最近一直在处理交通数据，有时间、车牌，经过的路口地址，数据量较大，本篇针对各车经过的路口时间先后顺序，生成贵阳交通的可通行有向图，即相连的交通路口间是否是双向通行、单向通行。
一、关于数据的说明
rm(list=ls(all=TRUE))
gc()
library(RODBC)
channel=odbcConnect("transport-connector-R", uid="transport", pwd="transport") #连接mysql test 数据库
sqlTables(channel) # 显示test数据库中的表格
#检索test.transport20140901 中贵阳的车辆信息，含车牌，经过的路口
transections_data<-sqlQuery(channel,"select plate,address from transport20140901 where plate like '贵A%' order by plate,time")
odbcClose(channel)
# 读取文件中排序好的路口地址数据
address_file <-file("/home/wanglinlin/transport/address.txt","r")
sorted_address <-readLines(address_file)
close(address_file)
#sorted_address[256]
#生成贵阳交通路口连通性有向图初始矩阵
transection_count <- length(sorted_address)
tansport_map <- matrix(0,transection_count,transection_count)
#tansport_map
#根据目标地址名称，在地址表中查找其位置编号
find_address<- function(target,address_table){
len=length(address_table)
for(i in 1:len)
if(target==address_table[i])
return (i)
return (0)
}
#根据贵阳本地车辆信息，生成贵阳交通图的双向有向图矩阵
transport_data_count <- 6725490
counter <- transport_data_count-1
transection_id_one=find_address(transections_data[1,2],sorted_address)
for (i in 1:counter){
transection_id_two=find_address(transections_data[i+1,2],sorted_address)
if (transections_data[i,1]==transections_data[i+1,1]){
tansport_map[transection_id_one,transection_id_two] <- 1
}
transection_id_one <- transection_id_two
}
write.table(tansport_map,"/home/wanglinlin/transport/tansport_map_two.txt",row.names = FALSE,col.names = FALSE)
<ul><li><span style="font-family: Arial, Helvetica, sans-serif;">find_address(transections_data[i+1,2],sorted_address)</span></li><li><span style="font-family: Arial, Helvetica, sans-serif;">transections_data[i,1]==transections_data[i+1,1]</span></li></ul>这两个操作分别是在数组中查找字符串的位置（当前路口地址在地址列表中的位置），比较两个字符串是否相等（两个车牌号是否相同），都是关于字符串的操作，相当耗时。
rm(list=ls(all=TRUE))
gc()
library(RODBC)
library(hash)
channel=odbcConnect("transport-connector-R", uid="transport", pwd="transport") #连接mysql test 数据库
sqlTables(channel) # 显示test数据库中的表格
#检索test.transport20140901 中贵阳的车辆信息，含车牌，经过的路口
transections_data<-sqlQuery(channel,"select plate,address from transport20140901 where plate like '贵A%' order by plate,time")
#找出贵阳所有车牌号，并散列化，形成键值对表
plates<-sqlQuery(channel,"select distinct plate from transport20140901 where plate like '贵A%'")
odbcClose(channel)
plate_list=(as.matrix(plates))[,1]
plate_count=length(plate_list)
plate_hash_pairs=hash(plate_list,1:plate_count)
# 读取文件中排序好的路口地址数据
address_file <-file("/home/wanglinlin/transport/address.txt","r")
sorted_address <-readLines(address_file)
sorted_address_hash_pairs<-hash(sorted_address,1:269)
close(address_file)
#sorted_address[256]
#生成贵阳交通路口连通性有向图初始矩阵
transection_count <- length(sorted_address)
transport_map <- matrix(0,transection_count,transection_count)
#tansport_map
#根据贵阳本地车辆信息，生成贵阳交通图的双向有向图矩阵
transport_data_count <- 6725490
counter <- transport_data_count-1
plate_hash_pairs[[as.character(transections_data[1,1])]]
plate_hash_pairs[[as.character(transections_data[2,1])]]
sorted_address_hash_pairs[[as.character(transections_data[1,2])]]
sorted_address_hash_pairs[[as.character(transections_data[2,2])]]
for (i in 1:counter){
if (plate_hash_pairs[[as.character(transections_data[i,1])]]==plate_hash_pairs[[as.character(transections_data[i+1,1])]]){
transport_map[sorted_address_hash_pairs[[as.character(transections_data[i,2])]],sorted_address_hash_pairs[[as.character(transections_data[i+1,2])]]] <- 1
}
}
write.table(transport_map,"/home/wanglinlin/transport/transport_map.txt",row.names = FALSE,col.names = FALSE)
原文地址：http://blog.csdn.net/gufe_hfding/article/details/46371819
