使用 ggplot 绘制 COVID 数据的气泡图

Question

我有一个包含捷克共和国 14 个地区的经纬度信息的电子表格（文件 here）。我正在尝试绘制地图并为每个区域的活动案例放置气泡。经纬度坐标适用于每个地区的首府城市。

library(sf)
library(ggplot2)
library(maps)
library(rstudioapi)
library(dplyr)
library(ggmap)
library(mapproj)
library(viridis)

#----------------------------#
# Set your working directory #
#----------------------------#

setwd(dirname(rstudioapi::getActiveDocumentContext()$path)) # RStudio IDE preferred
getwd() # Path to your working directory

# Country Boundary and the 14 regions within the Czech Republic

worldmap <- map_data("world")

worldmap2 <- dplyr::filter(worldmap, region %in% data.frame(countries = "Czech Republic"))

ggplot(worldmap2) + geom_polygon(aes(long,lat, group=group), col = "black", fill = "white", size = 1) + 
     labs(title = "COVID-19 in the Czech Republic", subtitle = "As of July 1, 2021", x = "Longitude", y = "Latitude", 
          caption = "(Source: Ministerstvo zdravotnictví České republiky)")

电子表格的第六列包含活动案例编号。我试图让数字在上面的地图上显示为气泡。我尝试了以下方法，但所有点的大小都相同。如何合并情节 1 和情节 2？

my_df <- read.csv("CZE_InitialSeedData.csv", header = T)

class(my_df)

my_sf <- st_as_sf(my_df, coords = c('Lon', 'Lat'))

my_sf <- st_set_crs(my_sf, value = 4326)

my_sf 

seedPlot <- ggplot(my_sf) + 
      geom_sf(aes(fill = InitialInfections))

seedPlot <- seedPlot + 
            scale_fill_continuous(name = "Active Cases", low = "pink", high = "red", na.value = "grey50")

seedPlot <- seedPlot + 
     theme(legend.position = "bottom", legend.text.align = 1, legend.title.align = 0.5)

seedPlot

Answer 1

无需将您的数据转换为sf 对象。您可以简单地通过 geom_point 将数据添加到地图中。要将气泡与size 美学上的活动案例映射到您的列：

library(ggplot2)
library(maps)
library(dplyr)

worldmap <- map_data("world")

worldmap2 <- dplyr::filter(worldmap, region == "Czech Republic")

base_map <- ggplot(worldmap2) +
  geom_polygon(aes(long, lat, group = group), col = "black", fill = "white", size = 1) +
  labs(
    title = "COVID-19 in the Czech Republic", subtitle = "As of July 1, 2021", x = "Longitude", y = "Latitude",
    caption = "(Source: Ministerstvo zdravotnictví České republiky)"
  )

base_map +
  geom_point(
    data = my_df,
    aes(x = Lon, y = Lat, color = InitialInfections, size = InitialInfections)
  ) +
  scale_color_continuous(name = "Active Cases", low = "pink", high = "red", na.value = "grey50") +
  scale_size_continuous(name = "Active Cases") +
  theme(legend.position = "bottom", legend.text.align = 1, legend.title.align = 0.5)

编辑据我所知，您可以为非 SF 坐标添加指北针和比例尺。但是，转换为 sf 对象将自动为比例尺选择正确的单位。为此，将底图和点图层都转换为sf 对象，如下所示：

library(ggplot2)
library(maps)
library(dplyr)
library(ggspatial)
library(sf)

worldmap <- map_data("world")

worldmap2 <- dplyr::filter(worldmap, region == "Czech Republic") %>% 
  st_as_sf(coords = c("long", "lat"), crs = 4326) %>% 
  st_combine() %>% 
  st_cast("POLYGON")

base_map <- ggplot(worldmap2) +
  geom_sf(col = "black", fill = "white", size = 1) +
  annotation_north_arrow() +
  annotation_scale(location = "tl") +
  labs(
    title = "COVID-19 in the Czech Republic", subtitle = "As of July 1, 2021", x = "Longitude", y = "Latitude",
    caption = "(Source: Ministerstvo zdravotnictví České republiky)"
  )

my_df <- my_df %>% 
  st_as_sf(coords = c("Lon", "Lat"), crs = 4326)

base_map +
  geom_sf(data = my_df, aes(color = InitialInfections, size = InitialInfections)) +
  scale_color_continuous(name = "Active Cases", low = "pink", high = "red", na.value = "grey50") +
  scale_size_continuous(name = "Active Cases") +
  theme(legend.position = "bottom", legend.text.align = 1, legend.title.align = 0.5)

数据

my_df <- structure(list(Location = c(
  "Prague", "CentralBohemian", "SouthBohemian",
  "Plzen", "KarlovyVary", "UstinadLabem", "Liberec", "HradecKralove",
  "Pardubice", "Vysocina", "SouthMoravian", "Olomouc", "Zlin",
  "Moravian-Silesian"
), Lat = c(
  50.083333, 50, 49.083333, 49.7475,
  50.230556, 50.658333, 50.685584, 50.209167, 49.951136, 49.6079,
  49.363161, 49.593889, 49.29786, 49.988449
), Lon = c(
  14.416667,
  14.533333, 14.666667, 13.3775, 12.8725, 14.041667, 14.537747,
  15.831944, 15.795636, 15.580728, 16.643175, 17.250833, 17.393135,
  17.464759
), InitialVaccinated = c(
  252944L, 159560L, 93490L, 82014L,
  40129L, 104454L, 59442L, 82074L, 65060L, 66325L, 165250L, 89116L,
  80125L, 159490L
), InitialExposed = c(
  1380L, 1274L, 1048L, 500L,
  50L, 1098L, 506L, 42L, 492L, 820L, 1406L, 1090L, 1116L, 2404L
), InitialInfections = c(
  690L, 637L, 524L, 250L, 25L, 549L, 253L,
  21L, 246L, 410L, 703L, 545L, 558L, 1202L
), InitialRecovered = c(
  181947L,
  226944L, 97405L, 95944L, 43882L, 120416L, 79029L, 102835L, 91729L,
  78308L, 151627L, 90887L, 89163L, 174251L
), InitialDead = c(
  2736L,
  3421L, 1978L, 1912L, 1484L, 2523L, 1280L, 1811L, 1437L, 1375L,
  3412L, 1709L, 1594L, 3521L
)), class = "data.frame", row.names = c(
  NA,
  -14L
))