Convert/export googleway 输出到数据框
Convert/export googleway output to data frame
我试图理解并将 googleway.distance 输出转换为数据框。我有以下 10 个位置的示例：
> origins
V1 V2
1 38.82402 -78.28962
2 39.66405 -75.68834
3 38.68630 -77.30899
4 38.98991 -76.92997
5 39.26476 -77.88584
6 39.14255 -77.08824
7 38.95339 -77.16538
8 39.15798 -77.16514
9 39.03455 -77.47300
10 38.42632 -76.46342
> destinations
V1 V2
1 38.90826 -78.20459
2 38.89980 -77.02137
3 38.87326 -77.05361
4 38.97834 -76.92821
5 39.25996 -77.88017
6 39.14281 -77.08835
7 38.84812 -77.07491
8 39.00266 -77.09257
9 38.84438 -77.11938
10 38.37362 -76.44139
我的脚本和部分输出如下所示：
res <- google_distance(origins, destinations, mode = c("driving", "walking",
"bicycling", "transit"), departure_time = NULL, arrival_time = NULL,
avoid = NULL, units = c("metric", "imperial"), traffic_model = NULL,
transit_mode = NULL, transit_routing_preference = NULL, language = NULL,
key = api_key, simplify = TRUE, curl_proxy = NULL)
> res$rows$elements
[[1]]
distance.text distance.value duration.text duration.value duration_in_traffic.text
1 17.6 km 17589 17 mins 993 16 mins
2 131 km 130516 1 hour 37 mins 5802 1 hour 34 mins
3 129 km 128937 1 hour 30 mins 5405 1 hour 29 mins
4 152 km 152260 1 hour 50 mins 6596 1 hour 48 mins
5 72.0 km 71975 1 hour 7 mins 4000 1 hour 3 mins
6 157 km 156716 1 hour 45 mins 6305 1 hour 44 mins
7 133 km 132546 1 hour 33 mins 5577 1 hour 32 mins
8 133 km 132895 1 hour 32 mins 5496 1 hour 30 mins
9 132 km 131620 1 hour 31 mins 5467 1 hour 29 mins
10 226 km 226302 2 hours 33 mins 9166 2 hours 28 mins
duration_in_traffic.value status
1 973 OK
2 5617 OK
3 5315 OK
4 6484 OK
5 3789 OK
6 6210 OK
7 5493 OK
8 5393 OK
9 5343 OK
10 8859 OK
[[2]]
distance.text distance.value duration.text duration.value duration_in_traffic.text
1 270 km 269899 2 hours 47 mins 10012 2 hours 45 mins
2 157 km 156825 1 hour 47 mins 6422 1 hour 44 mins
3 164 km 164106 1 hour 48 mins 6473 1 hour 44 mins
4 148 km 148312 1 hour 39 mins 5947 1 hour 37 mins
5 225 km 224905 2 hours 15 mins 8106 2 hours 14 mins
6 154 km 154192 1 hour 35 mins 5699 1 hour 35 mins
7 168 km 168099 1 hour 52 mins 6714 1 hour 48 mins
8 156 km 156140 1 hour 40 mins 5971 1 hour 38 mins
9 171 km 171489 1 hour 58 mins 7050 1 hour 52 mins
10 214 km 214136 2 hours 26 mins 8771 2 hours 20 mins
duration_in_traffic.value status
1 9895 OK
2 6242 OK
3 6253 OK
