如何从人口普查形状文件（邮政编码级别）中删除所有小岛？

我已经下载了邮政编码级别的人口普查形状文件，cb_2017_us_zcta510_500k.shp (https://www.census.gov/geo/maps-data/data/cbf/cbf_zcta.html https://www.census.gov/geo/maps-data/data/cbf/cbf_zcta.html)

我还下载了映射文件，它允许我添加相应的STATE多变的 （https://www.census.gov/geo/maps-data/data/zcta_rel_download.html https://www.census.gov/geo/maps-data/data/zcta_rel_download.html)

我将两者合并，得到：

library(sf)
library(dplyr)

big_df 

Simple feature collection with 44434 features and 2 fields
geometry type:  MULTIPOLYGON
dimension:      XY
bbox:           xmin: -176.6847 ymin: -14.37374 xmax: 145.8304 ymax: 71.34122
epsg (SRID):    4269
proj4string:    +proj=longlat +datum=NAD83 +no_defs
First 10 features:
   ZCTA5CE10 STATE                       geometry
1      35442     1 MULTIPOLYGON (((-88.25262 3...
2      35442     1 MULTIPOLYGON (((-88.25262 3...
3      35442     1 MULTIPOLYGON (((-88.25262 3...

现在，我尝试过滤所有小岛和阿拉斯加：

remove_list <-  c("02", "15", "72", "66", "78", "60", "69",
"64", "68", "70", "74", "81", "84", "86", "87", "89", "71", "76",
"95", "79")



big_df %>% filter(!STATE %in% map(remove_list, as.integer)) %>% 
  tm_shape(.) + tm_polygons('pt_count',palette = "Reds", 
                            style = "quantile", n = 10, 
                            title = "counts") 

但我还是得到了一些小岛。

我在这里缺少什么？ 谢谢！

以下是获取美国大陆几何形状（国家轮廓）的方法：

library(raster)
library(sf)
library(dplyr)

us = getData('GADM', country='USA', level=0) %>%
  st_as_sf() %>%
  st_cast("POLYGON") %>%
  mutate(area = st_area(.)) %>%
  arrange(desc(area)) %>%
  slice(1) # mainland US should be the largest

然后您可以使用它来运行st_intersection(big_df, us)仅提取部分big_df within us。请注意，首先创建一个st_buffer or st_convex_hull around us以确保您的big_df不会在其边界的某个地方被剪裁。