China accident map

with mapview

Author

Tony Duan

1 data

data source :https://github.com/percent4/chinese_incident_tracker

Code

library(tidyverse)
library(rvest)
library(jsonlite)
library(curl)
library(lubridate)
library(plotly)
library(ggplot2)
library(openxlsx)
library(readxl)

2 one file

Code

#url <- "https://raw.githubusercontent.com/percent4/chinese_incident_tracker/main/elk/data/00105670-df53-4be8-9039-8a07fe2d2b4d.json"
#download.file(url,"./data/SAFI.json", mode = "wb")

Code

data001 <- read_json("./data/SAFI.json")

Code

data002=data001 %>% as.data.frame()
colnames(data002)[14] = "latitude"
colnames(data002)[15] = "longitude"
glimpse(data002)

Rows: 1
Columns: 22
$ item_id            <chr> "00105670-df53-4be8-9039-8a07fe2d2b4d"
$ news_channel       <chr> "新闻坊"
$ title              <chr> "一养老院突发火灾，已致3死10伤！"
$ report             <chr> "4月4日\n\n“东莞应急管理”\n\n发布情况通报\n\n↓↓↓\n\n4月4日4时21分，东莞万…
$ original_websites  <chr> "https://mp.weixin.qq.com/s/xUZR8gZ_N0UqGj0GvH6L8A"
$ start_date         <chr> "2024-04-04"
$ start_time         <chr> "2024-04-04 04:21:00"
$ update_time        <chr> "2024-05-03 10:50:01"
$ incident_type      <chr> "火灾"
$ incident_reason    <chr> "该建筑为一栋11层楼房，起火部位为第三层303房，过火面积约20平方米。"…
$ person_death_num   <int> 3
$ person_injury_num  <int> 10
$ person_missing_num <int> 0
$ latitude           <dbl> 113.6952
$ longitude          <dbl> 23.07464
$ place              <chr> "东莞万江街道康怡护理院（公助民办养老院）"
$ province           <chr> "广东省"
$ city               <chr> "东莞市"
$ county             <chr> ""
$ town               <chr> "万江街道"
$ village            <chr> ""
$ is_final           <lgl> TRUE

3 all file

Code

#url="https://github.com/percent4/chinese_incident_tracker/archive/refs/heads/main.zip"
#download.file(url,"./data/data.zip", mode = "wb")

Code

#unzip("./data/data.zip",exdir="./data/out")

Code

from <- "./data/out/chinese_incident_tracker-main/elk/data"
to   <- "./data/json_folder"
file.copy(list.files(from, full.names = TRUE), 
          to, 
          recursive = TRUE)

 [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[16] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[31] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[46] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE

Code

#list.files("./data/json_folder")

Code

all_data=tibble()

for (i in list.files("./data/json_folder")) {
  #print(i)
  data001=read_json(paste0("./data/json_folder/",i))
  data002=data001 %>% as.data.frame()
  colnames(data002)[14] = "Longitude"
  colnames(data002)[15] = "Latitude"
  #print(data002)
  
  all_data=rbind(all_data,data002)
}

Code

all_data=all_data %>% mutate(text=paste0(incident_type," ","死亡人数:",person_death_num," 受伤人数:",person_injury_num)
                             ,month_year= format_ISO8601(ymd(start_date), precision = "ym")
                             )

Code

glimpse(all_data)