4 5834 OK
5 8053 OK
6 5711 OK
7 6462 OK
8 5893 OK
9 6749 OK
10 8425 OK
> dput(res$rows$elements)
list(structure(list(distance = structure(list(text = c("17.6 km",
"131 km", "129 km", "152 km", "72.0 km", "157 km", "133 km",
"133 km", "132 km", "226 km"), value = c(17589L, 130516L, 128937L,
152260L, 71975L, 156716L, 132546L, 132895L, 131620L, 226302L)), .Names = c("text",
"value"), class = "data.frame", row.names = c(NA, 10L)), duration = structure(list(
text = c("17 mins", "1 hour 37 mins", "1 hour 30 mins", "1 hour 50 mins",
"1 hour 7 mins", "1 hour 45 mins", "1 hour 33 mins", "1 hour 32 mins",
"1 hour 31 mins", "2 hours 33 mins"), value = c(993L, 5802L,
5405L, 6596L, 4000L, 6305L, 5577L, 5496L, 5467L, 9166L)), .Names = c("text",
"value"), class = "data.frame", row.names = c(NA, 10L)), duration_in_traffic = structure(list(
text = c("16 mins", "1 hour 34 mins", "1 hour 29 mins", "1 hour 48 mins",
"1 hour 3 mins", "1 hour 44 mins", "1 hour 32 mins", "1 hour 30 mins",
"1 hour 29 mins", "2 hours 28 mins"), value = c(973L, 5617L,
5315L, 6484L, 3789L, 6210L, 5493L, 5393L, 5343L, 8859L)), .Names = c("text",
"value"), class = "data.frame", row.names = c(NA, 10L)), status = c("OK",
"OK", "OK", "OK", "OK", "OK", "OK", "OK", "OK", "OK")), .Names = c("distance",
"duration", "duration_in_traffic", "status"), class = "data.frame", row.names = c(NA,
10L)),
这只是我输出的一部分（太长了所以我删掉了）；整个结果从 [[1]] 到 [[10]]。为什么有 10 个列表，每个列表包含 10 个元素？
我选择了4种交通方式（驾车、步行、骑自行车、公交），但结果似乎只包括驾车时间和距离。任何方式来包括所有模式的距离和时间？如何将此列表转换为数据框？
这些是我尝试过的方法：
newdf <- distance_elements(res)
do.call(rbind.data.frame, newdf)
错误：
Error in `row.names<-.data.frame`(`*tmp*`, value = value) :
duplicate 'row.names' are not allowed
In addition: Warning message:
non-unique values when setting 'row.names': ‘1’, ‘10’, ‘2’, ‘3’, ‘4’, ‘5’, ‘6’, ‘7’, ‘8’, ‘9’
然后newdf1 <- ldply (newdf, data.frame):
Error in allocate_column(df[[var]], nrows, dfs, var) :
Data frame column 'distance' not supported by rbind.fill
我想要的输出是 1o 对 lat/long 的距离和时间（例如，起点的第一个元素和终点的第一元素，起点的第二个元素和终点的第二个元素，等等）
is a service that provides travel distance and time for a matrix of origins and destinations.
也就是说，您将获得所有可能的出发地和目的地组合的距离。
鉴于您的描述
My desired output is distance and time of 1o pairs of lat/long (e.g., the 1st element of origins and 1st element of destinations, 2nd element of origins and 2nd element of destinations, etc.)
