R语言根据经纬度获得对应样本的省份

一.输入

包含样本的经纬度
二.代码

复制代码
library(sf)
library(dplyr)
library(osmextract)

# 1. 准备省份中英文对照表
province_names <- data.frame(
  name_en = c("Beijing", "Tianjin", "Shanghai", "Chongqing", 
              "Hebei", "Shanxi", "Inner Mongolia", "Liaoning",
              "Jilin", "Heilongjiang", "Jiangsu", "Zhejiang",
              "Anhui", "Fujian", "Jiangxi", "Shandong",
              "Henan", "Hubei", "Hunan", "Guangdong",
              "Guangxi", "Hainan", "Sichuan", "Guizhou",
              "Yunnan", "Tibet", "Shaanxi", "Gansu",
              "Qinghai", "Ningxia", "Xinjiang", "Taiwan"),
  province_cn = c("北京市", "天津市", "上海市", "重庆市",
                  "河北省", "山西省", "内蒙古自治区", "辽宁省",
                  "吉林省", "黑龙江省", "江苏省", "浙江省",
                  "安徽省", "福建省", "江西省", "山东省",
                  "河南省", "湖北省", "湖南省", "广东省",
                  "广西壮族自治区", "海南省", "四川省", "贵州省",
                  "云南省", "西藏自治区", "陕西省", "甘肃省",
                  "青海省", "宁夏回族自治区", "新疆维吾尔自治区", "台湾省")
)

# 2. 读取元数据
metadata <- read.csv("lib_metadata2.csv") %>% 
  filter(!is.na(latitude), !is.na(longitude))

# 3. 获取中国行政区划数据（两种方式任选其一）
# 方式A：使用osmextract获取数据
poly_china <- openstreetmap_fr_zones %>% 
  filter(parent == "china") %>% 
  left_join(province_names, by = c("name" = "name_en")) %>% 
  mutate(province_cn = ifelse(is.na(province_cn), name, province_cn))

# 方式B：使用本地GeoJSON文件（推荐，更稳定）
# china_map <- st_read("D:/path/to/china.json") %>% 
#   left_join(province_names, by = c("name" = "name_en")) %>% 
#   mutate(province_cn = coalesce(province_cn, name))

# 4. 转换为空间点数据
points <- st_as_sf(
  metadata,
  coords = c("longitude", "latitude"),
  crs = 4326,  # WGS84坐标系
  remove = FALSE  # 保留原始列
) %>% 
  st_transform(st_crs(poly_china))  # 转换为与多边形相同的坐标系

# 5. 执行空间连接（带中文省份名称）
result <- st_join(points, poly_china, join = st_within) %>% 
  select(lib_id, genus, species, latitude, longitude, 
         region_en = name, region_cn = province_cn)

# 6. 处理未匹配的点（可选）
if(any(is.na(result$region_cn))) {
  # 方法A：标记未匹配点
  result <- result %>% 
    mutate(region_cn = ifelse(is.na(region_cn), "未知地区", region_cn))
  
  # 方法B：使用最近邻匹配（更精确）
  # unmatched <- result %>% filter(is.na(region_cn))
  # nearest <- st_nearest_feature(unmatched, poly_china)
  # result[is.na(result$region_cn), "region_cn"] <- poly_china$province_cn[nearest]
}

# 7. 检查结果
print(result %>% 
        count(region_cn, sort = TRUE) %>% 
        as.data.frame())

# 8. 保存结果（UTF-8编码支持中文）
write.csv(result, "D:/file/BGI/蚊虫项目/Wolbachia/bam/metadata_with_regions.csv", 
          row.names = FALSE, fileEncoding = "UTF-8")