识别属于纬度和经度坐标的邮政编码
identify zip codes that fall within latitude and longitudinal coordinates
我在 R 中有几个数据框。第一个数据框包含按市场计算的一组经纬度坐标的凸包（由 R 中的 chull 提供）。它看起来像这样：
MyGeo<- "Part of Chicago & Wisconsin"
Longitude <- c(-90.31914, -90.61911, -89.37842, -88.0988, -87.44875)
Latitude <- c(38.45781, 38.80097, 43.07961, 43.0624,41.49182)
dat <- data.frame(Longitude, Latitude, MyGeo)
第二个具有按纬度和经度坐标划分的邮政编码（由美国人口普查网站提供）。它看起来像这样：
CensuseZip <- c("SomeZipCode1","SomeZipCode2","SomeZipCode3","SomeZipCode4","SomeZipCode5","SomeZipCode6","SomeZipCode7")
Longitude2 <- c(-131.470425,-133.457924,-131.693453,-87.64957,-87.99734,-87.895,-88.0228)
Latitude2 <- c(55.138352,56.239062,56.370538,41.87485,42.0086,42.04957,41.81055)
cen <- data.frame(Longitude2, Latitude2, CensuseZip)
现在我相信第一个数据 table 为我提供了一个多边形或边框，我 应该 可以使用它来识别属于其中的邮政编码那个边界。理想情况下，我想创建第三个数据 table 看起来像这样：
Longitude2 Latitude2 CensusZip MyGeo
-131.470425 55.138352 SomeZipCode1
-133.457924 56.239062 SomeZipCode2
-131.693453 56.370538 SomeZipCode3
-87.64957 41.87485 SomeZipCode4 Part of Chicago & Wisconsin
-87.99734 42.0086 SomeZipCode5 Part of Chicago & Wisconsin
-87.895 42.04957 SomeZipCode6 Part of Chicago & Wisconsin
-88.0228 41.81055 SomeZipCode7 Part of Chicago & Wisconsin
本质上，我希望识别位于蓝色（见下方可点击图片）长点和纬度点之间的所有邮政编码。虽然它在下面可视化，但我实际上是在寻找上面描述的 table。
但是...我在执行此操作时遇到问题...我已尝试使用以下包和脚本：
library(rgeos)
library(sp)
library(rgdal)
coordinates(dat) <- ~ Longitude + Latitude
coordinates(cen) <- ~ Longitude2 + Latitude2
over(cen, dat)
但我收到了所有 NAs。
我用library(sf)来解决这种多边形中的点问题（sf是sp的继承者）。
函数sf::st_intersection() 给出了两个sf 对象的交集。在您的情况下，您可以构造单独的 POLYGON 和 POINT sf 对象。
library(sf)
Longitude <- c(-90.31914, -90.61911, -89.37842, -88.0988, -87.44875)
Latitude <- c(38.45781, 38.80097, 43.07961, 43.0624,41.49182)
## closing the polygon
Longitude[length(Longitude) + 1] <- Longitude[1]
Latitude[length(Latitude) + 1] <- Latitude[1]
## construct sf POLYGON
sf_poly <- sf::st_sf( geometry = sf::st_sfc( sf::st_polygon( x = list(matrix(c(Longitude, Latitude), ncol = 2)))) )
## construct sf POINT
sf_points <- sf::st_as_sf( cen, coords = c("Longitude2", "Latitude2"))
sf::st_intersection(sf_points, sf_poly)
# Simple feature collection with 4 features and 1 field
# geometry type: POINT
# dimension: XY
# bbox: xmin: -88.0228 ymin: 41.81055 xmax: -87.64957 ymax: 42.04957
# epsg (SRID): NA
# proj4string: NA
# CensuseZip geometry
# 4 SomeZipCode4 POINT (-87.64957 41.87485)
# 5 SomeZipCode5 POINT (-87.99734 42.0086)
# 6 SomeZipCode6 POINT (-87.895 42.04957)
# 7 SomeZipCode7 POINT (-88.0228 41.81055)
# Warning message:
# attribute variables are assumed to be spatially constant throughout all geometries
结果是多边形内的所有点
你也可以用sf::st_join(sf_poly, sf_points)得到同样的结果
并且，函数 sf::st_intersects(sf_points, sf_poly) 将 return 一个列表，说明给定的点是否在多边形内
sf::st_intersects(sf_points, sf_poly)
# Sparse geometry binary predicate list of length 7, where the predicate was `intersects'
# 1: (empty)
# 2: (empty)
# 3: (empty)
# 4: 1
# 5: 1
# 6: 1
# 7: 1
您可以将其用作原始 sf_points 对象的索引/标识符以在
上添加新列
is_in <- sf::st_intersects(sf_points, sf_poly)
sf_points$inside_polygon <- as.logical(is_in)
sf_points
# Simple feature collection with 7 features and 2 fields
# geometry type: POINT
# dimension: XY
# bbox: xmin: -133.4579 ymin: 41.81055 xmax: -87.64957 ymax: 56.37054
# epsg (SRID): NA
# proj4string: NA
# CensuseZip geometry inside_polygon
# 1 SomeZipCode1 POINT (-131.4704 55.13835) NA
# 2 SomeZipCode2 POINT (-133.4579 56.23906) NA
# 3 SomeZipCode3 POINT (-131.6935 56.37054) NA
# 4 SomeZipCode4 POINT (-87.64957 41.87485) TRUE
# 5 SomeZipCode5 POINT (-87.99734 42.0086) TRUE
# 6 SomeZipCode6 POINT (-87.895 42.04957) TRUE
# 7 SomeZipCode7 POINT (-88.0228 41.81055) TRUE
我在 R 中有几个数据框。第一个数据框包含按市场计算的一组经纬度坐标的凸包（由 R 中的 chull 提供）。它看起来像这样：