你实际上只需要每 origin/destination 对一个值。
此外，API一次只能接受一个请求，所以如果你想遍历所有O/D对和所有传输模式，你需要使用循环
例子
library(googleway)
set_key("your_api_key")
## iterate over each row of origins/destinaions
lst <- lapply(1:nrow(origins), function(x) {
google_distance(origins = c(origins[x, "V1"], origins[x,"V2"]),
destinations = c(destinations[x, "V1"], destinations[x, "V2"]),
mode = "driving", ## you can only do one mode at a time
)
})
## in the above iteration, we used 'lapply', so our results are stored in a list
## you have to access the specific elements/results from that list
lst_elements <- lapply(lst, function(x){
stats::setNames(
cbind(
distance_elements(x)[[1]][['duration']],
distance_elements(x)[[1]][['distance']]
)
, c("duration_text", "duration_value", "distance_text", "distance_value")
)
})
## then you can start to create your data.frames (or data.table in this case)
dt_durations <- data.table::rbindlist(lst_elements)
# duration_text duration_value distance_text distance_value
# 1: 17 mins 993 17.6 km 17589
# 2: 1 hour 47 mins 6429 158 km 158198
# 3: 33 mins 2009 38.6 km 38630
# 4: 8 mins 504 2.5 km 2466
# 5: 4 mins 225 1.5 km 1486
# 6: 1 min 1 2 m 2
# 7: 22 mins 1312 19.5 km 19495
# 8: 27 mins 1630 27.1 km 27094
# 9: 47 mins 2845 61.0 km 61024
# 10: 6 mins 364 7.0 km 7001
您必须执行类似的 'loop' 来遍历不同的 modes
更进一步
如果需要，您也可以使用 directions API 获取它们之间的行车路线
lst <- lapply(1:nrow(origins), function(x) {
google_directions(origin = c(origins[x, "V1"], origins[x,"V2"]),
destination = c(destinations[x, "V1"], destinations[x, "V2"]),
mode = "driving", ## you can only do one mode at a time
)
})
lst_elements <- lapply(lst, function(x){
data.frame(
polyline = direction_polyline(x)
)
})
dt_routes <- data.table::rbindlist(lst_elements)
df_distances <- cbind(origins, destinations)
df_distances <- stats::setNames(df_distances, c("origin_lat", "origin_lon", "destination_lat", "destination_lon"))
df_distances <- cbind(df_distances, dt_routes, dt_durations)
df_distances$colour <- "blue" ## for colouring some markers
df_distances$info <- paste0("<b>Duration:</b>", df_distances$distance_value,
"<br><b>Distance:</b>", df_distances$duration_value)
set_key("your_api_key", api = "map")
google_map(data = df_distances) %>%
add_markers(lat = "origin_lat", lon = "origin_lon") %>%
add_markers(lat = "destination_lat", lon = "destination_lon", colour = "colour") %>%
add_polylines(polyline = "polyline", info_window = "info")
我试图理解并将 googleway.distance 输出转换为数据框。我有以下 10 个位置的示例：
> origins
V1 V2
1 38.82402 -78.28962
2 39.66405 -75.68834
3 38.68630 -77.30899
4 38.98991 -76.92997
5 39.26476 -77.88584
6 39.14255 -77.08824
7 38.95339 -77.16538
8 39.15798 -77.16514
9 39.03455 -77.47300
10 38.42632 -76.46342
> destinations
V1 V2
1 38.90826 -78.20459
2 38.89980 -77.02137
3 38.87326 -77.05361
4 38.97834 -76.92821
5 39.25996 -77.88017
6 39.14281 -77.08835
7 38.84812 -77.07491
8 39.00266 -77.09257
9 38.84438 -77.11938
10 38.37362 -76.44139
我的脚本和部分输出如下所示：
res <- google_distance(origins, destinations, mode = c("driving", "walking",
"bicycling", "transit"), departure_time = NULL, arrival_time = NULL,
avoid = NULL, units = c("metric", "imperial"), traffic_model = NULL,
transit_mode = NULL, transit_routing_preference = NULL, language = NULL,
key = api_key, simplify = TRUE, curl_proxy = NULL)
> res$rows$elements
[[1]]
distance.text distance.value duration.text duration.value duration_in_traffic.text
1 17.6 km 17589 17 mins 993 16 mins
