelphia, pa  149888
V8     galveston, tx  178946     home 202106 505.29253      9   tuscaloosa, al  169944
V9    tuscaloosa, al  169944     work 202106 505.29253      8    galveston, tx  178946
V10    hollywood, fl  136421     cell 202106 666.83785      9   tuscaloosa, al  169944