R - Cloropleth：在多边形内的数据点中，有多少百分比具有特定的列值？

Question

此线程的扩展：Create choropleth map from coordinate points。 （为了与尽可能多的人相关，我不想将这两个线程结合起来。）

我有一个由多个观测值组成的数据帧，每个观测值都有地理坐标（纬度 - 经度）和布尔值（是 - 否）值。我想要生成一个世界的世界地图，其中每个区域/多边形都被其内相关布尔值等于true的点的百分比所着色。

这里是一个最小可重现的例子，它现在只根据多边形中的点数进行着色。 “喜欢”的数据列是我的布尔值。

# Load package 
library(tidyverse) 
library(ggmap) 
library(maps) 
library(maptools) 
library(sf) 

data <- data.frame(class = c("Private", "Private", "Private", "Private", "Private", "Private", "Not Private", "Not Private", "Private", "Private", "Not Private", "Private", "Not Private", "Private", "Private", "Not Private", "Not Private", "Private", "Private", "Not Private"), 
        lat = c(33.663944, 41.117936, 28.049601, 39.994684, 36.786042, 12.797659, 52.923318, 33.385555, 9.295242, 32.678207, 41.833585, -28.762956, 39.284713, 36.060964, 36.052239, 36.841764, 33.714237, 33.552863, 32.678207, -38.132401), 
        lon = c(-83.98686, -77.60468, -81.97271, -82.98577, -119.78246, 121.82814, -1.16057, -86.76009, 123.27758, -83.17387, -87.73201, 32.05737, -76.62048, -115.13517, -79.39961, -76.35592, -85.85172, -112.12468, -83.17387, 144.36946)) 

# Convert to simple feature object 
point_sf <- st_as_sf(data, coords = c("lon", "lat"), crs = 4326) 

# Get world map data 
worldmap <- maps::map("world", fill = TRUE, plot = FALSE) 

# Convert world to sp class 
IDs <- sapply(strsplit(worldmap$names, ":"), "[", 1L) 
world_sp <- map2SpatialPolygons(worldmap, IDs = IDs, 
           proj4string = CRS("+proj=longlat +datum=WGS84")) 

# Convert world_sp to simple feature object 
world_sf <- st_as_sf(world_sp) 

# Add country ID 
world_sf <- world_sf %>% 
    mutate(region = map_chr(1:length(world_sp@polygons), function(i){ 
    world_sp@polygons[[i]]@ID 
    })) 

# Use st_within 
result <- st_within(point_sf, world_sf, sparse = FALSE) 

# Calculate the total count of each polygon 
# Store the result as a new column "Count" in world_sf 
world_sf <- world_sf %>% 
    mutate(Count = apply(result, 2, sum)) 

# Convert world_sf to a data frame world_df 
world_df <- world_sf 
st_geometry(world_df) <- NULL 

# Get world data frame 
world_data <- map_data("world") 

# Merge world_data and world_df 
world_data2 <- world_data %>% 
    left_join(world_df, by = c("region")) 

ggplot() + 
    geom_polygon(data = world_data2, aes(x = long, y = lat, group = group, fill = Count)) + 
    coord_fixed(1.3) 

特别感谢https://stackoverflow.com/users/7669809/ycw寻求帮助。

Answer 1

我们可以先计算多边形中有多少个点，然后过滤列中标记为Private的记录的数据集，然后再计算多边形中的多少个点。我们可以通过使用Private计数数除以所有计数并以100％乘以来计算百分比。

关于sf对象的一个​​很好的功能是它也是一个数据框架。因此，管理数据帧的操作（例如dplyr包中的filter）也适用于sf对象。所以我们可以使用像point_private_sf <- point_sf %>% filter(class %in% "Private")这样的指令轻松过滤点。

# Load package 
library(tidyverse) 
library(maps) 
library(maptools) 
library(sf) 

### Data Preparation 

data <- data.frame(class = c("Private", "Private", "Private", "Private", "Private", "Private", "Not Private", "Not Private", "Private", "Private", "Not Private", "Private", "Not Private", "Private", "Private", "Not Private", "Not Private", "Private", "Private", "Not Private"), 
        lat = c(33.663944, 41.117936, 28.049601, 39.994684, 36.786042, 12.797659, 52.923318, 33.385555, 9.295242, 32.678207, 41.833585, -28.762956, 39.284713, 36.060964, 36.052239, 36.841764, 33.714237, 33.552863, 32.678207, -38.132401), 
        lon = c(-83.98686, -77.60468, -81.97271, -82.98577, -119.78246, 121.82814, -1.16057, -86.76009, 123.27758, -83.17387, -87.73201, 32.05737, -76.62048, -115.13517, -79.39961, -76.35592, -85.85172, -112.12468, -83.17387, 144.36946)) 

# Convert to simple feature object 
point_sf <- st_as_sf(data, coords = c("lon", "lat"), crs = 4326) 

# Get world map data 
worldmap <- maps::map("world", fill = TRUE, plot = FALSE) 

# Convert world to sp class 
IDs <- sapply(strsplit(worldmap$names, ":"), "[", 1L) 
world_sp <- map2SpatialPolygons(worldmap, IDs = IDs, 
           proj4string = CRS("+proj=longlat +datum=WGS84")) 

# Convert world_sp to simple feature object 
world_sf <- st_as_sf(world_sp) 

# Add country ID 
world_sf <- world_sf %>% 
    mutate(region = map_chr(1:length(world_sp@polygons), function(i){ 
    world_sp@polygons[[i]]@ID 
    })) 

### Use st_within for the analysis 

# Use st_within for all points 
result_all <- st_within(point_sf, world_sf, sparse = FALSE) 

# Filter the points by "Private" in the class column 
point_private_sf <- point_sf %>% filter(class %in% "Private") 

# Use st_within for private points 
result_private <- st_within(point_private_sf, world_sf, sparse = FALSE) 

### Calculate the total count of each polygon 
# Store the result as ew columns "Count_all" and "Count_private" in world_sf 
world_sf <- world_sf %>% 
    mutate(Count_all = apply(result_all, 2, sum), 
     Count_private = apply(result_private, 2, sum)) %>% 
    # Calculate the percentage 
    mutate(Percent = ifelse(Count_all == 0, Count_all, Count_private/Count_all * 100)) 

### Plot the data 

# Convert world_sf to a data frame world_df 
world_df <- world_sf 
st_geometry(world_df) <- NULL 

# Get world data frame 
world_data <- map_data("world") 

# Merge world_data and world_df 
world_data2 <- world_data %>% 
    left_join(world_df, by = c("region")) 

ggplot() + 
    geom_polygon(data = world_data2, aes(x = long, y = lat, group = group, fill = Percent)) + 
    coord_fixed(1.3)