2 131 km 130516 1 hour 37 mins 5802 1 hour 34 mins
3 129 km 128937 1 hour 30 mins 5405 1 hour 29 mins
4 152 km 152260 1 hour 50 mins 6596 1 hour 48 mins
5 72.0 km 71975 1 hour 7 mins 4000 1 hour 3 mins
6 157 km 156716 1 hour 45 mins 6305 1 hour 44 mins
7 133 km 132546 1 hour 33 mins 5577 1 hour 32 mins
8 133 km 132895 1 hour 32 mins 5496 1 hour 30 mins
9 132 km 131620 1 hour 31 mins 5467 1 hour 29 mins
10 226 km 226302 2 hours 33 mins 9166 2 hours 28 mins
duration_in_traffic.value status
1 973 OK
2 5617 OK
3 5315 OK
4 6484 OK
5 3789 OK
6 6210 OK
7 5493 OK
8 5393 OK
9 5343 OK
10 8859 OK
[[2]]
distance.text distance.value duration.text duration.value duration_in_traffic.text
1 270 km 269899 2 hours 47 mins 10012 2 hours 45 mins
2 157 km 156825 1 hour 47 mins 6422 1 hour 44 mins
3 164 km 164106 1 hour 48 mins 6473 1 hour 44 mins
4 148 km 148312 1 hour 39 mins 5947 1 hour 37 mins
5 225 km 224905 2 hours 15 mins 8106 2 hours 14 mins
6 154 km 154192 1 hour 35 mins 5699 1 hour 35 mins
7 168 km 168099 1 hour 52 mins 6714 1 hour 48 mins
8 156 km 156140 1 hour 40 mins 5971 1 hour 38 mins
9 171 km 171489 1 hour 58 mins 7050 1 hour 52 mins
10 214 km 214136 2 hours 26 mins 8771 2 hours 20 mins
duration_in_traffic.value status
1 9895 OK
2 6242 OK
3 6253 OK
4 5834 OK
5 8053 OK
6 5711 OK
7 6462 OK
8 5893 OK
9 6749 OK
10 8425 OK
> dput(res$rows$elements)
list(structure(list(distance = structure(list(text = c("17.6 km",
"131 km", "129 km", "152 km", "72.0 km", "157 km", "133 km",
"133 km", "132 km", "226 km"), value = c(17589L, 130516L, 128937L,
152260L, 71975L, 156716L, 132546L, 132895L, 131620L, 226302L)), .Names = c("text",
"value"), class = "data.frame", row.names = c(NA, 10L)), duration = structure(list(
text = c("17 mins", "1 hour 37 mins", "1 hour 30 mins", "1 hour 50 mins",
"1 hour 7 mins", "1 hour 45 mins", "1 hour 33 mins", "1 hour 32 mins",
"1 hour 31 mins", "2 hours 33 mins"), value = c(993L, 5802L,
5405L, 6596L, 4000L, 6305L, 5577L, 5496L, 5467L, 9166L)), .Names = c("text",
"value"), class = "data.frame", row.names = c(NA, 10L)), duration_in_traffic = structure(list(
text = c("16 mins", "1 hour 34 mins", "1 hour 29 mins", "1 hour 48 mins",
"1 hour 3 mins", "1 hour 44 mins", "1 hour 32 mins", "1 hour 30 mins",
"1 hour 29 mins", "2 hours 28 mins"), value = c(973L, 5617L,
5315L, 6484L, 3789L, 6210L, 5493L, 5393L, 5343L, 8859L)), .Names = c("text",
"value"), class = "data.frame", row.names = c(NA, 10L)), status = c("OK",
"OK", "OK", "OK", "OK", "OK", "OK", "OK", "OK", "OK")), .Names = c("distance",
"duration", "duration_in_traffic", "status"), class = "data.frame", row.names = c(NA,
10L)),
这只是我输出的一部分（太长了所以我删掉了）；整个结果从 [[1]] 到 [[10]]。为什么有 10 个列表，每个列表包含 10 个元素？ 我选择了4种交通方式（驾车、步行、骑自行车、公交），但结果似乎只包括驾车时间和距离。任何方式来包括所有模式的距离和时间？如何将此列表转换为数据框？
这些是我尝试过的方法：
newdf <- distance_elements(res)
do.call(rbind.data.frame, newdf)
错误：
Error in `row.names<-.data.frame`(`*tmp*`, value = value) :
duplicate 'row.names' are not allowed
In addition: Warning message:
non-unique values when setting 'row.names': ‘1’, ‘10’, ‘2’, ‘3’, ‘4’, ‘5’, ‘6’, ‘7’, ‘8’, ‘9’
然后newdf1 <- ldply (newdf, data.frame):
Error in allocate_column(df[[var]], nrows, dfs, var) :
Data frame column 'distance' not supported by rbind.fill
我想要的输出是 1o 对 lat/long 的距离和时间（例如，起点的第一个元素和终点的第一元素，起点的第二个元素和终点的第二个元素，等等）
is a service that provides travel distance and time for a matrix of origins and destinations.
