In ahorawzy/Mreport: Monthly Report of traffic condition

knitr::opts_chunk$set(echo = F,message = F)

本实验探索分日数据的分析框架

环境准备

options(stringsAsFactors = F)
options(digits = 2)
rm(list = ls())
source("D:\\R\\packages\\Mreport\\scripts\\source_toglobal.R", encoding = "utf-8")

library(Mreport)
library(plyr)
library(ggplot2)
library(reshape2)
library(knitr)

load_base()
load_sample_base()

数据准备

2018年端午

jddwnew <- read.csv("D:\\data\\sx_raw\\交调数据\\jd2018_06_DuanWu_2.csv")
dim(jddwnew)

拆分日期

x <- strsplit(jddwnew$观测日期,split = "-")
y <- sapply(x,'[',3)
jddwnew$日 <- y

jddwnew <- split_day(jddwnew)
jddwnew <- caculate_equivalent(jddwnew)
jddwnew <- select_atts_forday(jddwnew)
jddwnew <- handle_mergeline(jddwnew,station_line)
jddwnew <- handle_mergesample(jddwnew,sample_base)
jddwnew <- merge(jddwnew,roadlevel,by="index",all.x = T)
jddwnew <- subset(jddwnew,index %in% station_use)

2017年端午

jddwprevious <- read.csv("D:\\data\\sx_raw\\交调数据\\jd2017_06_DuanWu.csv")
dim(jddwprevious)

jddwprevious <- split_day(jddwprevious)
jddwprevious <- caculate_equivalent(jddwprevious)
jddwprevious <- select_atts_forday(jddwprevious)
jddwprevious <- handle_mergeline(jddwprevious,station_line)
jddwprevious <- handle_mergesample(jddwprevious,sample_base)
jddwprevious <- merge(jddwprevious,roadlevel,by="index",all.x = T)
jddwprevious <- subset(jddwprevious,index %in% station_use)

1. 总体分析

1.1 分道路等级

(dwallnewlevel <- ddply(jddwnew,"level",summarise,Wmean = weighted.mean(cars,w=mileage))) %>% kable()

(dwallpreviouslevel <- ddply(jddwprevious,"level",summarise,Wmean = weighted.mean(cars,w=mileage))) %>% kable()

caculate_increaseratio(dwallnewlevel,dwallpreviouslevel) %>% kable()

1.2 分日期

(dwallnewday <- ddply(jddwnew,"day",summarise,Wmean = weighted.mean(cars,w=mileage))) %>% kable()

2. 分省分析

province_level <- c("北京市","天津市","河北省","山西省","内蒙古自治区","辽宁省","吉林省","黑龙江省",
                    "上海市","江苏省","浙江省","安徽省","福建省","江西省","山东省","河南省",
                    "湖北省","湖南省","广东省","广西壮族自治区","海南省","重庆市","四川省","贵州省",
                    "云南省","西藏自治区","陕西省","甘肃省","青海省","宁夏回族自治区","新疆维吾尔自治区")

dwprovincenew <- caculate_carsmean(jddwnew,"province")

dwprovinceprevious <- caculate_carsmean(jddwprevious,"province")
x1 <- caculate_increaseratio(dwprovincenew,dwprovinceprevious)

t <- merge(dwprovincenew,x1,by="province")
t$province <- factor(t$province,ordered = T,levels = province_level)
kable(t[order(t$province),])

3. 旅游景区

dwscenerynew <- caculate_carsmean(jddwnew,"scenery")

同比

dwsceneryprevious <- caculate_carsmean(jddwprevious,"scenery")
x1 <- caculate_increaseratio(dwscenerynew,dwsceneryprevious)

t <- table(jddwnew$province,jddwnew$scenery) %>% as.data.frame()
t <- t[t$Freq!=0,c(1,2)]
names(t) <- c("province","scenery")

k <- merge(dwscenerynew,x1,by="scenery")
g <- merge(k,t,by="scenery")
g$province <- factor(g$province,ordered = T,levels=province_level)
kable(g[order(g$province),])

4. 大城市出入口

dwbigcityionew <- caculate_carsmean(jddwnew,"bigcityio")

dwbigcityioprevious <- caculate_carsmean(jddwprevious,"bigcityio")
x1 <- caculate_increaseratio(dwbigcityionew,dwbigcityioprevious)

t <- table(jddwnew$province,jddwnew$bigcityio) %>% as.data.frame()
t <- t[t$Freq!=0,c(1,2)]
names(t) <- c("province","bigcityio")

k <- merge(dwbigcityionew,x1,by="bigcityio")
g <- merge(k,t,by="bigcityio")
g$province <- factor(g$province,ordered = T,levels=province_level)
kable(g[order(g$province),])

5. 机场

dwairportnew <- caculate_carsmean(jddwnew,"airport")

dwairportprevious <- caculate_carsmean(jddwprevious,"airport")
x1 <- caculate_increaseratio(dwairportnew,dwairportprevious)

t <- table(jddwnew$province,jddwnew$airport) %>% as.data.frame()
t <- t[t$Freq!=0,c(1,2)]
names(t) <- c("province","airport")

k <- merge(dwairportnew,x1,by="airport")
g <- merge(k,t,by="airport")
g$province <- factor(g$province,ordered = T,levels=province_level)
kable(g[order(g$province),])