MyGeo<- "Part of Chicago & Wisconsin"
Longitude <- c(-90.31914, -90.61911, -89.37842, -88.0988, -87.44875)
Latitude <- c(38.45781, 38.80097, 43.07961, 43.0624,41.49182)
dat <- data.frame(Longitude, Latitude, MyGeo)
第二个具有按纬度和经度坐标划分的邮政编码（由美国人口普查网站提供）。它看起来像这样：
CensuseZip <- c("SomeZipCode1","SomeZipCode2","SomeZipCode3","SomeZipCode4","SomeZipCode5","SomeZipCode6","SomeZipCode7")
Longitude2 <- c(-131.470425,-133.457924,-131.693453,-87.64957,-87.99734,-87.895,-88.0228)
Latitude2 <- c(55.138352,56.239062,56.370538,41.87485,42.0086,42.04957,41.81055)
cen <- data.frame(Longitude2, Latitude2, CensuseZip)
现在我相信第一个数据 table 为我提供了一个多边形或边框，我 应该 可以使用它来识别属于其中的邮政编码那个边界。理想情况下，我想创建第三个数据 table 看起来像这样：
Longitude2 Latitude2 CensusZip MyGeo
-131.470425 55.138352 SomeZipCode1
-133.457924 56.239062 SomeZipCode2
-131.693453 56.370538 SomeZipCode3
-87.64957 41.87485 SomeZipCode4 Part of Chicago & Wisconsin
-87.99734 42.0086 SomeZipCode5 Part of Chicago & Wisconsin
-87.895 42.04957 SomeZipCode6 Part of Chicago & Wisconsin
-88.0228 41.81055 SomeZipCode7 Part of Chicago & Wisconsin
本质上，我希望识别位于蓝色（见下方可点击图片）长点和纬度点之间的所有邮政编码。虽然它在下面可视化，但我实际上是在寻找上面描述的 table。
但是...我在执行此操作时遇到问题...我已尝试使用以下包和脚本：
library(rgeos)
library(sp)
library(rgdal)
coordinates(dat) <- ~ Longitude + Latitude
coordinates(cen) <- ~ Longitude2 + Latitude2
over(cen, dat)
但我收到了所有 NAs。
我用library(sf)来解决这种多边形中的点问题（sf是sp的继承者）。
函数sf::st_intersection() 给出了两个sf 对象的交集。在您的情况下，您可以构造单独的 POLYGON 和 POINT sf 对象。
library(sf)
Longitude <- c(-90.31914, -90.61911, -89.37842, -88.0988, -87.44875)
Latitude <- c(38.45781, 38.80097, 43.07961, 43.0624,41.49182)
## closing the polygon
Longitude[length(Longitude) + 1] <- Longitude[1]
Latitude[length(Latitude) + 1] <- Latitude[1]
## construct sf POLYGON
sf_poly <- sf::st_sf( geometry = sf::st_sfc( sf::st_polygon( x = list(matrix(c(Longitude, Latitude), ncol = 2)))) )
## construct sf POINT
sf_points <- sf::st_as_sf( cen, coords = c("Longitude2", "Latitude2"))
sf::st_intersection(sf_points, sf_poly)
# Simple feature collection with 4 features and 1 field
# geometry type: POINT
# dimension: XY
# bbox: xmin: -88.0228 ymin: 41.81055 xmax: -87.64957 ymax: 42.04957
# epsg (SRID): NA
# proj4string: NA
# CensuseZip geometry
# 4 SomeZipCode4 POINT (-87.64957 41.87485)
# 5 SomeZipCode5 POINT (-87.99734 42.0086)
# 6 SomeZipCode6 POINT (-87.895 42.04957)
# 7 SomeZipCode7 POINT (-88.0228 41.81055)
# Warning message:
# attribute variables are assumed to be spatially constant throughout all geometries
结果是多边形内的所有点
你也可以用sf::st_join(sf_poly, sf_points)得到同样的结果
并且，函数 sf::st_intersects(sf_points, sf_poly) 将 return 一个列表，说明给定的点是否在多边形内
sf::st_intersects(sf_points, sf_poly)
# Sparse geometry binary predicate list of length 7, where the predicate was `intersects'
# 1: (empty)
# 2: (empty)
# 3: (empty)
# 4: 1
# 5: 1
# 6: 1
# 7: 1
您可以将其用作原始 sf_points 对象的索引/标识符以在
is_in <- sf::st_intersects(sf_points, sf_poly)
sf_points$inside_polygon <- as.logical(is_in)
sf_points
# Simple feature collection with 7 features and 2 fields
# geometry type: POINT
# dimension: XY
# bbox: xmin: -133.4579 ymin: 41.81055 xmax: -87.64957 ymax: 56.37054
# epsg (SRID): NA
# proj4string: NA
# CensuseZip geometry inside_polygon
# 1 SomeZipCode1 POINT (-131.4704 55.13835) NA
# 2 SomeZipCode2 POINT (-133.4579 56.23906) NA
# 3 SomeZipCode3 POINT (-131.6935 56.37054) NA
# 4 SomeZipCode4 POINT (-87.64957 41.87485) TRUE
# 5 SomeZipCode5 POINT (-87.99734 42.0086) TRUE
# 6 SomeZipCode6 POINT (-87.895 42.04957) TRUE
# 7 SomeZipCode7 POINT (-88.0228 41.81055) TRUE