Rows: 60
Columns: 24
$ item_id            <chr> "00105670-df53-4be8-9039-8a07fe2d2b4d", "0683ba1e-7…
$ news_channel       <chr> "新闻坊", "中国新闻网", "凤凰网", "搜狐网", "每日经济新闻", "中国新闻网", "杭…
$ title              <chr> "一养老院突发火灾，已致3死10伤！", "江西于都一矿企发生事故 致3死2伤", "#云南镇雄突发山…
$ report             <chr> "4月4日\n\n“东莞应急管理”\n\n发布情况通报\n\n↓↓↓\n\n4月4日4时21分，东莞万…
$ original_websites  <chr> "https://mp.weixin.qq.com/s/xUZR8gZ_N0UqGj0GvH6L8A"…
$ start_date         <chr> "2024-04-04", "2024-04-24", "2024-01-22", "2024-02-…
$ start_time         <chr> "2024-04-04 04:21:00", "2024-04-24 00:08:48", "2024…
$ update_time        <chr> "2024-05-03 10:50:01", "2024-05-03 00:08:48", "2024…
$ incident_type      <chr> "火灾", "溃水", "山体滑坡", "房屋坍塌", "燃气爆炸", "火灾", "摔伤", "摔伤…
$ incident_reason    <chr> "该建筑为一栋11层楼房，起火部位为第三层303房，过火面积约20平方米。", "企业清理排洪隧洞时溃…
$ person_death_num   <int> 3, 3, 44, 1, 7, 4, 1, 1, 7, 1, 18, 4, 5, 1, 15, 12,…
$ person_injury_num  <int> 10, 2, 2, 0, 27, 4, 0, 0, 0, 11, 1155, 0, 3, 2, 44,…
$ person_missing_num <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 6, 0, …
$ Longitude          <dbl> 113.69524, 115.32158, 104.95514, 113.28304, 116.808…
$ Latitude           <dbl> 23.07464, 25.72126, 27.49063, 32.22574, 39.95258, 4…
$ place              <chr> "东莞万江街道康怡护理院（公助民办养老院）", "于都县龙鑫矿业有限公司选矿厂", "云南省昭通市镇雄…
$ province           <chr> "广东省", "江西省", "云南省", "湖北省", "河北省", "内蒙古自治区", "新疆维吾尔…
$ city               <chr> "东莞市", "赣州市", "昭通市", "随州市", "廊坊市", "呼和浩特市", "伊犁哈萨克自…
$ county             <chr> "", "于都县", "镇雄县", "随县", "三河市", "新城区", "富蕴县", "富蕴县",…
$ town               <chr> "万江街道", "祁禄山镇", "塘房镇", "万和镇", "燕郊镇", "", "", "", "宁…
$ village            <chr> "", "金沙村", "", "", "小张各庄", "", "", "", "乔家沟", "", "…
$ is_final           <lgl> TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRU…
$ text               <chr> "火灾 死亡人数:3 受伤人数:10", "溃水 死亡人数:3 受伤人数:2", "山体滑坡 死亡人数…
$ month_year         <chr> "2024-04", "2024-04", "2024-01", "2024-02", "2024-0…

Code

#write.xlsx(all_data,'all_data.xlsx')

4 chart

group to month ::: {.cell}

Code

chartdata001=all_data %>% group_by(month_year)  %>%  summarise(person_death_num=sum(person_death_num)
                                                           ,person_injury_num=sum(person_injury_num)
                                                           )

:::

wide to long ::: {.cell}

Code

chartdata002=chartdata001 %>%select(month_year,person_death_num,person_injury_num) %>% 
  pivot_longer(!c(month_year), names_to = 'type', values_to = 'DATA')

:::

Code

gg=ggplot(chartdata001, aes(x=month_year, y=person_death_num,label = person_death_num))+
  geom_bar(stat="identity",fill='red')+ geom_text(vjust = -1,
              position = position_dodge(width = 0.9))+ theme_bw()


ggplotly(gg)

Code

gg=ggplot(chartdata002, aes(fill=type, y=DATA, x=month_year)) +
    geom_col(position = "dodge") +
    geom_text(aes(label = DATA), vjust = 1.5,
              position = position_dodge(width = 0.9))+scale_y_log10()+ theme_light()

pp=ggplotly(gg)

pp

5 map

Code

all_data2 =all_data %>%  mutate(report=report %>% str_trunc(100))

Code

#write.xlsx(all_data2,'all_data2.xlsx')

Code

library(mapview)
library(sf)
library(stringr)

mapview(all_data2, map.types='OpenStreetMap',label='text',xcol = "Longitude", ycol = "Latitude", zcol='incident_type',cex="person_death_num",crs = 4269, grid = FALSE)

6 resouce:

https://github.com/percent4/chinese_incident_tracker

https://github.com/r-spatial/mapview

https://maps.clb.org.hk/