“from”和“to”可以通过将以下行中的值“向上移动”来生成。停止信息可以简单地连接在一起。
让我用一个例子来解释,并使用
library(data.table)
。
## here I"m using Melbourne's GTFS ("http://transitfeeds.com/p/ptv/497/latest/download")
#dt_stop_times <- lst[[6]]$stop_times
#dt_stops <- lst[[7]]$stops
#setDT(dt_stop_times)
#setDT(dt_stops)
## join on whatever stop information you want
dt_stop_times <- dt_stop_times[ dt_stops, on = c("stop_id"), nomatch = 0]
## set the order of stops for each group (in this case, each group is a trip_id)
setorder(dt_stop_times, trip_id, stop_sequence)
## create a new column by shifting the stop_id of the following row up
dt_stop_times[, stop_id_to := shift(stop_id, type = "lead"), by = .(trip_id)]
## you will have NAs at this point because the last stop doesn't go anywhere.
## you can do the same operation on multiple columns at the same time
dt_stop_times[, `:=`(stop_id_to = shift(stop_id, type = "lead"),
arrival_time_stop_to = shift(arrival_time, type = "lead"),
departure_time_stop_to = shift(departure_time, type = "lead")),
by = .(trip_id)]
## now you have your 'from' and 'to' columns from which you can make your igraph
## here's a subset of the result
dt_stop_times[, .(trip_id, stop_id, stop_name_from = stop_name, arrival_time, stop_id_to, arrival_time_stop_to)]
# trip_id stop_id stop_name_from arrival_time stop_id_to
# 1: 1.T0.3-86-A-mjp-1.7.R 4174 71-RMIT/Plenty Rd (Bundoora) 25:42:00 4485
# 2: 1.T0.3-86-A-mjp-1.7.R 4485 70-Janefield Dr/Plenty Rd (Bundoora) 25:43:00 4486
# 3: 1.T0.3-86-A-mjp-1.7.R 4486 69-Taunton Dr/Plenty Rd (Bundoora) 25:44:00 4487
# 4: 1.T0.3-86-A-mjp-1.7.R 4487 68-Greenhills Rd/Plenty Rd (Bundoora) 25:45:00 4488
# 5: 1.T0.3-86-A-mjp-1.7.R 4488 67-Bundoora Square SC/Plenty Rd (Bundoora) 25:46:00 4489
# ---
# 9415793: 9999.UQ.3-19-E-mjp-1.1.H 17871 7-Queen Victoria Market/Elizabeth St (Melbourne City) 23:25:00 17873
# 9415794: 9999.UQ.3-19-E-mjp-1.1.H 17873 5-Melbourne Central Station/Elizabeth St (Melbourne City) 23:27:00 17875
# 9415795: 9999.UQ.3-19-E-mjp-1.1.H 17875 3-Bourke Street Mall/Elizabeth St (Melbourne City) 23:30:00 17876
# 9415796: 9999.UQ.3-19-E-mjp-1.1.H 17876 2-Collins St/Elizabeth St (Melbourne City) 23:31:00 17877
# 9415797: 9999.UQ.3-19-E-mjp-1.1.H 17877 1-Flinders Street Railway Station/Elizabeth St (Melbourne City) 23:32:00 NA
# arrival_time_stop_to
# 1: 25:43:00
# 2: 25:44:00
# 3: 25:45:00
# 4: 25:46:00
# 5: 25:47:00
# ---
# 9415793: 23:27:00
# 9415794: 23:30:00
# 9415795: 23:31:00
# 9415796: 23:32:00
# 9415797: NA
现在,使用
graph_from_data_frame{igraph}
只需按照以下步骤操作:
nodes <- dt_stops[, .(stop_id, stop_lon, stop_lat)]
links <- dt_stop_times[,.(stop_id, stop_id_to, trip_id)]
g <- graph_from_data_frame(links , directed=TRUE, vertices=nodes)
请注意,在一个
GTFS.zip
文件中可能会有多个运输模式(火车、公交车、地铁等),而一些站点对之间的连通性要高得多,这是由于服务频率的差异造成的。目前还不清楚在从
GTFS.zip
构建图形时应如何考虑这两个问题。可能的解决方法是根据其频率加权每个边,并建立一个具有某些站点共同跨越每种运输模式的相互依赖层的多层网络。