Question

我有一个data.table，其中包含一些州名的缩写和县名。我想得到大约。每行的ggplot2::map_data('county')坐标。

我可以使用:=用多行代码顺序执行此操作，但是我只想调用一个函数。

以下是我尝试过的内容：

数据：

library(data.table)
library(ggplot2)

> dput(dt[1:20, .(state, county, prime_mover)])
structure(list(state = c("AZ", "AZ", "CA", "CA", "CA", "CT", 
"FL", "IN", "MA", "MA", "MA", "MN", "NJ", "NJ", "NJ", "NY", "NC", 
"SC", "TN", "TX"), county = c("Maricopa", "Maricopa", "Los Angeles", 
"Orange", "Los Angeles", "Fairfield", "Hillsborough", "Morgan", 
"Barnstable", "Nantucket", "Essex", "Dakota", "Cape May", "Salem", 
"Middlesex", "Kings", "Buncombe", "Anderson", "Shelby", "Tarrant"
), prime_mover = c("GT", "GT", "CT", "CT", "CT", "CT", "GT", 
"CT", "GT", "GT", "GT", "GT", "CT", "GT", "CT", "GT", "CT", "CT", 
"CT", "CT")), .Names = c("state", "county", "prime_mover"), row.names = c(NA, 
-20L), class = c("data.table", "data.frame"))

coord_data <- as.data.table(map_data('county'))

代码：

getCoords <- function(state, county){
  prov <- state.name[grep(state, state.abb)]
  ck <- coord_data[region == tolower(prov) & subregion == tolower(county), 
                   .(lon = mean(long), lat = mean(lat))]
  return(list(unname(unlist(ck))))
}

# Testing getCoords
> getCoords('AZ', 'Maricopa')
[[1]]
[1] -111.88668   33.58126

错误：

> dt[, c('lon', 'lat') := lapply(.SD, getCoords), .SDcols = c('state', 'county')]
Error in tolower(county) : argument "county" is missing, with no default
In addition: Warning message:
In grep(state, state.abb) :
  argument 'pattern' has length > 1 and only the first element will be used

我已经看到以下答案，但无法完全理解我在做什么：

我能够通过其他方式（多行，dplyr或什至基R）实现我想要的功能，但是我更喜欢使用data.table方法。

Answer 1

我要进行两个 update联接：

LifecycleUtils.init(objects.values());

library(data.table)
# aggregate coordinates
cols <- c("long", "lat")
agg_coord <- coord_data[, lapply(.SD, mean), .SDcols = cols, by = .(region, subregion)]
# coerce to data.table by reference
setDT(dt)[
  # 1st update join to append region/state.name
  .(state = state.abb, state.name = tolower(state.name)), 
  on = "state", region := state.name][
    # append subregion
    , subregion := tolower(county)][
      # 2nd update join to append coordinates
      agg_coord, on = .(region, subregion), (cols) := .(long, lat)][
        # remove helper columns
        , c("region", "subregion") := NULL]
# print updated dt
dt[]

根据其他列创建新的data.table列

1 个答案: