将 purrr::map2() 与 dbplyr 一起使用

Question

我试图从一个表（“位置”）中选择行，其中特定列（“位置”）的值落在另一个表（“my_ranges”）中定义的范围内，然后从“我的范围”表。

我可以使用 tibbles 和几个purrr::map2调用来完成此操作，但相同的方法不适用于 dbplyr 数据库 tibbles。这是预期的行为吗？如果是，我是否应该采取不同的方法来使用 dbplyr 来完成此类任务？

这是我的例子：

library("tidyverse")
set.seed(42)

my_ranges <-
  tibble(
    group_id = c("a", "b", "c", "d"),
    start = c(1, 7, 2, 25),
    end = c(5, 23, 7, 29)
    )

positions <-
  tibble(
    position = as.integer(runif(n = 100, min = 0, max = 30)),
    annotation = stringi::stri_rand_strings(n = 100, length = 10)
  )

# note: this works as I expect and returns a tibble with 106 obs of 3 variables:
result <- map2(.x = my_ranges$start, .y = my_ranges$end,
             .f = function(x, y) {between(positions$position, x, y)}) %>%
  map2(.y = my_ranges$group_id,
              .f = function(x, y){
                positions %>%
                  filter(x) %>%
                  mutate(group_id = y)}
) %>% bind_rows()

# next, make an in-memory db for testing:
con <- DBI::dbConnect(RSQLite::SQLite(), path = ":memory:")

# copy data to db
copy_to(con, my_ranges, "my_ranges", temporary = FALSE)
copy_to(con, positions, "positions", temporary = FALSE)

# get db-backed tibbles:
my_ranges_db <- tbl(con, "my_ranges")
positions_db <- tbl(con, "positions")

# note: this does not work as I expect, and instead returns a tibble with 0 obsevations of 0 variables:
# database range-based query:
db_result <- map2(.x = my_ranges_db$start, .y = my_ranges_db$end,
                  .f = function(x, y) {
                    between(positions_db$position, x, y)
                    }) %>%
  map2(.y = my_ranges_db$group_id,
       .f = function(x, y){
         positions_db %>%
           filter(x) %>%
           mutate(group_id = y)}
  ) %>% bind_rows()

Answer 1

只要每次迭代创建一个相同维度的表，那么就可能有一种巧妙的方法将整个操作推送到数据库。这个想法是同时使用map()和reduce()from purrr。每个tbl_sql()操作都是惰性的，因此我们可以迭代它们，而不必担心发送一堆查询，然后我们可以使用它基本上将每次迭代生成的 SQL 使用给定数据库中的子句union()附加到下一次迭代。UNION这是一个例子：

library(dbplyr, warn.conflicts = FALSE)
library(dplyr, warn.conflicts = FALSE)
library(purrr, warn.conflicts = FALSE)
library(DBI, warn.conflicts = FALSE)
library(rlang, warn.conflicts = FALSE)

con <- DBI::dbConnect(RSQLite::SQLite(), path = ":dbname:")

db_mtcars <- copy_to(con, mtcars)

cyls <- c(4, 6, 8)

all <- cyls %>%
  map(~{
    db_mtcars %>%
      filter(cyl == .x) %>%
      summarise(mpg = mean(mpg, na.rm = TRUE)
      )
  }) %>%
  reduce(function(x, y) union(x, y)) 

all
#> # Source:   lazy query [?? x 1]
#> # Database: sqlite 3.22.0 []
#>     mpg
#>   <dbl>
#> 1  15.1
#> 2  19.7
#> 3  26.7

show_query(all)
#> <SQL>
#> SELECT AVG(`mpg`) AS `mpg`
#> FROM (SELECT *
#> FROM (SELECT *
#> FROM `mtcars`)
#> WHERE (`cyl` = 4.0))
#> UNION
#> SELECT AVG(`mpg`) AS `mpg`
#> FROM (SELECT *
#> FROM (SELECT *
#> FROM `mtcars`)
#> WHERE (`cyl` = 6.0))
#> UNION
#> SELECT AVG(`mpg`) AS `mpg`
#> FROM (SELECT *
#> FROM (SELECT *
#> FROM `mtcars`)
#> WHERE (`cyl` = 8.0))

dbDisconnect(con)