上海地铁数据可视化

已部署到shinyapps.io，详见SHMetro

0.配置环境和加载包

## encoding
options(encoding = "UTF-8")      ## for chines
## use getOption("encoding") to see if things were changed

loc <- function(os, language = "english") {
  switch(language,
         english = ifelse(os == "Windows", "English_United States.1252", "en_US.UTF-8"),
         chinese = ifelse(os == "Windows", "Chinese", "zh_CN.utf-8"))
}
## set locale
Sys.setlocale(category = "LC_ALL", loc(Sys.info()[["sysname"]], "chinese"))

##加载工作环境和所需包
setwd("/Users/jeevanyue/Rproject/map/SHMetro")
library(data.table)
library(bit64)
library(dplyr)
library(tidyr)
library(scales)
library(lubridate)  #日期处理包
library(shiny)
library(leaflet)
library(lattice)
library(plotly)
library(chorddiag)  #绘制chord

1. 地铁数据

#地铁站进站数据和出站数据
shmetro_in <- fread("data/shmetro_in.csv",encoding="UTF-8")
shmetro_out <- fread("data/shmetro_out.csv",encoding="UTF-8")

## 进出地铁站数据
shmetro_line_in_out <- fread("data/shmetro_line_in_out.csv",encoding="UTF-8")

## 进出地铁站关联
in_out <- shmetro_line_in_out %>%
  spread(line_out,count)
in_out[is.na(in_out)]<-0

## 地铁站经纬度
stations <- fread("data/stations.csv",encoding="UTF-8")
stations <- stations %>% 
  select(c(1:5)) %>%
  arrange(line,line_id)
stations_no <- nrow(stations)
for (i in 1:stations_no) {
    s <- stations$station[i]
    stations$lines[i] <- paste(stations[stations$station==s,]$line,sep="",collapse="/")
}

1.1 地铁站经纬度

stations <- fread("data/stations.csv",encoding="UTF-8")
stations <- stations %>% 
  select(c(1:5)) %>%
  arrange(line,line_id)

stations_no <- nrow(stations)
for (i in 1:stations_no) {
    s <- stations$station[i]
    stations$lines[i] <- paste(stations[stations$station==s,]$line,sep="",collapse="/")
}
invisible(gc())

1.2 交通卡交易数据

交通卡的交易信息有7个字段，分别是:卡号、交易日期、交易时间、站点名称、行业名称、交易金额、交易性质。

• 卡号:交通卡卡号

• 交易日期:日期格式yyyy-mm-dd

• 交易时间:时间个是hh:mm:ss

• 站点名称:内容包括线路和站名，如:"1号线莘庄"

• 行业名称:都是"地铁"

• 交易金额:0和大于0的值，0表示进站，大于0的值表示出战

• 交易性质:"优惠"和"非优惠"

#mac下用如下读取
system.time(trade <- read.csv("/Users/jeevanyue/Desktop/SPTCC-20150401.csv",header = F,sep=",", fileEncoding = "GB2312"))
#windows下用如下读取
#system.time(trade <- fread("SPTCC-20150401/SPTCC-20150401.csv",integer64='character',stringsAsFactors=F))
#trade <- read.csv('data/SPTCC-20150401_Sample.txt',header=T,encoding='UTF-8',stringsAsFactors = F)

#重命名
names(trade) <- c('card_id','date','time','station','vehicle','money','property')
#筛选地铁数据
trade_metro <- trade %>%
  filter(vehicle=='地铁')
rm(trade)
invisible(gc())

#将"station"(原含义为线路和站名),分为"line"和"station"
trade_metro <- trade_metro %>% 
  separate(station, c('line', 'station'), sep = '号线')
invisible(gc())

#按五分钟统计时间，向上取整
trade_metro <- trade_metro %>%
  mutate(M5=ceiling(period_to_seconds(hms(time))/300))
invisible(gc())

#删除不需要的字段
trade_metro <- trade_metro %>%
  select(-vehicle,-property,-date)
invisible(gc())

#时间格式
#trade_metro$time <-  strptime(paste("2015-04-01", trade_metro$time, sep=' '), "%Y-%m-%d %H:%M:%S", tz = "GMT")

1.3 处理异常值

## 对与stations地铁站名不一致的trade数据进行处理
trade_metro[trade_metro$station=="淞浜路",]$station <- "淞滨路"
trade_metro[trade_metro$station=="大木桥路 ",]$station <- "大木桥路"
trade_metro[trade_metro$station=="上海大学站",]$station <- "上海大学"

1.4 进/出站数据

## 进站数据
trade_metro_in <- trade_metro %>%
  filter(money==0) %>%
  select(card_id,"time_in"=time,"line_in"=line,"station_in"=station,"M5_in"=M5)
## 出站数据
trade_metro_out <- trade_metro %>%
  filter(money>0)%>%
  select(card_id,"time_out"=time,"line_out"=line,"station_out"=station,money,"M5_out"=M5)

1.5 虚拟换乘

上海火车站为虚拟换乘，删除半小时内3/4换1和1换3/4的数据

3/4换1的数据

## 3/4换1的数据，统计发现在上海火车站3/4号线出站以3号线名义出站
trade_metro_out_34 <- trade_metro_out %>%
  filter(station_out=='上海火车站') %>%
  filter(line_out==3 | line_out==4)
trade_metro_in_1 <- trade_metro_in %>%
  filter(station_in=='上海火车站', line_in==1)

## merge出站和进站的