也就是说，您将获得所有可能的出发地和目的地组合的距离。
鉴于您的描述
My desired output is distance and time of 1o pairs of lat/long (e.g., the 1st element of origins and 1st element of destinations, 2nd element of origins and 2nd element of destinations, etc.)
你实际上只需要每 origin/destination 对一个值。
此外，API一次只能接受一个请求，所以如果你想遍历所有O/D对和所有传输模式，你需要使用循环
例子
library(googleway)
set_key("your_api_key")
## iterate over each row of origins/destinaions
lst <- lapply(1:nrow(origins), function(x) {
google_distance(origins = c(origins[x, "V1"], origins[x,"V2"]),
destinations = c(destinations[x, "V1"], destinations[x, "V2"]),
mode = "driving", ## you can only do one mode at a time
)
})
## in the above iteration, we used 'lapply', so our results are stored in a list
## you have to access the specific elements/results from that list
lst_elements <- lapply(lst, function(x){
stats::setNames(
cbind(
distance_elements(x)[[1]][['duration']],
distance_elements(x)[[1]][['distance']]
)
, c("duration_text", "duration_value", "distance_text", "distance_value")
)
})
## then you can start to create your data.frames (or data.table in this case)
dt_durations <- data.table::rbindlist(lst_elements)
# duration_text duration_value distance_text distance_value
# 1: 17 mins 993 17.6 km 17589
# 2: 1 hour 47 mins 6429 158 km 158198
# 3: 33 mins 2009 38.6 km 38630
# 4: 8 mins 504 2.5 km 2466
# 5: 4 mins 225 1.5 km 1486
# 6: 1 min 1 2 m 2
# 7: 22 mins 1312 19.5 km 19495
# 8: 27 mins 1630 27.1 km 27094
# 9: 47 mins 2845 61.0 km 61024
# 10: 6 mins 364 7.0 km 7001
您必须执行类似的 'loop' 来遍历不同的 modes
更进一步
如果需要，您也可以使用 directions API 获取它们之间的行车路线
lst <- lapply(1:nrow(origins), function(x) {
google_directions(origin = c(origins[x, "V1"], origins[x,"V2"]),
destination = c(destinations[x, "V1"], destinations[x, "V2"]),
mode = "driving", ## you can only do one mode at a time
)
})
lst_elements <- lapply(lst, function(x){
data.frame(
polyline = direction_polyline(x)
)
})
dt_routes <- data.table::rbindlist(lst_elements)
df_distances <- cbind(origins, destinations)
df_distances <- stats::setNames(df_distances, c("origin_lat", "origin_lon", "destination_lat", "destination_lon"))
df_distances <- cbind(df_distances, dt_routes, dt_durations)
df_distances$colour <- "blue" ## for colouring some markers
df_distances$info <- paste0("<b>Duration:</b>", df_distances$distance_value,
"<br><b>Distance:</b>", df_distances$duration_value)
set_key("your_api_key", api = "map")
google_map(data = df_distances) %>%
add_markers(lat = "origin_lat", lon = "origin_lon") %>%
add_markers(lat = "destination_lat", lon = "destination_lon", colour = "colour") %>%
add_polylines(polyline = "polyline", info_window = "info")